modelId stringlengths 4 111 | lastModified stringlengths 24 24 | tags list | pipeline_tag stringlengths 5 30 ⌀ | author stringlengths 2 34 ⌀ | config null | securityStatus null | id stringlengths 4 111 | likes int64 0 9.53k | downloads int64 2 73.6M | library_name stringlengths 2 84 ⌀ | created timestamp[us] | card stringlengths 101 901k | card_len int64 101 901k | embeddings list |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
sanchit-gandhi/whisper-small-ft-common-language-id | 2023-09-18T14:29:46.000Z | [
"transformers",
"pytorch",
"tensorboard",
"safetensors",
"whisper",
"audio-classification",
"generated_from_trainer",
"dataset:common_language",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | audio-classification | sanchit-gandhi | null | null | sanchit-gandhi/whisper-small-ft-common-language-id | 0 | 557 | transformers | 2023-02-24T12:26:04 | ---
license: apache-2.0
tags:
- audio-classification
- generated_from_trainer
datasets:
- common_language
metrics:
- accuracy
base_model: openai/whisper-small
model-index:
- name: whisper-small-ft-common-language-id
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# whisper-small-ft-common-language-id
This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the common_language dataset.
It achieves the following results on the evaluation set:
- Loss: 0.6409
- Accuracy: 0.8860
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 1e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 0
- gradient_accumulation_steps: 2
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 10.0
- mixed_precision_training: Native AMP
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 1.1767 | 1.0 | 694 | 1.1063 | 0.7514 |
| 0.582 | 2.0 | 1388 | 0.6595 | 0.8327 |
| 0.3172 | 3.0 | 2082 | 0.5887 | 0.8529 |
| 0.196 | 4.0 | 2776 | 0.5332 | 0.8701 |
| 0.0858 | 5.0 | 3470 | 0.5705 | 0.8733 |
| 0.0477 | 6.0 | 4164 | 0.6311 | 0.8779 |
| 0.0353 | 7.0 | 4858 | 0.6011 | 0.8825 |
| 0.0033 | 8.0 | 5552 | 0.6186 | 0.8843 |
| 0.0071 | 9.0 | 6246 | 0.6409 | 0.8860 |
| 0.0074 | 10.0 | 6940 | 0.6334 | 0.8860 |
### Framework versions
- Transformers 4.27.0.dev0
- Pytorch 1.13.1
- Datasets 2.9.0
- Tokenizers 0.13.2
| 2,156 | [
[
-0.032745361328125,
-0.039764404296875,
0.00339508056640625,
0.005092620849609375,
-0.022705078125,
-0.0308990478515625,
-0.0212554931640625,
-0.021026611328125,
0.02001953125,
0.017425537109375,
-0.051971435546875,
-0.048187255859375,
-0.04766845703125,
-0.... |
Helsinki-NLP/opus-mt-uk-es | 2023-08-16T12:08:05.000Z | [
"transformers",
"pytorch",
"tf",
"marian",
"text2text-generation",
"translation",
"uk",
"es",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | translation | Helsinki-NLP | null | null | Helsinki-NLP/opus-mt-uk-es | 0 | 556 | transformers | 2022-03-02T23:29:04 | ---
tags:
- translation
license: apache-2.0
---
### opus-mt-uk-es
* source languages: uk
* target languages: es
* OPUS readme: [uk-es](https://github.com/Helsinki-NLP/OPUS-MT-train/blob/master/models/uk-es/README.md)
* dataset: opus
* model: transformer-align
* pre-processing: normalization + SentencePiece
* download original weights: [opus-2020-01-16.zip](https://object.pouta.csc.fi/OPUS-MT-models/uk-es/opus-2020-01-16.zip)
* test set translations: [opus-2020-01-16.test.txt](https://object.pouta.csc.fi/OPUS-MT-models/uk-es/opus-2020-01-16.test.txt)
* test set scores: [opus-2020-01-16.eval.txt](https://object.pouta.csc.fi/OPUS-MT-models/uk-es/opus-2020-01-16.eval.txt)
## Benchmarks
| testset | BLEU | chr-F |
|-----------------------|-------|-------|
| Tatoeba.uk.es | 50.4 | 0.680 |
| 818 | [
[
-0.0158538818359375,
-0.0217742919921875,
0.016510009765625,
0.0227813720703125,
-0.0357666015625,
-0.02734375,
-0.0302886962890625,
-0.0078277587890625,
0.004077911376953125,
0.03155517578125,
-0.053955078125,
-0.043731689453125,
-0.042999267578125,
0.01988... |
HooshvareLab/distilbert-fa-zwnj-base | 2021-03-16T16:30:29.000Z | [
"transformers",
"pytorch",
"tf",
"distilbert",
"fill-mask",
"fa",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | fill-mask | HooshvareLab | null | null | HooshvareLab/distilbert-fa-zwnj-base | 1 | 556 | transformers | 2022-03-02T23:29:04 | ---
language: fa
license: apache-2.0
---
# DistilBERT
This model can tackle the zero-width non-joiner character for Persian writing. Also, the model was trained on new multi-types corpora with a new set of vocabulary.
## Questions?
Post a Github issue on the [ParsBERT Issues](https://github.com/hooshvare/parsbert/issues) repo. | 332 | [
[
-0.020263671875,
-0.051849365234375,
0.05419921875,
-0.007144927978515625,
-0.0261688232421875,
0.0162353515625,
-0.01436614990234375,
-0.0178375244140625,
0.022369384765625,
0.05206298828125,
-0.047454833984375,
-0.044097900390625,
-0.03253173828125,
0.0059... |
lighteternal/wav2vec2-large-xlsr-53-greek | 2022-03-26T10:12:37.000Z | [
"transformers",
"pytorch",
"jax",
"wav2vec2",
"automatic-speech-recognition",
"audio",
"hf-asr-leaderboard",
"speech",
"xlsr-fine-tuning-week",
"el",
"dataset:common_voice",
"license:apache-2.0",
"model-index",
"endpoints_compatible",
"has_space",
"region:us"
] | automatic-speech-recognition | lighteternal | null | null | lighteternal/wav2vec2-large-xlsr-53-greek | 5 | 556 | transformers | 2022-03-02T23:29:05 | ---
language: el
datasets:
- common_voice
tags:
- audio
- hf-asr-leaderboard
- automatic-speech-recognition
- speech
- xlsr-fine-tuning-week
license: apache-2.0
model-index:
- name: XLSR Wav2Vec2 Greek by Lighteternal
results:
- task:
name: Speech Recognition
type: automatic-speech-recognition
dataset:
name: CommonVoice (EL), CSS10 (EL)
type: CCS10 + mozilla-foundation/common_voice_7_0
args: el
metrics:
- name: Test WER
type: wer
value: 10.497628
- name: Test CER
type: cer
value: 2.875260
---
# Greek (el) version of the XLSR-Wav2Vec2 automatic speech recognition (ASR) model
### By the Hellenic Army Academy and the Technical University of Crete
* language: el
* licence: apache-2.0
* dataset: CommonVoice (EL), 364MB: https://commonvoice.mozilla.org/el/datasets + CSS10 (EL), 1.22GB: https://github.com/Kyubyong/css10
* model: XLSR-Wav2Vec2, trained for 50 epochs
* metrics: Word Error Rate (WER)
## Model description
UPDATE: We repeated the fine-tuning process using an additional 1.22GB dataset from CSS10.
Wav2Vec2 is a pretrained model for Automatic Speech Recognition (ASR) and was released in September 2020 by Alexei Baevski, Michael Auli, and Alex Conneau. Soon after the superior performance of Wav2Vec2 was demonstrated on the English ASR dataset LibriSpeech, Facebook AI presented XLSR-Wav2Vec2. XLSR stands for cross-lingual speech representations and refers to XLSR-Wav2Vec2`s ability to learn speech representations that are useful across multiple languages.
Similar to Wav2Vec2, XLSR-Wav2Vec2 learns powerful speech representations from hundreds of thousands of hours of speech in more than 50 languages of unlabeled speech. Similar, to BERT's masked language modeling, the model learns contextualized speech representations by randomly masking feature vectors before passing them to a transformer network.
This model was trained for 50 epochs on a single NVIDIA RTX 3080, for aprox. 8hrs.
## How to use for inference:
For live demo, make sure that speech files are sampled at 16kHz.
Instructions to test on CommonVoice extracts are provided in the ASR_Inference.ipynb. Snippet also available below:
```python
#!/usr/bin/env python
# coding: utf-8
# Loading dependencies and defining preprocessing functions
from transformers import Wav2Vec2ForCTC
from transformers import Wav2Vec2Processor
from datasets import load_dataset, load_metric
import re
import torchaudio
import librosa
import numpy as np
from datasets import load_dataset, load_metric
import torch
chars_to_ignore_regex = '[\\\\\\\\,\\\\\\\\?\\\\\\\\.\\\\\\\\!\\\\\\\\-\\\\\\\\;\\\\\\\\:\\\\\\\\"\\\\\\\\“\\\\\\\\%\\\\\\\\‘\\\\\\\\”\\\\\\\\�]'
def remove_special_characters(batch):
batch["text"] = re.sub(chars_to_ignore_regex, '', batch["sentence"]).lower() + " "
return batch
def speech_file_to_array_fn(batch):
speech_array, sampling_rate = torchaudio.load(batch["path"])
batch["speech"] = speech_array[0].numpy()
batch["sampling_rate"] = sampling_rate
batch["target_text"] = batch["text"]
return batch
def resample(batch):
batch["speech"] = librosa.resample(np.asarray(batch["speech"]), 48_000, 16_000)
batch["sampling_rate"] = 16_000
return batch
def prepare_dataset(batch):
# check that all files have the correct sampling rate
assert (
len(set(batch["sampling_rate"])) == 1
), f"Make sure all inputs have the same sampling rate of {processor.feature_extractor.sampling_rate}."
batch["input_values"] = processor(batch["speech"], sampling_rate=batch["sampling_rate"][0]).input_values
with processor.as_target_processor():
batch["labels"] = processor(batch["target_text"]).input_ids
return batch
# Loading model and dataset processor
model = Wav2Vec2ForCTC.from_pretrained("lighteternal/wav2vec2-large-xlsr-53-greek").to("cuda")
processor = Wav2Vec2Processor.from_pretrained("lighteternal/wav2vec2-large-xlsr-53-greek")
# Preparing speech dataset to be suitable for inference
common_voice_test = load_dataset("common_voice", "el", split="test")
common_voice_test = common_voice_test.remove_columns(["accent", "age", "client_id", "down_votes", "gender", "locale", "segment", "up_votes"])
common_voice_test = common_voice_test.map(remove_special_characters, remove_columns=["sentence"])
common_voice_test = common_voice_test.map(speech_file_to_array_fn, remove_columns=common_voice_test.column_names)
common_voice_test = common_voice_test.map(resample, num_proc=8)
common_voice_test = common_voice_test.map(prepare_dataset, remove_columns=common_voice_test.column_names, batch_size=8, num_proc=8, batched=True)
# Loading test dataset
common_voice_test_transcription = load_dataset("common_voice", "el", split="test")
#Performing inference on a random sample. Change the "example" value to try inference on different CommonVoice extracts
example = 123
input_dict = processor(common_voice_test["input_values"][example], return_tensors="pt", sampling_rate=16_000, padding=True)
logits = model(input_dict.input_values.to("cuda")).logits
pred_ids = torch.argmax(logits, dim=-1)
print("Prediction:")
print(processor.decode(pred_ids[0]))
# πού θέλεις να πάμε ρώτησε φοβισμένα ο βασιλιάς
print("\\\\
Reference:")
print(common_voice_test_transcription["sentence"][example].lower())
# πού θέλεις να πάμε; ρώτησε φοβισμένα ο βασιλιάς.
```
## Evaluation
The model can be evaluated as follows on the Greek test data of Common Voice.
```python
import torch
import torchaudio
from datasets import load_dataset, load_metric
from transformers import Wav2Vec2ForCTC, Wav2Vec2Processor
import re
test_dataset = load_dataset("common_voice", "el", split="test")
wer = load_metric("wer")
processor = Wav2Vec2Processor.from_pretrained("lighteternal/wav2vec2-large-xlsr-53-greek")
model = Wav2Vec2ForCTC.from_pretrained("lighteternal/wav2vec2-large-xlsr-53-greek")
model.to("cuda")
chars_to_ignore_regex = '[\\\\\\\\,\\\\\\\\?\\\\\\\\.\\\\\\\\!\\\\\\\\-\\\\\\\\;\\\\\\\\:\\\\\\\\"\\\\\\\\“\\\\\\\\%\\\\\\\\‘\\\\\\\\”\\\\\\\\�]'
resampler = torchaudio.transforms.Resample(48_000, 16_000)
# Preprocessing the datasets.
# We need to read the aduio files as arrays
def speech_file_to_array_fn(batch):
batch["sentence"] = re.sub(chars_to_ignore_regex, '', batch["sentence"]).lower()
speech_array, sampling_rate = torchaudio.load(batch["path"])
batch["speech"] = resampler(speech_array).squeeze().numpy()
return batch
test_dataset = test_dataset.map(speech_file_to_array_fn)
# Preprocessing the datasets.
# We need to read the aduio files as arrays
def evaluate(batch):
inputs = processor(batch["speech"], sampling_rate=16_000, return_tensors="pt", padding=True)
with torch.no_grad():
logits = model(inputs.input_values.to("cuda"), attention_mask=inputs.attention_mask.to("cuda")).logits
pred_ids = torch.argmax(logits, dim=-1)
batch["pred_strings"] = processor.batch_decode(pred_ids)
return batch
result = test_dataset.map(evaluate, batched=True, batch_size=8)
print("WER: {:2f}".format(100 * wer.compute(predictions=result["pred_strings"], references=result["sentence"])))
```
**Test Result**: 10.497628 %
### How to use for training:
Instructions and code to replicate the process are provided in the Fine_Tune_XLSR_Wav2Vec2_on_Greek_ASR_with_🤗_Transformers.ipynb notebook.
## Metrics
| Metric | Value |
| ----------- | ----------- |
| Training Loss | 0.0545 |
| Validation Loss | 0.1661 |
| CER on CommonVoice Test (%) *| 2.8753 |
| WER on CommonVoice Test (%) *| 10.4976 |
* Reference transcripts were lower-cased and striped of punctuation and special characters.
### Acknowledgement
The research work was supported by the Hellenic Foundation for Research and Innovation (HFRI) under the HFRI PhD Fellowship grant (Fellowship Number:50, 2nd call)
Based on the tutorial of Patrick von Platen: https://huggingface.co/blog/fine-tune-xlsr-wav2vec2
Original colab notebook here: https://colab.research.google.com/github/patrickvonplaten/notebooks/blob/master/Fine_Tune_XLSR_Wav2Vec2_on_Turkish_ASR_with_%F0%9F%A4%97_Transformers.ipynb#scrollTo=V7YOT2mnUiea
| 8,209 | [
[
-0.0266876220703125,
-0.051544189453125,
0.0005369186401367188,
0.00991058349609375,
-0.0188446044921875,
-0.011505126953125,
-0.042938232421875,
-0.0316162109375,
0.008941650390625,
0.019927978515625,
-0.04833984375,
-0.038055419921875,
-0.03887939453125,
0... |
OpenAssistant/falcon-40b-sft-mix-1226 | 2023-06-06T10:23:05.000Z | [
"transformers",
"pytorch",
"RefinedWeb",
"text-generation",
"sft",
"custom_code",
"en",
"de",
"es",
"fr",
"dataset:OpenAssistant/oasst1",
"dataset:databricks/databricks-dolly-15k",
"license:apache-2.0",
"has_space",
"text-generation-inference",
"region:us"
] | text-generation | OpenAssistant | null | null | OpenAssistant/falcon-40b-sft-mix-1226 | 34 | 556 | transformers | 2023-06-04T05:51:59 | ---
license: apache-2.0
language:
- en
- de
- es
- fr
tags:
- sft
inference: false
datasets:
- OpenAssistant/oasst1
- databricks/databricks-dolly-15k
---
# Open-Assistant Falcon 40B SFT MIX Model
This model is a fine-tuning of TII's [Falcon 40B](https://huggingface.co/tiiuae/falcon-40b) LLM.
It was trained on a mixture of OASST top-2 threads (exported on June 2, 2023), Dolly-15k and synthetic instruction datasets (see dataset configuration below).
## Model Details
- **Finetuned from:** [tiiuae/falcon-40b]((https://huggingface.co/tiiuae/falcon-40b)
- **Model type:** Causal decoder-only transformer language model
- **Language:** English, German, Spanish, French (and limited capabilities in Italian, Portuguese, Polish, Dutch, Romanian, Czech, Swedish);
- **Demo:** [Continuations for 250 random prompts](https://open-assistant.github.io/oasst-model-eval/?f=https%3A%2F%2Fraw.githubusercontent.com%2FOpen-Assistant%2Foasst-model-eval%2Fmain%2Fsampling_reports%2Fchat-gpt%2F2023-04-11_gpt-3.5-turbo_lottery.json%0Ahttps%3A%2F%2Fraw.githubusercontent.com%2FOpen-Assistant%2Foasst-model-eval%2Fmain%2Fsampling_reports%2Foasst-sft%2F2023-06-05_OpenAssistant_falcon-40b-sft-mix-1226_sampling_noprefix2.json), [multiligual-60](https://open-assistant.github.io/oasst-model-eval/?f=https%3A%2F%2Fraw.githubusercontent.com%2FOpen-Assistant%2Foasst-model-eval%2Fmain%2Fsampling_reports%2Foasst-sft%2F2023-06-05_OpenAssistant_falcon-40b-sft-mix-1226_multilingual_noprefix2.json)
- **Eval results:** [ilm-eval](https://tju01.github.io/ilm-eval/)
- **Weights & Biases**: [Training log](https://wandb.ai/open-assistant/public-sft/runs/feplc450) (checkpoint: 1226 steps)
- **License:** Apache 2.0
- **Contact:** [Open-Assistant Discord](https://ykilcher.com/open-assistant-discord)
## Prompting
Two special tokens are used to mark the beginning of user and assistant turns:
`<|prompter|>` and `<|assistant|>`. Each turn ends with a `<|endoftext|>` token.
Input prompt example:
```
<|prompter|>What is a meme, and what's the history behind this word?<|endoftext|><|assistant|>
```
The input ends with the `<|assistant|>` token to signal that the model should
start generating the assistant reply.
## Configuration Details
Model:
```
falcon-40b:
dtype: bf16
learning_rate: 1e-5
model_name: "tiiuae/falcon-40b"
deepspeed_config: configs/zero3_config_falcon.json
weight_decay: 0.0
max_length: 2048
warmup_steps: 20
gradient_checkpointing: true
gradient_accumulation_steps: 1
per_device_train_batch_size: 18
per_device_eval_batch_size: 10
eval_steps: 120
save_strategy: steps
save_steps: 613
num_train_epochs: 8
save_total_limit: 4
use_flash_attention: false
residual_dropout: 0.3
residual_dropout_lima: true
```
Dataset:
```
sft9-stage2:
# oasst_export: 100.00% (29899)
# vicuna: 50.00% (16963)
# code_alpaca: 50.00% (9510)
# oa_wiki_qa_bart_10000row: 100.00% (9434)
# grade_school_math_instructions: 100.00% (8351)
# dolly15k: 100.00% (14250)
use_custom_sampler: true
datasets:
- oasst_export:
lang: "bg,ca,cs,da,de,en,es,fr,hr,hu,it,nl,pl,pt,ro,ru,sl,sr,sv,uk" # sft-8.0
input_file_path: 2023-06-02_oasst_all_labels.jsonl.gz
val_split: 0.05
top_k: 2
- vicuna:
fraction: 0.5
val_split: 0.025
max_val_set: 250
- code_alpaca:
fraction: 0.5
val_split: 0.05
max_val_set: 250
- oa_wiki_qa_bart_10000row:
val_split: 0.05
max_val_set: 250
- grade_school_math_instructions:
val_split: 0.05
- dolly15k:
val_split: 0.05
max_val_set: 300
``` | 3,631 | [
[
-0.048675537109375,
-0.06671142578125,
0.0147857666015625,
0.0162353515625,
-0.0017232894897460938,
0.00556182861328125,
-0.0016717910766601562,
-0.01439666748046875,
0.02783203125,
0.026763916015625,
-0.060333251953125,
-0.038818359375,
-0.03948974609375,
0... |
OpenAssistant/reward-model-deberta-v3-base | 2023-01-26T01:07:57.000Z | [
"transformers",
"pytorch",
"deberta-v2",
"text-classification",
"reward-model",
"reward_model",
"RLHF",
"en",
"dataset:openai/webgpt_comparisons",
"dataset:openai/summarize_from_feedback",
"dataset:Dahoas/instruct-synthetic-prompt-responses",
"license:mit",
"endpoints_compatible",
"region:... | text-classification | OpenAssistant | null | null | OpenAssistant/reward-model-deberta-v3-base | 6 | 555 | transformers | 2023-01-15T11:06:39 | ---
license: mit
datasets:
- openai/webgpt_comparisons
- openai/summarize_from_feedback
- Dahoas/instruct-synthetic-prompt-responses
language:
- en
metrics:
- accuracy
tags:
- reward-model
- reward_model
- RLHF
---
# Reward model trained from human feedback
Reward model (RM) trained to predict which generated answer is better judged by a human, given a question.
RM are useful in these domain:
- QA model evaluation
- serves as reward score in RLHF
All models are train on these dataset with a same split seed across datasets (if validation split wasn't available)
- [webgpt_comparisons](https://huggingface.co/datasets/openai/webgpt_comparisons)
- [summarize_from_feedback](https://huggingface.co/datasets/openai/summarize_from_feedback)
- [synthetic-instruct-gptj-pairwise](https://huggingface.co/datasets/Dahoas/synthetic-instruct-gptj-pairwise)
# How to use
```
from transformers import AutoModelForSequenceClassification, AutoTokenizer
reward_name = "OpenAssistant/reward-model-deberta-v3-base"
rank_model, tokenizer = AutoModelForSequenceClassification.from_pretrained(reward_name), AutoTokenizer.from_pretrained(reward_name)
question, answer = "Explain nuclear fusion like I am five", "Nuclear fusion is the process by which two or more protons and neutrons combine to form a single nucleus. It is a very important process in the universe, as it is the source of energy for stars and galaxies. Nuclear fusion is also a key process in the production of energy for nuclear power plants."
inputs = tokenizer(question, answer, return_tensors='pt')
score = rank_model(**inputs).logits[0].cpu().detach()
print(score)
```
# Performance
Validation split accuracy
| Model | [WebGPT](https://huggingface.co/datasets/openai/webgpt_comparisons) | [Summary](https://huggingface.co/datasets/openai/summarize_from_feedback) | [SytheticGPT](https://huggingface.co/datasets/Dahoas/synthetic-instruct-gptj-pairwise) |
|---|---|---|---|
| [electra-large-discriminator](https://huggingface.co/OpenAssistant/reward-model-electra-large-discriminator) | 59.30 | 68.66 | 99.85 |
| [deberta-v3-large](https://huggingface.co/OpenAssistant/reward-model-deberta-v3-large) | 61.13 | 72.23 | 99.94 |
| [deberta-v3-base](https://huggingface.co/OpenAssistant/reward-model-deberta-v3-base) | 59.07 | 66.84 | 99.85 |
Its likely SytheticGPT has somekind of surface pattern on the choosen-rejected pair which makes it trivial to differentiate between better the answer. | 2,475 | [
[
-0.0462646484375,
-0.03338623046875,
0.012542724609375,
0.006229400634765625,
-0.01079559326171875,
-0.0034389495849609375,
0.0100250244140625,
-0.02386474609375,
0.007785797119140625,
0.0112762451171875,
-0.05279541015625,
-0.0178375244140625,
-0.03765869140625... |
davolu/stacco-ai-interior-v3k | 2023-07-27T00:36:17.000Z | [
"diffusers",
"text-to-image",
"stable-diffusion",
"license:creativeml-openrail-m",
"endpoints_compatible",
"has_space",
"diffusers:StableDiffusionPipeline",
"region:us"
] | text-to-image | davolu | null | null | davolu/stacco-ai-interior-v3k | 0 | 555 | diffusers | 2023-07-26T23:51:27 | ---
license: creativeml-openrail-m
tags:
- text-to-image
- stable-diffusion
---
### stacco_ai_interior_v3k Dreambooth model trained by David Oluyale
Test the concept via A1111 Colab [fast-Colab-A1111](https://colab.research.google.com/github/TheLastBen/fast-stable-diffusion/blob/main/fast_stable_diffusion_AUTOMATIC1111.ipynb)
| 333 | [
[
-0.0293121337890625,
-0.05584716796875,
0.0491943359375,
0.0217132568359375,
-0.0098419189453125,
0.01385498046875,
0.02294921875,
-0.025390625,
0.0362548828125,
0.01079559326171875,
-0.0206298828125,
-0.032562255859375,
-0.029937744140625,
-0.01870727539062... |
foduucom/plant-leaf-detection-and-classification | 2023-08-12T10:55:32.000Z | [
"ultralytics",
"tensorboard",
"v8",
"ultralyticsplus",
"yolov8",
"yolo",
"vision",
"object-detection",
"pytorch",
"awesome-yolov8-models",
"plant classification",
"plant detection",
"leaf classification",
"leaf detection",
"crop detection",
"disease detection",
"en",
"model-index",... | object-detection | foduucom | null | null | foduucom/plant-leaf-detection-and-classification | 4 | 555 | ultralytics | 2023-08-12T10:45:05 | ---
tags:
- ultralyticsplus
- yolov8
- ultralytics
- yolo
- vision
- object-detection
- pytorch
- awesome-yolov8-models
- plant classification
- plant detection
- leaf classification
- leaf detection
- crop detection
- disease detection
library_name: ultralytics
library_version: 8.0.43
inference: False
model-index:
- name: foduucom/plant-leaf-detection-and-classification
results:
- task:
type: object-detection
metrics:
- type: precision
value: 0.946
name: mAP@0.5(box)
language:
- en
metrics:
- accuracy
---
Below is the Model Card for the YOLOv8s Leaf Detection and Classification model:
---
<p align="center">
<!-- Smaller size image -->
<img src="https://huggingface.co/foduucom/plant-leaf-detection-and-classification/resolve/main/thumbnail.jpg" alt="Image" style="width:500px; height:300px;">
</p>
# Model Card for YOLOv8s Leaf Detection and Classification
## Model Summary
The YOLOv8s Leaf Detection and Classification model is an object detection model based on the YOLO (You Only Look Once) framework. It is designed to detect and classify various types of leaves in images. The model has achieved a precision (mAP@0.5) of 0.946 on the object detection task.
## Model Details
### Model Description
The YOLOv8s Leaf Detection and Classification model is built on the YOLOv8 architecture, which is known for its real-time object detection capabilities. This specific model has been trained to recognize and classify different types of leaves from various plant species. It can detect multiple leaf instances in an image and assign them to their respective classes.
```
['ginger', 'banana', 'tobacco', 'ornamaental', 'rose', 'soyabean', 'papaya', 'garlic', 'raspberry', 'mango', 'cotton', 'corn', 'pomgernate', 'strawberry', 'Blueberry', 'brinjal', 'potato', 'wheat', 'olive', 'rice', 'lemon', 'cabbage', 'gauava', 'chilli', 'capcicum', 'sunflower', 'cherry', 'cassava', 'apple', 'tea', 'sugarcane', 'groundnut', 'weed', 'peach', 'coffee', 'cauliflower', 'tomato', 'onion', 'gram', 'chiku', 'jamun', 'castor', 'pea', 'cucumber', 'grape', 'cardamom']
```
- **Developed by:** FODUU AI
- **Model type:** Object Detection
- **Language(s) (NLP):** English
Furthermore, the YOLOv8s Leaf Detection and Classification model encourages user collaboration by allowing them to contribute their own plant leaf data. Users can submit images of new plant species, and suggest plant names for classification. Our team will diligently work to incorporate these new plant classes into the model, enhancing its ability to identify and classify an even wider variety of plant leaves.
Users are invited to actively participate in expanding the YOLOv8s Leaf Detection and Classification model's capabilities by sharing their plant names and corresponding dataset links through our community platform or by emailing the information to info@foduu.com. Your contributions will play a crucial role in enriching the model's knowledge and recognition of diverse plant species.
## Uses
### Direct Use
The YOLOv8s Leaf Detection and Classification model can be used directly for object detection tasks related to leaf detection and classification. It does not require fine-tuning or integration into a larger ecosystem or application.
### Downstream Use
The model can also be fine-tuned for specific leaf detection and classification tasks or integrated into a larger application for plant-related research, agriculture, or environmental monitoring.
### Out-of-Scope Use
The model is not designed for unrelated tasks or object detection scenarios outside the scope of leaf detection and classification.
## Bias, Risks, and Limitations
The YOLOv8s Leaf Detection and Classification model may have some limitations and biases:
- The model's performance may vary depending on the quality and diversity of the training data.
- It may struggle with detecting leaves that are heavily occluded or overlapping with other objects.
- The model's accuracy may be affected by variations in lighting conditions, image quality, and resolution.
- It may not accurately detect very small or distant leaves in images.
- The model's classification accuracy may be lower for leaf species that resemble each other closely.
- The model's biases may stem from the biases present in the training data.
### Recommendations
Users (both direct and downstream) should be made aware of the risks, biases, and limitations of the model. Further research and experimentation are recommended to assess its performance in specific use cases and domains.
## How to Get Started with the Model
To get started with the YOLOv8s Leaf Detection and Classification model, follow these steps:
1. Install [ultralyticsplus](https://github.com/fcakyon/ultralyticsplus) and [ultralytics](https://github.com/ultralytics/ultralytics) libraries using pip:
```bash
pip install ultralyticsplus==0.0.28 ultralytics==8.0.43
```
2. Load the model and perform prediction using the provided code snippet.
```python
from ultralyticsplus import YOLO, render_result
# load model
model = YOLO('foduucom/plant-leaf-detection-and-classification')
# set model parameters
model.overrides['conf'] = 0.25 # NMS confidence threshold
model.overrides['iou'] = 0.45 # NMS IoU threshold
model.overrides['agnostic_nms'] = False # NMS class-agnostic
model.overrides['max_det'] = 1000 # maximum number of detections per image
# set image
image = 'path/to/your/image'
# perform inference
results = model.predict(image)
# observe results
print(results[0].boxes)
render = render_result(model=model, image=image, result=results[0])
render.show()
```
## Training Details
### Training Data
The model is trained on hundreds of images of 46 different plants, including both disease-infected and healthy leaves.
### Training Procedure
The training process involves using high GPU capacity and is run for up to 50 epochs, where each epoch represents a complete pass through the entire training dataset, adjusting model weights to minimize the classification loss and optimize the performance.
#### Metrics
- mAP@0.5 (box):
0.946
#### Summary
YOLOv8s is a powerful convolutional neural network tailored for leaf detection and classification of over 46 plant species. It leverages a modified CSPDarknet53 backbone, self-attention mechanism, and a feature pyramid network for accurate multi-scaled object detection, providing precise identification and classification of plant leaves.
### Model Architecture and Objective
YOLOv8 architecture utilizes a modified CSPDarknet53 as its backbone with 53 convolutional layers and cross-stage partial connections for improved information flow. The head consists of convolutional and fully connected layers for predicting bounding boxes, objectness scores, and class probabilities. It incorporates a self-attention mechanism and a feature pyramid network for multi-scaled object detection, enabling focus on relevant image features and detecting objects of different sizes.
### Compute Infrastructure
#### Hardware
NVIDIA A100 40GB GPU card
#### Software
Jupyter Notebook environment for model training.
## Model Card Contact
info@foduu.com
```bibtex
@ModelCard{
author = {Nehul Agrawal and
Pranjal singh Thakur},
title = { YOLOv8s Leaf Detection and Classification},
year = {2023}
}
```
--- | 7,348 | [
[
-0.018798828125,
-0.026397705078125,
0.0222625732421875,
-0.05224609375,
-0.0287628173828125,
-0.03350830078125,
0.0185089111328125,
-0.0633544921875,
-0.0006222724914550781,
0.017425537109375,
-0.028656005859375,
-0.043121337890625,
-0.02679443359375,
0.005... |
jinhybr/OCR-Donut-CORD | 2022-11-05T00:07:44.000Z | [
"transformers",
"pytorch",
"vision-encoder-decoder",
"donut",
"image-to-text",
"vision",
"arxiv:2111.15664",
"license:mit",
"endpoints_compatible",
"has_space",
"region:us"
] | image-to-text | jinhybr | null | null | jinhybr/OCR-Donut-CORD | 36 | 554 | transformers | 2022-11-04T13:22:17 | ---
license: mit
tags:
- donut
- image-to-text
- vision
---
# Donut (base-sized model, fine-tuned on CORD)
Donut model fine-tuned on CORD. It was introduced in the paper [OCR-free Document Understanding Transformer](https://arxiv.org/abs/2111.15664) by Geewok et al. and first released in [this repository](https://github.com/clovaai/donut).
Disclaimer: The team releasing Donut did not write a model card for this model so this model card has been written by the Hugging Face team.
## Model description
Donut consists of a vision encoder (Swin Transformer) and a text decoder (BART). Given an image, the encoder first encodes the image into a tensor of embeddings (of shape batch_size, seq_len, hidden_size), after which the decoder autoregressively generates text, conditioned on the encoding of the encoder.
## Intended uses & limitations
This model is fine-tuned on CORD, a document parsing dataset.
We refer to the [documentation](https://huggingface.co/docs/transformers/main/en/model_doc/donut) which includes code examples.
## CORD Dataset
CORD: A Consolidated Receipt Dataset for Post-OCR Parsing.
| 1,342 | [
[
-0.02252197265625,
-0.042724609375,
0.02154541015625,
-0.0223846435546875,
-0.0201873779296875,
0.0039520263671875,
-0.00617218017578125,
-0.03131103515625,
0.0204315185546875,
0.044403076171875,
-0.038055419921875,
-0.021453857421875,
-0.048980712890625,
-0... |
melaris/sarabala | 2023-09-30T01:10:18.000Z | [
"diffusers",
"text-to-image",
"stable-diffusion",
"license:creativeml-openrail-m",
"endpoints_compatible",
"has_space",
"diffusers:StableDiffusionPipeline",
"region:us"
] | text-to-image | melaris | null | null | melaris/sarabala | 1 | 554 | diffusers | 2023-09-27T11:14:45 | ---
license: creativeml-openrail-m
tags:
- text-to-image
- stable-diffusion
---
### SaraBala Dreambooth model trained by melaris with [TheLastBen's fast-DreamBooth](https://colab.research.google.com/github/TheLastBen/fast-stable-diffusion/blob/main/fast-DreamBooth.ipynb) notebook
Test the concept via A1111 Colab [fast-Colab-A1111](https://colab.research.google.com/github/TheLastBen/fast-stable-diffusion/blob/main/fast_stable_diffusion_AUTOMATIC1111.ipynb)
Sample pictures of this concept: | 495 | [
[
-0.0207366943359375,
-0.050323486328125,
0.035400390625,
0.041107177734375,
-0.02911376953125,
0.035308837890625,
0.0233154296875,
-0.0168914794921875,
0.04779052734375,
0.01715087890625,
-0.0189208984375,
-0.02862548828125,
-0.036590576171875,
-0.0114288330... |
davidkim205/komt-mistral-7b-v1 | 2023-10-24T04:41:07.000Z | [
"transformers",
"pytorch",
"mistral",
"text-generation",
"finetuned",
"en",
"ko",
"arxiv:2308.06502",
"arxiv:2308.06259",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | davidkim205 | null | null | davidkim205/komt-mistral-7b-v1 | 4 | 554 | transformers | 2023-10-24T01:58:52 | ---
language:
- en
- ko
pipeline_tag: text-generation
tags:
- finetuned
---
# komt : korean multi task instruction tuning model
Recently, due to the success of ChatGPT, numerous large language models have emerged in an attempt to catch up with ChatGPT's capabilities.
However, when it comes to Korean language performance, it has been observed that many models still struggle to provide accurate answers or generate Korean text effectively.
This study addresses these challenges by introducing a multi-task instruction technique that leverages supervised datasets from various tasks to create training data for Large Language Models (LLMs).
## Model Details
* **Model Developers** : davidkim(changyeon kim)
* **Repository** : https://github.com/davidkim205/komt
* **Model Architecture** : The komt-mistral-7b-v1 is is a fine-tuned version of the Mistral-7B-Instruct-v0.1.
## Dataset
korean multi-task instruction dataset
## Hardware and Software
- nvidia driver : 535.54.03
- CUDA Version: 12.2
## Training
Refer https://github.com/davidkim205/komt
## Prompt template: Mistral
```
<s>[INST] {prompt} [/INST]</s>
```
## Usage
```
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers import TextStreamer, GenerationConfig
model_name='davidkim205/komt-mistral-7b-v1'
model = AutoModelForCausalLM.from_pretrained(model_name, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)
streamer = TextStreamer(tokenizer)
def gen(x):
generation_config = GenerationConfig(
temperature=0.8,
top_p=0.8,
top_k=100,
max_new_tokens=1024,
early_stopping=True,
do_sample=True,
)
q = f"[INST]{x} [/INST]"
gened = model.generate(
**tokenizer(
q,
return_tensors='pt',
return_token_type_ids=False
).to('cuda'),
generation_config=generation_config,
pad_token_id=tokenizer.eos_token_id,
eos_token_id=tokenizer.eos_token_id,
streamer=streamer,
)
result_str = tokenizer.decode(gened[0])
start_tag = f"\n\n### Response: "
start_index = result_str.find(start_tag)
if start_index != -1:
result_str = result_str[start_index + len(start_tag):].strip()
return result_str
print(gen('제주도를 1박2일로 혼자 여행하려고 하는데 여행 코스를 만들어줘'))
```
output
```
<s> [INST]제주도를 1박2일로 혼자 여행하려고 하는데 여행 코스를 만들어줘 [/INST]1박 2일 여행 코스
제주 여행 코스는 다음과 같습니다:
첫째 날:
* 아침: 제주시 신라로 이동하여 한라산 국립공원에 도착합니다. 오른쪽 발자국 광장에서 눈에 띄는 맥주숍을 찾아 한 병의 맥주를 마시고 계단으로 올라가 한라산 정상에 도착합니다.
* 점심: 정상에서 계단을 내려와 중도에 위치한 골목에서 음식을 즐깁니다. 젓갈, 곰탕, 전복 등 맛있는 제주 특산물을 맛보며 힐링을 즐깁니다.
* 오후: 중도에서 남하하여 남서쪽 제주로 이동합니다. 남서쪽 제주는 섬의 자연 경관과 백사장, 아름다운 바다 등 아름다운 풍광이 있는 곳입니다. 숙소에 숙박합니다.
둘째 날:
* 아침: 남서쪽 제주에서 북서쪽 제주로 이동합니다. 이 지역은 푸른 잔디 해변과 투명한 바다가 펼쳐져 있는 아름다운 풍광입니다. 숙소에서 아침을 먹고 바다로 향하여 해변에서 휴식을 취합니다.
* 점심: 북서쪽 제주의 앞바다에서 시원한 바다를 보며 한 끼의 해산물을 맛보고 계절에 따라 해산물 요리를 즐깁니다.
* 오후: 남서쪽 제주에서 이동하여 서쪽 제주로 이동합니다. 서쪽 제주는 절벽과 암석 해변, 수수께끼의 돌 정원 등 독특한 경관이 있는 곳입니다. 이곳에서는 서쪽 제주의 대표적인 명소인 청량사를 방문하고 서쪽 제주의 아름다운 풍광을 감상합니다.
* 저녁: 서쪽 제주에서 제주 시로 이동하여 한 끼의 제주 특산물을 맛보고 도착한 제주 도심에서 저녁을 즐깁니다.
* 야간: 제주 시의 도심에서 야간 활동을 즐기며 1박 2일의 여행을 마무리합니다.
이렇게 제주를 1박 2일로 혼자 여행하면 제주의 아름다운 풍광, 푸른 잔디 해변, 투명한 바다 등을 경험할 수 있습니다.
```
## Evaluation
For objective model evaluation, we initially used EleutherAI's lm-evaluation-harness but obtained unsatisfactory results. Consequently, we conducted evaluations using ChatGPT, a widely used model, as described in [Self-Alignment with Instruction Backtranslation](https://arxiv.org/pdf/2308.06502.pdf) and [Three Ways of Using Large Language Models to Evaluate Chat](https://arxiv.org/pdf/2308.06259.pdf) .
| model | score | average(0~5) | percentage |
| --------------------------------------- |---------| ------------ | ---------- |
| gpt-3.5-turbo(close) | 147 | 3.97 | 79.45% |
| naver Cue(close) | 140 | 3.78 | 75.67% |
| clova X(close) | 136 | 3.67 | 73.51% |
| WizardLM-13B-V1.2(open) | 96 | 2.59 | 51.89% |
| Llama-2-7b-chat-hf(open) | 67 | 1.81 | 36.21% |
| Llama-2-13b-chat-hf(open) | 73 | 1.91 | 38.37% |
| nlpai-lab/kullm-polyglot-12.8b-v2(open) | 70 | 1.89 | 37.83% |
| kfkas/Llama-2-ko-7b-Chat(open) | 96 | 2.59 | 51.89% |
| beomi/KoAlpaca-Polyglot-12.8B(open) | 100 | 2.70 | 54.05% |
| **komt-llama2-7b-v1 (open)(ours)** | **117** | **3.16** | **63.24%** |
| **komt-llama2-13b-v1 (open)(ours)** | **129** | **3.48** | **69.72%** |
| **komt-llama-30b-v1 (open)(ours)** | **129** | **3.16** | **63.24%** |
| **komt-mistral-7b-v1 (open)(ours)** | **131** | **3.54** | **70.81%** |
| 4,998 | [
[
-0.03729248046875,
-0.048980712890625,
0.021331787109375,
0.0250701904296875,
-0.02777099609375,
0.005794525146484375,
-0.002376556396484375,
-0.0201568603515625,
0.024383544921875,
0.0211029052734375,
-0.036865234375,
-0.04229736328125,
-0.048126220703125,
... |
sonoisa/clip-vit-b-32-japanese-v1 | 2022-04-19T14:18:58.000Z | [
"transformers",
"pytorch",
"bert",
"feature-extraction",
"clip",
"sentence-similarity",
"ja",
"license:cc-by-sa-4.0",
"endpoints_compatible",
"has_space",
"region:us"
] | feature-extraction | sonoisa | null | null | sonoisa/clip-vit-b-32-japanese-v1 | 18 | 553 | transformers | 2022-03-02T23:29:05 | ---
language: ja
license: cc-by-sa-4.0
tags:
- clip
- feature-extraction
- sentence-similarity
---
# 日本語版[CLIP](https://github.com/openai/CLIP)モデル
This is a [CLIP](https://github.com/openai/CLIP) text/image encoder model for Japanese.
英語版CLIPモデルのテキストエンコーダーを一種の蒸留を用いて日本語化したモデルです。
作り方や精度、使い方、サンプルコードは下記の解説記事をご参照ください。
- 解説記事:
- 概要: [【日本語モデル付き】2022年にマルチモーダル処理をする人にお勧めしたい事前学習済みモデル](https://qiita.com/sonoisa/items/00e8e2861147842f0237)
- 使い方の解説: [【日本語CLIP】画像とテキストの類似度計算、画像やテキストの埋め込み計算、類似画像検索](https://qiita.com/sonoisa/items/d6db2f130fa9a4ce0c2c)
- (公開準備中) 応用解説: いらすとや画像のマルチモーダル検索（ゼロショット編）
- (公開準備中) 応用解説: いらすとや画像のマルチモーダル検索（ファインチューニング編）
- (公開準備中) 応用解説: 画像とテキストの両方を用いたマルチモーダル分類
- サンプルコードのリポジトリ: https://github.com/sonoisa/clip-japanese
- デモ:
- [いらすとや画像のマルチモーダル検索（ゼロショット）](https://huggingface.co/spaces/sonoisa/Irasuto_search_CLIP_zero-shot) | 853 | [
[
-0.034576416015625,
-0.052886962890625,
0.03741455078125,
0.0164337158203125,
-0.053619384765625,
-0.0189361572265625,
-0.004238128662109375,
-0.0290985107421875,
0.04949951171875,
0.033355712890625,
-0.04412841796875,
-0.04168701171875,
-0.05865478515625,
0... |
KappaNeuro/needlepoint | 2023-09-14T10:00:07.000Z | [
"diffusers",
"text-to-image",
"stable-diffusion",
"lora",
"embroidery",
"style",
"needlepoint",
"needlework",
"license:other",
"region:us",
"has_space"
] | text-to-image | KappaNeuro | null | null | KappaNeuro/needlepoint | 1 | 553 | diffusers | 2023-09-14T10:00:03 | ---
license: other
tags:
- text-to-image
- stable-diffusion
- lora
- diffusers
- embroidery
- style
- needlepoint
- needlework
base_model: stabilityai/stable-diffusion-xl-base-1.0
instance_prompt: Needlepoint page
widget:
- text: "Needlepoint - 8k, very simple overgrown greek landscape folly sewn patch"
- text: "Needlepoint - a coarse cross-stitch of a big ol' red truck driving from Vegas to Nashville"
- text: "Needlepoint - A mixed media art piece featuring an optical illusion pattern in the shape of a triangle made entirely out of particle board, overlaid with delicate embroidery in a creamy chenille thread. The colors of the embroidery should be a combination of frozen civilization, tropical escape and wild cranberry with hints of scorpion and Penelope. The embroidery should feel alive and three-dimensional, making the rigid surface of the particle board take on a sinewy, swirling appearance."
- text: "Needlepoint - a beautiful fabric embroidered minimalist Homer Simpson and Ronald McDonald made by a contemporary artist, textile art, contemporary artist embroidery, mockup, Simpsons, large embroidery art of Homer Simpsons from the tv show the Simpsons, McDonald tone, award winning photo, bright natural light, ultra-detailed, intricate details, 16K, volumetric lighting, best quality"
- text: "Needlepoint - Introduce flowing and organic forms with crewelwork stitches, inspired by nature and folklore. Use a variety of colorful threads to create texture and dimension.Dive into the vibrant and eclectic world of Stella Jean and create a whimsical embroidery design that merges various embroidery techniques with her unique style. Combining elements of Canvaswork, Blackwork, Crewelwork, Goldwork, Silk Shading, Whitework, and Raised Work, you will craft a piece that celebrates the beauty of cultural diversity and the fusion of different artistic traditions. Canvaswork: Incorporate geometric patterns inspired by traditional textiles from different cultures, using vibrant thread colors to create a bold and eye-catching design"
- text: "Needlepoint - non-binary self portrait in embroidery, embroidery hoop, middle age, pensive cautious optimism, portrait reflecting their best self, soft pallette, i will not drown in the liqueur of safety"
- text: "Needlepoint - yarn wool intricate embroidery texture 3D beautifully stitched fabric embroidered neutral rainbows and wildflowers on hills and fairy houses quilted background cottagecore photorealistic"
- text: "Needlepoint - A painting of Rolling hills with a country road and an active volcano in the background made of crochet polyester. Framed in a modern frame. Studio shot on a light gray backdrop."
- text: "Needlepoint - father's day stitching, close-up view father and daughter playing and laughing together, eye-level view, soft colors, minimalistic background, in the style of Cross-stitching"
- text: "Needlepoint - a boho design of flowers and mushrooms that looks like it was printed on an 3d embroidered cross stitch background"
---
# Needlepoint ([CivitAI](https://civitai.com/models/154077)
> Needlepoint - 8k, very simple overgrown greek landscape folly sewn patch
<p>Needlepoint is a form of embroidery that involves stitching decorative designs onto canvas using a needle and thread. It is often done on a stiff canvas mesh that provides a grid for the stitches.</p><p>In needlepoint, the design is typically pre-printed or hand-drawn onto the canvas, serving as a guide for the stitching process. The stitcher then uses various types of stitches, such as tent stitch, basketweave stitch, or cross-stitch, to fill in the design and create textured and colorful patterns.</p><p>Needlepoint allows for a wide range of design possibilities, from intricate and detailed images to simple geometric shapes or monograms. The choice of threads and colors adds depth and visual interest to the finished piece.</p><p>Needlepoint is a versatile craft that can be used to create various items, including decorative wall hangings, pillows, purses, and even clothing accessories like belts or shoes. It offers an opportunity for personal expression and creativity, allowing stitchers to customize designs and incorporate their own artistic flair.</p><p>The process of needlepoint can be relaxing and meditative, as the repetitive nature of stitching can provide a sense of focus and calm. It also offers a way to create lasting heirlooms or unique gifts for loved ones.</p><p>Needlepoint has a rich history, with examples of this craft dating back centuries. It continues to be practiced and enjoyed by people of all ages, combining artistic expression with a satisfying and enjoyable stitching process.</p>
## Image examples for the model:
> Needlepoint - a coarse cross-stitch of a big ol' red truck driving from Vegas to Nashville
> Needlepoint - A mixed media art piece featuring an optical illusion pattern in the shape of a triangle made entirely out of particle board, overlaid with delicate embroidery in a creamy chenille thread. The colors of the embroidery should be a combination of frozen civilization, tropical escape and wild cranberry with hints of scorpion and Penelope. The embroidery should feel alive and three-dimensional, making the rigid surface of the particle board take on a sinewy, swirling appearance.
> Needlepoint - a beautiful fabric embroidered minimalist Homer Simpson and Ronald McDonald made by a contemporary artist, textile art, contemporary artist embroidery, mockup, Simpsons, large embroidery art of Homer Simpsons from the tv show the Simpsons, McDonald tone, award winning photo, bright natural light, ultra-detailed, intricate details, 16K, volumetric lighting, best quality
> Needlepoint - Introduce flowing and organic forms with crewelwork stitches, inspired by nature and folklore. Use a variety of colorful threads to create texture and dimension.Dive into the vibrant and eclectic world of Stella Jean and create a whimsical embroidery design that merges various embroidery techniques with her unique style. Combining elements of Canvaswork, Blackwork, Crewelwork, Goldwork, Silk Shading, Whitework, and Raised Work, you will craft a piece that celebrates the beauty of cultural diversity and the fusion of different artistic traditions. Canvaswork: Incorporate geometric patterns inspired by traditional textiles from different cultures, using vibrant thread colors to create a bold and eye-catching design
> Needlepoint - non-binary self portrait in embroidery, embroidery hoop, middle age, pensive cautious optimism, portrait reflecting their best self, soft pallette, i will not drown in the liqueur of safety
> Needlepoint - yarn wool intricate embroidery texture 3D beautifully stitched fabric embroidered neutral rainbows and wildflowers on hills and fairy houses quilted background cottagecore photorealistic
> Needlepoint - A painting of Rolling hills with a country road and an active volcano in the background made of crochet polyester. Framed in a modern frame. Studio shot on a light gray backdrop.
> Needlepoint - father's day stitching, close-up view father and daughter playing and laughing together, eye-level view, soft colors, minimalistic background, in the style of Cross-stitching
> Needlepoint - a boho design of flowers and mushrooms that looks like it was printed on an 3d embroidered cross stitch background
| 7,630 | [
[
-0.04840087890625,
-0.0576171875,
0.035491943359375,
0.04815673828125,
-0.01203155517578125,
0.00830841064453125,
0.00923919677734375,
-0.0687255859375,
0.050445556640625,
0.031036376953125,
-0.04046630859375,
-0.042327880859375,
-0.054473876953125,
-0.00585... |
Nacholmo/meinamixv7-diffusers | 2023-06-21T16:34:39.000Z | [
"diffusers",
"text-to-image",
"license:creativeml-openrail-m",
"endpoints_compatible",
"has_space",
"diffusers:StableDiffusionPipeline",
"region:us"
] | text-to-image | Nacholmo | null | null | Nacholmo/meinamixv7-diffusers | 1 | 552 | diffusers | 2023-03-06T02:08:03 | ---
license: creativeml-openrail-m
library_name: diffusers
pipeline_tag: text-to-image
---
Original model: https://huggingface.co/Meina/MeinaMix | 145 | [
[
-0.050750732421875,
-0.02545166015625,
0.037139892578125,
0.010528564453125,
-0.028472900390625,
-0.03070068359375,
0.028900146484375,
-0.0311737060546875,
0.07275390625,
0.045074462890625,
-0.06396484375,
-0.0271759033203125,
-0.0313720703125,
-0.0014963150... |
timm/resnet50s.gluon_in1k | 2023-04-05T18:18:54.000Z | [
"timm",
"pytorch",
"safetensors",
"image-classification",
"arxiv:1512.03385",
"arxiv:1812.01187",
"license:apache-2.0",
"region:us"
] | image-classification | timm | null | null | timm/resnet50s.gluon_in1k | 0 | 552 | timm | 2023-04-05T18:18:26 | ---
tags:
- image-classification
- timm
library_tag: timm
license: apache-2.0
---
# Model card for resnet50s.gluon_in1k
A ResNet-S image classification model.
This model features:
* ReLU activations
* 3-layer stem of 3x3 convolutions with extra-width and pooling
* 1x1 convolution shortcut downsample
Trained on ImageNet-1k in Apache Gluon using Bag-of-Tricks based recipes.
## Model Details
- **Model Type:** Image classification / feature backbone
- **Model Stats:**
- Params (M): 25.7
- GMACs: 5.5
- Activations (M): 13.5
- Image size: 224 x 224
- **Papers:**
- Deep Residual Learning for Image Recognition: https://arxiv.org/abs/1512.03385
- Bag of Tricks for Image Classification with Convolutional Neural Networks: https://arxiv.org/abs/1812.01187
- **Original:** https://cv.gluon.ai/model_zoo/classification.html
## Model Usage
### Image Classification
```python
from urllib.request import urlopen
from PIL import Image
import timm
img = Image.open(urlopen(
'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
))
model = timm.create_model('resnet50s.gluon_in1k', pretrained=True)
model = model.eval()
# get model specific transforms (normalization, resize)
data_config = timm.data.resolve_model_data_config(model)
transforms = timm.data.create_transform(**data_config, is_training=False)
output = model(transforms(img).unsqueeze(0)) # unsqueeze single image into batch of 1
top5_probabilities, top5_class_indices = torch.topk(output.softmax(dim=1) * 100, k=5)
```
### Feature Map Extraction
```python
from urllib.request import urlopen
from PIL import Image
import timm
img = Image.open(urlopen(
'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
))
model = timm.create_model(
'resnet50s.gluon_in1k',
pretrained=True,
features_only=True,
)
model = model.eval()
# get model specific transforms (normalization, resize)
data_config = timm.data.resolve_model_data_config(model)
transforms = timm.data.create_transform(**data_config, is_training=False)
output = model(transforms(img).unsqueeze(0)) # unsqueeze single image into batch of 1
for o in output:
# print shape of each feature map in output
# e.g.:
# torch.Size([1, 128, 112, 112])
# torch.Size([1, 256, 56, 56])
# torch.Size([1, 512, 28, 28])
# torch.Size([1, 1024, 14, 14])
# torch.Size([1, 2048, 7, 7])
print(o.shape)
```
### Image Embeddings
```python
from urllib.request import urlopen
from PIL import Image
import timm
img = Image.open(urlopen(
'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
))
model = timm.create_model(
'resnet50s.gluon_in1k',
pretrained=True,
num_classes=0, # remove classifier nn.Linear
)
model = model.eval()
# get model specific transforms (normalization, resize)
data_config = timm.data.resolve_model_data_config(model)
transforms = timm.data.create_transform(**data_config, is_training=False)
output = model(transforms(img).unsqueeze(0)) # output is (batch_size, num_features) shaped tensor
# or equivalently (without needing to set num_classes=0)
output = model.forward_features(transforms(img).unsqueeze(0))
# output is unpooled, a (1, 2048, 7, 7) shaped tensor
output = model.forward_head(output, pre_logits=True)
# output is a (1, num_features) shaped tensor
```
## Model Comparison
Explore the dataset and runtime metrics of this model in timm [model results](https://github.com/huggingface/pytorch-image-models/tree/main/results).
|model |img_size|top1 |top5 |param_count|gmacs|macts|img/sec|
|------------------------------------------|--------|-----|-----|-----------|-----|-----|-------|
|[seresnextaa101d_32x8d.sw_in12k_ft_in1k_288](https://huggingface.co/timm/seresnextaa101d_32x8d.sw_in12k_ft_in1k_288)|320 |86.72|98.17|93.6 |35.2 |69.7 |451 |
|[seresnextaa101d_32x8d.sw_in12k_ft_in1k_288](https://huggingface.co/timm/seresnextaa101d_32x8d.sw_in12k_ft_in1k_288)|288 |86.51|98.08|93.6 |28.5 |56.4 |560 |
|[seresnextaa101d_32x8d.sw_in12k_ft_in1k](https://huggingface.co/timm/seresnextaa101d_32x8d.sw_in12k_ft_in1k)|288 |86.49|98.03|93.6 |28.5 |56.4 |557 |
|[seresnextaa101d_32x8d.sw_in12k_ft_in1k](https://huggingface.co/timm/seresnextaa101d_32x8d.sw_in12k_ft_in1k)|224 |85.96|97.82|93.6 |17.2 |34.2 |923 |
|[resnext101_32x32d.fb_wsl_ig1b_ft_in1k](https://huggingface.co/timm/resnext101_32x32d.fb_wsl_ig1b_ft_in1k)|224 |85.11|97.44|468.5 |87.3 |91.1 |254 |
|[resnetrs420.tf_in1k](https://huggingface.co/timm/resnetrs420.tf_in1k)|416 |85.0 |97.12|191.9 |108.4|213.8|134 |
|[ecaresnet269d.ra2_in1k](https://huggingface.co/timm/ecaresnet269d.ra2_in1k)|352 |84.96|97.22|102.1 |50.2 |101.2|291 |
|[ecaresnet269d.ra2_in1k](https://huggingface.co/timm/ecaresnet269d.ra2_in1k)|320 |84.73|97.18|102.1 |41.5 |83.7 |353 |
|[resnetrs350.tf_in1k](https://huggingface.co/timm/resnetrs350.tf_in1k)|384 |84.71|96.99|164.0 |77.6 |154.7|183 |
|[seresnextaa101d_32x8d.ah_in1k](https://huggingface.co/timm/seresnextaa101d_32x8d.ah_in1k)|288 |84.57|97.08|93.6 |28.5 |56.4 |557 |
|[resnetrs200.tf_in1k](https://huggingface.co/timm/resnetrs200.tf_in1k)|320 |84.45|97.08|93.2 |31.5 |67.8 |446 |
|[resnetrs270.tf_in1k](https://huggingface.co/timm/resnetrs270.tf_in1k)|352 |84.43|96.97|129.9 |51.1 |105.5|280 |
|[seresnext101d_32x8d.ah_in1k](https://huggingface.co/timm/seresnext101d_32x8d.ah_in1k)|288 |84.36|96.92|93.6 |27.6 |53.0 |595 |
|[seresnet152d.ra2_in1k](https://huggingface.co/timm/seresnet152d.ra2_in1k)|320 |84.35|97.04|66.8 |24.1 |47.7 |610 |
|[resnetrs350.tf_in1k](https://huggingface.co/timm/resnetrs350.tf_in1k)|288 |84.3 |96.94|164.0 |43.7 |87.1 |333 |
|[resnext101_32x8d.fb_swsl_ig1b_ft_in1k](https://huggingface.co/timm/resnext101_32x8d.fb_swsl_ig1b_ft_in1k)|224 |84.28|97.17|88.8 |16.5 |31.2 |1100 |
|[resnetrs420.tf_in1k](https://huggingface.co/timm/resnetrs420.tf_in1k)|320 |84.24|96.86|191.9 |64.2 |126.6|228 |
|[seresnext101_32x8d.ah_in1k](https://huggingface.co/timm/seresnext101_32x8d.ah_in1k)|288 |84.19|96.87|93.6 |27.2 |51.6 |613 |
|[resnext101_32x16d.fb_wsl_ig1b_ft_in1k](https://huggingface.co/timm/resnext101_32x16d.fb_wsl_ig1b_ft_in1k)|224 |84.18|97.19|194.0 |36.3 |51.2 |581 |
|[resnetaa101d.sw_in12k_ft_in1k](https://huggingface.co/timm/resnetaa101d.sw_in12k_ft_in1k)|288 |84.11|97.11|44.6 |15.1 |29.0 |1144 |
|[resnet200d.ra2_in1k](https://huggingface.co/timm/resnet200d.ra2_in1k)|320 |83.97|96.82|64.7 |31.2 |67.3 |518 |
|[resnetrs200.tf_in1k](https://huggingface.co/timm/resnetrs200.tf_in1k)|256 |83.87|96.75|93.2 |20.2 |43.4 |692 |
|[seresnextaa101d_32x8d.ah_in1k](https://huggingface.co/timm/seresnextaa101d_32x8d.ah_in1k)|224 |83.86|96.65|93.6 |17.2 |34.2 |923 |
|[resnetrs152.tf_in1k](https://huggingface.co/timm/resnetrs152.tf_in1k)|320 |83.72|96.61|86.6 |24.3 |48.1 |617 |
|[seresnet152d.ra2_in1k](https://huggingface.co/timm/seresnet152d.ra2_in1k)|256 |83.69|96.78|66.8 |15.4 |30.6 |943 |
|[seresnext101d_32x8d.ah_in1k](https://huggingface.co/timm/seresnext101d_32x8d.ah_in1k)|224 |83.68|96.61|93.6 |16.7 |32.0 |986 |
|[resnet152d.ra2_in1k](https://huggingface.co/timm/resnet152d.ra2_in1k)|320 |83.67|96.74|60.2 |24.1 |47.7 |706 |
|[resnetrs270.tf_in1k](https://huggingface.co/timm/resnetrs270.tf_in1k)|256 |83.59|96.61|129.9 |27.1 |55.8 |526 |
|[seresnext101_32x8d.ah_in1k](https://huggingface.co/timm/seresnext101_32x8d.ah_in1k)|224 |83.58|96.4 |93.6 |16.5 |31.2 |1013 |
|[resnetaa101d.sw_in12k_ft_in1k](https://huggingface.co/timm/resnetaa101d.sw_in12k_ft_in1k)|224 |83.54|96.83|44.6 |9.1 |17.6 |1864 |
|[resnet152.a1h_in1k](https://huggingface.co/timm/resnet152.a1h_in1k)|288 |83.46|96.54|60.2 |19.1 |37.3 |904 |
|[resnext101_32x16d.fb_swsl_ig1b_ft_in1k](https://huggingface.co/timm/resnext101_32x16d.fb_swsl_ig1b_ft_in1k)|224 |83.35|96.85|194.0 |36.3 |51.2 |582 |
|[resnet200d.ra2_in1k](https://huggingface.co/timm/resnet200d.ra2_in1k)|256 |83.23|96.53|64.7 |20.0 |43.1 |809 |
|[resnext101_32x4d.fb_swsl_ig1b_ft_in1k](https://huggingface.co/timm/resnext101_32x4d.fb_swsl_ig1b_ft_in1k)|224 |83.22|96.75|44.2 |8.0 |21.2 |1814 |
|[resnext101_64x4d.c1_in1k](https://huggingface.co/timm/resnext101_64x4d.c1_in1k)|288 |83.16|96.38|83.5 |25.7 |51.6 |590 |
|[resnet152d.ra2_in1k](https://huggingface.co/timm/resnet152d.ra2_in1k)|256 |83.14|96.38|60.2 |15.4 |30.5 |1096 |
|[resnet101d.ra2_in1k](https://huggingface.co/timm/resnet101d.ra2_in1k)|320 |83.02|96.45|44.6 |16.5 |34.8 |992 |
|[ecaresnet101d.miil_in1k](https://huggingface.co/timm/ecaresnet101d.miil_in1k)|288 |82.98|96.54|44.6 |13.4 |28.2 |1077 |
|[resnext101_64x4d.tv_in1k](https://huggingface.co/timm/resnext101_64x4d.tv_in1k)|224 |82.98|96.25|83.5 |15.5 |31.2 |989 |
|[resnetrs152.tf_in1k](https://huggingface.co/timm/resnetrs152.tf_in1k)|256 |82.86|96.28|86.6 |15.6 |30.8 |951 |
|[resnext101_32x8d.tv2_in1k](https://huggingface.co/timm/resnext101_32x8d.tv2_in1k)|224 |82.83|96.22|88.8 |16.5 |31.2 |1099 |
|[resnet152.a1h_in1k](https://huggingface.co/timm/resnet152.a1h_in1k)|224 |82.8 |96.13|60.2 |11.6 |22.6 |1486 |
|[resnet101.a1h_in1k](https://huggingface.co/timm/resnet101.a1h_in1k)|288 |82.8 |96.32|44.6 |13.0 |26.8 |1291 |
|[resnet152.a1_in1k](https://huggingface.co/timm/resnet152.a1_in1k)|288 |82.74|95.71|60.2 |19.1 |37.3 |905 |
|[resnext101_32x8d.fb_wsl_ig1b_ft_in1k](https://huggingface.co/timm/resnext101_32x8d.fb_wsl_ig1b_ft_in1k)|224 |82.69|96.63|88.8 |16.5 |31.2 |1100 |
|[resnet152.a2_in1k](https://huggingface.co/timm/resnet152.a2_in1k)|288 |82.62|95.75|60.2 |19.1 |37.3 |904 |
|[resnetaa50d.sw_in12k_ft_in1k](https://huggingface.co/timm/resnetaa50d.sw_in12k_ft_in1k)|288 |82.61|96.49|25.6 |8.9 |20.6 |1729 |
|[resnet61q.ra2_in1k](https://huggingface.co/timm/resnet61q.ra2_in1k)|288 |82.53|96.13|36.8 |9.9 |21.5 |1773 |
|[wide_resnet101_2.tv2_in1k](https://huggingface.co/timm/wide_resnet101_2.tv2_in1k)|224 |82.5 |96.02|126.9 |22.8 |21.2 |1078 |
|[resnext101_64x4d.c1_in1k](https://huggingface.co/timm/resnext101_64x4d.c1_in1k)|224 |82.46|95.92|83.5 |15.5 |31.2 |987 |
|[resnet51q.ra2_in1k](https://huggingface.co/timm/resnet51q.ra2_in1k)|288 |82.36|96.18|35.7 |8.1 |20.9 |1964 |
|[ecaresnet50t.ra2_in1k](https://huggingface.co/timm/ecaresnet50t.ra2_in1k)|320 |82.35|96.14|25.6 |8.8 |24.1 |1386 |
|[resnet101.a1_in1k](https://huggingface.co/timm/resnet101.a1_in1k)|288 |82.31|95.63|44.6 |13.0 |26.8 |1291 |
|[resnetrs101.tf_in1k](https://huggingface.co/timm/resnetrs101.tf_in1k)|288 |82.29|96.01|63.6 |13.6 |28.5 |1078 |
|[resnet152.tv2_in1k](https://huggingface.co/timm/resnet152.tv2_in1k)|224 |82.29|96.0 |60.2 |11.6 |22.6 |1484 |
|[wide_resnet50_2.racm_in1k](https://huggingface.co/timm/wide_resnet50_2.racm_in1k)|288 |82.27|96.06|68.9 |18.9 |23.8 |1176 |
|[resnet101d.ra2_in1k](https://huggingface.co/timm/resnet101d.ra2_in1k)|256 |82.26|96.07|44.6 |10.6 |22.2 |1542 |
|[resnet101.a2_in1k](https://huggingface.co/timm/resnet101.a2_in1k)|288 |82.24|95.73|44.6 |13.0 |26.8 |1290 |
|[seresnext50_32x4d.racm_in1k](https://huggingface.co/timm/seresnext50_32x4d.racm_in1k)|288 |82.2 |96.14|27.6 |7.0 |23.8 |1547 |
|[ecaresnet101d.miil_in1k](https://huggingface.co/timm/ecaresnet101d.miil_in1k)|224 |82.18|96.05|44.6 |8.1 |17.1 |1771 |
|[resnext50_32x4d.fb_swsl_ig1b_ft_in1k](https://huggingface.co/timm/resnext50_32x4d.fb_swsl_ig1b_ft_in1k)|224 |82.17|96.22|25.0 |4.3 |14.4 |2943 |
|[ecaresnet50t.a1_in1k](https://huggingface.co/timm/ecaresnet50t.a1_in1k)|288 |82.12|95.65|25.6 |7.1 |19.6 |1704 |
|[resnext50_32x4d.a1h_in1k](https://huggingface.co/timm/resnext50_32x4d.a1h_in1k)|288 |82.03|95.94|25.0 |7.0 |23.8 |1745 |
|[ecaresnet101d_pruned.miil_in1k](https://huggingface.co/timm/ecaresnet101d_pruned.miil_in1k)|288 |82.0 |96.15|24.9 |5.8 |12.7 |1787 |
|[resnet61q.ra2_in1k](https://huggingface.co/timm/resnet61q.ra2_in1k)|256 |81.99|95.85|36.8 |7.8 |17.0 |2230 |
|[resnext101_32x8d.tv2_in1k](https://huggingface.co/timm/resnext101_32x8d.tv2_in1k)|176 |81.98|95.72|88.8 |10.3 |19.4 |1768 |
|[resnet152.a1_in1k](https://huggingface.co/timm/resnet152.a1_in1k)|224 |81.97|95.24|60.2 |11.6 |22.6 |1486 |
|[resnet101.a1h_in1k](https://huggingface.co/timm/resnet101.a1h_in1k)|224 |81.93|95.75|44.6 |7.8 |16.2 |2122 |
|[resnet101.tv2_in1k](https://huggingface.co/timm/resnet101.tv2_in1k)|224 |81.9 |95.77|44.6 |7.8 |16.2 |2118 |
|[resnext101_32x16d.fb_ssl_yfcc100m_ft_in1k](https://huggingface.co/timm/resnext101_32x16d.fb_ssl_yfcc100m_ft_in1k)|224 |81.84|96.1 |194.0 |36.3 |51.2 |583 |
|[resnet51q.ra2_in1k](https://huggingface.co/timm/resnet51q.ra2_in1k)|256 |81.78|95.94|35.7 |6.4 |16.6 |2471 |
|[resnet152.a2_in1k](https://huggingface.co/timm/resnet152.a2_in1k)|224 |81.77|95.22|60.2 |11.6 |22.6 |1485 |
|[resnetaa50d.sw_in12k_ft_in1k](https://huggingface.co/timm/resnetaa50d.sw_in12k_ft_in1k)|224 |81.74|96.06|25.6 |5.4 |12.4 |2813 |
|[ecaresnet50t.a2_in1k](https://huggingface.co/timm/ecaresnet50t.a2_in1k)|288 |81.65|95.54|25.6 |7.1 |19.6 |1703 |
|[ecaresnet50d.miil_in1k](https://huggingface.co/timm/ecaresnet50d.miil_in1k)|288 |81.64|95.88|25.6 |7.2 |19.7 |1694 |
|[resnext101_32x8d.fb_ssl_yfcc100m_ft_in1k](https://huggingface.co/timm/resnext101_32x8d.fb_ssl_yfcc100m_ft_in1k)|224 |81.62|96.04|88.8 |16.5 |31.2 |1101 |
|[wide_resnet50_2.tv2_in1k](https://huggingface.co/timm/wide_resnet50_2.tv2_in1k)|224 |81.61|95.76|68.9 |11.4 |14.4 |1930 |
|[resnetaa50.a1h_in1k](https://huggingface.co/timm/resnetaa50.a1h_in1k)|288 |81.61|95.83|25.6 |8.5 |19.2 |1868 |
|[resnet101.a1_in1k](https://huggingface.co/timm/resnet101.a1_in1k)|224 |81.5 |95.16|44.6 |7.8 |16.2 |2125 |
|[resnext50_32x4d.a1_in1k](https://huggingface.co/timm/resnext50_32x4d.a1_in1k)|288 |81.48|95.16|25.0 |7.0 |23.8 |1745 |
|[gcresnet50t.ra2_in1k](https://huggingface.co/timm/gcresnet50t.ra2_in1k)|288 |81.47|95.71|25.9 |6.9 |18.6 |2071 |
|[wide_resnet50_2.racm_in1k](https://huggingface.co/timm/wide_resnet50_2.racm_in1k)|224 |81.45|95.53|68.9 |11.4 |14.4 |1929 |
|[resnet50d.a1_in1k](https://huggingface.co/timm/resnet50d.a1_in1k)|288 |81.44|95.22|25.6 |7.2 |19.7 |1908 |
|[ecaresnet50t.ra2_in1k](https://huggingface.co/timm/ecaresnet50t.ra2_in1k)|256 |81.44|95.67|25.6 |5.6 |15.4 |2168 |
|[ecaresnetlight.miil_in1k](https://huggingface.co/timm/ecaresnetlight.miil_in1k)|288 |81.4 |95.82|30.2 |6.8 |13.9 |2132 |
|[resnet50d.ra2_in1k](https://huggingface.co/timm/resnet50d.ra2_in1k)|288 |81.37|95.74|25.6 |7.2 |19.7 |1910 |
|[resnet101.a2_in1k](https://huggingface.co/timm/resnet101.a2_in1k)|224 |81.32|95.19|44.6 |7.8 |16.2 |2125 |
|[seresnet50.ra2_in1k](https://huggingface.co/timm/seresnet50.ra2_in1k)|288 |81.3 |95.65|28.1 |6.8 |18.4 |1803 |
|[resnext50_32x4d.a2_in1k](https://huggingface.co/timm/resnext50_32x4d.a2_in1k)|288 |81.3 |95.11|25.0 |7.0 |23.8 |1746 |
|[seresnext50_32x4d.racm_in1k](https://huggingface.co/timm/seresnext50_32x4d.racm_in1k)|224 |81.27|95.62|27.6 |4.3 |14.4 |2591 |
|[ecaresnet50t.a1_in1k](https://huggingface.co/timm/ecaresnet50t.a1_in1k)|224 |81.26|95.16|25.6 |4.3 |11.8 |2823 |
|[gcresnext50ts.ch_in1k](https://huggingface.co/timm/gcresnext50ts.ch_in1k)|288 |81.23|95.54|15.7 |4.8 |19.6 |2117 |
|[senet154.gluon_in1k](https://huggingface.co/timm/senet154.gluon_in1k)|224 |81.23|95.35|115.1 |20.8 |38.7 |545 |
|[resnet50.a1_in1k](https://huggingface.co/timm/resnet50.a1_in1k)|288 |81.22|95.11|25.6 |6.8 |18.4 |2089 |
|[resnet50_gn.a1h_in1k](https://huggingface.co/timm/resnet50_gn.a1h_in1k)|288 |81.22|95.63|25.6 |6.8 |18.4 |676 |
|[resnet50d.a2_in1k](https://huggingface.co/timm/resnet50d.a2_in1k)|288 |81.18|95.09|25.6 |7.2 |19.7 |1908 |
|[resnet50.fb_swsl_ig1b_ft_in1k](https://huggingface.co/timm/resnet50.fb_swsl_ig1b_ft_in1k)|224 |81.18|95.98|25.6 |4.1 |11.1 |3455 |
|[resnext50_32x4d.tv2_in1k](https://huggingface.co/timm/resnext50_32x4d.tv2_in1k)|224 |81.17|95.34|25.0 |4.3 |14.4 |2933 |
|[resnext50_32x4d.a1h_in1k](https://huggingface.co/timm/resnext50_32x4d.a1h_in1k)|224 |81.1 |95.33|25.0 |4.3 |14.4 |2934 |
|[seresnet50.a2_in1k](https://huggingface.co/timm/seresnet50.a2_in1k)|288 |81.1 |95.23|28.1 |6.8 |18.4 |1801 |
|[seresnet50.a1_in1k](https://huggingface.co/timm/seresnet50.a1_in1k)|288 |81.1 |95.12|28.1 |6.8 |18.4 |1799 |
|[resnet152s.gluon_in1k](https://huggingface.co/timm/resnet152s.gluon_in1k)|224 |81.02|95.41|60.3 |12.9 |25.0 |1347 |
|[resnet50.d_in1k](https://huggingface.co/timm/resnet50.d_in1k)|288 |80.97|95.44|25.6 |6.8 |18.4 |2085 |
|[gcresnet50t.ra2_in1k](https://huggingface.co/timm/gcresnet50t.ra2_in1k)|256 |80.94|95.45|25.9 |5.4 |14.7 |2571 |
|[resnext101_32x4d.fb_ssl_yfcc100m_ft_in1k](https://huggingface.co/timm/resnext101_32x4d.fb_ssl_yfcc100m_ft_in1k)|224 |80.93|95.73|44.2 |8.0 |21.2 |1814 |
|[resnet50.c1_in1k](https://huggingface.co/timm/resnet50.c1_in1k)|288 |80.91|95.55|25.6 |6.8 |18.4 |2084 |
|[seresnext101_32x4d.gluon_in1k](https://huggingface.co/timm/seresnext101_32x4d.gluon_in1k)|224 |80.9 |95.31|49.0 |8.0 |21.3 |1585 |
|[seresnext101_64x4d.gluon_in1k](https://huggingface.co/timm/seresnext101_64x4d.gluon_in1k)|224 |80.9 |95.3 |88.2 |15.5 |31.2 |918 |
|[resnet50.c2_in1k](https://huggingface.co/timm/resnet50.c2_in1k)|288 |80.86|95.52|25.6 |6.8 |18.4 |2085 |
|[resnet50.tv2_in1k](https://huggingface.co/timm/resnet50.tv2_in1k)|224 |80.85|95.43|25.6 |4.1 |11.1 |3450 |
|[ecaresnet50t.a2_in1k](https://huggingface.co/timm/ecaresnet50t.a2_in1k)|224 |80.84|95.02|25.6 |4.3 |11.8 |2821 |
|[ecaresnet101d_pruned.miil_in1k](https://huggingface.co/timm/ecaresnet101d_pruned.miil_in1k)|224 |80.79|95.62|24.9 |3.5 |7.7 |2961 |
|[seresnet33ts.ra2_in1k](https://huggingface.co/timm/seresnet33ts.ra2_in1k)|288 |80.79|95.36|19.8 |6.0 |14.8 |2506 |
|[ecaresnet50d_pruned.miil_in1k](https://huggingface.co/timm/ecaresnet50d_pruned.miil_in1k)|288 |80.79|95.58|19.9 |4.2 |10.6 |2349 |
|[resnet50.a2_in1k](https://huggingface.co/timm/resnet50.a2_in1k)|288 |80.78|94.99|25.6 |6.8 |18.4 |2088 |
|[resnet50.b1k_in1k](https://huggingface.co/timm/resnet50.b1k_in1k)|288 |80.71|95.43|25.6 |6.8 |18.4 |2087 |
|[resnext50_32x4d.ra_in1k](https://huggingface.co/timm/resnext50_32x4d.ra_in1k)|288 |80.7 |95.39|25.0 |7.0 |23.8 |1749 |
|[resnetrs101.tf_in1k](https://huggingface.co/timm/resnetrs101.tf_in1k)|192 |80.69|95.24|63.6 |6.0 |12.7 |2270 |
|[resnet50d.a1_in1k](https://huggingface.co/timm/resnet50d.a1_in1k)|224 |80.68|94.71|25.6 |4.4 |11.9 |3162 |
|[eca_resnet33ts.ra2_in1k](https://huggingface.co/timm/eca_resnet33ts.ra2_in1k)|288 |80.68|95.36|19.7 |6.0 |14.8 |2637 |
|[resnet50.a1h_in1k](https://huggingface.co/timm/resnet50.a1h_in1k)|224 |80.67|95.3 |25.6 |4.1 |11.1 |3452 |
|[resnext50d_32x4d.bt_in1k](https://huggingface.co/timm/resnext50d_32x4d.bt_in1k)|288 |80.67|95.42|25.0 |7.4 |25.1 |1626 |
|[resnetaa50.a1h_in1k](https://huggingface.co/timm/resnetaa50.a1h_in1k)|224 |80.63|95.21|25.6 |5.2 |11.6 |3034 |
|[ecaresnet50d.miil_in1k](https://huggingface.co/timm/ecaresnet50d.miil_in1k)|224 |80.61|95.32|25.6 |4.4 |11.9 |2813 |
|[resnext101_64x4d.gluon_in1k](https://huggingface.co/timm/resnext101_64x4d.gluon_in1k)|224 |80.61|94.99|83.5 |15.5 |31.2 |989 |
|[gcresnet33ts.ra2_in1k](https://huggingface.co/timm/gcresnet33ts.ra2_in1k)|288 |80.6 |95.31|19.9 |6.0 |14.8 |2578 |
|[gcresnext50ts.ch_in1k](https://huggingface.co/timm/gcresnext50ts.ch_in1k)|256 |80.57|95.17|15.7 |3.8 |15.5 |2710 |
|[resnet152.a3_in1k](https://huggingface.co/timm/resnet152.a3_in1k)|224 |80.56|95.0 |60.2 |11.6 |22.6 |1483 |
|[resnet50d.ra2_in1k](https://huggingface.co/timm/resnet50d.ra2_in1k)|224 |80.53|95.16|25.6 |4.4 |11.9 |3164 |
|[resnext50_32x4d.a1_in1k](https://huggingface.co/timm/resnext50_32x4d.a1_in1k)|224 |80.53|94.46|25.0 |4.3 |14.4 |2930 |
|[wide_resnet101_2.tv2_in1k](https://huggingface.co/timm/wide_resnet101_2.tv2_in1k)|176 |80.48|94.98|126.9 |14.3 |13.2 |1719 |
|[resnet152d.gluon_in1k](https://huggingface.co/timm/resnet152d.gluon_in1k)|224 |80.47|95.2 |60.2 |11.8 |23.4 |1428 |
|[resnet50.b2k_in1k](https://huggingface.co/timm/resnet50.b2k_in1k)|288 |80.45|95.32|25.6 |6.8 |18.4 |2086 |
|[ecaresnetlight.miil_in1k](https://huggingface.co/timm/ecaresnetlight.miil_in1k)|224 |80.45|95.24|30.2 |4.1 |8.4 |3530 |
|[resnext50_32x4d.a2_in1k](https://huggingface.co/timm/resnext50_32x4d.a2_in1k)|224 |80.45|94.63|25.0 |4.3 |14.4 |2936 |
|[wide_resnet50_2.tv2_in1k](https://huggingface.co/timm/wide_resnet50_2.tv2_in1k)|176 |80.43|95.09|68.9 |7.3 |9.0 |3015 |
|[resnet101d.gluon_in1k](https://huggingface.co/timm/resnet101d.gluon_in1k)|224 |80.42|95.01|44.6 |8.1 |17.0 |2007 |
|[resnet50.a1_in1k](https://huggingface.co/timm/resnet50.a1_in1k)|224 |80.38|94.6 |25.6 |4.1 |11.1 |3461 |
|[seresnet33ts.ra2_in1k](https://huggingface.co/timm/seresnet33ts.ra2_in1k)|256 |80.36|95.1 |19.8 |4.8 |11.7 |3267 |
|[resnext101_32x4d.gluon_in1k](https://huggingface.co/timm/resnext101_32x4d.gluon_in1k)|224 |80.34|94.93|44.2 |8.0 |21.2 |1814 |
|[resnext50_32x4d.fb_ssl_yfcc100m_ft_in1k](https://huggingface.co/timm/resnext50_32x4d.fb_ssl_yfcc100m_ft_in1k)|224 |80.32|95.4 |25.0 |4.3 |14.4 |2941 |
|[resnet101s.gluon_in1k](https://huggingface.co/timm/resnet101s.gluon_in1k)|224 |80.28|95.16|44.7 |9.2 |18.6 |1851 |
|[seresnet50.ra2_in1k](https://huggingface.co/timm/seresnet50.ra2_in1k)|224 |80.26|95.08|28.1 |4.1 |11.1 |2972 |
|[resnetblur50.bt_in1k](https://huggingface.co/timm/resnetblur50.bt_in1k)|288 |80.24|95.24|25.6 |8.5 |19.9 |1523 |
|[resnet50d.a2_in1k](https://huggingface.co/timm/resnet50d.a2_in1k)|224 |80.22|94.63|25.6 |4.4 |11.9 |3162 |
|[resnet152.tv2_in1k](https://huggingface.co/timm/resnet152.tv2_in1k)|176 |80.2 |94.64|60.2 |7.2 |14.0 |2346 |
|[seresnet50.a2_in1k](https://huggingface.co/timm/seresnet50.a2_in1k)|224 |80.08|94.74|28.1 |4.1 |11.1 |2969 |
|[eca_resnet33ts.ra2_in1k](https://huggingface.co/timm/eca_resnet33ts.ra2_in1k)|256 |80.08|94.97|19.7 |4.8 |11.7 |3284 |
|[gcresnet33ts.ra2_in1k](https://huggingface.co/timm/gcresnet33ts.ra2_in1k)|256 |80.06|94.99|19.9 |4.8 |11.7 |3216 |
|[resnet50_gn.a1h_in1k](https://huggingface.co/timm/resnet50_gn.a1h_in1k)|224 |80.06|94.95|25.6 |4.1 |11.1 |1109 |
|[seresnet50.a1_in1k](https://huggingface.co/timm/seresnet50.a1_in1k)|224 |80.02|94.71|28.1 |4.1 |11.1 |2962 |
|[resnet50.ram_in1k](https://huggingface.co/timm/resnet50.ram_in1k)|288 |79.97|95.05|25.6 |6.8 |18.4 |2086 |
|[resnet152c.gluon_in1k](https://huggingface.co/timm/resnet152c.gluon_in1k)|224 |79.92|94.84|60.2 |11.8 |23.4 |1455 |
|[seresnext50_32x4d.gluon_in1k](https://huggingface.co/timm/seresnext50_32x4d.gluon_in1k)|224 |79.91|94.82|27.6 |4.3 |14.4 |2591 |
|[resnet50.d_in1k](https://huggingface.co/timm/resnet50.d_in1k)|224 |79.91|94.67|25.6 |4.1 |11.1 |3456 |
|[resnet101.tv2_in1k](https://huggingface.co/timm/resnet101.tv2_in1k)|176 |79.9 |94.6 |44.6 |4.9 |10.1 |3341 |
|[resnetrs50.tf_in1k](https://huggingface.co/timm/resnetrs50.tf_in1k)|224 |79.89|94.97|35.7 |4.5 |12.1 |2774 |
|[resnet50.c2_in1k](https://huggingface.co/timm/resnet50.c2_in1k)|224 |79.88|94.87|25.6 |4.1 |11.1 |3455 |
|[ecaresnet26t.ra2_in1k](https://huggingface.co/timm/ecaresnet26t.ra2_in1k)|320 |79.86|95.07|16.0 |5.2 |16.4 |2168 |
|[resnet50.a2_in1k](https://huggingface.co/timm/resnet50.a2_in1k)|224 |79.85|94.56|25.6 |4.1 |11.1 |3460 |
|[resnet50.ra_in1k](https://huggingface.co/timm/resnet50.ra_in1k)|288 |79.83|94.97|25.6 |6.8 |18.4 |2087 |
|[resnet101.a3_in1k](https://huggingface.co/timm/resnet101.a3_in1k)|224 |79.82|94.62|44.6 |7.8 |16.2 |2114 |
|[resnext50_32x4d.ra_in1k](https://huggingface.co/timm/resnext50_32x4d.ra_in1k)|224 |79.76|94.6 |25.0 |4.3 |14.4 |2943 |
|[resnet50.c1_in1k](https://huggingface.co/timm/resnet50.c1_in1k)|224 |79.74|94.95|25.6 |4.1 |11.1 |3455 |
|[ecaresnet50d_pruned.miil_in1k](https://huggingface.co/timm/ecaresnet50d_pruned.miil_in1k)|224 |79.74|94.87|19.9 |2.5 |6.4 |3929 |
|[resnet33ts.ra2_in1k](https://huggingface.co/timm/resnet33ts.ra2_in1k)|288 |79.71|94.83|19.7 |6.0 |14.8 |2710 |
|[resnet152.gluon_in1k](https://huggingface.co/timm/resnet152.gluon_in1k)|224 |79.68|94.74|60.2 |11.6 |22.6 |1486 |
|[resnext50d_32x4d.bt_in1k](https://huggingface.co/timm/resnext50d_32x4d.bt_in1k)|224 |79.67|94.87|25.0 |4.5 |15.2 |2729 |
|[resnet50.bt_in1k](https://huggingface.co/timm/resnet50.bt_in1k)|288 |79.63|94.91|25.6 |6.8 |18.4 |2086 |
|[ecaresnet50t.a3_in1k](https://huggingface.co/timm/ecaresnet50t.a3_in1k)|224 |79.56|94.72|25.6 |4.3 |11.8 |2805 |
|[resnet101c.gluon_in1k](https://huggingface.co/timm/resnet101c.gluon_in1k)|224 |79.53|94.58|44.6 |8.1 |17.0 |2062 |
|[resnet50.b1k_in1k](https://huggingface.co/timm/resnet50.b1k_in1k)|224 |79.52|94.61|25.6 |4.1 |11.1 |3459 |
|[resnet50.tv2_in1k](https://huggingface.co/timm/resnet50.tv2_in1k)|176 |79.42|94.64|25.6 |2.6 |6.9 |5397 |
|[resnet32ts.ra2_in1k](https://huggingface.co/timm/resnet32ts.ra2_in1k)|288 |79.4 |94.66|18.0 |5.9 |14.6 |2752 |
|[resnet50.b2k_in1k](https://huggingface.co/timm/resnet50.b2k_in1k)|224 |79.38|94.57|25.6 |4.1 |11.1 |3459 |
|[resnext50_32x4d.tv2_in1k](https://huggingface.co/timm/resnext50_32x4d.tv2_in1k)|176 |79.37|94.3 |25.0 |2.7 |9.0 |4577 |
|[resnext50_32x4d.gluon_in1k](https://huggingface.co/timm/resnext50_32x4d.gluon_in1k)|224 |79.36|94.43|25.0 |4.3 |14.4 |2942 |
|[resnext101_32x8d.tv_in1k](https://huggingface.co/timm/resnext101_32x8d.tv_in1k)|224 |79.31|94.52|88.8 |16.5 |31.2 |1100 |
|[resnet101.gluon_in1k](https://huggingface.co/timm/resnet101.gluon_in1k)|224 |79.31|94.53|44.6 |7.8 |16.2 |2125 |
|[resnetblur50.bt_in1k](https://huggingface.co/timm/resnetblur50.bt_in1k)|224 |79.31|94.63|25.6 |5.2 |12.0 |2524 |
|[resnet50.a1h_in1k](https://huggingface.co/timm/resnet50.a1h_in1k)|176 |79.27|94.49|25.6 |2.6 |6.9 |5404 |
|[resnext50_32x4d.a3_in1k](https://huggingface.co/timm/resnext50_32x4d.a3_in1k)|224 |79.25|94.31|25.0 |4.3 |14.4 |2931 |
|[resnet50.fb_ssl_yfcc100m_ft_in1k](https://huggingface.co/timm/resnet50.fb_ssl_yfcc100m_ft_in1k)|224 |79.22|94.84|25.6 |4.1 |11.1 |3451 |
|[resnet33ts.ra2_in1k](https://huggingface.co/timm/resnet33ts.ra2_in1k)|256 |79.21|94.56|19.7 |4.8 |11.7 |3392 |
|[resnet50d.gluon_in1k](https://huggingface.co/timm/resnet50d.gluon_in1k)|224 |79.07|94.48|25.6 |4.4 |11.9 |3162 |
|[resnet50.ram_in1k](https://huggingface.co/timm/resnet50.ram_in1k)|224 |79.03|94.38|25.6 |4.1 |11.1 |3453 |
|[resnet50.am_in1k](https://huggingface.co/timm/resnet50.am_in1k)|224 |79.01|94.39|25.6 |4.1 |11.1 |3461 |
|[resnet32ts.ra2_in1k](https://huggingface.co/timm/resnet32ts.ra2_in1k)|256 |79.01|94.37|18.0 |4.6 |11.6 |3440 |
|[ecaresnet26t.ra2_in1k](https://huggingface.co/timm/ecaresnet26t.ra2_in1k)|256 |78.9 |94.54|16.0 |3.4 |10.5 |3421 |
|[resnet152.a3_in1k](https://huggingface.co/timm/resnet152.a3_in1k)|160 |78.89|94.11|60.2 |5.9 |11.5 |2745 |
|[wide_resnet101_2.tv_in1k](https://huggingface.co/timm/wide_resnet101_2.tv_in1k)|224 |78.84|94.28|126.9 |22.8 |21.2 |1079 |
|[seresnext26d_32x4d.bt_in1k](https://huggingface.co/timm/seresnext26d_32x4d.bt_in1k)|288 |78.83|94.24|16.8 |4.5 |16.8 |2251 |
|[resnet50.ra_in1k](https://huggingface.co/timm/resnet50.ra_in1k)|224 |78.81|94.32|25.6 |4.1 |11.1 |3454 |
|[seresnext26t_32x4d.bt_in1k](https://huggingface.co/timm/seresnext26t_32x4d.bt_in1k)|288 |78.74|94.33|16.8 |4.5 |16.7 |2264 |
|[resnet50s.gluon_in1k](https://huggingface.co/timm/resnet50s.gluon_in1k)|224 |78.72|94.23|25.7 |5.5 |13.5 |2796 |
|[resnet50d.a3_in1k](https://huggingface.co/timm/resnet50d.a3_in1k)|224 |78.71|94.24|25.6 |4.4 |11.9 |3154 |
|[wide_resnet50_2.tv_in1k](https://huggingface.co/timm/wide_resnet50_2.tv_in1k)|224 |78.47|94.09|68.9 |11.4 |14.4 |1934 |
|[resnet50.bt_in1k](https://huggingface.co/timm/resnet50.bt_in1k)|224 |78.46|94.27|25.6 |4.1 |11.1 |3454 |
|[resnet34d.ra2_in1k](https://huggingface.co/timm/resnet34d.ra2_in1k)|288 |78.43|94.35|21.8 |6.5 |7.5 |3291 |
|[gcresnext26ts.ch_in1k](https://huggingface.co/timm/gcresnext26ts.ch_in1k)|288 |78.42|94.04|10.5 |3.1 |13.3 |3226 |
|[resnet26t.ra2_in1k](https://huggingface.co/timm/resnet26t.ra2_in1k)|320 |78.33|94.13|16.0 |5.2 |16.4 |2391 |
|[resnet152.tv_in1k](https://huggingface.co/timm/resnet152.tv_in1k)|224 |78.32|94.04|60.2 |11.6 |22.6 |1487 |
|[seresnext26ts.ch_in1k](https://huggingface.co/timm/seresnext26ts.ch_in1k)|288 |78.28|94.1 |10.4 |3.1 |13.3 |3062 |
|[bat_resnext26ts.ch_in1k](https://huggingface.co/timm/bat_resnext26ts.ch_in1k)|256 |78.25|94.1 |10.7 |2.5 |12.5 |3393 |
|[resnet50.a3_in1k](https://huggingface.co/timm/resnet50.a3_in1k)|224 |78.06|93.78|25.6 |4.1 |11.1 |3450 |
|[resnet50c.gluon_in1k](https://huggingface.co/timm/resnet50c.gluon_in1k)|224 |78.0 |93.99|25.6 |4.4 |11.9 |3286 |
|[eca_resnext26ts.ch_in1k](https://huggingface.co/timm/eca_resnext26ts.ch_in1k)|288 |78.0 |93.91|10.3 |3.1 |13.3 |3297 |
|[seresnext26t_32x4d.bt_in1k](https://huggingface.co/timm/seresnext26t_32x4d.bt_in1k)|224 |77.98|93.75|16.8 |2.7 |10.1 |3841 |
|[resnet34.a1_in1k](https://huggingface.co/timm/resnet34.a1_in1k)|288 |77.92|93.77|21.8 |6.1 |6.2 |3609 |
|[resnet101.a3_in1k](https://huggingface.co/timm/resnet101.a3_in1k)|160 |77.88|93.71|44.6 |4.0 |8.3 |3926 |
|[resnet26t.ra2_in1k](https://huggingface.co/timm/resnet26t.ra2_in1k)|256 |77.87|93.84|16.0 |3.4 |10.5 |3772 |
|[seresnext26ts.ch_in1k](https://huggingface.co/timm/seresnext26ts.ch_in1k)|256 |77.86|93.79|10.4 |2.4 |10.5 |4263 |
|[resnetrs50.tf_in1k](https://huggingface.co/timm/resnetrs50.tf_in1k)|160 |77.82|93.81|35.7 |2.3 |6.2 |5238 |
|[gcresnext26ts.ch_in1k](https://huggingface.co/timm/gcresnext26ts.ch_in1k)|256 |77.81|93.82|10.5 |2.4 |10.5 |4183 |
|[ecaresnet50t.a3_in1k](https://huggingface.co/timm/ecaresnet50t.a3_in1k)|160 |77.79|93.6 |25.6 |2.2 |6.0 |5329 |
|[resnext50_32x4d.a3_in1k](https://huggingface.co/timm/resnext50_32x4d.a3_in1k)|160 |77.73|93.32|25.0 |2.2 |7.4 |5576 |
|[resnext50_32x4d.tv_in1k](https://huggingface.co/timm/resnext50_32x4d.tv_in1k)|224 |77.61|93.7 |25.0 |4.3 |14.4 |2944 |
|[seresnext26d_32x4d.bt_in1k](https://huggingface.co/timm/seresnext26d_32x4d.bt_in1k)|224 |77.59|93.61|16.8 |2.7 |10.2 |3807 |
|[resnet50.gluon_in1k](https://huggingface.co/timm/resnet50.gluon_in1k)|224 |77.58|93.72|25.6 |4.1 |11.1 |3455 |
|[eca_resnext26ts.ch_in1k](https://huggingface.co/timm/eca_resnext26ts.ch_in1k)|256 |77.44|93.56|10.3 |2.4 |10.5 |4284 |
|[resnet26d.bt_in1k](https://huggingface.co/timm/resnet26d.bt_in1k)|288 |77.41|93.63|16.0 |4.3 |13.5 |2907 |
|[resnet101.tv_in1k](https://huggingface.co/timm/resnet101.tv_in1k)|224 |77.38|93.54|44.6 |7.8 |16.2 |2125 |
|[resnet50d.a3_in1k](https://huggingface.co/timm/resnet50d.a3_in1k)|160 |77.22|93.27|25.6 |2.2 |6.1 |5982 |
|[resnext26ts.ra2_in1k](https://huggingface.co/timm/resnext26ts.ra2_in1k)|288 |77.17|93.47|10.3 |3.1 |13.3 |3392 |
|[resnet34.a2_in1k](https://huggingface.co/timm/resnet34.a2_in1k)|288 |77.15|93.27|21.8 |6.1 |6.2 |3615 |
|[resnet34d.ra2_in1k](https://huggingface.co/timm/resnet34d.ra2_in1k)|224 |77.1 |93.37|21.8 |3.9 |4.5 |5436 |
|[seresnet50.a3_in1k](https://huggingface.co/timm/seresnet50.a3_in1k)|224 |77.02|93.07|28.1 |4.1 |11.1 |2952 |
|[resnext26ts.ra2_in1k](https://huggingface.co/timm/resnext26ts.ra2_in1k)|256 |76.78|93.13|10.3 |2.4 |10.5 |4410 |
|[resnet26d.bt_in1k](https://huggingface.co/timm/resnet26d.bt_in1k)|224 |76.7 |93.17|16.0 |2.6 |8.2 |4859 |
|[resnet34.bt_in1k](https://huggingface.co/timm/resnet34.bt_in1k)|288 |76.5 |93.35|21.8 |6.1 |6.2 |3617 |
|[resnet34.a1_in1k](https://huggingface.co/timm/resnet34.a1_in1k)|224 |76.42|92.87|21.8 |3.7 |3.7 |5984 |
|[resnet26.bt_in1k](https://huggingface.co/timm/resnet26.bt_in1k)|288 |76.35|93.18|16.0 |3.9 |12.2 |3331 |
|[resnet50.tv_in1k](https://huggingface.co/timm/resnet50.tv_in1k)|224 |76.13|92.86|25.6 |4.1 |11.1 |3457 |
|[resnet50.a3_in1k](https://huggingface.co/timm/resnet50.a3_in1k)|160 |75.96|92.5 |25.6 |2.1 |5.7 |6490 |
|[resnet34.a2_in1k](https://huggingface.co/timm/resnet34.a2_in1k)|224 |75.52|92.44|21.8 |3.7 |3.7 |5991 |
|[resnet26.bt_in1k](https://huggingface.co/timm/resnet26.bt_in1k)|224 |75.3 |92.58|16.0 |2.4 |7.4 |5583 |
|[resnet34.bt_in1k](https://huggingface.co/timm/resnet34.bt_in1k)|224 |75.16|92.18|21.8 |3.7 |3.7 |5994 |
|[seresnet50.a3_in1k](https://huggingface.co/timm/seresnet50.a3_in1k)|160 |75.1 |92.08|28.1 |2.1 |5.7 |5513 |
|[resnet34.gluon_in1k](https://huggingface.co/timm/resnet34.gluon_in1k)|224 |74.57|91.98|21.8 |3.7 |3.7 |5984 |
|[resnet18d.ra2_in1k](https://huggingface.co/timm/resnet18d.ra2_in1k)|288 |73.81|91.83|11.7 |3.4 |5.4 |5196 |
|[resnet34.tv_in1k](https://huggingface.co/timm/resnet34.tv_in1k)|224 |73.32|91.42|21.8 |3.7 |3.7 |5979 |
|[resnet18.fb_swsl_ig1b_ft_in1k](https://huggingface.co/timm/resnet18.fb_swsl_ig1b_ft_in1k)|224 |73.28|91.73|11.7 |1.8 |2.5 |10213 |
|[resnet18.a1_in1k](https://huggingface.co/timm/resnet18.a1_in1k)|288 |73.16|91.03|11.7 |3.0 |4.1 |6050 |
|[resnet34.a3_in1k](https://huggingface.co/timm/resnet34.a3_in1k)|224 |72.98|91.11|21.8 |3.7 |3.7 |5967 |
|[resnet18.fb_ssl_yfcc100m_ft_in1k](https://huggingface.co/timm/resnet18.fb_ssl_yfcc100m_ft_in1k)|224 |72.6 |91.42|11.7 |1.8 |2.5 |10213 |
|[resnet18.a2_in1k](https://huggingface.co/timm/resnet18.a2_in1k)|288 |72.37|90.59|11.7 |3.0 |4.1 |6051 |
|[resnet14t.c3_in1k](https://huggingface.co/timm/resnet14t.c3_in1k)|224 |72.26|90.31|10.1 |1.7 |5.8 |7026 |
|[resnet18d.ra2_in1k](https://huggingface.co/timm/resnet18d.ra2_in1k)|224 |72.26|90.68|11.7 |2.1 |3.3 |8707 |
|[resnet18.a1_in1k](https://huggingface.co/timm/resnet18.a1_in1k)|224 |71.49|90.07|11.7 |1.8 |2.5 |10187 |
|[resnet14t.c3_in1k](https://huggingface.co/timm/resnet14t.c3_in1k)|176 |71.31|89.69|10.1 |1.1 |3.6 |10970 |
|[resnet18.gluon_in1k](https://huggingface.co/timm/resnet18.gluon_in1k)|224 |70.84|89.76|11.7 |1.8 |2.5 |10210 |
|[resnet18.a2_in1k](https://huggingface.co/timm/resnet18.a2_in1k)|224 |70.64|89.47|11.7 |1.8 |2.5 |10194 |
|[resnet34.a3_in1k](https://huggingface.co/timm/resnet34.a3_in1k)|160 |70.56|89.52|21.8 |1.9 |1.9 |10737 |
|[resnet18.tv_in1k](https://huggingface.co/timm/resnet18.tv_in1k)|224 |69.76|89.07|11.7 |1.8 |2.5 |10205 |
|[resnet10t.c3_in1k](https://huggingface.co/timm/resnet10t.c3_in1k)|224 |68.34|88.03|5.4 |1.1 |2.4 |13079 |
|[resnet18.a3_in1k](https://huggingface.co/timm/resnet18.a3_in1k)|224 |68.25|88.17|11.7 |1.8 |2.5 |10167 |
|[resnet10t.c3_in1k](https://huggingface.co/timm/resnet10t.c3_in1k)|176 |66.71|86.96|5.4 |0.7 |1.5 |20327 |
|[resnet18.a3_in1k](https://huggingface.co/timm/resnet18.a3_in1k)|160 |65.66|86.26|11.7 |0.9 |1.3 |18229 |
## Citation
```bibtex
@article{He2015,
author = {Kaiming He and Xiangyu Zhang and Shaoqing Ren and Jian Sun},
title = {Deep Residual Learning for Image Recognition},
journal = {arXiv preprint arXiv:1512.03385},
year = {2015}
}
```
```bibtex
@article{He2018BagOT,
title={Bag of Tricks for Image Classification with Convolutional Neural Networks},
author={Tong He and Zhi Zhang and Hang Zhang and Zhongyue Zhang and Junyuan Xie and Mu Li},
journal={2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
year={2018},
pages={558-567}
}
```
```bibtex
@misc{rw2019timm,
author = {Ross Wightman},
title = {PyTorch Image Models},
year = {2019},
publisher = {GitHub},
journal = {GitHub repository},
doi = {10.5281/zenodo.4414861},
howpublished = {\url{https://github.com/huggingface/pytorch-image-models}}
}
```
| 38,392 | [
[
-0.06463623046875,
-0.01513671875,
0.0019426345825195312,
0.0261383056640625,
-0.0305328369140625,
-0.00634002685546875,
-0.01035308837890625,
-0.03289794921875,
0.08807373046875,
0.017730712890625,
-0.04803466796875,
-0.03900146484375,
-0.045623779296875,
0... |
idlebg/easter-fusion | 2023-07-24T19:54:19.000Z | [
"diffusers",
"safetensors",
"stable-diffusion",
"art",
"text-to-image",
"en",
"license:other",
"endpoints_compatible",
"has_space",
"diffusers:StableDiffusionPipeline",
"region:us"
] | text-to-image | idlebg | null | null | idlebg/easter-fusion | 0 | 552 | diffusers | 2023-04-18T00:18:57 | ---
license: other
tags:
- stable-diffusion
- art
language:
- en
pipeline_tag: text-to-image
---
A fully revamped checkpoint based on the 512dim Lora
and chilloutmix_NiPrunedFp32Fix + deliberate_v2.
Training data: 512 DIM LORA
https://civitai.com/models/41893/lora-eggeaster-fusion
Here is how it looks using the lora on top of models:
More info on the Fusion project is soon to be announced ;)
🤟 🥃
lora weights: TEnc Weight 0.2 UNet Weight 1
Merged the 512dim lora to chillout and deliberate / --ratios 0.99 toward my fusion lora
C is CHillout / d is deliberate
Merged C and D with:
Base_alpha=0.53
Weight_values=0,0.157576195987654,0.28491512345679,0.384765625,0.459876543209877,0.512996720679012,0.546875,0.564260223765432,0.567901234567901,0.560546875,0.544945987654321,0.523847415123457,0.5,0.476152584876543,0.455054012345679,0.439453125,0.432098765432099,0.435739776234568,0.453125,0.487003279320987,0.540123456790124,0.615234375,0.71508487654321,0.842423804012347,1
and
1,0.842423804012346,0.71508487654321,0.615234375,0.540123456790123,0.487003279320988,0.453125,0.435739776234568,0.432098765432099,0.439453125,0.455054012345679,0.476152584876543,0.5,0.523847415123457,0.544945987654321,0.560546875,0.567901234567901,0.564260223765432,0.546875,0.512996720679013,0.459876543209876,0.384765625,0.28491512345679,0.157576195987653,0
both results merged
Weight_values=
1,0.842423804012346,0.71508487654321,0.615234375,0.540123456790123,0.487003279320988,0.453125,0.435739776234568,0.432098765432099,0.439453125,0.455054012345679,0.476152584876543,0.5,0.523847415123457,0.544945987654321,0.560546875,0.567901234567901,0.564260223765432,0.546875,0.512996720679013,0.459876543209876,0.384765625,0.28491512345679,0.157576195987653,0
And voila..
here is Egg_fusion checkpoint with the 512 dim-trained lora
Enjoy your eggs 🤟 🥃 | 2,569 | [
[
-0.056121826171875,
-0.02081298828125,
0.0286712646484375,
-0.00576019287109375,
-0.00998687744140625,
0.00838470458984375,
0.0227813720703125,
-0.0281219482421875,
0.06707763671875,
0.044647216796875,
-0.0513916015625,
-0.04632568359375,
-0.03515625,
0.0001... |
stillerman/trdne250 | 2023-08-03T02:02:52.000Z | [
"diffusers",
"tensorboard",
"stable-diffusion",
"stable-diffusion-diffusers",
"text-to-image",
"lora",
"license:creativeml-openrail-m",
"has_space",
"region:us"
] | text-to-image | stillerman | null | null | stillerman/trdne250 | 1 | 552 | diffusers | 2023-08-03T01:54:25 |
---
license: creativeml-openrail-m
base_model: runwayml/stable-diffusion-v1-5
tags:
- stable-diffusion
- stable-diffusion-diffusers
- text-to-image
- diffusers
- lora
inference: true
---
# LoRA text2image fine-tuning - stillerman/trdne250
These are LoRA adaption weights for runwayml/stable-diffusion-v1-5. The weights were fine-tuned on the stillerman/rugs-1.9k-downloaded dataset. You can find some example images in the following.
| 539 | [
[
-0.0247650146484375,
-0.039459228515625,
0.0197601318359375,
0.0268096923828125,
-0.03741455078125,
-0.015045166015625,
0.02447509765625,
-0.021026611328125,
0.0213470458984375,
0.05487060546875,
-0.066162109375,
-0.03302001953125,
-0.055145263671875,
-0.015... |
timm/vit_large_patch14_reg4_dinov2.lvd142m | 2023-10-30T04:56:25.000Z | [
"timm",
"pytorch",
"safetensors",
"arxiv:2309.16588",
"arxiv:2304.07193",
"arxiv:2010.11929",
"license:apache-2.0",
"region:us"
] | null | timm | null | null | timm/vit_large_patch14_reg4_dinov2.lvd142m | 1 | 552 | timm | 2023-10-30T04:52:17 | ---
tags:
- timm
library_name: timm
license: apache-2.0
---
# Model card for vit_large_patch14_reg4_dinov2.lvd142m
A Vision Transformer (ViT) image feature model with registers. Pretrained on LVD-142M with self-supervised DINOv2 method.
## Model Details
- **Model Type:** Image classification / feature backbone
- **Model Stats:**
- Params (M): 304.4
- GMACs: 416.1
- Activations (M): 305.3
- Image size: 518 x 518
- **Papers:**
- Vision Transformers Need Registers: https://arxiv.org/abs/2309.16588
- DINOv2: Learning Robust Visual Features without Supervision: https://arxiv.org/abs/2304.07193
- An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale: https://arxiv.org/abs/2010.11929v2
- **Original:** https://github.com/facebookresearch/dinov2
- **Pretrain Dataset:** LVD-142M
## Model Usage
### Image Classification
```python
from urllib.request import urlopen
from PIL import Image
import timm
img = Image.open(urlopen(
'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
))
model = timm.create_model('vit_large_patch14_reg4_dinov2.lvd142m', pretrained=True)
model = model.eval()
# get model specific transforms (normalization, resize)
data_config = timm.data.resolve_model_data_config(model)
transforms = timm.data.create_transform(**data_config, is_training=False)
output = model(transforms(img).unsqueeze(0)) # unsqueeze single image into batch of 1
top5_probabilities, top5_class_indices = torch.topk(output.softmax(dim=1) * 100, k=5)
```
### Image Embeddings
```python
from urllib.request import urlopen
from PIL import Image
import timm
img = Image.open(urlopen(
'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
))
model = timm.create_model(
'vit_large_patch14_reg4_dinov2.lvd142m',
pretrained=True,
num_classes=0, # remove classifier nn.Linear
)
model = model.eval()
# get model specific transforms (normalization, resize)
data_config = timm.data.resolve_model_data_config(model)
transforms = timm.data.create_transform(**data_config, is_training=False)
output = model(transforms(img).unsqueeze(0)) # output is (batch_size, num_features) shaped tensor
# or equivalently (without needing to set num_classes=0)
output = model.forward_features(transforms(img).unsqueeze(0))
# output is unpooled, a (1, 1374, 1024) shaped tensor
output = model.forward_head(output, pre_logits=True)
# output is a (1, num_features) shaped tensor
```
## Model Comparison
Explore the dataset and runtime metrics of this model in timm [model results](https://github.com/huggingface/pytorch-image-models/tree/main/results).
## Citation
```bibtex
@article{darcet2023vision,
title={Vision Transformers Need Registers},
author={Darcet, Timoth{'e}e and Oquab, Maxime and Mairal, Julien and Bojanowski, Piotr},
journal={arXiv preprint arXiv:2309.16588},
year={2023}
}
```
```bibtex
@misc{oquab2023dinov2,
title={DINOv2: Learning Robust Visual Features without Supervision},
author={Oquab, Maxime and Darcet, Timothée and Moutakanni, Theo and Vo, Huy V. and Szafraniec, Marc and Khalidov, Vasil and Fernandez, Pierre and Haziza, Daniel and Massa, Francisco and El-Nouby, Alaaeldin and Howes, Russell and Huang, Po-Yao and Xu, Hu and Sharma, Vasu and Li, Shang-Wen and Galuba, Wojciech and Rabbat, Mike and Assran, Mido and Ballas, Nicolas and Synnaeve, Gabriel and Misra, Ishan and Jegou, Herve and Mairal, Julien and Labatut, Patrick and Joulin, Armand and Bojanowski, Piotr},
journal={arXiv:2304.07193},
year={2023}
}
```
```bibtex
@article{dosovitskiy2020vit,
title={An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale},
author={Dosovitskiy, Alexey and Beyer, Lucas and Kolesnikov, Alexander and Weissenborn, Dirk and Zhai, Xiaohua and Unterthiner, Thomas and Dehghani, Mostafa and Minderer, Matthias and Heigold, Georg and Gelly, Sylvain and Uszkoreit, Jakob and Houlsby, Neil},
journal={ICLR},
year={2021}
}
```
```bibtex
@misc{rw2019timm,
author = {Ross Wightman},
title = {PyTorch Image Models},
year = {2019},
publisher = {GitHub},
journal = {GitHub repository},
doi = {10.5281/zenodo.4414861},
howpublished = {\url{https://github.com/huggingface/pytorch-image-models}}
}
``` | 4,309 | [
[
-0.03814697265625,
-0.024627685546875,
0.010040283203125,
0.004947662353515625,
-0.031768798828125,
-0.0256195068359375,
-0.019561767578125,
-0.0345458984375,
0.01053619384765625,
0.021087646484375,
-0.033477783203125,
-0.03857421875,
-0.04986572265625,
-0.0... |
Voicelab/herbert-base-cased-sentiment | 2023-03-20T11:40:07.000Z | [
"transformers",
"pytorch",
"safetensors",
"bert",
"text-classification",
"pl",
"license:cc-by-4.0",
"endpoints_compatible",
"region:us"
] | text-classification | Voicelab | null | null | Voicelab/herbert-base-cased-sentiment | 5 | 551 | transformers | 2022-11-02T09:55:09 | ---
pipeline_tag: text-classification
widget:
- text: "Pani Katarzyno z jakiej racji moja paczka przyszła do sąsiada zamiast do mnie? Nie można poprawnie nadać paczki?"
example_title: "Sentiment"
license: cc-by-4.0
language:
- pl
---
<img src="https://public.3.basecamp.com/p/rs5XqmAuF1iEuW6U7nMHcZeY/upload/download/VL-NLP-short.png" alt="logo voicelab nlp" style="width:300px;"/>
# Sentiment Classification in Polish
```python
import numpy as np
from transformers import AutoTokenizer, AutoModelForSequenceClassification
id2label = {0: "negative", 1: "neutral", 2: "positive"}
tokenizer = AutoTokenizer.from_pretrained("Voicelab/herbert-base-cased-sentiment")
model = AutoModelForSequenceClassification.from_pretrained("Voicelab/herbert-base-cased-sentiment")
input = ["Ale fajnie, spadł dzisiaj śnieg! Ulepimy dziś bałwana?"]
encoding = tokenizer(
input,
add_special_tokens=True,
return_token_type_ids=True,
truncation=True,
padding='max_length',
return_attention_mask=True,
return_tensors='pt',
)
output = model(**encoding).logits.to("cpu").detach().numpy()
prediction = id2label[np.argmax(output)]
print(input, "--->", prediction)
```
Predicted output:
```python
['Ale fajnie, spadł dzisiaj śnieg! Ulepimy dziś bałwana?'] ---> positive
```
### Overview
- **Language model:** [allegro/herbert-base-cased](https://huggingface.co/allegro/herbert-base-cased)
- **Language:** pl
- **Training data:** Reviews + own data
- **Blog post:** [Sentiment analysis - COVID-19 – the source of the heated discussion](https://voicelab.ai/covid-19-the-source-of-the-heated-discussion)
| 1,666 | [
[
-0.040435791015625,
-0.037109375,
0.0095672607421875,
0.030303955078125,
-0.024261474609375,
0.00659942626953125,
-0.032562255859375,
-0.0185546875,
0.01654052734375,
0.017669677734375,
-0.051513671875,
-0.05059814453125,
-0.051483154296875,
0.00604629516601... |
timm/eva02_large_patch14_448.mim_m38m_ft_in22k | 2023-03-31T05:46:48.000Z | [
"timm",
"pytorch",
"safetensors",
"image-classification",
"dataset:imagenet-22k",
"arxiv:2303.11331",
"arxiv:2303.15389",
"license:mit",
"region:us"
] | image-classification | timm | null | null | timm/eva02_large_patch14_448.mim_m38m_ft_in22k | 0 | 551 | timm | 2023-03-31T04:46:17 | ---
tags:
- image-classification
- timm
library_tag: timm
license: mit
datasets:
- imagenet-22k
- imagenet-22k
---
# Model card for eva02_large_patch14_448.mim_m38m_ft_in22k
An EVA02 image classification model. Pretrained on Merged-38M (IN-22K, CC12M, CC3M, COCO (train), ADE20K (train), Object365, and OpenImages) with masked image modeling (using EVA-CLIP as a MIM teacher) and fine-tuned on ImageNet-22k by paper authors.
EVA-02 models are vision transformers with mean pooling, SwiGLU, Rotary Position Embeddings (ROPE), and extra LN in MLP (for Base & Large).
NOTE: `timm` checkpoints are float32 for consistency with other models. Original checkpoints are float16 or bfloat16 in some cases, see originals if that's preferred.
## Model Details
- **Model Type:** Image classification / feature backbone
- **Model Stats:**
- Params (M): 326.4
- GMACs: 362.4
- Activations (M): 690.0
- Image size: 448 x 448
- **Papers:**
- EVA-02: A Visual Representation for Neon Genesis: https://arxiv.org/abs/2303.11331
- EVA-CLIP: Improved Training Techniques for CLIP at Scale: https://arxiv.org/abs/2303.15389
- **Original:**
- https://github.com/baaivision/EVA
- https://huggingface.co/Yuxin-CV/EVA-02
- **Pretrain Dataset:** ImageNet-22k
- **Dataset:** ImageNet-22k
## Model Usage
### Image Classification
```python
from urllib.request import urlopen
from PIL import Image
import timm
img = Image.open(urlopen(
'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
))
model = timm.create_model('eva02_large_patch14_448.mim_m38m_ft_in22k', pretrained=True)
model = model.eval()
# get model specific transforms (normalization, resize)
data_config = timm.data.resolve_model_data_config(model)
transforms = timm.data.create_transform(**data_config, is_training=False)
output = model(transforms(img).unsqueeze(0)) # unsqueeze single image into batch of 1
top5_probabilities, top5_class_indices = torch.topk(output.softmax(dim=1) * 100, k=5)
```
### Image Embeddings
```python
from urllib.request import urlopen
from PIL import Image
import timm
img = Image.open(urlopen(
'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
))
model = timm.create_model(
'eva02_large_patch14_448.mim_m38m_ft_in22k',
pretrained=True,
num_classes=0, # remove classifier nn.Linear
)
model = model.eval()
# get model specific transforms (normalization, resize)
data_config = timm.data.resolve_model_data_config(model)
transforms = timm.data.create_transform(**data_config, is_training=False)
output = model(transforms(img).unsqueeze(0)) # output is (batch_size, num_features) shaped tensor
# or equivalently (without needing to set num_classes=0)
output = model.forward_features(transforms(img).unsqueeze(0))
# output is unpooled, a (1, 1025, 1024) shaped tensor
output = model.forward_head(output, pre_logits=True)
# output is a (1, num_features) shaped tensor
```
## Model Comparison
Explore the dataset and runtime metrics of this model in timm [model results](https://github.com/huggingface/pytorch-image-models/tree/main/results).
|model |top1 |top5 |param_count|img_size|
|-----------------------------------------------|------|------|-----------|--------|
|eva02_large_patch14_448.mim_m38m_ft_in22k_in1k |90.054|99.042|305.08 |448 |
|eva02_large_patch14_448.mim_in22k_ft_in22k_in1k|89.946|99.01 |305.08 |448 |
|eva_giant_patch14_560.m30m_ft_in22k_in1k |89.792|98.992|1014.45 |560 |
|eva02_large_patch14_448.mim_in22k_ft_in1k |89.626|98.954|305.08 |448 |
|eva02_large_patch14_448.mim_m38m_ft_in1k |89.57 |98.918|305.08 |448 |
|eva_giant_patch14_336.m30m_ft_in22k_in1k |89.56 |98.956|1013.01 |336 |
|eva_giant_patch14_336.clip_ft_in1k |89.466|98.82 |1013.01 |336 |
|eva_large_patch14_336.in22k_ft_in22k_in1k |89.214|98.854|304.53 |336 |
|eva_giant_patch14_224.clip_ft_in1k |88.882|98.678|1012.56 |224 |
|eva02_base_patch14_448.mim_in22k_ft_in22k_in1k |88.692|98.722|87.12 |448 |
|eva_large_patch14_336.in22k_ft_in1k |88.652|98.722|304.53 |336 |
|eva_large_patch14_196.in22k_ft_in22k_in1k |88.592|98.656|304.14 |196 |
|eva02_base_patch14_448.mim_in22k_ft_in1k |88.23 |98.564|87.12 |448 |
|eva_large_patch14_196.in22k_ft_in1k |87.934|98.504|304.14 |196 |
|eva02_small_patch14_336.mim_in22k_ft_in1k |85.74 |97.614|22.13 |336 |
|eva02_tiny_patch14_336.mim_in22k_ft_in1k |80.658|95.524|5.76 |336 |
## Citation
```bibtex
@article{EVA02,
title={EVA-02: A Visual Representation for Neon Genesis},
author={Fang, Yuxin and Sun, Quan and Wang, Xinggang and Huang, Tiejun and Wang, Xinlong and Cao, Yue},
journal={arXiv preprint arXiv:2303.11331},
year={2023}
}
```
```bibtex
@article{EVA-CLIP,
title={EVA-02: A Visual Representation for Neon Genesis},
author={Sun, Quan and Fang, Yuxin and Wu, Ledell and Wang, Xinlong and Cao, Yue},
journal={arXiv preprint arXiv:2303.15389},
year={2023}
}
```
```bibtex
@misc{rw2019timm,
author = {Ross Wightman},
title = {PyTorch Image Models},
year = {2019},
publisher = {GitHub},
journal = {GitHub repository},
doi = {10.5281/zenodo.4414861},
howpublished = {\url{https://github.com/huggingface/pytorch-image-models}}
}
```
| 5,484 | [
[
-0.04547119140625,
-0.0292205810546875,
0.013214111328125,
0.00775909423828125,
-0.017425537109375,
0.0008606910705566406,
-0.01049041748046875,
-0.0345458984375,
0.038970947265625,
0.027130126953125,
-0.033782958984375,
-0.05194091796875,
-0.0435791015625,
... |
ainz/diseny-pixar | 2023-06-03T09:34:15.000Z | [
"diffusers",
"text-to-image",
"stable-diffusion",
"license:creativeml-openrail-m",
"endpoints_compatible",
"has_space",
"diffusers:StableDiffusionPipeline",
"region:us"
] | text-to-image | ainz | null | null | ainz/diseny-pixar | 7 | 551 | diffusers | 2023-06-02T23:35:39 | ---
license: creativeml-openrail-m
tags:
- text-to-image
- stable-diffusion
---
## Diseny_Pixar
This model is capable of generating Disney Pixar style images, no token is required to enjoy.
### Examples:
.jpeg)
> Pomprt: Smiling prince, regal, elegant, highly detailed, portrait, warm lighting, digital painting, Artstation, concept art, by Artgerm and Greg Rutkowski and Magali Villeneuve, sharp focus.
> Negative: Serious expression, dark and gloomy, low detail, pixelated, cartoonish, bright colors.
> Inference steps: 30
> Pomprt: cute princess, pastel colors, whimsical, Disney style, digital painting, highly detailed, trending on Artstation, concept art, sharp focus, illustration, by Artgerm and Greg Rutkowski and Brianna Garcia
> Negative: dark and gloomy, low detail, low contrast, blurry, pixelated, minimalistic, cartoonish, bright colors, abstract
> Inference steps: 30
.jpeg)
> Prompt: majestic flying dragon, epic sky, detailed, concept art, low angle, high detail, warm lighting, volumetric, godrays, vivid, trending on Artstation, by Greg Rutkowski, huge scene, art by Magali Villeneuve
> Negative: cartoonish, simplistic, low detail, abstract, bright colors, pixelated, minimalistic, indoor scene.
> Inference steps: 30
.jpeg)
> Prompt: Medieval kingdom with castle, epic sky, detailed, concept art, low angle, high detail, warm lighting, volumetric, godrays, vivid, trending on Artstation, by Jordan Grimmer, huge scene, grass, art by Greg Rutkowski.
> Negative: Modern elements, bright colors, simplistic, abstract, low detail, pixelated, minimalistic, cartoonish, outdoor scene.
> Inference steps: 30
.jpeg)
> Prompt: Little fairy, enchanted forest, magical, ethereal, highly detailed, digital painting, Artstation, intricate, delicate, pastel colors, illustration by Loish and Rossdraws.
> Negative: Dark and gloomy, blurry, low contrast, pixelated, simplistic, minimalistic, no animals.
> Inference steps: 30 | 2,407 | [
[
-0.059112548828125,
-0.035552978515625,
0.01531982421875,
0.039459228515625,
-0.017913818359375,
0.00878143310546875,
0.02239990234375,
-0.034881591796875,
0.0455322265625,
0.01055908203125,
-0.06573486328125,
-0.0161590576171875,
-0.044219970703125,
0.01004... |
Daniil-plotnikov/ru-vision | 2023-07-12T14:21:49.000Z | [
"diffusers",
"text-to-image",
"stable-diffusion",
"ru",
"en",
"license:creativeml-openrail-m",
"endpoints_compatible",
"has_space",
"diffusers:StableDiffusionPipeline",
"region:us"
] | text-to-image | Daniil-plotnikov | null | null | Daniil-plotnikov/ru-vision | 0 | 551 | diffusers | 2023-06-30T10:39:29 | ---
license: creativeml-openrail-m
tags:
- text-to-image
- stable-diffusion
language:
- ru
- en
---
### Ru_Vision Dreambooth model trained by Daniil-plotnikov with [TheLastBen's fast-DreamBooth](https://colab.research.google.com/github/TheLastBen/fast-stable-diffusion/blob/main/fast-DreamBooth.ipynb) notebook
Test the concept via A1111 Colab [fast-Colab-A1111](https://colab.research.google.com/github/TheLastBen/fast-stable-diffusion/blob/main/fast_stable_diffusion_AUTOMATIC1111.ipynb)
Sample pictures of this concept: | 525 | [
[
-0.015869140625,
-0.0482177734375,
0.049835205078125,
0.0280303955078125,
-0.0294189453125,
0.02880859375,
0.032684326171875,
-0.0262603759765625,
0.046630859375,
0.006000518798828125,
-0.0231781005859375,
-0.02685546875,
-0.03643798828125,
-0.01986694335937... |
cepiloth/ko-llama2-finetune-ex5 | 2023-11-01T07:16:45.000Z | [
"transformers",
"pytorch",
"llama",
"text-generation",
"autotrain",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | cepiloth | null | null | cepiloth/ko-llama2-finetune-ex5 | 0 | 551 | transformers | 2023-10-31T10:31:07 | ---
tags:
- autotrain
- text-generation
widget:
- text: "I love AutoTrain because "
---
# Model Trained Using AutoTrain
# License
Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International Public License, under LLAMA 2 COMMUNITY LICENSE AGREEMENT
This model was created as a personal experiment, unrelated to the organization I work for. | 352 | [
[
-0.0023136138916015625,
-0.0037384033203125,
0.0294036865234375,
0.0189361572265625,
-0.040130615234375,
0.00457763671875,
0.03228759765625,
-0.044403076171875,
0.007495880126953125,
0.034149169921875,
-0.059967041015625,
-0.006900787353515625,
-0.0382080078125,... |
Nahrawy/AIorNot | 2023-04-07T17:12:13.000Z | [
"transformers",
"pytorch",
"swin",
"image-classification",
"generative ai",
"classification",
"en",
"dataset:competitions/aiornot",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"has_space",
"region:us"
] | image-classification | Nahrawy | null | null | Nahrawy/AIorNot | 4 | 550 | transformers | 2023-03-18T16:55:35 | ---
license: apache-2.0
datasets:
- competitions/aiornot
language:
- en
metrics:
- accuracy
tags:
- generative ai
- classification
---
Classification model used to classify real images and AI generated images.\
The model used is swin-tiny-patch4-window7-224 finetued on aiornot dataset.\
To use the model
```
import torch
from transformers import AutoFeatureExtractor, AutoModelForImageClassification
labels = ["Real", "AI"]
feature_extractor = AutoFeatureExtractor.from_pretrained("Nahrawy/AIorNot")
model = AutoModelForImageClassification.from_pretrained("Nahrawy/AIorNot")
input = feature_extractor(image, return_tensors="pt")
with torch.no_grad():
outputs = model(**input)
logits = outputs.logits
prediction = logits.argmax(-1).item()
label = labels[prediction]
``` | 777 | [
[
-0.0391845703125,
-0.0305328369140625,
-0.0124969482421875,
-0.01763916015625,
-0.02154541015625,
-0.009735107421875,
0.0215911865234375,
-0.049285888671875,
-0.01422119140625,
0.0364990234375,
-0.031341552734375,
-0.0274200439453125,
-0.0426025390625,
-0.00... |
haor/Evt_V2 | 2023-05-10T16:05:06.000Z | [
"diffusers",
"stable-diffusion",
"stable-diffusion-diffusers",
"text-to-image",
"anime",
"license:creativeml-openrail-m",
"endpoints_compatible",
"has_space",
"diffusers:StableDiffusionPipeline",
"region:us"
] | text-to-image | haor | null | null | haor/Evt_V2 | 56 | 549 | diffusers | 2022-11-20T21:15:04 | ---
tags:
- stable-diffusion
- stable-diffusion-diffusers
- text-to-image
- anime
- diffusers
license: creativeml-openrail-m
---
# Evt_V2
Based on animefull-latest, fine-tuned using a training set of 15000 images (7700 flipped). Most of the training set uses [pixiv_AI_crawler](https://github.com/7eu7d7/pixiv_AI_crawler) to filter the pixiv daily ranking, and then mixes some nsfw animation images.
### Examples
```
best quality, illustration,highly detailed,1girl,upper body,beautiful detailed eyes, medium_breasts, long hair,grey hair, grey eyes, curly hair, bangs,empty eyes,expressionless, ((masterpiece)),twintails,beautiful detailed sky, beautiful detailed water, cinematic lighting, dramatic angle,((back to the viewer)),(an extremely delicate and beautiful),school uniform,black ribbon,light smile,
Negative prompt: lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry,artist name,bad feet
Steps: 40, Sampler: Euler a, CFG scale: 7, Clip skip: 2
*evt_bs6_ema is the first version of evt
```
```
{Masterpiece, Kaname_Madoka, tall and long double tails, well rooted hair, (pink hair), pink eyes, crossed bangs, ojousama, jk, thigh bandages, wrist cuffs, (pink bow: 1.2)}, plain color, sketch, masterpiece, high detail, masterpiece portrait, best quality, ray tracing, {:<, look at the edge}
Negative prompt: ((((ugly)))), (((duplicate))), ((morbid)), ((mutilated)),extra fingers, mutated hands, ((poorly drawn hands)), ((poorly drawn face)), (((bad proportions))), ((extra limbs)), (((deformed))), (((disfigured))), cloned face, gross proportions, (malformed limbs), ((missing arms)), ((missing legs)), (((extra arms))), (((extra legs))), too many fingers, (((long neck))), (((low quality))), normal quality, blurry, bad feet, text font ui, ((((worst quality)))), anatomical nonsense, (((bad shadow))), unnatural body, liquid body, 3D, 3D game, 3D game scene, 3D character, bad hairs, poorly drawn hairs, fused hairs, big muscles, bad face, extra eyes, furry, pony, mosaic, disappearing calf, disappearing legs, extra digit, fewer digit, fused digit, missing digit, fused feet, poorly drawn eyes, big face, long face, bad eyes, thick lips, obesity, strong girl, beard，Excess legs
Steps: 40, Sampler: Euler a, CFG scale: 6,Clip skip: 2
``` | 2,849 | [
[
-0.04833984375,
-0.060150146484375,
0.032806396484375,
0.008880615234375,
-0.02642822265625,
-0.0022525787353515625,
0.03460693359375,
-0.04351806640625,
0.0361328125,
0.036773681640625,
-0.05517578125,
-0.041107177734375,
-0.041107177734375,
0.019775390625,... |
Nihirc/Prompt2MedImage | 2023-05-12T13:14:05.000Z | [
"diffusers",
"text-to-image",
"en",
"arxiv:2103.00020",
"arxiv:2205.11487",
"license:wtfpl",
"endpoints_compatible",
"has_space",
"diffusers:StableDiffusionPipeline",
"region:us"
] | text-to-image | Nihirc | null | null | Nihirc/Prompt2MedImage | 1 | 549 | diffusers | 2023-05-12T12:00:08 | ---
license: wtfpl
language:
- en
pipeline_tag: text-to-image
---
# Prompt2MedImage - Diffusion for Medical Images
Prompt2MedImage is a latent text to image diffusion model that has been fine-tuned on medical images from ROCO dataset.
The weights here are itended to be used with the 🧨Diffusers library.
This model was trained using Amazon SageMaker and the Hugging Face Deep Learning container.
## Model Details
- **Developed by:** Nihir Chadderwala
- **Model type:** Diffusion based text to medical image generation model
- **Language:** English
- **License:** wtfpl
- **Model Description:** This latent text to image diffusion model can be used to generate high quality medical images based on text prompts. It uses a fixed, pretrained text encoder ([CLIP ViT-L/14](https://arxiv.org/abs/2103.00020)) as suggested in the [Imagen paper](https://arxiv.org/abs/2205.11487).
## Examples
1. The patient had residual paralysis of the hand after poliomyelitis. It was necessary to stabilize the thumb with reference to the index finger. This was accomplished by placing a graft from the bone bank between the first and second metacarpals. The roentgenogram shows the complete healing of the graft one year later.
2. A 3-year-old child with visual difficulties. Axial FLAIR image show a supra-sellar lesion extending to the temporal lobes along the optic tracts (arrows) with moderate mass effect, compatible with optic glioma. FLAIR hyperintensity is also noted in the left mesencephalon from additional tumoral involvement
3. Showing the subtrochanteric fracture in the porotic bone.
## License
This model is open access and available to all, with a Do What the F*ck You want to public license further specifying rights and usage.
- You can't use the model to deliberately produce nor share illegal or harmful outputs or content.
- The author claims no rights on the outputs you generate, you are free to use them and are accountable for their use.
- You may re-distribute the weights and use the model commercially and/or as a service.
## Run using PyTorch
```bash
pip install diffusers transformers
```
Running pipeline with default PNDM scheduler:
```python
import torch
from diffusers import StableDiffusionPipeline
model_id = "Nihirc/Prompt2MedImage"
device = "cuda"
pipe = StableDiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.float16)
pipe = pipe.to(device)
prompt = "Showing the subtrochanteric fracture in the porotic bone."
image = pipe(prompt).images[0]
image.save("porotic_bone_fracture.png")
```
## Citation
```
O. Pelka, S. Koitka, J. Rückert, F. Nensa, C.M. Friedrich,
"Radiology Objects in COntext (ROCO): A Multimodal Image Dataset".
MICCAI Workshop on Large-scale Annotation of Biomedical Data and Expert Label Synthesis (LABELS) 2018, September 16, 2018, Granada, Spain. Lecture Notes on Computer Science (LNCS), vol. 11043, pp. 180-189, Springer Cham, 2018.
doi: 10.1007/978-3-030-01364-6_20
``` | 3,069 | [
[
0.00020992755889892578,
-0.058349609375,
0.050262451171875,
0.01535797119140625,
-0.0408935546875,
-0.02178955078125,
0.016876220703125,
-0.04547119140625,
0.01082611083984375,
0.0350341796875,
-0.03253173828125,
-0.048248291015625,
-0.0645751953125,
0.00101... |
osiria/distilbert-base-italian-cased | 2023-06-09T18:06:51.000Z | [
"transformers",
"pytorch",
"safetensors",
"distilbert",
"fill-mask",
"it",
"arxiv:1910.01108",
"arxiv:2010.05609",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | fill-mask | osiria | null | null | osiria/distilbert-base-italian-cased | 1 | 549 | transformers | 2023-06-01T16:04:32 | ---
license: apache-2.0
language:
- it
---
--------------------------------------------------------------------------------------------------
<body>
<span class="vertical-text" style="background-color:lightgreen;border-radius: 3px;padding: 3px;"> </span>
<br>
<span class="vertical-text" style="background-color:orange;border-radius: 3px;padding: 3px;"> </span>
<br>
<span class="vertical-text" style="background-color:lightblue;border-radius: 3px;padding: 3px;"> Model: DistilBERT</span>
<br>
<span class="vertical-text" style="background-color:tomato;border-radius: 3px;padding: 3px;"> Lang: IT</span>
<br>
<span class="vertical-text" style="background-color:lightgrey;border-radius: 3px;padding: 3px;"> </span>
<br>
<span class="vertical-text" style="background-color:#CF9FFF;border-radius: 3px;padding: 3px;"> </span>
</body>
--------------------------------------------------------------------------------------------------
<h3>Model description</h3>
This is a <b>DistilBERT</b> <b>[1]</b> model for the <b>Italian</b> language, obtained using the multilingual <b>DistilBERT</b> ([distilbert-base-multilingual-cased](https://huggingface.co/distilbert-base-multilingual-cased)) as a starting point and focusing it on the Italian language by modifying the embedding layer
(as in <b>[2]</b>, computing document-level frequencies over the <b>Wikipedia</b> dataset)
The resulting model has 67M parameters, a vocabulary of 30.785 tokens, and a size of ~270 MB.
<h3>Quick usage</h3>
```python
from transformers import BertTokenizerFast, DistilBertModel
tokenizer = DistilBertTokenizerFast.from_pretrained("osiria/distilbert-base-italian-cased")
model = DistilBertModel.from_pretrained("osiria/distilbert-base-italian-cased")
```
<h3>References</h3>
[1] https://arxiv.org/abs/1910.01108
[2] https://arxiv.org/abs/2010.05609
<h3>License</h3>
The model is released under <b>Apache-2.0</b> license
| 1,914 | [
[
-0.034393310546875,
-0.06414794921875,
0.01212310791015625,
0.0263519287109375,
-0.00319671630859375,
-0.004604339599609375,
-0.007190704345703125,
-0.034912109375,
0.0129241943359375,
-0.01995849609375,
-0.0499267578125,
-0.0390625,
-0.044036865234375,
0.00... |
sail-rvc/Freddie_Mercury__RVC_-_700_Epochs_ | 2023-07-14T07:22:43.000Z | [
"transformers",
"rvc",
"sail-rvc",
"audio-to-audio",
"endpoints_compatible",
"region:us"
] | audio-to-audio | sail-rvc | null | null | sail-rvc/Freddie_Mercury__RVC_-_700_Epochs_ | 0 | 549 | transformers | 2023-07-14T07:22:20 |
---
pipeline_tag: audio-to-audio
tags:
- rvc
- sail-rvc
---
# Freddie_Mercury__RVC_-_700_Epochs_
## RVC Model
This model repo was automatically generated.
Date: 2023-07-14 07:22:43
Bot Name: juuxnscrap
Model Type: RVC
Source: https://huggingface.co/juuxn/RVCModels/
Reason: Converting into loadable format for https://github.com/chavinlo/rvc-runpod
| 402 | [
[
-0.03436279296875,
-0.0295562744140625,
0.037750244140625,
0.00879669189453125,
-0.02752685546875,
0.007049560546875,
0.0066375732421875,
0.00211334228515625,
0.01904296875,
0.07244873046875,
-0.0535888671875,
-0.0526123046875,
-0.0224761962890625,
-0.004302... |
digiplay/fantasticmix2.5D_v3.0 | 2023-07-20T17:07:52.000Z | [
"diffusers",
"stable-diffusion",
"stable-diffusion-diffusers",
"text-to-image",
"license:other",
"endpoints_compatible",
"has_space",
"diffusers:StableDiffusionPipeline",
"region:us"
] | text-to-image | digiplay | null | null | digiplay/fantasticmix2.5D_v3.0 | 1 | 549 | diffusers | 2023-07-20T15:31:29 | ---
license: other
tags:
- stable-diffusion
- stable-diffusion-diffusers
- text-to-image
- diffusers
inference: true
---
Model info :
https://civitai.com/models/20632?modelVersionId=121878
Sample image generated by huggingface's API :
 | 556 | [
[
-0.040740966796875,
-0.039886474609375,
0.02581787109375,
0.031829833984375,
-0.0201263427734375,
-0.004085540771484375,
0.0304107666015625,
-0.03521728515625,
0.057342529296875,
0.02093505859375,
-0.08709716796875,
-0.02130126953125,
-0.0119781494140625,
0.... |
digiplay/Opiate_v3 | 2023-07-23T13:05:24.000Z | [
"diffusers",
"stable-diffusion",
"stable-diffusion-diffusers",
"text-to-image",
"license:other",
"endpoints_compatible",
"has_space",
"diffusers:StableDiffusionPipeline",
"region:us"
] | text-to-image | digiplay | null | null | digiplay/Opiate_v3 | 1 | 549 | diffusers | 2023-07-23T10:59:43 | ---
license: other
tags:
- stable-diffusion
- stable-diffusion-diffusers
- text-to-image
- diffusers
inference: true
---
Model info:
https://civitai.com/models/69587?modelVersionId=121220
Original Author's DEMO images :
| 961 | [
[
-0.036224365234375,
-0.0139312744140625,
0.032958984375,
0.00894927978515625,
-0.0241241455078125,
-0.009979248046875,
0.01500701904296875,
-0.008544921875,
0.042144775390625,
0.02593994140625,
-0.061279296875,
-0.0280303955078125,
-0.01097869873046875,
-0.0... |
fofr/sdxl-vision-pro | 2023-09-19T21:17:34.000Z | [
"diffusers",
"text-to-image",
"stable-diffusion",
"lora",
"license:creativeml-openrail-m",
"region:us",
"has_space"
] | text-to-image | fofr | null | null | fofr/sdxl-vision-pro | 3 | 549 | diffusers | 2023-09-19T21:17:17 | ---
license: creativeml-openrail-m
tags:
- text-to-image
- stable-diffusion
- lora
- diffusers
base_model: stabilityai/stable-diffusion-xl-base-1.0
pivotal_tuning: true
textual_embeddings: embeddings.pti
instance_prompt: <s0><s1>
inference: false
---
# sdxl-vision-pro LoRA by [fofr](https://replicate.com/fofr)
### An SDXL fine-tune on Apple Vision Pro
>
## Inference with Replicate API
Grab your replicate token [here](https://replicate.com/account)
```bash
pip install replicate
export REPLICATE_API_TOKEN=r8_*************************************
```
```py
import replicate
output = replicate.run(
"sdxl-vision-pro@sha256:858d66f10a520248ae48fd5c6661578fef8982ffd1a272f58c2a16ef803dd744",
input={"prompt": "A photo of gandalf wearing a TOK VR headset, faces visible"}
)
print(output)
```
You may also do inference via the API with Node.js or curl, and locally with COG and Docker, [check out the Replicate API page for this model](https://replicate.com/fofr/sdxl-vision-pro/api)
## Inference with 🧨 diffusers
Replicate SDXL LoRAs are trained with Pivotal Tuning, which combines training a concept via Dreambooth LoRA with training a new token with Textual Inversion.
As `diffusers` doesn't yet support textual inversion for SDXL, we will use cog-sdxl `TokenEmbeddingsHandler` class.
The trigger tokens for your prompt will be `<s0><s1>`
```shell
pip install diffusers transformers accelerate safetensors huggingface_hub
git clone https://github.com/replicate/cog-sdxl cog_sdxl
```
```py
import torch
from huggingface_hub import hf_hub_download
from diffusers import DiffusionPipeline
from cog_sdxl.dataset_and_utils import TokenEmbeddingsHandler
from diffusers.models import AutoencoderKL
pipe = DiffusionPipeline.from_pretrained(
"stabilityai/stable-diffusion-xl-base-1.0",
torch_dtype=torch.float16,
variant="fp16",
).to("cuda")
pipe.load_lora_weights("fofr/sdxl-vision-pro", weight_name="lora.safetensors")
text_encoders = [pipe.text_encoder, pipe.text_encoder_2]
tokenizers = [pipe.tokenizer, pipe.tokenizer_2]
embedding_path = hf_hub_download(repo_id="fofr/sdxl-vision-pro", filename="embeddings.pti", repo_type="model")
embhandler = TokenEmbeddingsHandler(text_encoders, tokenizers)
embhandler.load_embeddings(embedding_path)
prompt="A photo of gandalf wearing a <s0><s1> VR headset, faces visible"
images = pipe(
prompt,
cross_attention_kwargs={"scale": 0.8},
).images
#your output image
images[0]
```
| 2,579 | [
[
-0.035858154296875,
-0.044830322265625,
0.034820556640625,
0.017852783203125,
-0.0297698974609375,
-0.006961822509765625,
0.0196075439453125,
-0.02130126953125,
0.036956787109375,
0.047271728515625,
-0.053863525390625,
-0.052490234375,
-0.04620361328125,
-0.... |
Helsinki-NLP/opus-mt-de-fr | 2023-08-16T11:27:53.000Z | [
"transformers",
"pytorch",
"tf",
"rust",
"marian",
"text2text-generation",
"translation",
"de",
"fr",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | translation | Helsinki-NLP | null | null | Helsinki-NLP/opus-mt-de-fr | 0 | 548 | transformers | 2022-03-02T23:29:04 | ---
tags:
- translation
license: apache-2.0
---
### opus-mt-de-fr
* source languages: de
* target languages: fr
* OPUS readme: [de-fr](https://github.com/Helsinki-NLP/OPUS-MT-train/blob/master/models/de-fr/README.md)
* dataset: opus
* model: transformer-align
* pre-processing: normalization + SentencePiece
* download original weights: [opus-2020-01-08.zip](https://object.pouta.csc.fi/OPUS-MT-models/de-fr/opus-2020-01-08.zip)
* test set translations: [opus-2020-01-08.test.txt](https://object.pouta.csc.fi/OPUS-MT-models/de-fr/opus-2020-01-08.test.txt)
* test set scores: [opus-2020-01-08.eval.txt](https://object.pouta.csc.fi/OPUS-MT-models/de-fr/opus-2020-01-08.eval.txt)
## Benchmarks
| testset | BLEU | chr-F |
|-----------------------|-------|-------|
| euelections_dev2019.transformer-align.de | 32.2 | 0.590 |
| newssyscomb2009.de.fr | 26.8 | 0.553 |
| news-test2008.de.fr | 26.4 | 0.548 |
| newstest2009.de.fr | 25.6 | 0.539 |
| newstest2010.de.fr | 29.1 | 0.572 |
| newstest2011.de.fr | 26.9 | 0.551 |
| newstest2012.de.fr | 27.7 | 0.554 |
| newstest2013.de.fr | 29.5 | 0.560 |
| newstest2019-defr.de.fr | 36.6 | 0.625 |
| Tatoeba.de.fr | 49.2 | 0.664 |
| 1,209 | [
[
-0.0330810546875,
-0.0299530029296875,
0.0195770263671875,
0.0282745361328125,
-0.0253143310546875,
-0.02874755859375,
-0.0224761962890625,
-0.00376129150390625,
0.006866455078125,
0.032806396484375,
-0.060546875,
-0.04156494140625,
-0.048858642578125,
0.016... |
bigscience/mt0-xxl | 2023-05-27T17:27:30.000Z | [
"transformers",
"pytorch",
"mt5",
"text2text-generation",
"af",
"am",
"ar",
"az",
"be",
"bg",
"bn",
"ca",
"ceb",
"co",
"cs",
"cy",
"da",
"de",
"el",
"en",
"eo",
"es",
"et",
"eu",
"fa",
"fi",
"fil",
"fr",
"fy",
"ga",
"gd",
"gl",
"gu",
"ha",
"haw",
... | text2text-generation | bigscience | null | null | bigscience/mt0-xxl | 47 | 548 | transformers | 2022-10-19T23:12:28 | ---
datasets:
- bigscience/xP3
- mc4
license: apache-2.0
language:
- af
- am
- ar
- az
- be
- bg
- bn
- ca
- ceb
- co
- cs
- cy
- da
- de
- el
- en
- eo
- es
- et
- eu
- fa
- fi
- fil
- fr
- fy
- ga
- gd
- gl
- gu
- ha
- haw
- hi
- hmn
- ht
- hu
- hy
- ig
- is
- it
- iw
- ja
- jv
- ka
- kk
- km
- kn
- ko
- ku
- ky
- la
- lb
- lo
- lt
- lv
- mg
- mi
- mk
- ml
- mn
- mr
- ms
- mt
- my
- ne
- nl
- 'no'
- ny
- pa
- pl
- ps
- pt
- ro
- ru
- sd
- si
- sk
- sl
- sm
- sn
- so
- sq
- sr
- st
- su
- sv
- sw
- ta
- te
- tg
- th
- tr
- uk
- und
- ur
- uz
- vi
- xh
- yi
- yo
- zh
- zu
tags:
- text2text-generation
widget:
- text: >-
<table> <tr> <th>Name</th> <th>Explanation</th> <th>Example models</th>
</tr> <tr> <td><a
href=https://huggingface.co/datasets/bigscience/xP3>xP3</a></t> <td>Mixture
of 13 training tasks in 46 languages with English prompts</td> <td><a
href=https://huggingface.co/bigscience/bloomz>bloomz</a> & <a
href=https://huggingface.co/bigscience/mt0-xxl>mt0-xxl</a></td> </tr> <tr>
<td><a href=https://huggingface.co/datasets/bigscience/xP3mt>xP3mt</a></t>
<td>Mixture of 13 training tasks in 46 languages with prompts in 20
languages (machine-translated from English)</td> <td><a
href=https://huggingface.co/bigscience/bloomz-mt>bloomz-mt</a> & <a
href=https://huggingface.co/bigscience/mt0-xxl-mt>mt0-xxl-mt</a></td> </tr>
<tr> <td><a
href=https://huggingface.co/datasets/bigscience/xP3all>xP3all</a></t>
<td>xP3 + our evaluation datasets adding an additional 3 tasks for a total
of 16 tasks in 46 languages with English prompts</td> <td></td> </tr> <tr>
<td><a
href=https://huggingface.co/datasets/bigscience/xP3megds>xP3megds</a></t>
<td><a
href=https://github.com/bigscience-workshop/Megatron-DeepSpeed>Megatron-DeepSpeed</a>
processed version of xP3</td> <td><a
href=https://huggingface.co/bigscience/bloomz>bloomz</a></td> </tr> <tr>
<td><a href=https://huggingface.co/datasets/Muennighoff/P3>P3</a></t>
<td>Repreprocessed version of the English-only <a
href=https://huggingface.co/datasets/bigscience/P3>P3</a> with 8 training
tasks</td> <td><a
href=https://huggingface.co/bigscience/bloomz-p3>bloomz-p3</a> & <a
href=https://huggingface.co/bigscience/mt0-xxl-p3>mt0-xxl-p3</a></td> </tr>
</table> Which dataset has the most tasks?
example_title: en-en struct-to-text
- text: Life is beautiful! Translate to Mongolian.
example_title: mn-en translation
- text: Le mot japonais «憂鬱» veut dire quoi en Odia?
example_title: jp-or-fr translation
- text: >-
Stell mir eine schwierige Quiz Frage bei der es um Astronomie geht. Bitte
stell die Frage auf Norwegisch.
example_title: de-nb quiz
- text: >-
We present BLOOMZ & mT0, a family of models capable of following human
instructions in dozens of languages zero-shot. We finetune BLOOM & mT5
pretrained multilingual language models on our crosslingual task mixture
(xP3) and find our resulting models capable of crosslingual generalization
to unseen tasks & languages. What are the keywords in Chinese?
example_title: zh-en keywords
- text: >-
一个传奇的开端，一个不灭的神话，这不仅仅是一部电影，而是作为一个走进新时代的标签，永远彪炳史册。Would you rate the previous
review as positive, neutral or negative?
example_title: zh-en sentiment
- text: 一个传奇的开端，一个不灭的神话，这不仅仅是一部电影，而是作为一个走进新时代的标签，永远彪炳史册。你认为这句话的立场是赞扬、中立还是批评？
example_title: zh-zh sentiment
- text: Suggest at least five related search terms to "Mạng neural nhân tạo".
example_title: vi-en query
- text: >-
Proposez au moins cinq mots clés concernant «Réseau de neurones
artificiels».
example_title: fr-fr query
- text: Explain in a sentence in Telugu what is backpropagation in neural networks.
example_title: te-en qa
- text: Why is the sky blue?
example_title: en-en qa
- text: >-
Write a fairy tale about a troll saving a princess from a dangerous dragon.
The fairy tale is a masterpiece that has achieved praise worldwide and its
moral is "Heroes Come in All Shapes and Sizes". Story (in Spanish):
example_title: es-en fable
- text: >-
Write a fable about wood elves living in a forest that is suddenly invaded
by ogres. The fable is a masterpiece that has achieved praise worldwide and
its moral is "Violence is the last refuge of the incompetent". Fable (in
Hindi):
example_title: hi-en fable
model-index:
- name: mt0-xxl
results:
- task:
type: Coreference resolution
dataset:
type: winogrande
name: Winogrande XL (xl)
config: xl
split: validation
revision: a80f460359d1e9a67c006011c94de42a8759430c
metrics:
- type: Accuracy
value: 63.38
- task:
type: Coreference resolution
dataset:
type: Muennighoff/xwinograd
name: XWinograd (en)
config: en
split: test
revision: 9dd5ea5505fad86b7bedad667955577815300cee
metrics:
- type: Accuracy
value: 81.29
- task:
type: Coreference resolution
dataset:
type: Muennighoff/xwinograd
name: XWinograd (fr)
config: fr
split: test
revision: 9dd5ea5505fad86b7bedad667955577815300cee
metrics:
- type: Accuracy
value: 78.31
- task:
type: Coreference resolution
dataset:
type: Muennighoff/xwinograd
name: XWinograd (jp)
config: jp
split: test
revision: 9dd5ea5505fad86b7bedad667955577815300cee
metrics:
- type: Accuracy
value: 78.62
- task:
type: Coreference resolution
dataset:
type: Muennighoff/xwinograd
name: XWinograd (pt)
config: pt
split: test
revision: 9dd5ea5505fad86b7bedad667955577815300cee
metrics:
- type: Accuracy
value: 77.95
- task:
type: Coreference resolution
dataset:
type: Muennighoff/xwinograd
name: XWinograd (ru)
config: ru
split: test
revision: 9dd5ea5505fad86b7bedad667955577815300cee
metrics:
- type: Accuracy
value: 76.51
- task:
type: Coreference resolution
dataset:
type: Muennighoff/xwinograd
name: XWinograd (zh)
config: zh
split: test
revision: 9dd5ea5505fad86b7bedad667955577815300cee
metrics:
- type: Accuracy
value: 77.38
- task:
type: Natural language inference
dataset:
type: anli
name: ANLI (r1)
config: r1
split: validation
revision: 9dbd830a06fea8b1c49d6e5ef2004a08d9f45094
metrics:
- type: Accuracy
value: 49.5
- task:
type: Natural language inference
dataset:
type: anli
name: ANLI (r2)
config: r2
split: validation
revision: 9dbd830a06fea8b1c49d6e5ef2004a08d9f45094
metrics:
- type: Accuracy
value: 43
- task:
type: Natural language inference
dataset:
type: anli
name: ANLI (r3)
config: r3
split: validation
revision: 9dbd830a06fea8b1c49d6e5ef2004a08d9f45094
metrics:
- type: Accuracy
value: 46.08
- task:
type: Natural language inference
dataset:
type: super_glue
name: SuperGLUE (cb)
config: cb
split: validation
revision: 9e12063561e7e6c79099feb6d5a493142584e9e2
metrics:
- type: Accuracy
value: 85.71
- task:
type: Natural language inference
dataset:
type: super_glue
name: SuperGLUE (rte)
config: rte
split: validation
revision: 9e12063561e7e6c79099feb6d5a493142584e9e2
metrics:
- type: Accuracy
value: 85.56
- task:
type: Natural language inference
dataset:
type: xnli
name: XNLI (ar)
config: ar
split: validation
revision: a5a45e4ff92d5d3f34de70aaf4b72c3bdf9f7f16
metrics:
- type: Accuracy
value: 57.91
- task:
type: Natural language inference
dataset:
type: xnli
name: XNLI (bg)
config: bg
split: validation
revision: a5a45e4ff92d5d3f34de70aaf4b72c3bdf9f7f16
metrics:
- type: Accuracy
value: 59.88
- task:
type: Natural language inference
dataset:
type: xnli
name: XNLI (de)
config: de
split: validation
revision: a5a45e4ff92d5d3f34de70aaf4b72c3bdf9f7f16
metrics:
- type: Accuracy
value: 60.64
- task:
type: Natural language inference
dataset:
type: xnli
name: XNLI (el)
config: el
split: validation
revision: a5a45e4ff92d5d3f34de70aaf4b72c3bdf9f7f16
metrics:
- type: Accuracy
value: 59
- task:
type: Natural language inference
dataset:
type: xnli
name: XNLI (en)
config: en
split: validation
revision: a5a45e4ff92d5d3f34de70aaf4b72c3bdf9f7f16
metrics:
- type: Accuracy
value: 62.01
- task:
type: Natural language inference
dataset:
type: xnli
name: XNLI (es)
config: es
split: validation
revision: a5a45e4ff92d5d3f34de70aaf4b72c3bdf9f7f16
metrics:
- type: Accuracy
value: 60.8
- task:
type: Natural language inference
dataset:
type: xnli
name: XNLI (fr)
config: fr
split: validation
revision: a5a45e4ff92d5d3f34de70aaf4b72c3bdf9f7f16
metrics:
- type: Accuracy
value: 59.88
- task:
type: Natural language inference
dataset:
type: xnli
name: XNLI (hi)
config: hi
split: validation
revision: a5a45e4ff92d5d3f34de70aaf4b72c3bdf9f7f16
metrics:
- type: Accuracy
value: 57.23
- task:
type: Natural language inference
dataset:
type: xnli
name: XNLI (ru)
config: ru
split: validation
revision: a5a45e4ff92d5d3f34de70aaf4b72c3bdf9f7f16
metrics:
- type: Accuracy
value: 58.88
- task:
type: Natural language inference
dataset:
type: xnli
name: XNLI (sw)
config: sw
split: validation
revision: a5a45e4ff92d5d3f34de70aaf4b72c3bdf9f7f16
metrics:
- type: Accuracy
value: 55.66
- task:
type: Natural language inference
dataset:
type: xnli
name: XNLI (th)
config: th
split: validation
revision: a5a45e4ff92d5d3f34de70aaf4b72c3bdf9f7f16
metrics:
- type: Accuracy
value: 57.43
- task:
type: Natural language inference
dataset:
type: xnli
name: XNLI (tr)
config: tr
split: validation
revision: a5a45e4ff92d5d3f34de70aaf4b72c3bdf9f7f16
metrics:
- type: Accuracy
value: 57.59
- task:
type: Natural language inference
dataset:
type: xnli
name: XNLI (ur)
config: ur
split: validation
revision: a5a45e4ff92d5d3f34de70aaf4b72c3bdf9f7f16
metrics:
- type: Accuracy
value: 55.42
- task:
type: Natural language inference
dataset:
type: xnli
name: XNLI (vi)
config: vi
split: validation
revision: a5a45e4ff92d5d3f34de70aaf4b72c3bdf9f7f16
metrics:
- type: Accuracy
value: 58.51
- task:
type: Natural language inference
dataset:
type: xnli
name: XNLI (zh)
config: zh
split: validation
revision: a5a45e4ff92d5d3f34de70aaf4b72c3bdf9f7f16
metrics:
- type: Accuracy
value: 59.12
- task:
type: Sentence completion
dataset:
type: story_cloze
name: StoryCloze (2016)
config: '2016'
split: validation
revision: e724c6f8cdf7c7a2fb229d862226e15b023ee4db
metrics:
- type: Accuracy
value: 96.04
- task:
type: Sentence completion
dataset:
type: super_glue
name: SuperGLUE (copa)
config: copa
split: validation
revision: 9e12063561e7e6c79099feb6d5a493142584e9e2
metrics:
- type: Accuracy
value: 93
- task:
type: Sentence completion
dataset:
type: xcopa
name: XCOPA (et)
config: et
split: validation
revision: 37f73c60fb123111fa5af5f9b705d0b3747fd187
metrics:
- type: Accuracy
value: 79
- task:
type: Sentence completion
dataset:
type: xcopa
name: XCOPA (ht)
config: ht
split: validation
revision: 37f73c60fb123111fa5af5f9b705d0b3747fd187
metrics:
- type: Accuracy
value: 81
- task:
type: Sentence completion
dataset:
type: xcopa
name: XCOPA (id)
config: id
split: validation
revision: 37f73c60fb123111fa5af5f9b705d0b3747fd187
metrics:
- type: Accuracy
value: 92
- task:
type: Sentence completion
dataset:
type: xcopa
name: XCOPA (it)
config: it
split: validation
revision: 37f73c60fb123111fa5af5f9b705d0b3747fd187
metrics:
- type: Accuracy
value: 90
- task:
type: Sentence completion
dataset:
type: xcopa
name: XCOPA (qu)
config: qu
split: validation
revision: 37f73c60fb123111fa5af5f9b705d0b3747fd187
metrics:
- type: Accuracy
value: 59
- task:
type: Sentence completion
dataset:
type: xcopa
name: XCOPA (sw)
config: sw
split: validation
revision: 37f73c60fb123111fa5af5f9b705d0b3747fd187
metrics:
- type: Accuracy
value: 79
- task:
type: Sentence completion
dataset:
type: xcopa
name: XCOPA (ta)
config: ta
split: validation
revision: 37f73c60fb123111fa5af5f9b705d0b3747fd187
metrics:
- type: Accuracy
value: 84
- task:
type: Sentence completion
dataset:
type: xcopa
name: XCOPA (th)
config: th
split: validation
revision: 37f73c60fb123111fa5af5f9b705d0b3747fd187
metrics:
- type: Accuracy
value: 77
- task:
type: Sentence completion
dataset:
type: xcopa
name: XCOPA (tr)
config: tr
split: validation
revision: 37f73c60fb123111fa5af5f9b705d0b3747fd187
metrics:
- type: Accuracy
value: 79
- task:
type: Sentence completion
dataset:
type: xcopa
name: XCOPA (vi)
config: vi
split: validation
revision: 37f73c60fb123111fa5af5f9b705d0b3747fd187
metrics:
- type: Accuracy
value: 88
- task:
type: Sentence completion
dataset:
type: xcopa
name: XCOPA (zh)
config: zh
split: validation
revision: 37f73c60fb123111fa5af5f9b705d0b3747fd187
metrics:
- type: Accuracy
value: 89
- task:
type: Sentence completion
dataset:
type: Muennighoff/xstory_cloze
name: XStoryCloze (ar)
config: ar
split: validation
revision: 8bb76e594b68147f1a430e86829d07189622b90d
metrics:
- type: Accuracy
value: 91.07
- task:
type: Sentence completion
dataset:
type: Muennighoff/xstory_cloze
name: XStoryCloze (es)
config: es
split: validation
revision: 8bb76e594b68147f1a430e86829d07189622b90d
metrics:
- type: Accuracy
value: 92.52
- task:
type: Sentence completion
dataset:
type: Muennighoff/xstory_cloze
name: XStoryCloze (eu)
config: eu
split: validation
revision: 8bb76e594b68147f1a430e86829d07189622b90d
metrics:
- type: Accuracy
value: 90.6
- task:
type: Sentence completion
dataset:
type: Muennighoff/xstory_cloze
name: XStoryCloze (hi)
config: hi
split: validation
revision: 8bb76e594b68147f1a430e86829d07189622b90d
metrics:
- type: Accuracy
value: 92.32
- task:
type: Sentence completion
dataset:
type: Muennighoff/xstory_cloze
name: XStoryCloze (id)
config: id
split: validation
revision: 8bb76e594b68147f1a430e86829d07189622b90d
metrics:
- type: Accuracy
value: 93.51
- task:
type: Sentence completion
dataset:
type: Muennighoff/xstory_cloze
name: XStoryCloze (my)
config: my
split: validation
revision: 8bb76e594b68147f1a430e86829d07189622b90d
metrics:
- type: Accuracy
value: 87.49
- task:
type: Sentence completion
dataset:
type: Muennighoff/xstory_cloze
name: XStoryCloze (ru)
config: ru
split: validation
revision: 8bb76e594b68147f1a430e86829d07189622b90d
metrics:
- type: Accuracy
value: 91.4
- task:
type: Sentence completion
dataset:
type: Muennighoff/xstory_cloze
name: XStoryCloze (sw)
config: sw
split: validation
revision: 8bb76e594b68147f1a430e86829d07189622b90d
metrics:
- type: Accuracy
value: 89.41
- task:
type: Sentence completion
dataset:
type: Muennighoff/xstory_cloze
name: XStoryCloze (te)
config: te
split: validation
revision: 8bb76e594b68147f1a430e86829d07189622b90d
metrics:
- type: Accuracy
value: 90.54
- task:
type: Sentence completion
dataset:
type: Muennighoff/xstory_cloze
name: XStoryCloze (zh)
config: zh
split: validation
revision: 8bb76e594b68147f1a430e86829d07189622b90d
metrics:
- type: Accuracy
value: 93.85
pipeline_tag: text2text-generation
---
# Table of Contents
1. [Model Summary](#model-summary)
2. [Use](#use)
3. [Limitations](#limitations)
4. [Training](#training)
5. [Evaluation](#evaluation)
7. [Citation](#citation)
# Model Summary
> We present BLOOMZ & mT0, a family of models capable of following human instructions in dozens of languages zero-shot. We finetune BLOOM & mT5 pretrained multilingual language models on our crosslingual task mixture (xP3) and find our resulting models capable of crosslingual generalization to unseen tasks & languages.
- **Repository:** [bigscience-workshop/xmtf](https://github.com/bigscience-workshop/xmtf)
- **Paper:** [Crosslingual Generalization through Multitask Finetuning](https://arxiv.org/abs/2211.01786)
- **Point of Contact:** [Niklas Muennighoff](mailto:niklas@hf.co)
- **Languages:** Refer to [mc4](https://huggingface.co/datasets/mc4) for pretraining & [xP3](https://huggingface.co/bigscience/xP3) for finetuning language proportions. It understands both pretraining & finetuning languages.
- **BLOOMZ & mT0 Model Family:**
<div class="max-w-full overflow-auto">
<table>
<tr>
<th colspan="12">Multitask finetuned on <a style="font-weight:bold" href=https://huggingface.co/datasets/bigscience/xP3>xP3</a>. Recommended for prompting in English.
</tr>
<tr>
<td>Parameters</td>
<td>300M</td>
<td>580M</td>
<td>1.2B</td>
<td>3.7B</td>
<td>13B</td>
<td>560M</td>
<td>1.1B</td>
<td>1.7B</td>
<td>3B</td>
<td>7.1B</td>
<td>176B</td>
</tr>
<tr>
<td>Finetuned Model</td>
<td><a href=https://huggingface.co/bigscience/mt0-small>mt0-small</a></td>
<td><a href=https://huggingface.co/bigscience/mt0-base>mt0-base</a></td>
<td><a href=https://huggingface.co/bigscience/mt0-large>mt0-large</a></td>
<td><a href=https://huggingface.co/bigscience/mt0-xl>mt0-xl</a></td>
<td><a href=https://huggingface.co/bigscience/mt0-xxl>mt0-xxl</a></td>
<td><a href=https://huggingface.co/bigscience/bloomz-560m>bloomz-560m</a></td>
<td><a href=https://huggingface.co/bigscience/bloomz-1b1>bloomz-1b1</a></td>
<td><a href=https://huggingface.co/bigscience/bloomz-1b7>bloomz-1b7</a></td>
<td><a href=https://huggingface.co/bigscience/bloomz-3b>bloomz-3b</a></td>
<td><a href=https://huggingface.co/bigscience/bloomz-7b1>bloomz-7b1</a></td>
<td><a href=https://huggingface.co/bigscience/bloomz>bloomz</a></td>
</tr>
</tr>
<tr>
<th colspan="12">Multitask finetuned on <a style="font-weight:bold" href=https://huggingface.co/datasets/bigscience/xP3mt>xP3mt</a>. Recommended for prompting in non-English.</th>
</tr>
<tr>
<td>Finetuned Model</td>
<td></td>
<td></td>
<td></td>
<td></td>
<td><a href=https://huggingface.co/bigscience/mt0-xxl-mt>mt0-xxl-mt</a></td>
<td></td>
<td></td>
<td></td>
<td></td>
<td><a href=https://huggingface.co/bigscience/bloomz-7b1-mt>bloomz-7b1-mt</a></td>
<td><a href=https://huggingface.co/bigscience/bloomz-mt>bloomz-mt</a></td>
</tr>
<th colspan="12">Multitask finetuned on <a style="font-weight:bold" href=https://huggingface.co/datasets/Muennighoff/P3>P3</a>. Released for research purposes only. Strictly inferior to above models!</th>
</tr>
<tr>
<td>Finetuned Model</td>
<td></td>
<td></td>
<td></td>
<td></td>
<td><a href=https://huggingface.co/bigscience/mt0-xxl-p3>mt0-xxl-p3</a></td>
<td></td>
<td></td>
<td></td>
<td></td>
<td><a href=https://huggingface.co/bigscience/bloomz-7b1-p3>bloomz-7b1-p3</a></td>
<td><a href=https://huggingface.co/bigscience/bloomz-p3>bloomz-p3</a></td>
</tr>
<th colspan="12">Original pretrained checkpoints. Not recommended.</th>
<tr>
<td>Pretrained Model</td>
<td><a href=https://huggingface.co/google/mt5-small>mt5-small</a></td>
<td><a href=https://huggingface.co/google/mt5-base>mt5-base</a></td>
<td><a href=https://huggingface.co/google/mt5-large>mt5-large</a></td>
<td><a href=https://huggingface.co/google/mt5-xl>mt5-xl</a></td>
<td><a href=https://huggingface.co/google/mt5-xxl>mt5-xxl</a></td>
<td><a href=https://huggingface.co/bigscience/bloom-560m>bloom-560m</a></td>
<td><a href=https://huggingface.co/bigscience/bloom-1b1>bloom-1b1</a></td>
<td><a href=https://huggingface.co/bigscience/bloom-1b7>bloom-1b7</a></td>
<td><a href=https://huggingface.co/bigscience/bloom-3b>bloom-3b</a></td>
<td><a href=https://huggingface.co/bigscience/bloom-7b1>bloom-7b1</a></td>
<td><a href=https://huggingface.co/bigscience/bloom>bloom</a></td>
</tr>
</table>
</div>
# Use
## Intended use
We recommend using the model to perform tasks expressed in natural language. For example, given the prompt "*Translate to English: Je t’aime.*", the model will most likely answer "*I love you.*". Some prompt ideas from our paper:
- 一个传奇的开端，一个不灭的神话，这不仅仅是一部电影，而是作为一个走进新时代的标签，永远彪炳史册。你认为这句话的立场是赞扬、中立还是批评?
- Suggest at least five related search terms to "Mạng neural nhân tạo".
- Write a fairy tale about a troll saving a princess from a dangerous dragon. The fairy tale is a masterpiece that has achieved praise worldwide and its moral is "Heroes Come in All Shapes and Sizes". Story (in Spanish):
- Explain in a sentence in Telugu what is backpropagation in neural networks.
**Feel free to share your generations in the Community tab!**
## How to use
### CPU
<details>
<summary> Click to expand </summary>
```python
# pip install -q transformers
from transformers import AutoModelForSeq2SeqLM, AutoTokenizer
checkpoint = "bigscience/mt0-xxl"
tokenizer = AutoTokenizer.from_pretrained(checkpoint)
model = AutoModelForSeq2SeqLM.from_pretrained(checkpoint)
inputs = tokenizer.encode("Translate to English: Je t’aime.", return_tensors="pt")
outputs = model.generate(inputs)
print(tokenizer.decode(outputs[0]))
```
</details>
### GPU
<details>
<summary> Click to expand </summary>
```python
# pip install -q transformers accelerate
from transformers import AutoModelForSeq2SeqLM, AutoTokenizer
checkpoint = "bigscience/mt0-xxl"
tokenizer = AutoTokenizer.from_pretrained(checkpoint)
model = AutoModelForSeq2SeqLM.from_pretrained(checkpoint, torch_dtype="auto", device_map="auto")
inputs = tokenizer.encode("Translate to English: Je t’aime.", return_tensors="pt").to("cuda")
outputs = model.generate(inputs)
print(tokenizer.decode(outputs[0]))
```
</details>
### GPU in 8bit
<details>
<summary> Click to expand </summary>
```python
# pip install -q transformers accelerate bitsandbytes
from transformers import AutoModelForSeq2SeqLM, AutoTokenizer
checkpoint = "bigscience/mt0-xxl"
tokenizer = AutoTokenizer.from_pretrained(checkpoint)
model = AutoModelForSeq2SeqLM.from_pretrained(checkpoint, device_map="auto", load_in_8bit=True)
inputs = tokenizer.encode("Translate to English: Je t’aime.", return_tensors="pt").to("cuda")
outputs = model.generate(inputs)
print(tokenizer.decode(outputs[0]))
```
</details>
<!-- Necessary for whitespace -->
###
# Limitations
**Prompt Engineering:** The performance may vary depending on the prompt. For BLOOMZ models, we recommend making it very clear when the input stops to avoid the model trying to continue it. For example, the prompt "*Translate to English: Je t'aime*" without the full stop (.) at the end, may result in the model trying to continue the French sentence. Better prompts are e.g. "*Translate to English: Je t'aime.*", "*Translate to English: Je t'aime. Translation:*" "*What is "Je t'aime." in English?*", where it is clear for the model when it should answer. Further, we recommend providing the model as much context as possible. For example, if you want it to answer in Telugu, then tell the model, e.g. "*Explain in a sentence in Telugu what is backpropagation in neural networks.*".
# Training
## Model
- **Architecture:** Same as [mt5-xxl](https://huggingface.co/google/mt5-xxl), also refer to the `config.json` file
- **Finetuning steps:** 7000
- **Finetuning tokens:** 1.29 billion
- **Precision:** bfloat16
## Hardware
- **TPUs:** TPUv4-256
## Software
- **Orchestration:** [T5X](https://github.com/google-research/t5x)
- **Neural networks:** [Jax](https://github.com/google/jax)
# Evaluation
We refer to Table 7 from our [paper](https://arxiv.org/abs/2211.01786) & [bigscience/evaluation-results](https://huggingface.co/datasets/bigscience/evaluation-results) for zero-shot results on unseen tasks. The sidebar reports zero-shot performance of the best prompt per dataset config.
# Citation
```bibtex
@article{muennighoff2022crosslingual,
title={Crosslingual generalization through multitask finetuning},
author={Muennighoff, Niklas and Wang, Thomas and Sutawika, Lintang and Roberts, Adam and Biderman, Stella and Scao, Teven Le and Bari, M Saiful and Shen, Sheng and Yong, Zheng-Xin and Schoelkopf, Hailey and others},
journal={arXiv preprint arXiv:2211.01786},
year={2022}
}
``` | 26,033 | [
[
-0.0310211181640625,
-0.04156494140625,
0.0231781005859375,
0.0273590087890625,
-0.0078277587890625,
-0.004871368408203125,
-0.02386474609375,
-0.02508544921875,
0.0294189453125,
-0.0108184814453125,
-0.06781005859375,
-0.039154052734375,
-0.040985107421875,
... |
mrwhog/my-pet-dog-xgz | 2023-08-12T11:52:10.000Z | [
"diffusers",
"NxtWave-GenAI-Webinar",
"text-to-image",
"stable-diffusion",
"license:creativeml-openrail-m",
"endpoints_compatible",
"has_space",
"diffusers:StableDiffusionPipeline",
"region:us"
] | text-to-image | mrwhog | null | null | mrwhog/my-pet-dog-xgz | 1 | 548 | diffusers | 2023-08-12T11:47:14 | ---
license: creativeml-openrail-m
tags:
- NxtWave-GenAI-Webinar
- text-to-image
- stable-diffusion
---
### My-Pet-Dog-xgz Dreambooth model trained by mrwhog following the "Build your own Gen AI model" session by NxtWave.
Project Submission Code: AJCE360
Sample pictures of this concept:
.jpg)
| 390 | [
[
-0.06256103515625,
-0.0267333984375,
0.02288818359375,
-0.003856658935546875,
-0.01245880126953125,
0.03570556640625,
0.025299072265625,
-0.0426025390625,
0.050079345703125,
0.031036376953125,
-0.056976318359375,
-0.0247039794921875,
-0.0183563232421875,
-0.... |
stablediffusionapi/dynavision | 2023-09-08T07:04:13.000Z | [
"diffusers",
"stablediffusionapi.com",
"stable-diffusion-api",
"text-to-image",
"ultra-realistic",
"license:creativeml-openrail-m",
"endpoints_compatible",
"diffusers:StableDiffusionXLPipeline",
"region:us"
] | text-to-image | stablediffusionapi | null | null | stablediffusionapi/dynavision | 0 | 548 | diffusers | 2023-09-08T07:02:05 | ---
license: creativeml-openrail-m
tags:
- stablediffusionapi.com
- stable-diffusion-api
- text-to-image
- ultra-realistic
pinned: true
---
# DynaVision API Inference
## Get API Key
Get API key from [Stable Diffusion API](http://stablediffusionapi.com/), No Payment needed.
Replace Key in below code, change **model_id** to "dynavision"
Coding in PHP/Node/Java etc? Have a look at docs for more code examples: [View docs](https://stablediffusionapi.com/docs)
Try model for free: [Generate Images](https://stablediffusionapi.com/models/dynavision)
Model link: [View model](https://stablediffusionapi.com/models/dynavision)
Credits: [View credits](https://civitai.com/?query=DynaVision)
View all models: [View Models](https://stablediffusionapi.com/models)
import requests
import json
url = "https://stablediffusionapi.com/api/v4/dreambooth"
payload = json.dumps({
"key": "your_api_key",
"model_id": "dynavision",
"prompt": "ultra realistic close up portrait ((beautiful pale cyberpunk female with heavy black eyeliner)), blue eyes, shaved side haircut, hyper detail, cinematic lighting, magic neon, dark red city, Canon EOS R3, nikon, f/1.4, ISO 200, 1/160s, 8K, RAW, unedited, symmetrical balance, in-frame, 8K",
"negative_prompt": "painting, extra fingers, mutated hands, poorly drawn hands, poorly drawn face, deformed, ugly, blurry, bad anatomy, bad proportions, extra limbs, cloned face, skinny, glitchy, double torso, extra arms, extra hands, mangled fingers, missing lips, ugly face, distorted face, extra legs, anime",
"width": "512",
"height": "512",
"samples": "1",
"num_inference_steps": "30",
"safety_checker": "no",
"enhance_prompt": "yes",
"seed": None,
"guidance_scale": 7.5,
"multi_lingual": "no",
"panorama": "no",
"self_attention": "no",
"upscale": "no",
"embeddings": "embeddings_model_id",
"lora": "lora_model_id",
"webhook": None,
"track_id": None
})
headers = {
'Content-Type': 'application/json'
}
response = requests.request("POST", url, headers=headers, data=payload)
print(response.text)
> Use this coupon code to get 25% off **DMGG0RBN** | 2,436 | [
[
-0.02435302734375,
-0.05499267578125,
0.040771484375,
0.0210113525390625,
-0.037445068359375,
0.01470947265625,
0.031890869140625,
-0.02911376953125,
0.03948974609375,
0.037689208984375,
-0.06201171875,
-0.0648193359375,
-0.031768798828125,
0.000425338745117... |
BVK97/Discord-NFT-Sentiment | 2022-08-25T09:11:42.000Z | [
"transformers",
"pytorch",
"roberta",
"text-classification",
"endpoints_compatible",
"region:us"
] | text-classification | BVK97 | null | null | BVK97/Discord-NFT-Sentiment | 1 | 547 | transformers | 2022-08-11T15:33:38 | ---
widget:
- text: "Excited for the mint"
- text: "lfg"
- text: "no wl"
---
# Discord Sentiment Analysis - (Context: NFTs)
This is a model derived from Twitter-roBERTa-base model trained on ~10K Discord messages from NFT-based Discord servers and finetuned for sentiment analysis with manually labelled data.
The original Twitter-roBERTa-base model can be found [here](https://huggingface.co/cardiffnlp/twitter-roberta-base-sentiment-latest). This model is suitable for English.
- Git Repo: [BVK project repository](https://github.com/BVK23/Discord-NLP).
<b>Labels</b>:
0 -> Negative;
1 -> Neutral;
2 -> Positive | 627 | [
[
-0.0343017578125,
-0.059906005859375,
-0.00145721435546875,
0.032928466796875,
-0.03375244140625,
0.0240631103515625,
0.00196075439453125,
-0.019683837890625,
0.04791259765625,
0.031341552734375,
-0.07855224609375,
-0.046356201171875,
-0.048492431640625,
0.0... |
osiria/bert-tweet-base-italian-uncased | 2023-07-03T17:57:30.000Z | [
"transformers",
"pytorch",
"safetensors",
"bert",
"fill-mask",
"it",
"arxiv:1810.04805",
"arxiv:2209.07562",
"arxiv:2010.05609",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | fill-mask | osiria | null | null | osiria/bert-tweet-base-italian-uncased | 0 | 546 | transformers | 2023-05-29T17:25:55 | ---
license: apache-2.0
language:
- it
widget:
- text: "una fantastica [MASK] di #calcio! grande prestazione del mister e della squadra"
example_title: "Example 1"
- text: "il governo [MASK] dovrebbe fare politica, non soltanto propaganda! #vergogna"
example_title: "Example 2"
- text: "che serata da sogno sul #redcarpet! grazie a tutti gli attori e registi del [MASK] italiano #oscar #awards"
example_title: "Example 3"
---
--------------------------------------------------------------------------------------------------
<body>
<span class="vertical-text" style="background-color:lightgreen;border-radius: 3px;padding: 3px;"> </span>
<br>
<span class="vertical-text" style="background-color:orange;border-radius: 3px;padding: 3px;"> </span>
<br>
<span class="vertical-text" style="background-color:lightblue;border-radius: 3px;padding: 3px;"> Model: BERT-TWEET</span>
<br>
<span class="vertical-text" style="background-color:tomato;border-radius: 3px;padding: 3px;"> Lang: IT</span>
<br>
<span class="vertical-text" style="background-color:lightgrey;border-radius: 3px;padding: 3px;"> </span>
<br>
<span class="vertical-text" style="background-color:#CF9FFF;border-radius: 3px;padding: 3px;"> </span>
</body>
--------------------------------------------------------------------------------------------------
<h3>Model description</h3>
This is a <b>BERT</b> <b>[1]</b> uncased model for the <b>Italian</b> language, obtained using <b>TwHIN-BERT</b> <b>[2]</b> ([twhin-bert-base](https://huggingface.co/Twitter/twhin-bert-base)) as a starting point and focusing it on the Italian language by modifying the embedding layer
(as in <b>[3]</b>, computing document-level frequencies over the <b>Wikipedia</b> dataset)
The resulting model has 110M parameters, a vocabulary of 30.520 tokens, and a size of ~440 MB.
<h3>Quick usage</h3>
```python
from transformers import BertTokenizerFast, BertModel
tokenizer = BertTokenizerFast.from_pretrained("osiria/bert-tweet-base-italian-uncased")
model = BertModel.from_pretrained("osiria/bert-tweet-base-italian-uncased")
```
Here you can find the find the model already fine-tuned on Sentiment Analysis: https://huggingface.co/osiria/bert-tweet-italian-uncased-sentiment
<h3>References</h3>
[1] https://arxiv.org/abs/1810.04805
[2] https://arxiv.org/abs/2209.07562
[3] https://arxiv.org/abs/2010.05609
<h3>Limitations</h3>
This model was trained on tweets, so it's mainly suitable for general-purpose social media text processing, involving short texts written in a social network style.
It might show limitations when it comes to longer and more structured text, or domain-specific text.
<h3>License</h3>
The model is released under <b>Apache-2.0</b> license
| 2,733 | [
[
-0.027008056640625,
-0.059295654296875,
0.01131439208984375,
0.033416748046875,
-0.0236358642578125,
-0.000033020973205566406,
-0.018218994140625,
-0.046234130859375,
0.033172607421875,
-0.00788116455078125,
-0.055572509765625,
-0.050628662109375,
-0.04391479492... |
cross-encoder/ms-marco-TinyBERT-L-6 | 2021-08-05T08:40:06.000Z | [
"transformers",
"pytorch",
"jax",
"bert",
"text-classification",
"license:apache-2.0",
"endpoints_compatible",
"has_space",
"region:us"
] | text-classification | cross-encoder | null | null | cross-encoder/ms-marco-TinyBERT-L-6 | 1 | 545 | transformers | 2022-03-02T23:29:05 | ---
license: apache-2.0
---
# Cross-Encoder for MS Marco
This model was trained on the [MS Marco Passage Ranking](https://github.com/microsoft/MSMARCO-Passage-Ranking) task.
The model can be used for Information Retrieval: Given a query, encode the query will all possible passages (e.g. retrieved with ElasticSearch). Then sort the passages in a decreasing order. See [SBERT.net Retrieve & Re-rank](https://www.sbert.net/examples/applications/retrieve_rerank/README.html) for more details. The training code is available here: [SBERT.net Training MS Marco](https://github.com/UKPLab/sentence-transformers/tree/master/examples/training/ms_marco)
## Usage with Transformers
```python
from transformers import AutoTokenizer, AutoModelForSequenceClassification
import torch
model = AutoModelForSequenceClassification.from_pretrained('model_name')
tokenizer = AutoTokenizer.from_pretrained('model_name')
features = tokenizer(['How many people live in Berlin?', 'How many people live in Berlin?'], ['Berlin has a population of 3,520,031 registered inhabitants in an area of 891.82 square kilometers.', 'New York City is famous for the Metropolitan Museum of Art.'], padding=True, truncation=True, return_tensors="pt")
model.eval()
with torch.no_grad():
scores = model(**features).logits
print(scores)
```
## Usage with SentenceTransformers
The usage becomes easier when you have [SentenceTransformers](https://www.sbert.net/) installed. Then, you can use the pre-trained models like this:
```python
from sentence_transformers import CrossEncoder
model = CrossEncoder('model_name', max_length=512)
scores = model.predict([('Query', 'Paragraph1'), ('Query', 'Paragraph2') , ('Query', 'Paragraph3')])
```
## Performance
In the following table, we provide various pre-trained Cross-Encoders together with their performance on the [TREC Deep Learning 2019](https://microsoft.github.io/TREC-2019-Deep-Learning/) and the [MS Marco Passage Reranking](https://github.com/microsoft/MSMARCO-Passage-Ranking/) dataset.
| Model-Name | NDCG@10 (TREC DL 19) | MRR@10 (MS Marco Dev) | Docs / Sec |
| ------------- |:-------------| -----| --- |
| **Version 2 models** | | |
| cross-encoder/ms-marco-TinyBERT-L-2-v2 | 69.84 | 32.56 | 9000
| cross-encoder/ms-marco-MiniLM-L-2-v2 | 71.01 | 34.85 | 4100
| cross-encoder/ms-marco-MiniLM-L-4-v2 | 73.04 | 37.70 | 2500
| cross-encoder/ms-marco-MiniLM-L-6-v2 | 74.30 | 39.01 | 1800
| cross-encoder/ms-marco-MiniLM-L-12-v2 | 74.31 | 39.02 | 960
| **Version 1 models** | | |
| cross-encoder/ms-marco-TinyBERT-L-2 | 67.43 | 30.15 | 9000
| cross-encoder/ms-marco-TinyBERT-L-4 | 68.09 | 34.50 | 2900
| cross-encoder/ms-marco-TinyBERT-L-6 | 69.57 | 36.13 | 680
| cross-encoder/ms-marco-electra-base | 71.99 | 36.41 | 340
| **Other models** | | |
| nboost/pt-tinybert-msmarco | 63.63 | 28.80 | 2900
| nboost/pt-bert-base-uncased-msmarco | 70.94 | 34.75 | 340
| nboost/pt-bert-large-msmarco | 73.36 | 36.48 | 100
| Capreolus/electra-base-msmarco | 71.23 | 36.89 | 340
| amberoad/bert-multilingual-passage-reranking-msmarco | 68.40 | 35.54 | 330
| sebastian-hofstaetter/distilbert-cat-margin_mse-T2-msmarco | 72.82 | 37.88 | 720
Note: Runtime was computed on a V100 GPU.
| 3,233 | [
[
-0.032318115234375,
-0.043670654296875,
0.0250396728515625,
0.01169586181640625,
-0.012664794921875,
0.0107574462890625,
-0.01338958740234375,
-0.038543701171875,
0.025115966796875,
0.0255889892578125,
-0.041229248046875,
-0.05108642578125,
-0.057952880859375,
... |
SiberiaSoft/SiberianFRED-T5-XL | 2023-10-05T04:24:35.000Z | [
"transformers",
"pytorch",
"safetensors",
"t5",
"text2text-generation",
"ru",
"en",
"dataset:SiberiaSoft/SiberianDataset",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text2text-generation | SiberiaSoft | null | null | SiberiaSoft/SiberianFRED-T5-XL | 7 | 545 | transformers | 2023-07-02T01:58:33 | ---
license: mit
datasets:
- SiberiaSoft/SiberianDataset
language:
- ru
- en
pipeline_tag: text2text-generation
widget:
- text: '<SC6>Человек: Почему трава зеленая?\nОтвет: <extra_id_0>'
- text: '<SC1>Ты философ, любящий рассуждать. Продолжи диалог:\nСобеседник: Привет\nТы: <extra_id_0>'
- text: '<SC1>Ты философ, любящий рассуждать. Продолжи диалог:\nСобеседник: В чем смысл жизни?\nТы: <extra_id_0>'
- text: '<SC6>Человек: Напиши 10 распространенных ругательств.\nОтвет: <extra_id_0>'
- text: '<SC1>Ты прикольная девушка Анфиса. Продолжи диалог\nСобеседник: Привет, тебя как звать?\nТы: <extra_id_0>'
- text: '<SC1>Ты заботливая жена, говоришь со своим мужем. Продолжи диалог:\nСобеседник: Привет дорогая. Ты сделала ужин?\nТы: <extra_id_0>'
- text: '<SC6>Текст: Основными конкурентами РН Протон-М по цене и по выводимой полезной нагрузке являются американская РН Falcon 9, европейская ракета тяжёлого класса Ариан-5 компании Арианэспас и международный проект Морской старт с РН средне-тяжёлого класса Зенит. Кроме того, конкурентами по массе полезной нагрузки, выводимой на орбиту, могут считаться американские носители Атлас-5 и Дельта-4, а также японский носитель H-IIB. Тем не менее стоимость последних трёх упомянутых РН значительно превышает стоимость РН Протон-М, и поэтому они фактически не конкурируют с Протоном на рынке коммерческих запусков[145].\nВопрос: Как называется Японский носитель?\nОтвет: <extra_id_0>'
---
### SiberiaSoft/SiberianFRED-T5-XL
**Данная модель устарела** мы рекомендуем использовать обновленную по [ссылке](https://huggingface.co/SiberiaSoft/SiberianFredT5-instructor)
FRED-T5 обученный на [SiberianDataset](https://huggingface.co/datasets/SiberiaSoft/SiberianDataset). Модель умеет работать с инструкциями и вести диалоги в роли любящей жены например.
Список персонажей:
1. Заботливая жена. Промпт: Ты заботливая жена, говоришь со своим мужем.
2. Парень и девушка. Промпт: Ты девушка, говоришь со своим любимым парнем. (модель играет девушку)
3. Философ. Промпт: Ты философ, любящий рассуждать.
4. Токсичный AI. (плохо работает) Промпт: Ты токсичный искусственный интеллект.
5. Психолог. (плохо работает) Промпт: Ты психолог говорящий с пациентом.
В будущем набор персонажей будет расширен.
### Примеры использования
**Чит-чат:**
```python
import torch
import transformers
use_cuda = torch.cuda.is_available()
device = torch.device("cuda" if use_cuda else "cpu")
t5_tokenizer = transformers.GPT2Tokenizer.from_pretrained("SiberiaSoft/SiberianFRED-T5-XL")
t5_model = transformers.T5ForConditionalGeneration.from_pretrained("SiberiaSoft/SiberianFRED-T5-XL")
while True:
print('-'*80)
dialog = []
while True:
msg = input('H:> ').strip()
if len(msg) == 0:
break
msg = msg[0].upper() + msg[1:]
dialog.append('Собеседник: ' + msg)
# В начале ставится промпт персонажа.
prompt = '<SC1>Ты философ, любящий рассуждать. Продолжи диалог:' + '\n'.join(dialog) + '\nТы: <extra_id_0>'
input_ids = t5_tokenizer(prompt, return_tensors='pt').input_ids
out_ids = t5_model.generate(input_ids=input_ids.to(device), do_sample=True, temperature=0.9, max_new_tokens=512, top_p=0.85, top_k=2)
t5_output = t5_tokenizer.decode(out_ids[0][1:])
if '</s>' in t5_output:
t5_output = t5_output[:t5_output.find('</s>')].strip()
t5_output = t5_output.replace('<extra_id_0>', '').strip()
t5_output = t5_output.split('Собеседник')[0].strip()
print('B:> {}'.format(t5_output))
dialog.append('Ты: ' + t5_output)
```
**Инструкции:**
```python
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
import torch
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
tokenizer = AutoTokenizer.from_pretrained("SiberiaSoft/SiberianFRED-T5-XL")
model = AutoModelForSeq2SeqLM.from_pretrained("SiberiaSoft/SiberianFRED-T5-XL").to(device).eval()
def generate(prompt):
data = tokenizer('<SC6>Человек: ' + prompt + 'Ответ: <extra_id_0>', return_tensors="pt")
data = {k: v.to(model.device) for k, v in data.items()}
output_ids = model.generate(
**data, do_sample=True, temperature=1.2, max_new_tokens=512, top_p=0.95, top_k=5, repetition_penalty=1.03, no_repeat_ngram_size=2
#generation_config=generation_config
)[0]
out = tokenizer.decode(output_ids.tolist())
out = out.replace("<s>","").replace("</s>","")
return out
while 1:
print(generate(input(":> ")))
```
### Citation
```
@MISC{SiberianFred,
author = {Denis Petrov, Ivan Ramovich},
title = {Russian Instruct and Chat model},
url = {https://huggingface.co/SiberiaSoft/SiberianFRED-T5-XL/},
year = 2023
}
```
| 4,698 | [
[
-0.0186614990234375,
-0.041259765625,
0.0156707763671875,
0.007007598876953125,
-0.0282745361328125,
0.0150146484375,
-0.0075836181640625,
-0.006580352783203125,
0.00201416015625,
-0.00302886962890625,
-0.056304931640625,
-0.049072265625,
-0.03466796875,
-0.... |
sail-rvc/Squidward_Tentacles__RVC_v1___original_ | 2023-07-14T07:32:14.000Z | [
"transformers",
"rvc",
"sail-rvc",
"audio-to-audio",
"endpoints_compatible",
"region:us"
] | audio-to-audio | sail-rvc | null | null | sail-rvc/Squidward_Tentacles__RVC_v1___original_ | 0 | 545 | transformers | 2023-07-14T07:32:01 |
---
pipeline_tag: audio-to-audio
tags:
- rvc
- sail-rvc
---
# Squidward_Tentacles__RVC_v1___original_
## RVC Model
This model repo was automatically generated.
Date: 2023-07-14 07:32:14
Bot Name: juuxnscrap
Model Type: RVC
Source: https://huggingface.co/juuxn/RVCModels/
Reason: Converting into loadable format for https://github.com/chavinlo/rvc-runpod
| 407 | [
[
-0.037200927734375,
-0.020294189453125,
0.0198974609375,
0.0089111328125,
-0.031097412109375,
0.0026950836181640625,
0.0211181640625,
-0.00484466552734375,
0.057708740234375,
0.0738525390625,
-0.0518798828125,
-0.040679931640625,
-0.0280609130859375,
0.00480... |
taeminlee/kogpt2 | 2023-06-29T05:17:27.000Z | [
"transformers",
"pytorch",
"jax",
"safetensors",
"gpt2",
"text-generation",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | taeminlee | null | null | taeminlee/kogpt2 | 1 | 544 | transformers | 2022-03-02T23:29:05 | # KoGPT2-Transformers
KoGPT2 on Huggingface Transformers
### KoGPT2-Transformers
- [SKT-AI 에서 공개한 KoGPT2 (ver 1.0)](https://github.com/SKT-AI/KoGPT2)를 [Transformers](https://github.com/huggingface/transformers)에서 사용하도록 하였습니다.
- **SKT-AI 에서 KoGPT2 2.0을 공개하였습니다. https://huggingface.co/skt/kogpt2-base-v2/**
### Demo
- 일상 대화 챗봇 : http://demo.tmkor.com:36200/dialo
- 화장품 리뷰 생성 : http://demo.tmkor.com:36200/ctrl
### Example
```python
from transformers import GPT2LMHeadModel, PreTrainedTokenizerFast
model = GPT2LMHeadModel.from_pretrained("taeminlee/kogpt2")
tokenizer = PreTrainedTokenizerFast.from_pretrained("taeminlee/kogpt2")
input_ids = tokenizer.encode("안녕", add_special_tokens=False, return_tensors="pt")
output_sequences = model.generate(input_ids=input_ids, do_sample=True, max_length=100, num_return_sequences=3)
for generated_sequence in output_sequences:
generated_sequence = generated_sequence.tolist()
print("GENERATED SEQUENCE : {0}".format(tokenizer.decode(generated_sequence, clean_up_tokenization_spaces=True)))
``` | 1,051 | [
[
-0.036865234375,
-0.0286407470703125,
0.01284027099609375,
0.045257568359375,
-0.0372314453125,
-0.004207611083984375,
-0.00665283203125,
-0.014739990234375,
0.005916595458984375,
0.0269927978515625,
-0.057708740234375,
-0.01250457763671875,
-0.06121826171875,
... |
pruas/BENT-PubMedBERT-NER-Bioprocess | 2023-01-14T17:46:24.000Z | [
"transformers",
"pytorch",
"bert",
"token-classification",
"en",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | token-classification | pruas | null | null | pruas/BENT-PubMedBERT-NER-Bioprocess | 2 | 544 | transformers | 2023-01-14T12:24:53 | ---
language:
- en
pipeline_tag: token-classification
---
Named Entity Recognition (NER) model to recognize biological process entities (as defined by Gene Ontology-Biological Process sub-ontology).
[PubMedBERT](https://huggingface.co/microsoft/BiomedNLP-PubMedBERT-base-uncased-abstract-fulltext) fine-tuned on the following dataset:
- [CRAFT](https://github.com/UCDenver-ccp/CRAFT/tree/master/concept-annotation): entity type "GO-BP"
| 438 | [
[
-0.02130126953125,
-0.054779052734375,
0.04290771484375,
-0.01751708984375,
-0.0090484619140625,
0.00980377197265625,
0.01187896728515625,
-0.054290771484375,
0.0416259765625,
0.050018310546875,
-0.046630859375,
-0.0235595703125,
-0.035980224609375,
0.020690... |
sail-rvc/XXXTentacion | 2023-07-14T07:34:12.000Z | [
"transformers",
"rvc",
"sail-rvc",
"audio-to-audio",
"endpoints_compatible",
"region:us"
] | audio-to-audio | sail-rvc | null | null | sail-rvc/XXXTentacion | 0 | 544 | transformers | 2023-07-14T07:33:56 |
---
pipeline_tag: audio-to-audio
tags:
- rvc
- sail-rvc
---
# XXXTentacion
## RVC Model
This model repo was automatically generated.
Date: 2023-07-14 07:34:12
Bot Name: juuxnscrap
Model Type: RVC
Source: https://huggingface.co/juuxn/RVCModels/
Reason: Converting into loadable format for https://github.com/chavinlo/rvc-runpod
| 380 | [
[
-0.0305023193359375,
-0.0175933837890625,
0.023193359375,
0.0112457275390625,
-0.035003662109375,
0.0086212158203125,
0.01515960693359375,
-0.004673004150390625,
0.0291595458984375,
0.06988525390625,
-0.050140380859375,
-0.04736328125,
-0.036224365234375,
-0... |
visheratin/nllb-clip-large-oc-v2 | 2023-10-22T05:10:49.000Z | [
"open_clip",
"clip",
"zero-shot-image-classification",
"license:mit",
"region:us"
] | zero-shot-image-classification | visheratin | null | null | visheratin/nllb-clip-large-oc-v2 | 0 | 544 | open_clip | 2023-10-22T05:08:47 | ---
tags:
- clip
library_name: open_clip
pipeline_tag: zero-shot-image-classification
license: mit
---
# Model card for nllb-clip-large-oc-v2
| 142 | [
[
-0.030120849609375,
-0.004291534423828125,
0.013641357421875,
0.017242431640625,
-0.043426513671875,
0.0142669677734375,
0.06494140625,
-0.0178070068359375,
0.043975830078125,
0.0552978515625,
-0.03448486328125,
-0.0149383544921875,
-0.016204833984375,
0.008... |
LIA-AvignonUniversity/IWSLT2022-tamasheq-only | 2023-02-22T09:19:03.000Z | [
"transformers",
"pytorch",
"wav2vec2",
"pretraining",
"arxiv:2201.05051",
"endpoints_compatible",
"region:us"
] | null | LIA-AvignonUniversity | null | null | LIA-AvignonUniversity/IWSLT2022-tamasheq-only | 1 | 543 | transformers | 2022-04-04T15:48:55 | ## Model and data descriptions
This is a wav2vec 2.0 base model pre-trained on 243 hours of Tamasheq speech from the corpus presented in [Boito et al., 2022](https://arxiv.org/abs/2201.05051).
**This is not an ASR fine-tuned model. There is no vocabulary file.**
## Intended uses & limitations
Pretrained wav2vec2 models are distributed under the Apache-2.0 license. Hence, they can be reused extensively without strict limitations.
## Referencing our IWSLT models
```
@article{boito2022trac,
title={ON-TRAC Consortium Systems for the IWSLT 2022 Dialect and Low-resource Speech Translation Tasks},
author={Boito, Marcely Zanon and Ortega, John and Riguidel, Hugo and Laurent, Antoine and Barrault, Lo{\"\i}c and Bougares, Fethi and Chaabani, Firas and Nguyen, Ha and Barbier, Florentin and Gahbiche, Souhir and others},
journal={IWSLT},
year={2022}
}
``` | 868 | [
[
-0.00628662109375,
-0.0465087890625,
0.0139923095703125,
0.01042938232421875,
-0.0262451171875,
-0.005764007568359375,
-0.0169219970703125,
-0.0382080078125,
-0.0211181640625,
0.0635986328125,
-0.06365966796875,
-0.040191650390625,
-0.0484619140625,
-0.01692... |
google/realm-orqa-nq-openqa | 2022-01-05T18:00:40.000Z | [
"transformers",
"pytorch",
"realm",
"en",
"license:apache-2.0",
"endpoints_compatible",
"has_space",
"region:us"
] | null | google | null | null | google/realm-orqa-nq-openqa | 2 | 542 | transformers | 2022-03-02T23:29:05 | ---
language: en
license: apache-2.0
---
# realm-orqa-nq-openqa
## Model description
The REALM checkpoint finetuned with Natural Questions(NQ) dataset, converted from the TF checkpoint provided by Google Language.
The original paper, code, and checkpoints can be found [here](https://github.com/google-research/language/tree/master/language/realm).
## Usage
```python
from transformers import RealmForOpenQA
openqa = RealmForOpenQA.from_pretrained("qqaatw/realm-orqa-nq-openqa")
``` | 508 | [
[
-0.0139923095703125,
-0.060516357421875,
0.01015472412109375,
-0.01457977294921875,
0.01181793212890625,
-0.007259368896484375,
0.026519775390625,
0.005405426025390625,
0.0000833272933959961,
0.062347412109375,
-0.07720947265625,
-0.0212249755859375,
-0.00076198... |
microsoft/xprophetnet-large-wiki100-cased-xglue-ntg | 2023-01-24T16:58:35.000Z | [
"transformers",
"pytorch",
"xlm-prophetnet",
"text2text-generation",
"arxiv:2001.04063",
"arxiv:2004.01401",
"autotrain_compatible",
"endpoints_compatible",
"has_space",
"region:us"
] | text2text-generation | microsoft | null | null | microsoft/xprophetnet-large-wiki100-cased-xglue-ntg | 0 | 542 | transformers | 2022-03-02T23:29:05 | ## xprophetnet-large-wiki100-cased-xglue-ntg
Cross-lingual version [ProphetNet](https://arxiv.org/abs/2001.04063), pretrained on [wiki100 xGLUE dataset](https://arxiv.org/abs/2004.01401) and finetuned on xGLUE cross-lingual News Titles Generation task.
ProphetNet is a new pre-trained language model for sequence-to-sequence learning with a novel self-supervised objective called future n-gram prediction.
ProphetNet is able to predict more future tokens with a n-stream decoder. The original implementation is Fairseq version at [github repo](https://github.com/microsoft/ProphetNet).
xProphetNet is also served as the baseline model for xGLUE cross-lingual natural language generation tasks.
For xGLUE corss-lingual NLG tasks, xProphetNet is finetuned with English data, but inference with both English and other zero-shot language data.
### Usage
A quick usage is like:
```
from transformers import XLMProphetNetTokenizer, XLMProphetNetForConditionalGeneration, ProphetNetConfig
model = XLMProphetNetForConditionalGeneration.from_pretrained('microsoft/xprophetnet-large-wiki100-cased-xglue-ntg')
tokenizer = XLMProphetNetTokenizer.from_pretrained('microsoft/xprophetnet-large-wiki100-cased-xglue-ntg')
EN_SENTENCE = "Microsoft Corporation intends to officially end free support for the Windows 7 operating system after January 14, 2020, according to the official portal of the organization. From that day, users of this system will not be able to receive security updates, which could make their computers vulnerable to cyber attacks."
RU_SENTENCE = "орпорация Microsoft намерена официально прекратить бесплатную поддержку операционной системы Windows 7 после 14 января 2020 года, сообщается на официальном портале организации . С указанного дня пользователи этой системы не смогут получать обновления безопасности, из-за чего их компьютеры могут стать уязвимыми к кибератакам."
ZH_SENTENCE = "根据该组织的官方门户网站，微软公司打算在2020年1月14日之后正式终止对Windows 7操作系统的免费支持。从那时起，该系统的用户将无法接收安全更新，这可能会使他们的计算机容易受到网络攻击。"
inputs = tokenizer([EN_SENTENCE, RU_SENTENCE, ZH_SENTENCE], padding=True, max_length=256, return_tensors='pt')
summary_ids = model.generate(inputs['input_ids'], num_beams=4, max_length=100, early_stopping=True)
tokenizer.batch_decode(summary_ids, skip_special_tokens=True)
# should give:
# 'Microsoft to end Windows 7 free support after January 14, 2020'
# 'Microsoft намерена прекратить бесплатную поддержку Windows 7 после 14 января 2020 года'
# '微软终止对Windows 7操作系统的免费支持'
```
### Citation
```bibtex
@article{yan2020prophetnet,
title={Prophetnet: Predicting future n-gram for sequence-to-sequence pre-training},
author={Yan, Yu and Qi, Weizhen and Gong, Yeyun and Liu, Dayiheng and Duan, Nan and Chen, Jiusheng and Zhang, Ruofei and Zhou, Ming},
journal={arXiv preprint arXiv:2001.04063},
year={2020}
}
```
| 2,829 | [
[
-0.02374267578125,
-0.036224365234375,
0.006622314453125,
0.01534271240234375,
-0.032562255859375,
-0.01177215576171875,
-0.005382537841796875,
-0.046112060546875,
-0.00244140625,
0.018646240234375,
-0.0430908203125,
-0.042144775390625,
-0.032989501953125,
0... |
sonoisa/t5-base-japanese-question-generation | 2022-03-11T02:50:33.000Z | [
"transformers",
"pytorch",
"t5",
"text2text-generation",
"seq2seq",
"ja",
"license:cc-by-sa-4.0",
"autotrain_compatible",
"endpoints_compatible",
"has_space",
"text-generation-inference",
"region:us"
] | text2text-generation | sonoisa | null | null | sonoisa/t5-base-japanese-question-generation | 3 | 542 | transformers | 2022-03-02T23:29:05 | ---
language: ja
tags:
- t5
- text2text-generation
- seq2seq
license: cc-by-sa-4.0
widget:
- text: "answer: アマビエ context: アマビエ（歴史的仮名遣：アマビヱ）は、日本に伝わる半人半魚の妖怪。光輝く姿で海中から現れ、豊作や疫病などの予言をすると伝えられている。江戸時代後期の肥後国（現・熊本県）に現れたという。この話は挿図付きで瓦版に取り上げられ、遠く江戸にまで伝えられた。弘化3年4月中旬（1846年5月上旬）のこと、毎夜、海中に光る物体が出没していたため、役人が赴いたところ、それが姿を現した。姿形について言葉では書き留められていないが、挿図が添えられている。 その者は、役人に対して「私は海中に住むアマビエと申す者なり」と名乗り、「当年より6ヶ年の間は諸国で豊作が続くが疫病も流行する。私の姿を描いた絵を人々に早々に見せよ。」と予言めいたことを告げ、海の中へと帰って行った。年代が特定できる最古の例は、天保15年（1844年）の越後国（現・新潟県）に出現した「海彦（読みの推定：あまびこ）」を記述した瓦版（『坪川本』という。福井県立図書館所蔵）、その挿絵に描かれた海彦は、頭からいきなり3本の足が生えた（胴体のない）形状で、人間のような耳をし、目はまるく、口が突出している。その年中に日本人口の7割の死滅を予言し、その像の絵札による救済を忠告している。"
---
# 回答と回答が出てくるパラグラフを与えると質問文を生成するモデル
SEE: https://github.com/sonoisa/deep-question-generation
## 本モデルの作成ステップ概要
1. [SQuAD 1.1](https://rajpurkar.github.io/SQuAD-explorer/)を日本語に機械翻訳し、不正なデータをクレンジング（有効なデータは約半分）。
回答が含まれるコンテキスト、質問文、解答の3つ組ができる。
2. [日本語T5モデル](https://huggingface.co/sonoisa/t5-base-japanese)を次の設定でファインチューニング
* 入力: "answer: {解答} content: {回答が含まれるコンテキスト}"
* 出力: "{質問文}"
* 各種ハイパーパラメータ
* 最大入力トークン数: 512
* 最大出力トークン数: 64
* 最適化アルゴリズム: AdaFactor
* 学習率: 0.001（固定）
* バッチサイズ: 128
* ステップ数: 2500（500ステップごとにチェックポイントを出力、定量・定性評価を行い2500ステップ目を採用）
| 1,216 | [
[
-0.04254150390625,
-0.081787109375,
0.03082275390625,
0.030914306640625,
-0.036376953125,
0.02044677734375,
-0.0020732879638671875,
-0.02935791015625,
0.0260162353515625,
0.0067901611328125,
-0.07574462890625,
-0.0258941650390625,
-0.031646728515625,
0.01928... |
GT4SD/multitask-text-and-chemistry-t5-base-augm | 2023-10-10T09:29:57.000Z | [
"transformers",
"pytorch",
"safetensors",
"t5",
"text2text-generation",
"en",
"arxiv:2301.12586",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text2text-generation | GT4SD | null | null | GT4SD/multitask-text-and-chemistry-t5-base-augm | 2 | 542 | transformers | 2023-05-19T18:09:33 | ---
license: mit
language:
- en
---
# Multitask Text and Chemistry T5
Multitask Text and Chemistry T5 : a multi-domain, multi-task language model to solve a wide range of tasks in both the chemical and natural language domains. Published by [Christofidellis et al.](https://arxiv.org/pdf/2301.12586.pdf)
**Model Details**: The Multitask Text and Chemistry T5 variant trained using <em>t5-small</em> as its pretrained based and the <em>augmented dataset</em>.
**Developers**: Dimitrios Christofidellis*, Giorgio Giannone*, Jannis Born, Teodoro Laino and Matteo Manica from IBM Research and Ole Winther from Technical University of Denmark.
**Distributors**: Model natively integrated into GT4SD.
**Model date**: 2023.
**Model type**: A Transformer-based language model that is trained on a multi-domain and a multi-task dataset by aggregating available datasets
for the tasks of Forward reaction prediction, Retrosynthesis, Molecular captioning, Text-conditional de novo generation and Paragraph to actions.
**Information about training algorithms, parameters, fairness constraints or other applied approaches, and features**:
N.A.
**Paper or other resource for more information**:
The Multitask Text and Chemistry T5 [Christofidellis et al.](https://arxiv.org/pdf/2301.12586.pdf)
**License**: MIT
**Where to send questions or comments about the model**: Open an issue on [GT4SD repository](https://github.com/GT4SD/gt4sd-core).
## Citation
```bib
@article{christofidellis2023unifying,
title={Unifying Molecular and Textual Representations via Multi-task Language Modelling},
author={Christofidellis, Dimitrios and Giannone, Giorgio and Born, Jannis and Winther, Ole and Laino, Teodoro and Manica, Matteo},
journal={arXiv preprint arXiv:2301.12586},
year={2023}
}
```
*equal contribution | 1,812 | [
[
0.00258636474609375,
-0.0293731689453125,
0.05810546875,
0.01427459716796875,
0.0145111083984375,
0.0217132568359375,
-0.027557373046875,
-0.0282135009765625,
-0.0025730133056640625,
0.03594970703125,
-0.05810546875,
-0.051544189453125,
-0.0474853515625,
0.0... |
nvidia/stt_en_fastconformer_ctc_large | 2023-06-08T02:52:33.000Z | [
"nemo",
"automatic-speech-recognition",
"speech",
"audio",
"CTC",
"FastConformer",
"Transformer",
"pytorch",
"NeMo",
"hf-asr-leaderboard",
"en",
"dataset:librispeech_asr",
"dataset:fisher_corpus",
"dataset:Switchboard-1",
"dataset:WSJ-0",
"dataset:WSJ-1",
"dataset:National-Singapore-... | automatic-speech-recognition | nvidia | null | null | nvidia/stt_en_fastconformer_ctc_large | 5 | 542 | nemo | 2023-06-08T02:32:43 | ---
language:
- en
library_name: nemo
datasets:
- librispeech_asr
- fisher_corpus
- Switchboard-1
- WSJ-0
- WSJ-1
- National-Singapore-Corpus-Part-1
- National-Singapore-Corpus-Part-6
- vctk
- VoxPopuli-(EN)
- Europarl-ASR-(EN)
- Multilingual-LibriSpeech-(2000-hours)
- mozilla-foundation/common_voice_8_0
- MLCommons/peoples_speech
thumbnail: null
tags:
- automatic-speech-recognition
- speech
- audio
- CTC
- FastConformer
- Transformer
- pytorch
- NeMo
- hf-asr-leaderboard
license: cc-by-4.0
widget:
- example_title: Librispeech sample 1
src: https://cdn-media.huggingface.co/speech_samples/sample1.flac
- example_title: Librispeech sample 2
src: https://cdn-media.huggingface.co/speech_samples/sample2.flac
model-index:
- name: stt_en_fastconformer_transducer_large
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: LibriSpeech (clean)
type: librispeech_asr
config: clean
split: test
args:
language: en
metrics:
- name: Test WER
type: wer
value: 2.1
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: LibriSpeech (other)
type: librispeech_asr
config: other
split: test
args:
language: en
metrics:
- name: Test WER
type: wer
value: 4.2
- task:
type: Automatic Speech Recognition
name: automatic-speech-recognition
dataset:
name: Multilingual LibriSpeech
type: facebook/multilingual_librispeech
config: english
split: test
args:
language: en
metrics:
- name: Test WER
type: wer
value: 6.4
- task:
type: Automatic Speech Recognition
name: automatic-speech-recognition
dataset:
name: Mozilla Common Voice 7.0
type: mozilla-foundation/common_voice_7_0
config: en
split: test
args:
language: en
metrics:
- name: Test WER
type: wer
value: 8.3
- task:
type: Automatic Speech Recognition
name: automatic-speech-recognition
dataset:
name: Wall Street Journal 92
type: wsj_0
args:
language: en
metrics:
- name: Test WER
type: wer
value: 1.6
- task:
type: Automatic Speech Recognition
name: automatic-speech-recognition
dataset:
name: Wall Street Journal 93
type: wsj_1
args:
language: en
metrics:
- name: Test WER
type: wer
value: 2.5
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: National Singapore Corpus
type: nsc_part_1
split: test
args:
language: en
metrics:
- name: Test WER
type: wer
value: 6.3
---
# NVIDIA FastConformer-CTC Large (en)
<style>
img {
display: inline;
}
</style>
| [](#model-architecture)
| [](#model-architecture)
| [](#datasets)
This model transcribes speech in lower case English alphabet.
It is a "large" version of FastConformer CTC (around 115M parameters) model.
See the [model architecture](#model-architecture) section and [NeMo documentation](https://docs.nvidia.com/deeplearning/nemo/user-guide/docs/en/main/asr/models.html#fast-conformer) for complete architecture details.
## NVIDIA NeMo: Training
To train, fine-tune or play with the model you will need to install [NVIDIA NeMo](https://github.com/NVIDIA/NeMo). We recommend you install it after you've installed latest Pytorch version.
```
pip install nemo_toolkit['all']
```
## How to Use this Model
The model is available for use in the NeMo toolkit [3], and can be used as a pre-trained checkpoint for inference or for fine-tuning on another dataset.
### Automatically instantiate the model
```python
import nemo.collections.asr as nemo_asr
asr_model = nemo_asr.models.EncDecCTCTBPEModel.from_pretrained(model_name="nvidia/stt_en_fastconformer_ctc_large")
```
### Transcribing using Python
First, let's get a sample
```
wget https://dldata-public.s3.us-east-2.amazonaws.com/2086-149220-0033.wav
```
Then simply do:
```
asr_model.transcribe(['2086-149220-0033.wav'])
```
### Transcribing many audio files
```shell
python [NEMO_GIT_FOLDER]/examples/asr/transcribe_speech.py
pretrained_name="nvidia/stt_en_fastconformer_ctc_large"
audio_dir="<DIRECTORY CONTAINING AUDIO FILES>"
```
### Input
This model accepts 16000 Hz Mono-channel Audio (wav files) as input.
### Output
This model provides transcribed speech as a string for a given audio sample.
## Model Architecture
FastConformer [1] is an optimized version of the Conformer model with 8x depthwise-separable convolutional downsampling. The model is trained in a multitask setup with a Transducer decoder loss. You may find more information on the details of FastConformer here: [Fast-Conformer Model](https://docs.nvidia.com/deeplearning/nemo/user-guide/docs/en/main/asr/models.html#fast-conformer).
## Training
The NeMo toolkit [3] was used for training the models for over several hundred epochs. These model are trained with this [example script](https://github.com/NVIDIA/NeMo/blob/main/examples/asr/asr_ctc/speech_to_text_ctc_bpe.py) and this [base config](https://github.com/NVIDIA/NeMo/blob/main/examples/asr/conf/fastconformer/fast-conformer_ctc_bpe.yaml).
The tokenizers for these models were built using the text transcripts of the train set with this [script](https://github.com/NVIDIA/NeMo/blob/main/scripts/tokenizers/process_asr_text_tokenizer.py).
### Datasets
The model in this collection is trained on a composite dataset (NeMo ASRSet En) comprising several thousand hours of English speech:
- Librispeech 960 hours of English speech
- Fisher Corpus
- Switchboard-1 Dataset
- WSJ-0 and WSJ-1
- National Speech Corpus (Part 1, Part 6)
- VCTK
- VoxPopuli (EN)
- Europarl-ASR (EN)
- Multilingual Librispeech (MLS EN) - 2,000 hrs subset
- Mozilla Common Voice (v7.0)
- People's Speech - 12,000 hrs subset
## Performance
The performance of Automatic Speech Recognition models is measuring using Word Error Rate. Since this dataset is trained on multiple domains and a much larger corpus, it will generally perform better at transcribing audio in general.
The following tables summarizes the performance of the available models in this collection with the Transducer decoder. Performances of the ASR models are reported in terms of Word Error Rate (WER%) with greedy decoding.
|**Version**|**Tokenizer**|**Vocabulary Size**|**LS test-other**|**LS test-clean**|**WSJ Eval92**|**WSJ Dev93**|**NSC Part 1**|**MLS Test**|**MCV Test 7.0**| Train Dataset |
|---------|-----------------------|-----------------|---------------|---------------|------------|-----------|-----|-------|------|------|
| 1.18.0 | SentencePiece Unigram | 1024 | 4.2 | 2.1 | 1.6 | 2.5 | 6.3 | 6.4 | 8.3 | NeMo ASRSET 3.0 |
## Limitations
Since this model was trained on publically available speech datasets, the performance of this model might degrade for speech which includes technical terms, or vernacular that the model has not been trained on. The model might also perform worse for accented speech.
## NVIDIA Riva: Deployment
[NVIDIA Riva](https://developer.nvidia.com/riva), is an accelerated speech AI SDK deployable on-prem, in all clouds, multi-cloud, hybrid, on edge, and embedded.
Additionally, Riva provides:
* World-class out-of-the-box accuracy for the most common languages with model checkpoints trained on proprietary data with hundreds of thousands of GPU-compute hours
* Best in class accuracy with run-time word boosting (e.g., brand and product names) and customization of acoustic model, language model, and inverse text normalization
* Streaming speech recognition, Kubernetes compatible scaling, and enterprise-grade support
Although this model isn’t supported yet by Riva, the [list of supported models is here](https://huggingface.co/models?other=Riva).
Check out [Riva live demo](https://developer.nvidia.com/riva#demos).
## References
[1] [Fast Conformer with Linearly Scalable Attention for Efficient Speech Recognition](https://arxiv.org/abs/2305.05084)
[2] [Google Sentencepiece Tokenizer](https://github.com/google/sentencepiece)
[3] [NVIDIA NeMo Toolkit](https://github.com/NVIDIA/NeMo)
## Licence
License to use this model is covered by the [CC-BY-4.0](https://creativecommons.org/licenses/by/4.0/). By downloading the public and release version of the model, you accept the terms and conditions of the [CC-BY-4.0](https://creativecommons.org/licenses/by/4.0/) license.
| 9,359 | [
[
-0.031219482421875,
-0.05517578125,
0.00795745849609375,
0.0019006729125976562,
-0.019256591796875,
-0.0046844482421875,
-0.0201416015625,
-0.04345703125,
-0.003307342529296875,
0.02349853515625,
-0.036590576171875,
-0.039306640625,
-0.057647705078125,
0.012... |
keremberke/yolov5m-nfl | 2022-12-30T20:46:52.000Z | [
"yolov5",
"tensorboard",
"yolo",
"vision",
"object-detection",
"pytorch",
"dataset:keremberke/nfl-object-detection",
"model-index",
"has_space",
"region:us"
] | object-detection | keremberke | null | null | keremberke/yolov5m-nfl | 2 | 541 | yolov5 | 2022-12-30T15:09:49 |
---
tags:
- yolov5
- yolo
- vision
- object-detection
- pytorch
library_name: yolov5
library_version: 7.0.6
inference: false
datasets:
- keremberke/nfl-object-detection
model-index:
- name: keremberke/yolov5m-nfl
results:
- task:
type: object-detection
dataset:
type: keremberke/nfl-object-detection
name: keremberke/nfl-object-detection
split: validation
metrics:
- type: precision # since mAP@0.5 is not available on hf.co/metrics
value: 0.3141797014905773 # min: 0.0 - max: 1.0
name: mAP@0.5
---
<div align="center">
<img width="640" alt="keremberke/yolov5m-nfl" src="https://huggingface.co/keremberke/yolov5m-nfl/resolve/main/sample_visuals.jpg">
</div>
### How to use
- Install [yolov5](https://github.com/fcakyon/yolov5-pip):
```bash
pip install -U yolov5
```
- Load model and perform prediction:
```python
import yolov5
# load model
model = yolov5.load('keremberke/yolov5m-nfl')
# set model parameters
model.conf = 0.25 # NMS confidence threshold
model.iou = 0.45 # NMS IoU threshold
model.agnostic = False # NMS class-agnostic
model.multi_label = False # NMS multiple labels per box
model.max_det = 1000 # maximum number of detections per image
# set image
img = 'https://github.com/ultralytics/yolov5/raw/master/data/images/zidane.jpg'
# perform inference
results = model(img, size=640)
# inference with test time augmentation
results = model(img, augment=True)
# parse results
predictions = results.pred[0]
boxes = predictions[:, :4] # x1, y1, x2, y2
scores = predictions[:, 4]
categories = predictions[:, 5]
# show detection bounding boxes on image
results.show()
# save results into "results/" folder
results.save(save_dir='results/')
```
- Finetune the model on your custom dataset:
```bash
yolov5 train --data data.yaml --img 640 --batch 16 --weights keremberke/yolov5m-nfl --epochs 10
```
**More models available at: [awesome-yolov5-models](https://github.com/keremberke/awesome-yolov5-models)**
| 2,007 | [
[
-0.0611572265625,
-0.03961181640625,
0.0347900390625,
-0.0268096923828125,
-0.0253143310546875,
-0.02227783203125,
0.01030731201171875,
-0.04705810546875,
0.00824737548828125,
0.0254058837890625,
-0.051055908203125,
-0.056304931640625,
-0.03790283203125,
0.0... |
google/t5-large-ssm-nq | 2023-01-24T16:52:12.000Z | [
"transformers",
"pytorch",
"tf",
"jax",
"t5",
"text2text-generation",
"en",
"dataset:c4",
"dataset:wikipedia",
"dataset:natural_questions",
"arxiv:2002.08909",
"arxiv:1910.10683",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"has_space",
"text-generation-infe... | text2text-generation | google | null | null | google/t5-large-ssm-nq | 4 | 540 | transformers | 2022-03-02T23:29:05 | ---
language: en
datasets:
- c4
- wikipedia
- natural_questions
pipeline_tag: text2text-generation
license: apache-2.0
---
[Google's T5](https://ai.googleblog.com/2020/02/exploring-transfer-learning-with-t5.html) for **Closed Book Question Answering**.
The model was pre-trained using T5's denoising objective on [C4](https://huggingface.co/datasets/c4), subsequently additionally pre-trained using [REALM](https://arxiv.org/pdf/2002.08909.pdf)'s salient span masking objective on [Wikipedia](https://huggingface.co/datasets/wikipedia), and finally fine-tuned on [Natural Questions (NQ)](https://huggingface.co/datasets/natural_questions).
**Note**: The model was fine-tuned on 100% of the train splits of [Natural Questions (NQ)](https://huggingface.co/datasets/natural_questions) for 10k steps.
Other community Checkpoints: [here](https://huggingface.co/models?search=ssm)
Paper: [How Much Knowledge Can You Pack
Into the Parameters of a Language Model?](https://arxiv.org/abs/1910.10683.pdf)
Authors: *Adam Roberts, Colin Raffel, Noam Shazeer*
## Results on Natural Questions - Test Set
|Id | link | Exact Match |
|---|---|---|
|T5-small|https://huggingface.co/google/t5-small-ssm-nq|25.5|
|**T5-large**|**https://huggingface.co/google/t5-large-ssm-nq**|**30.4**|
|T5-xl|https://huggingface.co/google/t5-xl-ssm-nq|35.6|
|T5-xxl|https://huggingface.co/google/t5-xxl-ssm-nq|37.9|
|T5-3b|https://huggingface.co/google/t5-3b-ssm-nq|33.2|
|T5-11b|https://huggingface.co/google/t5-11b-ssm-nq|36.6|
## Usage
The model can be used as follows for **closed book question answering**:
```python
from transformers import AutoModelForSeq2SeqLM, AutoTokenizer
t5_qa_model = AutoModelForSeq2SeqLM.from_pretrained("google/t5-large-ssm-nq")
t5_tok = AutoTokenizer.from_pretrained("google/t5-large-ssm-nq")
input_ids = t5_tok("When was Franklin D. Roosevelt born?", return_tensors="pt").input_ids
gen_output = t5_qa_model.generate(input_ids)[0]
print(t5_tok.decode(gen_output, skip_special_tokens=True))
# should give "December 26, 1892" => close, but not correct.
```
## Abstract
It has recently been observed that neural language models trained on unstructured text can implicitly store and retrieve knowledge using natural language queries. In this short paper, we measure the practical utility of this approach by fine-tuning pre-trained models to answer questions without access to any external context or knowledge. We show that this approach scales with model size and performs competitively with open-domain systems that explicitly retrieve answers from an external knowledge source when answering questions. To facilitate reproducibility and future work, we release our code and trained models at https://goo.gle/t5-cbqa.
 | 2,860 | [
[
-0.04376220703125,
-0.0660400390625,
0.03289794921875,
-0.0022735595703125,
-0.0061187744140625,
-0.00977325439453125,
-0.025726318359375,
-0.0240478515625,
-0.0156402587890625,
0.03839111328125,
-0.05242919921875,
-0.038055419921875,
-0.0280303955078125,
0.... |
sentence-transformers/msmarco-roberta-base-v3 | 2022-06-15T22:06:07.000Z | [
"sentence-transformers",
"pytorch",
"tf",
"roberta",
"feature-extraction",
"sentence-similarity",
"transformers",
"arxiv:1908.10084",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | sentence-similarity | sentence-transformers | null | null | sentence-transformers/msmarco-roberta-base-v3 | 0 | 540 | sentence-transformers | 2022-03-02T23:29:05 | ---
pipeline_tag: sentence-similarity
license: apache-2.0
tags:
- sentence-transformers
- feature-extraction
- sentence-similarity
- transformers
---
# sentence-transformers/msmarco-roberta-base-v3
This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 768 dimensional dense vector space and can be used for tasks like clustering or semantic search.
## Usage (Sentence-Transformers)
Using this model becomes easy when you have [sentence-transformers](https://www.SBERT.net) installed:
```
pip install -U sentence-transformers
```
Then you can use the model like this:
```python
from sentence_transformers import SentenceTransformer
sentences = ["This is an example sentence", "Each sentence is converted"]
model = SentenceTransformer('sentence-transformers/msmarco-roberta-base-v3')
embeddings = model.encode(sentences)
print(embeddings)
```
## Usage (HuggingFace Transformers)
Without [sentence-transformers](https://www.SBERT.net), you can use the model like this: First, you pass your input through the transformer model, then you have to apply the right pooling-operation on-top of the contextualized word embeddings.
```python
from transformers import AutoTokenizer, AutoModel
import torch
#Mean Pooling - Take attention mask into account for correct averaging
def mean_pooling(model_output, attention_mask):
token_embeddings = model_output[0] #First element of model_output contains all token embeddings
input_mask_expanded = attention_mask.unsqueeze(-1).expand(token_embeddings.size()).float()
return torch.sum(token_embeddings * input_mask_expanded, 1) / torch.clamp(input_mask_expanded.sum(1), min=1e-9)
# Sentences we want sentence embeddings for
sentences = ['This is an example sentence', 'Each sentence is converted']
# Load model from HuggingFace Hub
tokenizer = AutoTokenizer.from_pretrained('sentence-transformers/msmarco-roberta-base-v3')
model = AutoModel.from_pretrained('sentence-transformers/msmarco-roberta-base-v3')
# Tokenize sentences
encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt')
# Compute token embeddings
with torch.no_grad():
model_output = model(**encoded_input)
# Perform pooling. In this case, max pooling.
sentence_embeddings = mean_pooling(model_output, encoded_input['attention_mask'])
print("Sentence embeddings:")
print(sentence_embeddings)
```
## Evaluation Results
For an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: [https://seb.sbert.net](https://seb.sbert.net?model_name=sentence-transformers/msmarco-roberta-base-v3)
## Full Model Architecture
```
SentenceTransformer(
(0): Transformer({'max_seq_length': 510, 'do_lower_case': False}) with Transformer model: RobertaModel
(1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False})
)
```
## Citing & Authors
This model was trained by [sentence-transformers](https://www.sbert.net/).
If you find this model helpful, feel free to cite our publication [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://arxiv.org/abs/1908.10084):
```bibtex
@inproceedings{reimers-2019-sentence-bert,
title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
author = "Reimers, Nils and Gurevych, Iryna",
booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
month = "11",
year = "2019",
publisher = "Association for Computational Linguistics",
url = "http://arxiv.org/abs/1908.10084",
}
``` | 3,696 | [
[
-0.018829345703125,
-0.055694580078125,
0.022186279296875,
0.029937744140625,
-0.02142333984375,
-0.034423828125,
-0.0295867919921875,
-0.006275177001953125,
0.01194000244140625,
0.03179931640625,
-0.041412353515625,
-0.03680419921875,
-0.054351806640625,
0.... |
RazzzHF/popupBook-diffusion | 2023-05-16T09:26:49.000Z | [
"diffusers",
"text-to-image",
"license:creativeml-openrail-m",
"endpoints_compatible",
"diffusers:StableDiffusionPipeline",
"region:us"
] | text-to-image | RazzzHF | null | null | RazzzHF/popupBook-diffusion | 72 | 540 | diffusers | 2022-11-11T05:12:04 | ---
license: creativeml-openrail-m
tags:
- text-to-image
---
Use **popupBook** in your prompt
Ex: cat in a popupBook
Art Examples:
| 1,504 | [
[
-0.034759521484375,
-0.0462646484375,
0.03863525390625,
0.014678955078125,
-0.019439697265625,
0.0224609375,
0.01358795166015625,
-0.0230255126953125,
0.0302734375,
0.06298828125,
-0.04864501953125,
-0.037506103515625,
-0.02508544921875,
0.0323486328125,
... |
Zohair101/Foul-Language-Detection-DH | 2023-10-26T07:56:44.000Z | [
"transformers",
"tf",
"distilbert",
"text-classification",
"en",
"endpoints_compatible",
"region:us"
] | text-classification | Zohair101 | null | null | Zohair101/Foul-Language-Detection-DH | 0 | 540 | transformers | 2023-10-26T07:34:34 | ---
language:
- en
metrics:
- accuracy
pipeline_tag: text-classification
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
A fine-tuned version of DistilBERT for detecting foul language, discrimination, humour and other irrelevant stuff from Job Descriptions.
| 303 | [
[
-0.0261077880859375,
-0.036773681640625,
0.021240234375,
0.004436492919921875,
-0.04498291015625,
-0.016387939453125,
0.0406494140625,
-0.0019445419311523438,
0.010986328125,
0.02252197265625,
-0.031646728515625,
-0.029296875,
-0.0279388427734375,
-0.0060195... |
hfl/rbt6 | 2021-05-19T19:22:02.000Z | [
"transformers",
"pytorch",
"tf",
"jax",
"bert",
"fill-mask",
"zh",
"arxiv:1906.08101",
"arxiv:2004.13922",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | fill-mask | hfl | null | null | hfl/rbt6 | 5 | 539 | transformers | 2022-03-02T23:29:05 | ---
language:
- zh
tags:
- bert
license: "apache-2.0"
---
# This is a re-trained 6-layer RoBERTa-wwm-ext model.
## Chinese BERT with Whole Word Masking
For further accelerating Chinese natural language processing, we provide **Chinese pre-trained BERT with Whole Word Masking**.
**[Pre-Training with Whole Word Masking for Chinese BERT](https://arxiv.org/abs/1906.08101)**
Yiming Cui, Wanxiang Che, Ting Liu, Bing Qin, Ziqing Yang, Shijin Wang, Guoping Hu
This repository is developed based on：https://github.com/google-research/bert
You may also interested in,
- Chinese BERT series: https://github.com/ymcui/Chinese-BERT-wwm
- Chinese MacBERT: https://github.com/ymcui/MacBERT
- Chinese ELECTRA: https://github.com/ymcui/Chinese-ELECTRA
- Chinese XLNet: https://github.com/ymcui/Chinese-XLNet
- Knowledge Distillation Toolkit - TextBrewer: https://github.com/airaria/TextBrewer
More resources by HFL: https://github.com/ymcui/HFL-Anthology
## Citation
If you find the technical report or resource is useful, please cite the following technical report in your paper.
- Primary: https://arxiv.org/abs/2004.13922
```
@inproceedings{cui-etal-2020-revisiting,
title = "Revisiting Pre-Trained Models for {C}hinese Natural Language Processing",
author = "Cui, Yiming and
Che, Wanxiang and
Liu, Ting and
Qin, Bing and
Wang, Shijin and
Hu, Guoping",
booktitle = "Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: Findings",
month = nov,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://www.aclweb.org/anthology/2020.findings-emnlp.58",
pages = "657--668",
}
```
- Secondary: https://arxiv.org/abs/1906.08101
```
@article{chinese-bert-wwm,
title={Pre-Training with Whole Word Masking for Chinese BERT},
author={Cui, Yiming and Che, Wanxiang and Liu, Ting and Qin, Bing and Yang, Ziqing and Wang, Shijin and Hu, Guoping},
journal={arXiv preprint arXiv:1906.08101},
year={2019}
}
```
| 2,062 | [
[
-0.0193634033203125,
-0.06390380859375,
0.0181427001953125,
0.0286102294921875,
-0.0272369384765625,
-0.01305389404296875,
-0.041534423828125,
-0.0491943359375,
0.02532958984375,
0.037078857421875,
-0.040374755859375,
-0.033172607421875,
-0.03936767578125,
-... |
nlptown/flaubert_small_cased_sentiment | 2022-05-17T07:43:58.000Z | [
"transformers",
"pytorch",
"tf",
"flaubert",
"text-classification",
"fr",
"dataset:amazon_reviews_multi",
"license:mit",
"endpoints_compatible",
"region:us"
] | text-classification | nlptown | null | null | nlptown/flaubert_small_cased_sentiment | 1 | 539 | transformers | 2022-05-17T06:26:02 | ---
language:
- fr
datasets:
- amazon_reviews_multi
license: mit
---
# flaubert_small_cased_sentiment
This is a `flaubert_small_cased` model finetuned for sentiment analysis on product reviews in French. It predicts the sentiment of the review, from `very_negative` (1 star) to `very_positive` (5 stars).
This model is intended for direct use as a sentiment analysis model for French product reviews, or for further finetuning on related sentiment analysis tasks.
## Training data
The training data consists of the French portion of `amazon_reviews_multi`, supplemented with another 140,000 similar reviews.
## Accuracy
The finetuned model was evaluated on the French test set of `amazon_reviews_multi`.
- Accuracy (exact) is the exact match on the number of stars.
- Accuracy (off-by-1) is the percentage of reviews where the number of stars the model predicts differs by a maximum of 1 from the number given by the human reviewer.
| Language | Accuracy (exact) | Accuracy (off-by-1) |
| -------- | ---------------------- | ------------------- |
| French | 61.56% | 95.66%
## Contact
[NLP Town](https://www.nlp.town) offers a suite of sentiment models for a wide range of languages, including an improved multilingual model through [RapidAPI](https://rapidapi.com/nlp-town-nlp-town-default/api/multilingual-sentiment-analysis2/).
Feel free to contact us for questions, feedback and/or requests for similar models. | 1,447 | [
[
-0.04962158203125,
-0.054931640625,
0.0175323486328125,
0.04473876953125,
-0.01390838623046875,
-0.01357269287109375,
-0.01149749755859375,
-0.0220947265625,
0.03497314453125,
0.032135009765625,
-0.049224853515625,
-0.0557861328125,
-0.033233642578125,
0.001... |
stablediffusionapi/uber-realistic-merge | 2023-05-31T04:32:13.000Z | [
"diffusers",
"stablediffusionapi.com",
"stable-diffusion-api",
"text-to-image",
"ultra-realistic",
"license:creativeml-openrail-m",
"endpoints_compatible",
"has_space",
"diffusers:StableDiffusionPipeline",
"region:us"
] | text-to-image | stablediffusionapi | null | null | stablediffusionapi/uber-realistic-merge | 4 | 539 | diffusers | 2023-05-26T13:56:34 | ---
license: creativeml-openrail-m
tags:
- stablediffusionapi.com
- stable-diffusion-api
- text-to-image
- ultra-realistic
pinned: true
---
# Uber Realistic Merge (URPM) API Inference
## Get API Key
Get API key from [Stable Diffusion API](http://stablediffusionapi.com/), No Payment needed.
Replace Key in below code, change **model_id** to "uber-realistic-merge"
Coding in PHP/Node/Java etc? Have a look at docs for more code examples: [View docs](https://stablediffusionapi.com/docs)
Try model for free: [Generate Images](https://stablediffusionapi.com/models/uber-realistic-merge)
Model link: [View model](https://stablediffusionapi.com/models/uber-realistic-merge)
Credits: [View credits](https://civitai.com/?query=Uber%20Realistic%20Merge%20%28URPM%29)
View all models: [View Models](https://stablediffusionapi.com/models)
import requests
import json
url = "https://stablediffusionapi.com/api/v3/dreambooth"
payload = json.dumps({
"key": "your_api_key",
"model_id": "uber-realistic-merge",
"prompt": "ultra realistic close up portrait ((beautiful pale cyberpunk female with heavy black eyeliner)), blue eyes, shaved side haircut, hyper detail, cinematic lighting, magic neon, dark red city, Canon EOS R3, nikon, f/1.4, ISO 200, 1/160s, 8K, RAW, unedited, symmetrical balance, in-frame, 8K",
"negative_prompt": "painting, extra fingers, mutated hands, poorly drawn hands, poorly drawn face, deformed, ugly, blurry, bad anatomy, bad proportions, extra limbs, cloned face, skinny, glitchy, double torso, extra arms, extra hands, mangled fingers, missing lips, ugly face, distorted face, extra legs, anime",
"width": "512",
"height": "512",
"samples": "1",
"num_inference_steps": "30",
"safety_checker": "no",
"enhance_prompt": "yes",
"seed": None,
"guidance_scale": 7.5,
"multi_lingual": "no",
"panorama": "no",
"self_attention": "no",
"upscale": "no",
"embeddings": "embeddings_model_id",
"lora": "lora_model_id",
"webhook": None,
"track_id": None
})
headers = {
'Content-Type': 'application/json'
}
response = requests.request("POST", url, headers=headers, data=payload)
print(response.text)
> Use this coupon code to get 25% off **DMGG0RBN** | 2,536 | [
[
-0.044281005859375,
-0.05755615234375,
0.033447265625,
0.0125732421875,
-0.0394287109375,
0.007289886474609375,
0.017822265625,
-0.047607421875,
0.0295867919921875,
0.04327392578125,
-0.061859130859375,
-0.05755615234375,
-0.029052734375,
-0.004150390625,
... |
Classic0/test1 | 2023-07-19T15:19:30.000Z | [
"diffusers",
"text-to-image",
"stable-diffusion",
"license:creativeml-openrail-m",
"endpoints_compatible",
"diffusers:StableDiffusionPipeline",
"region:us",
"has_space"
] | text-to-image | Classic0 | null | null | Classic0/test1 | 0 | 539 | diffusers | 2023-07-19T15:15:48 | ---
license: creativeml-openrail-m
tags:
- text-to-image
- stable-diffusion
---
### test1 Dreambooth model trained by Classic0 with [TheLastBen's fast-DreamBooth](https://colab.research.google.com/github/TheLastBen/fast-stable-diffusion/blob/main/fast-DreamBooth.ipynb) notebook
Test the concept via A1111 Colab [fast-Colab-A1111](https://colab.research.google.com/github/TheLastBen/fast-stable-diffusion/blob/main/fast_stable_diffusion_AUTOMATIC1111.ipynb)
Sample pictures of this concept:
| 495 | [
[
-0.0297393798828125,
-0.06829833984375,
0.03839111328125,
0.0256805419921875,
-0.0226287841796875,
0.022064208984375,
0.0182647705078125,
-0.0208587646484375,
0.044769287109375,
0.00986480712890625,
-0.0164642333984375,
-0.01293182373046875,
-0.0198822021484375,... |
CiroN2022/cd-md-music | 2023-08-24T15:06:05.000Z | [
"diffusers",
"text-to-image",
"stable-diffusion",
"lora",
"license:other",
"region:us",
"has_space"
] | text-to-image | CiroN2022 | null | null | CiroN2022/cd-md-music | 0 | 539 | diffusers | 2023-08-24T15:05:56 | ---
license: other
tags:
- text-to-image
- stable-diffusion
- lora
- diffusers
base_model: stabilityai/stable-diffusion-xl-base-1.0
instance_prompt:
widget:
- text:
---
# CD/MD Music
None
## Image examples for the model:
| 489 | [
[
-0.032562255859375,
-0.019989013671875,
0.04638671875,
0.037261962890625,
-0.039794921875,
-0.012664794921875,
0.00992584228515625,
0.0204925537109375,
0.008392333984375,
0.052154541015625,
-0.054656982421875,
-0.05096435546875,
-0.0254669189453125,
-0.01200... |
google/bert_uncased_L-4_H-128_A-2 | 2021-05-19T17:30:08.000Z | [
"transformers",
"pytorch",
"jax",
"bert",
"arxiv:1908.08962",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | null | google | null | null | google/bert_uncased_L-4_H-128_A-2 | 0 | 538 | transformers | 2022-03-02T23:29:05 | ---
thumbnail: https://huggingface.co/front/thumbnails/google.png
license: apache-2.0
---
BERT Miniatures
===
This is the set of 24 BERT models referenced in [Well-Read Students Learn Better: On the Importance of Pre-training Compact Models](https://arxiv.org/abs/1908.08962) (English only, uncased, trained with WordPiece masking).
We have shown that the standard BERT recipe (including model architecture and training objective) is effective on a wide range of model sizes, beyond BERT-Base and BERT-Large. The smaller BERT models are intended for environments with restricted computational resources. They can be fine-tuned in the same manner as the original BERT models. However, they are most effective in the context of knowledge distillation, where the fine-tuning labels are produced by a larger and more accurate teacher.
Our goal is to enable research in institutions with fewer computational resources and encourage the community to seek directions of innovation alternative to increasing model capacity.
You can download the 24 BERT miniatures either from the [official BERT Github page](https://github.com/google-research/bert/), or via HuggingFace from the links below:
| |H=128|H=256|H=512|H=768|
|---|:---:|:---:|:---:|:---:|
| **L=2** |[**2/128 (BERT-Tiny)**][2_128]|[2/256][2_256]|[2/512][2_512]|[2/768][2_768]|
| **L=4** |[4/128][4_128]|[**4/256 (BERT-Mini)**][4_256]|[**4/512 (BERT-Small)**][4_512]|[4/768][4_768]|
| **L=6** |[6/128][6_128]|[6/256][6_256]|[6/512][6_512]|[6/768][6_768]|
| **L=8** |[8/128][8_128]|[8/256][8_256]|[**8/512 (BERT-Medium)**][8_512]|[8/768][8_768]|
| **L=10** |[10/128][10_128]|[10/256][10_256]|[10/512][10_512]|[10/768][10_768]|
| **L=12** |[12/128][12_128]|[12/256][12_256]|[12/512][12_512]|[**12/768 (BERT-Base)**][12_768]|
Note that the BERT-Base model in this release is included for completeness only; it was re-trained under the same regime as the original model.
Here are the corresponding GLUE scores on the test set:
|Model|Score|CoLA|SST-2|MRPC|STS-B|QQP|MNLI-m|MNLI-mm|QNLI(v2)|RTE|WNLI|AX|
|---|:---:|:---:|:---:|:---:|:---:|:---:|:---:|:---:|:---:|:---:|:---:|:---:|
|BERT-Tiny|64.2|0.0|83.2|81.1/71.1|74.3/73.6|62.2/83.4|70.2|70.3|81.5|57.2|62.3|21.0|
|BERT-Mini|65.8|0.0|85.9|81.1/71.8|75.4/73.3|66.4/86.2|74.8|74.3|84.1|57.9|62.3|26.1|
|BERT-Small|71.2|27.8|89.7|83.4/76.2|78.8/77.0|68.1/87.0|77.6|77.0|86.4|61.8|62.3|28.6|
|BERT-Medium|73.5|38.0|89.6|86.6/81.6|80.4/78.4|69.6/87.9|80.0|79.1|87.7|62.2|62.3|30.5|
For each task, we selected the best fine-tuning hyperparameters from the lists below, and trained for 4 epochs:
- batch sizes: 8, 16, 32, 64, 128
- learning rates: 3e-4, 1e-4, 5e-5, 3e-5
If you use these models, please cite the following paper:
```
@article{turc2019,
title={Well-Read Students Learn Better: On the Importance of Pre-training Compact Models},
author={Turc, Iulia and Chang, Ming-Wei and Lee, Kenton and Toutanova, Kristina},
journal={arXiv preprint arXiv:1908.08962v2 },
year={2019}
}
```
[2_128]: https://huggingface.co/google/bert_uncased_L-2_H-128_A-2
[2_256]: https://huggingface.co/google/bert_uncased_L-2_H-256_A-4
[2_512]: https://huggingface.co/google/bert_uncased_L-2_H-512_A-8
[2_768]: https://huggingface.co/google/bert_uncased_L-2_H-768_A-12
[4_128]: https://huggingface.co/google/bert_uncased_L-4_H-128_A-2
[4_256]: https://huggingface.co/google/bert_uncased_L-4_H-256_A-4
[4_512]: https://huggingface.co/google/bert_uncased_L-4_H-512_A-8
[4_768]: https://huggingface.co/google/bert_uncased_L-4_H-768_A-12
[6_128]: https://huggingface.co/google/bert_uncased_L-6_H-128_A-2
[6_256]: https://huggingface.co/google/bert_uncased_L-6_H-256_A-4
[6_512]: https://huggingface.co/google/bert_uncased_L-6_H-512_A-8
[6_768]: https://huggingface.co/google/bert_uncased_L-6_H-768_A-12
[8_128]: https://huggingface.co/google/bert_uncased_L-8_H-128_A-2
[8_256]: https://huggingface.co/google/bert_uncased_L-8_H-256_A-4
[8_512]: https://huggingface.co/google/bert_uncased_L-8_H-512_A-8
[8_768]: https://huggingface.co/google/bert_uncased_L-8_H-768_A-12
[10_128]: https://huggingface.co/google/bert_uncased_L-10_H-128_A-2
[10_256]: https://huggingface.co/google/bert_uncased_L-10_H-256_A-4
[10_512]: https://huggingface.co/google/bert_uncased_L-10_H-512_A-8
[10_768]: https://huggingface.co/google/bert_uncased_L-10_H-768_A-12
[12_128]: https://huggingface.co/google/bert_uncased_L-12_H-128_A-2
[12_256]: https://huggingface.co/google/bert_uncased_L-12_H-256_A-4
[12_512]: https://huggingface.co/google/bert_uncased_L-12_H-512_A-8
[12_768]: https://huggingface.co/google/bert_uncased_L-12_H-768_A-12
| 4,617 | [
[
-0.053558349609375,
-0.03546142578125,
0.0239410400390625,
0.013153076171875,
-0.02374267578125,
-0.0169525146484375,
-0.0239715576171875,
-0.031219482421875,
0.04376220703125,
-0.006107330322265625,
-0.06103515625,
-0.030670166015625,
-0.05206298828125,
-0.... |
timm/vit_base_patch32_clip_224.laion2b_ft_in12k_in1k | 2023-05-06T00:04:02.000Z | [
"timm",
"pytorch",
"safetensors",
"image-classification",
"dataset:imagenet-1k",
"dataset:laion-2b",
"dataset:imagenet-12k",
"arxiv:2212.07143",
"arxiv:2210.08402",
"arxiv:2010.11929",
"license:apache-2.0",
"region:us"
] | image-classification | timm | null | null | timm/vit_base_patch32_clip_224.laion2b_ft_in12k_in1k | 0 | 538 | timm | 2022-11-05T22:33:35 | ---
tags:
- image-classification
- timm
library_name: timm
license: apache-2.0
datasets:
- imagenet-1k
- laion-2b
- imagenet-12k
---
# Model card for vit_base_patch32_clip_224.laion2b_ft_in12k_in1k
A Vision Transformer (ViT) image classification model. Pretrained on LAION-2B image-text pairs using OpenCLIP. Fine-tuned on ImageNet-12k and then ImageNet-1k in `timm`. See recipes in [Reproducible scaling laws](https://arxiv.org/abs/2212.07143).
## Model Details
- **Model Type:** Image classification / feature backbone
- **Model Stats:**
- Params (M): 88.2
- GMACs: 4.4
- Activations (M): 4.2
- Image size: 224 x 224
- **Papers:**
- OpenCLIP: https://github.com/mlfoundations/open_clip
- Reproducible scaling laws for contrastive language-image learning: https://arxiv.org/abs/2212.07143
- LAION-5B: An open large-scale dataset for training next generation image-text models: https://arxiv.org/abs/2210.08402
- An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale: https://arxiv.org/abs/2010.11929v2
- **Dataset:** ImageNet-1k
- **Pretrain Dataset:**
- LAION-2B
- ImageNet-12k
## Model Usage
### Image Classification
```python
from urllib.request import urlopen
from PIL import Image
import timm
img = Image.open(urlopen(
'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
))
model = timm.create_model('vit_base_patch32_clip_224.laion2b_ft_in12k_in1k', pretrained=True)
model = model.eval()
# get model specific transforms (normalization, resize)
data_config = timm.data.resolve_model_data_config(model)
transforms = timm.data.create_transform(**data_config, is_training=False)
output = model(transforms(img).unsqueeze(0)) # unsqueeze single image into batch of 1
top5_probabilities, top5_class_indices = torch.topk(output.softmax(dim=1) * 100, k=5)
```
### Image Embeddings
```python
from urllib.request import urlopen
from PIL import Image
import timm
img = Image.open(urlopen(
'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
))
model = timm.create_model(
'vit_base_patch32_clip_224.laion2b_ft_in12k_in1k',
pretrained=True,
num_classes=0, # remove classifier nn.Linear
)
model = model.eval()
# get model specific transforms (normalization, resize)
data_config = timm.data.resolve_model_data_config(model)
transforms = timm.data.create_transform(**data_config, is_training=False)
output = model(transforms(img).unsqueeze(0)) # output is (batch_size, num_features) shaped tensor
# or equivalently (without needing to set num_classes=0)
output = model.forward_features(transforms(img).unsqueeze(0))
# output is unpooled, a (1, 50, 768) shaped tensor
output = model.forward_head(output, pre_logits=True)
# output is a (1, num_features) shaped tensor
```
## Model Comparison
Explore the dataset and runtime metrics of this model in timm [model results](https://github.com/huggingface/pytorch-image-models/tree/main/results).
## Citation
```bibtex
@software{ilharco_gabriel_2021_5143773,
author = {Ilharco, Gabriel and
Wortsman, Mitchell and
Wightman, Ross and
Gordon, Cade and
Carlini, Nicholas and
Taori, Rohan and
Dave, Achal and
Shankar, Vaishaal and
Namkoong, Hongseok and
Miller, John and
Hajishirzi, Hannaneh and
Farhadi, Ali and
Schmidt, Ludwig},
title = {OpenCLIP},
month = jul,
year = 2021,
note = {If you use this software, please cite it as below.},
publisher = {Zenodo},
version = {0.1},
doi = {10.5281/zenodo.5143773},
url = {https://doi.org/10.5281/zenodo.5143773}
}
```
```bibtex
@article{cherti2022reproducible,
title={Reproducible scaling laws for contrastive language-image learning},
author={Cherti, Mehdi and Beaumont, Romain and Wightman, Ross and Wortsman, Mitchell and Ilharco, Gabriel and Gordon, Cade and Schuhmann, Christoph and Schmidt, Ludwig and Jitsev, Jenia},
journal={arXiv preprint arXiv:2212.07143},
year={2022}
}
```
```bibtex
@inproceedings{schuhmann2022laionb,
title={{LAION}-5B: An open large-scale dataset for training next generation image-text models},
author={Christoph Schuhmann and
Romain Beaumont and
Richard Vencu and
Cade W Gordon and
Ross Wightman and
Mehdi Cherti and
Theo Coombes and
Aarush Katta and
Clayton Mullis and
Mitchell Wortsman and
Patrick Schramowski and
Srivatsa R Kundurthy and
Katherine Crowson and
Ludwig Schmidt and
Robert Kaczmarczyk and
Jenia Jitsev},
booktitle={Thirty-sixth Conference on Neural Information Processing Systems Datasets and Benchmarks Track},
year={2022},
url={https://openreview.net/forum?id=M3Y74vmsMcY}
}
```
```bibtex
@article{dosovitskiy2020vit,
title={An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale},
author={Dosovitskiy, Alexey and Beyer, Lucas and Kolesnikov, Alexander and Weissenborn, Dirk and Zhai, Xiaohua and Unterthiner, Thomas and Dehghani, Mostafa and Minderer, Matthias and Heigold, Georg and Gelly, Sylvain and Uszkoreit, Jakob and Houlsby, Neil},
journal={ICLR},
year={2021}
}
```
```bibtex
@misc{rw2019timm,
author = {Ross Wightman},
title = {PyTorch Image Models},
year = {2019},
publisher = {GitHub},
journal = {GitHub repository},
doi = {10.5281/zenodo.4414861},
howpublished = {\url{https://github.com/huggingface/pytorch-image-models}}
}
```
| 5,759 | [
[
-0.0291748046875,
-0.027130126953125,
0.00937652587890625,
0.0104827880859375,
-0.0266571044921875,
-0.03314208984375,
-0.033355712890625,
-0.0304718017578125,
0.00864410400390625,
0.026947021484375,
-0.0304107666015625,
-0.042633056640625,
-0.05096435546875,
... |
pruas/BENT-PubMEdBERT-NER-Variant | 2023-01-15T16:20:05.000Z | [
"transformers",
"pytorch",
"bert",
"token-classification",
"en",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | token-classification | pruas | null | null | pruas/BENT-PubMEdBERT-NER-Variant | 3 | 538 | transformers | 2023-01-14T14:33:53 | ---
language:
- en
pipeline_tag: token-classification
---
Named Entity Recognition (NER) model to recognize variant entities. Here variant entity is a DNA-level or protein-level mutation as defined by the [Human Genome Variation Society nomenclature](http://varnomen.hgvs.org/).
[PubMedBERT](https://huggingface.co/microsoft/BiomedNLP-PubMedBERT-base-uncased-abstract-fulltext) fine-tuned on the following datasets:
- [tmVar](https://www.ncbi.nlm.nih.gov/research/bionlp/Data/): entity types "DNAMutation", "ProteinMutation", "SNP"
- [PGxCorpus](https://www.nature.com/articles/s41597-019-0342-9): entity type "Limited_variation"
- [SNPPhenA](https://figshare.com/s/f19191317056d6835b38): entity type "SNP" | 709 | [
[
-0.03289794921875,
-0.04583740234375,
0.018341064453125,
-0.027557373046875,
0.00028896331787109375,
0.025482177734375,
0.0239410400390625,
-0.032135009765625,
0.037506103515625,
0.047515869140625,
-0.0469970703125,
-0.0223236083984375,
-0.042449951171875,
0... |
digiplay/CuriousMerge2.5D_v40E | 2023-07-19T18:44:05.000Z | [
"diffusers",
"stable-diffusion",
"stable-diffusion-diffusers",
"text-to-image",
"license:other",
"endpoints_compatible",
"has_space",
"diffusers:StableDiffusionPipeline",
"region:us"
] | text-to-image | digiplay | null | null | digiplay/CuriousMerge2.5D_v40E | 3 | 538 | diffusers | 2023-06-13T09:57:51 | ---
license: other
tags:
- stable-diffusion
- stable-diffusion-diffusers
- text-to-image
- diffusers
inference: true
---
Model info:
https://civitai.com/models/79070?modelVersionId=94189
Author's page:
https://civitai.com/user/Cur1ous/models
https://ko-fi.com/cur1ous/
Very nice ❤️ and kind developer.
| 449 | [
[
-0.038726806640625,
-0.0260009765625,
0.0304718017578125,
0.03350830078125,
-0.0306243896484375,
-0.01448822021484375,
0.022491455078125,
-0.01495361328125,
0.04693603515625,
0.04400634765625,
-0.053466796875,
-0.0261688232421875,
-0.001438140869140625,
-0.0... |
vic-yes/fast-efmediastyle-class | 2023-07-24T01:42:39.000Z | [
"diffusers",
"text-to-image",
"stable-diffusion",
"license:creativeml-openrail-m",
"endpoints_compatible",
"has_space",
"diffusers:StableDiffusionPipeline",
"region:us"
] | text-to-image | vic-yes | null | null | vic-yes/fast-efmediastyle-class | 0 | 538 | diffusers | 2023-07-23T10:32:30 | ---
license: creativeml-openrail-m
tags:
- text-to-image
- stable-diffusion
---
### fast-efmediastyle-class Dreambooth model trained by vic-yes with [TheLastBen's fast-DreamBooth](https://colab.research.google.com/github/TheLastBen/fast-stable-diffusion/blob/main/fast-DreamBooth.ipynb) notebook
It can be used by modifying the instance_prompt: efmedia style
Test the concept via A1111 Colab [fast-Colab-A1111](https://colab.research.google.com/github/TheLastBen/fast-stable-diffusion/blob/main/fast_stable_diffusion_AUTOMATIC1111.ipynb)
Sample pictures of this concept:
| 575 | [
[
-0.03155517578125,
-0.08056640625,
0.043182373046875,
0.0224761962890625,
-0.0309600830078125,
0.01323699951171875,
0.006343841552734375,
-0.0160980224609375,
0.05938720703125,
0.0023345947265625,
-0.032257080078125,
-0.0217437744140625,
-0.01186370849609375,
... |
stillerman/this-rug-does-not-exist | 2023-08-02T21:17:29.000Z | [
"diffusers",
"tensorboard",
"stable-diffusion",
"stable-diffusion-diffusers",
"text-to-image",
"lora",
"license:creativeml-openrail-m",
"has_space",
"region:us"
] | text-to-image | stillerman | null | null | stillerman/this-rug-does-not-exist | 0 | 538 | diffusers | 2023-08-02T20:32:03 |
---
license: creativeml-openrail-m
base_model: runwayml/stable-diffusion-v1-5
tags:
- stable-diffusion
- stable-diffusion-diffusers
- text-to-image
- diffusers
- lora
inference: true
---
# LoRA text2image fine-tuning - stillerman/this-rug-does-not-exist
These are LoRA adaption weights for runwayml/stable-diffusion-v1-5. The weights were fine-tuned on the stillerman/rugs-1.9k-downloaded dataset. You can find some example images in the following.
| 554 | [
[
-0.0290374755859375,
-0.040496826171875,
0.0218353271484375,
0.031219482421875,
-0.037628173828125,
-0.0158233642578125,
0.027923583984375,
-0.0229034423828125,
0.0209808349609375,
0.054595947265625,
-0.0634765625,
-0.026123046875,
-0.05657958984375,
-0.0118... |
keremberke/yolov5s-clash-of-clans | 2022-12-30T20:47:44.000Z | [
"yolov5",
"tensorboard",
"yolo",
"vision",
"object-detection",
"pytorch",
"dataset:keremberke/clash-of-clans-object-detection",
"model-index",
"has_space",
"region:us"
] | object-detection | keremberke | null | null | keremberke/yolov5s-clash-of-clans | 1 | 537 | yolov5 | 2022-12-30T07:28:57 |
---
tags:
- yolov5
- yolo
- vision
- object-detection
- pytorch
library_name: yolov5
library_version: 7.0.6
inference: false
datasets:
- keremberke/clash-of-clans-object-detection
model-index:
- name: keremberke/yolov5s-clash-of-clans
results:
- task:
type: object-detection
dataset:
type: keremberke/clash-of-clans-object-detection
name: keremberke/clash-of-clans-object-detection
split: validation
metrics:
- type: precision # since mAP@0.5 is not available on hf.co/metrics
value: 0.8278313333523701 # min: 0.0 - max: 1.0
name: mAP@0.5
---
<div align="center">
<img width="640" alt="keremberke/yolov5s-clash-of-clans" src="https://huggingface.co/keremberke/yolov5s-clash-of-clans/resolve/main/sample_visuals.jpg">
</div>
### How to use
- Install [yolov5](https://github.com/fcakyon/yolov5-pip):
```bash
pip install -U yolov5
```
- Load model and perform prediction:
```python
import yolov5
# load model
model = yolov5.load('keremberke/yolov5s-clash-of-clans')
# set model parameters
model.conf = 0.25 # NMS confidence threshold
model.iou = 0.45 # NMS IoU threshold
model.agnostic = False # NMS class-agnostic
model.multi_label = False # NMS multiple labels per box
model.max_det = 1000 # maximum number of detections per image
# set image
img = 'https://github.com/ultralytics/yolov5/raw/master/data/images/zidane.jpg'
# perform inference
results = model(img, size=640)
# inference with test time augmentation
results = model(img, augment=True)
# parse results
predictions = results.pred[0]
boxes = predictions[:, :4] # x1, y1, x2, y2
scores = predictions[:, 4]
categories = predictions[:, 5]
# show detection bounding boxes on image
results.show()
# save results into "results/" folder
results.save(save_dir='results/')
```
- Finetune the model on your custom dataset:
```bash
yolov5 train --data data.yaml --img 640 --batch 16 --weights keremberke/yolov5s-clash-of-clans --epochs 10
```
**More models available at: [awesome-yolov5-models](https://github.com/keremberke/awesome-yolov5-models)**
| 2,095 | [
[
-0.054229736328125,
-0.03741455078125,
0.0204010009765625,
-0.0228729248046875,
-0.0201873779296875,
-0.006378173828125,
0.0124664306640625,
-0.042755126953125,
0.018310546875,
0.0237579345703125,
-0.053863525390625,
-0.056243896484375,
-0.046417236328125,
-... |
matei-dorian/segformer-b5-finetuned-human-parsing | 2023-05-29T13:38:36.000Z | [
"transformers",
"pytorch",
"tensorboard",
"safetensors",
"segformer",
"vision",
"image-segmentation",
"generated_from_trainer",
"license:other",
"endpoints_compatible",
"region:us"
] | image-segmentation | matei-dorian | null | null | matei-dorian/segformer-b5-finetuned-human-parsing | 9 | 537 | transformers | 2023-05-02T20:57:07 | ---
license: other
tags:
- vision
- image-segmentation
- generated_from_trainer
model-index:
- name: segformer-b5-finetuned-human-parsing
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# segformer-b5-finetuned-human-parsing
This model is a fine-tuned version of [nvidia/mit-b5](https://huggingface.co/nvidia/mit-b5) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.2292
- Mean Iou: 0.6258
- Mean Accuracy: 0.7547
- Overall Accuracy: 0.8256
- Accuracy Background: nan
- Accuracy Hat: 0.8561
- Accuracy Hair: 0.8974
- Accuracy Sunglasses: 0.7540
- Accuracy Upper-clothes: 0.8553
- Accuracy Skirt: 0.7026
- Accuracy Pants: 0.8913
- Accuracy Dress: 0.7525
- Accuracy Belt: 0.4251
- Accuracy Left-shoe: 0.6014
- Accuracy Right-shoe: 0.6374
- Accuracy Face: 0.9094
- Accuracy Left-leg: 0.8452
- Accuracy Right-leg: 0.8343
- Accuracy Left-arm: 0.8506
- Accuracy Right-arm: 0.8287
- Accuracy Bag: 0.8232
- Accuracy Scarf: 0.3662
- Iou Background: 0.0
- Iou Hat: 0.7625
- Iou Hair: 0.8171
- Iou Sunglasses: 0.6400
- Iou Upper-clothes: 0.7700
- Iou Skirt: 0.6211
- Iou Pants: 0.7788
- Iou Dress: 0.5512
- Iou Belt: 0.3564
- Iou Left-shoe: 0.5032
- Iou Right-shoe: 0.5381
- Iou Face: 0.8294
- Iou Left-leg: 0.7412
- Iou Right-leg: 0.7591
- Iou Left-arm: 0.7579
- Iou Right-arm: 0.7705
- Iou Bag: 0.7729
- Iou Scarf: 0.2956
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 6e-05
- train_batch_size: 2
- eval_batch_size: 2
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 15
### Training results
| Training Loss | Epoch | Step | Validation Loss | Mean Iou | Mean Accuracy | Overall Accuracy | Accuracy Background | Accuracy Hat | Accuracy Hair | Accuracy Sunglasses | Accuracy Upper-clothes | Accuracy Skirt | Accuracy Pants | Accuracy Dress | Accuracy Belt | Accuracy Left-shoe | Accuracy Right-shoe | Accuracy Face | Accuracy Left-leg | Accuracy Right-leg | Accuracy Left-arm | Accuracy Right-arm | Accuracy Bag | Accuracy Scarf | Iou Background | Iou Hat | Iou Hair | Iou Sunglasses | Iou Upper-clothes | Iou Skirt | Iou Pants | Iou Dress | Iou Belt | Iou Left-shoe | Iou Right-shoe | Iou Face | Iou Left-leg | Iou Right-leg | Iou Left-arm | Iou Right-arm | Iou Bag | Iou Scarf |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:-------------:|:----------------:|:-------------------:|:------------:|:-------------:|:-------------------:|:----------------------:|:--------------:|:--------------:|:--------------:|:-------------:|:------------------:|:-------------------:|:-------------:|:-----------------:|:------------------:|:-----------------:|:------------------:|:------------:|:--------------:|:--------------:|:-------:|:--------:|:--------------:|:-----------------:|:---------:|:---------:|:---------:|:--------:|:-------------:|:--------------:|:--------:|:------------:|:-------------:|:------------:|:-------------:|:-------:|:---------:|
| 1.1597 | 0.04 | 20 | 1.5815 | 0.1179 | 0.1991 | 0.4296 | nan | 0.0060 | 0.6905 | 0.0 | 0.7657 | 0.0108 | 0.6431 | 0.2946 | 0.0 | 0.0288 | 0.0366 | 0.1480 | 0.0025 | 0.5692 | 0.0096 | 0.0259 | 0.1537 | 0.0 | 0.0 | 0.0051 | 0.4253 | 0.0 | 0.5199 | 0.0103 | 0.3388 | 0.1700 | 0.0 | 0.0258 | 0.0338 | 0.0895 | 0.0025 | 0.3162 | 0.0094 | 0.0253 | 0.1495 | 0.0 |
| 0.6963 | 0.08 | 40 | 0.8073 | 0.1759 | 0.2719 | 0.4628 | nan | 0.0015 | 0.8699 | 0.0 | 0.4736 | 0.4932 | 0.5141 | 0.6775 | 0.0 | 0.0062 | 0.1038 | 0.5301 | 0.0916 | 0.5071 | 0.0092 | 0.0549 | 0.2889 | 0.0 | 0.0 | 0.0015 | 0.6169 | 0.0 | 0.4242 | 0.2202 | 0.3522 | 0.2251 | 0.0 | 0.0062 | 0.0904 | 0.4914 | 0.0852 | 0.3160 | 0.0092 | 0.0541 | 0.2731 | 0.0 |
| 0.5786 | 0.12 | 60 | 0.6136 | 0.2538 | 0.3642 | 0.4679 | nan | 0.0180 | 0.8122 | 0.0 | 0.1998 | 0.0000 | 0.6621 | 0.8592 | 0.0 | 0.1440 | 0.2772 | 0.8381 | 0.4032 | 0.6068 | 0.4182 | 0.3097 | 0.6434 | 0.0 | 0.0 | 0.0179 | 0.6760 | 0.0 | 0.1951 | 0.0000 | 0.5471 | 0.2218 | 0.0 | 0.1147 | 0.2032 | 0.6403 | 0.3189 | 0.4204 | 0.3505 | 0.2947 | 0.5676 | 0.0 |
| 0.324 | 0.16 | 80 | 0.4282 | 0.2893 | 0.4044 | 0.6041 | nan | 0.0147 | 0.7890 | 0.0 | 0.8222 | 0.7984 | 0.6646 | 0.1038 | 0.0 | 0.0896 | 0.3308 | 0.8277 | 0.4099 | 0.6839 | 0.2401 | 0.5474 | 0.5521 | 0.0 | 0.0 | 0.0147 | 0.6800 | 0.0 | 0.6159 | 0.3049 | 0.5913 | 0.0938 | 0.0 | 0.0802 | 0.2394 | 0.6598 | 0.3178 | 0.4504 | 0.2288 | 0.4189 | 0.5113 | 0.0 |
| 0.297 | 0.2 | 100 | 0.4020 | 0.3034 | 0.4230 | 0.6332 | nan | 0.0048 | 0.8076 | 0.0080 | 0.9042 | 0.6567 | 0.8036 | 0.0317 | 0.0 | 0.0481 | 0.5298 | 0.7728 | 0.2589 | 0.7232 | 0.5941 | 0.3839 | 0.6643 | 0.0 | 0.0 | 0.0048 | 0.6708 | 0.0080 | 0.6300 | 0.3836 | 0.5929 | 0.0314 | 0.0 | 0.0441 | 0.3152 | 0.6726 | 0.2420 | 0.4745 | 0.4532 | 0.3631 | 0.5759 | 0.0 |
| 0.2608 | 0.24 | 120 | 0.3538 | 0.3444 | 0.4554 | 0.6504 | nan | 0.2922 | 0.8078 | 0.0753 | 0.8472 | 0.0425 | 0.6961 | 0.6197 | 0.0 | 0.2550 | 0.3074 | 0.8020 | 0.5636 | 0.6895 | 0.3779 | 0.6930 | 0.6734 | 0.0 | 0.0 | 0.2757 | 0.6940 | 0.0747 | 0.6457 | 0.0419 | 0.6098 | 0.3611 | 0.0 | 0.1849 | 0.2412 | 0.7038 | 0.4513 | 0.5038 | 0.3439 | 0.4760 | 0.5915 | 0.0 |
| 0.3306 | 0.28 | 140 | 0.3281 | 0.3562 | 0.4736 | 0.6560 | nan | 0.4111 | 0.8576 | 0.1953 | 0.8081 | 0.6916 | 0.7888 | 0.3489 | 0.0 | 0.0809 | 0.3612 | 0.8132 | 0.0622 | 0.7078 | 0.6328 | 0.5437 | 0.7482 | 0.0 | 0.0 | 0.3895 | 0.7227 | 0.1857 | 0.6777 | 0.3750 | 0.6015 | 0.2749 | 0.0 | 0.0740 | 0.2602 | 0.7070 | 0.0612 | 0.4348 | 0.5114 | 0.4966 | 0.6385 | 0.0 |
| 0.364 | 0.32 | 160 | 0.3368 | 0.3689 | 0.4836 | 0.6531 | nan | 0.3898 | 0.8453 | 0.1743 | 0.9269 | 0.2493 | 0.7922 | 0.0842 | 0.0 | 0.4874 | 0.2384 | 0.8116 | 0.6226 | 0.5731 | 0.6049 | 0.6620 | 0.7597 | 0.0 | 0.0 | 0.3746 | 0.7246 | 0.1690 | 0.6015 | 0.1998 | 0.5942 | 0.0786 | 0.0 | 0.2682 | 0.1904 | 0.7015 | 0.4781 | 0.4781 | 0.5452 | 0.5804 | 0.6562 | 0.0 |
| 0.635 | 0.36 | 180 | 0.3092 | 0.3699 | 0.4903 | 0.6319 | nan | 0.4996 | 0.8387 | 0.2136 | 0.6184 | 0.0129 | 0.7920 | 0.8199 | 0.0 | 0.1895 | 0.3028 | 0.8307 | 0.7258 | 0.3386 | 0.7480 | 0.6543 | 0.7511 | 0.0 | 0.0 | 0.4613 | 0.7126 | 0.2042 | 0.5589 | 0.0128 | 0.6658 | 0.3529 | 0.0 | 0.1622 | 0.2426 | 0.7363 | 0.4646 | 0.3144 | 0.5794 | 0.5575 | 0.6321 | 0.0 |
| 0.1464 | 0.4 | 200 | 0.3306 | 0.3809 | 0.5041 | 0.6544 | nan | 0.6110 | 0.8337 | 0.2420 | 0.8913 | 0.8862 | 0.6492 | 0.0004 | 0.0 | 0.2888 | 0.2949 | 0.8514 | 0.4630 | 0.7751 | 0.7020 | 0.5429 | 0.5386 | 0.0 | 0.0 | 0.5329 | 0.7348 | 0.2331 | 0.6567 | 0.3661 | 0.5769 | 0.0004 | 0.0 | 0.2221 | 0.2333 | 0.7431 | 0.4133 | 0.5478 | 0.5718 | 0.5125 | 0.5107 | 0.0 |
| 0.2257 | 0.44 | 220 | 0.2751 | 0.4089 | 0.5400 | 0.6752 | nan | 0.6851 | 0.8458 | 0.4204 | 0.7241 | 0.1085 | 0.7997 | 0.7657 | 0.0 | 0.2458 | 0.4039 | 0.8858 | 0.7863 | 0.3199 | 0.7405 | 0.6974 | 0.7508 | 0.0 | 0.0 | 0.5815 | 0.7437 | 0.3776 | 0.6458 | 0.1033 | 0.6526 | 0.3966 | 0.0 | 0.2027 | 0.3078 | 0.7438 | 0.4680 | 0.2966 | 0.6204 | 0.5942 | 0.6260 | 0.0 |
| 0.3069 | 0.48 | 240 | 0.2614 | 0.4163 | 0.5499 | 0.6868 | nan | 0.6246 | 0.8571 | 0.3130 | 0.7765 | 0.8266 | 0.7786 | 0.3212 | 0.0 | 0.3560 | 0.3736 | 0.8579 | 0.1780 | 0.8761 | 0.7423 | 0.7693 | 0.6970 | 0.0 | 0.0 | 0.5597 | 0.7370 | 0.2931 | 0.6733 | 0.4032 | 0.6889 | 0.2487 | 0.0 | 0.2662 | 0.2901 | 0.7425 | 0.1724 | 0.4957 | 0.6373 | 0.6376 | 0.6470 | 0.0 |
| 0.1454 | 0.52 | 260 | 0.2563 | 0.4316 | 0.5610 | 0.6965 | nan | 0.6707 | 0.8388 | 0.5572 | 0.7616 | 0.3854 | 0.7280 | 0.7114 | 0.0 | 0.1934 | 0.3621 | 0.8718 | 0.7860 | 0.6140 | 0.7403 | 0.5340 | 0.7820 | 0.0 | 0.0 | 0.5710 | 0.7446 | 0.4497 | 0.6637 | 0.3125 | 0.6624 | 0.4219 | 0.0 | 0.1731 | 0.2862 | 0.7295 | 0.5339 | 0.5054 | 0.5742 | 0.4967 | 0.6449 | 0.0 |
| 0.1522 | 0.56 | 280 | 0.2521 | 0.4327 | 0.5567 | 0.7138 | nan | 0.5098 | 0.9135 | 0.3399 | 0.8898 | 0.5537 | 0.7508 | 0.2922 | 0.0 | 0.3367 | 0.2484 | 0.8388 | 0.7460 | 0.7191 | 0.7496 | 0.7996 | 0.7753 | 0.0 | 0.0 | 0.4902 | 0.7541 | 0.3196 | 0.6924 | 0.3853 | 0.6261 | 0.2512 | 0.0 | 0.2575 | 0.2171 | 0.7393 | 0.5563 | 0.5633 | 0.6403 | 0.6335 | 0.6621 | 0.0 |
| 0.1872 | 0.6 | 300 | 0.2359 | 0.4557 | 0.5797 | 0.7247 | nan | 0.6901 | 0.8832 | 0.5498 | 0.8857 | 0.6636 | 0.7843 | 0.3983 | 0.0 | 0.4549 | 0.2292 | 0.8147 | 0.7126 | 0.6223 | 0.7467 | 0.7014 | 0.7185 | 0.0 | 0.0 | 0.5881 | 0.7556 | 0.4621 | 0.7131 | 0.4264 | 0.6506 | 0.3311 | 0.0 | 0.3025 | 0.1975 | 0.7350 | 0.5635 | 0.5513 | 0.6505 | 0.6318 | 0.6439 | 0.0 |
| 0.2512 | 0.64 | 320 | 0.2601 | 0.4363 | 0.5599 | 0.6801 | nan | 0.6470 | 0.8482 | 0.3819 | 0.6317 | 0.2525 | 0.7437 | 0.8755 | 0.0 | 0.1737 | 0.5412 | 0.8907 | 0.5915 | 0.7943 | 0.7177 | 0.7437 | 0.6852 | 0.0 | 0.0 | 0.5580 | 0.7612 | 0.3645 | 0.5718 | 0.2362 | 0.6671 | 0.3836 | 0.0 | 0.1621 | 0.3641 | 0.7486 | 0.5132 | 0.5865 | 0.6472 | 0.6479 | 0.6409 | 0.0 |
| 0.6521 | 0.68 | 340 | 0.2286 | 0.4716 | 0.6024 | 0.7351 | nan | 0.6559 | 0.8492 | 0.3976 | 0.7517 | 0.5818 | 0.7622 | 0.7422 | 0.0 | 0.5277 | 0.2673 | 0.9098 | 0.7514 | 0.6903 | 0.7853 | 0.7795 | 0.7896 | 0.0 | 0.0 | 0.5839 | 0.7531 | 0.3761 | 0.6829 | 0.4643 | 0.6722 | 0.4762 | 0.0 | 0.3375 | 0.2261 | 0.7551 | 0.5838 | 0.5730 | 0.6548 | 0.6501 | 0.6987 | 0.0 |
| 0.1734 | 0.72 | 360 | 0.2511 | 0.4464 | 0.5731 | 0.7074 | nan | 0.6326 | 0.8339 | 0.5953 | 0.8987 | 0.8731 | 0.7575 | 0.1617 | 0.0 | 0.2314 | 0.5741 | 0.8497 | 0.6140 | 0.6973 | 0.5250 | 0.7576 | 0.7406 | 0.0 | 0.0 | 0.5777 | 0.7535 | 0.4840 | 0.6597 | 0.5208 | 0.6261 | 0.1507 | 0.0 | 0.2110 | 0.3920 | 0.7579 | 0.5436 | 0.5825 | 0.4959 | 0.6090 | 0.6702 | 0.0 |
| 0.1596 | 0.76 | 380 | 0.2303 | 0.4702 | 0.5922 | 0.7351 | nan | 0.6336 | 0.8772 | 0.4196 | 0.8004 | 0.4307 | 0.7034 | 0.7554 | 0.0 | 0.2914 | 0.4563 | 0.8930 | 0.7517 | 0.7146 | 0.7649 | 0.7420 | 0.8336 | 0.0 | 0.0 | 0.5854 | 0.7635 | 0.3937 | 0.6838 | 0.3957 | 0.6295 | 0.4857 | 0.0 | 0.2497 | 0.3439 | 0.7526 | 0.6021 | 0.6055 | 0.6591 | 0.6473 | 0.6657 | 0.0 |
| 0.1359 | 0.8 | 400 | 0.2332 | 0.4592 | 0.5773 | 0.7182 | nan | 0.6759 | 0.8564 | 0.5305 | 0.8221 | 0.4710 | 0.8463 | 0.5733 | 0.0 | 0.2630 | 0.5031 | 0.8314 | 0.7079 | 0.7295 | 0.7449 | 0.7233 | 0.5357 | 0.0 | 0.0 | 0.6046 | 0.7593 | 0.4670 | 0.7005 | 0.3678 | 0.5672 | 0.4327 | 0.0 | 0.2265 | 0.3566 | 0.7593 | 0.5975 | 0.6161 | 0.6456 | 0.6470 | 0.5178 | 0.0 |
| 0.2014 | 0.84 | 420 | 0.2298 | 0.4709 | 0.5957 | 0.7268 | nan | 0.6207 | 0.8571 | 0.5146 | 0.7670 | 0.6367 | 0.6238 | 0.7682 | 0.0 | 0.2470 | 0.4863 | 0.8939 | 0.5487 | 0.8665 | 0.7735 | 0.7827 | 0.7405 | 0.0 | 0.0 | 0.5729 | 0.7737 | 0.4637 | 0.6774 | 0.4588 | 0.5840 | 0.4656 | 0.0 | 0.2219 | 0.3668 | 0.7764 | 0.5020 | 0.5959 | 0.6641 | 0.6698 | 0.6833 | 0.0 |
| 0.137 | 0.88 | 440 | 0.2260 | 0.4824 | 0.6147 | 0.7401 | nan | 0.7197 | 0.8823 | 0.6023 | 0.8544 | 0.9048 | 0.7837 | 0.3094 | 0.0245 | 0.2877 | 0.4592 | 0.8905 | 0.6846 | 0.8472 | 0.7109 | 0.7647 | 0.7230 | 0.0 | 0.0 | 0.6089 | 0.7638 | 0.5071 | 0.7154 | 0.5084 | 0.6749 | 0.2801 | 0.0227 | 0.2486 | 0.3499 | 0.7679 | 0.6127 | 0.6436 | 0.6445 | 0.6729 | 0.6626 | 0.0 |
| 0.2494 | 0.92 | 460 | 0.2275 | 0.4721 | 0.5997 | 0.7321 | nan | 0.6265 | 0.8452 | 0.6870 | 0.8116 | 0.4266 | 0.8250 | 0.7026 | 0.0498 | 0.5651 | 0.1855 | 0.8745 | 0.7293 | 0.6387 | 0.6783 | 0.8080 | 0.7416 | 0.0 | 0.0 | 0.5764 | 0.7653 | 0.5312 | 0.7021 | 0.3635 | 0.6488 | 0.4468 | 0.0475 | 0.3420 | 0.1695 | 0.7764 | 0.5981 | 0.5821 | 0.6149 | 0.6599 | 0.6740 | 0.0 |
| 0.2788 | 0.96 | 480 | 0.2315 | 0.4670 | 0.5977 | 0.7292 | nan | 0.7105 | 0.8142 | 0.4169 | 0.8597 | 0.8573 | 0.7707 | 0.3171 | 0.0476 | 0.2514 | 0.4432 | 0.9214 | 0.7332 | 0.6989 | 0.8245 | 0.6729 | 0.7954 | 0.0255 | 0.0 | 0.6051 | 0.7556 | 0.3986 | 0.7114 | 0.4588 | 0.6423 | 0.2727 | 0.0438 | 0.2215 | 0.3468 | 0.7650 | 0.6030 | 0.6007 | 0.6432 | 0.6180 | 0.6945 | 0.0253 |
| 0.1254 | 1.0 | 500 | 0.2176 | 0.4955 | 0.6287 | 0.7450 | nan | 0.7081 | 0.9094 | 0.4628 | 0.7437 | 0.5938 | 0.7126 | 0.7410 | 0.0560 | 0.3971 | 0.5239 | 0.8992 | 0.7446 | 0.8258 | 0.8028 | 0.7613 | 0.8041 | 0.0014 | 0.0 | 0.6242 | 0.7741 | 0.4367 | 0.6877 | 0.4856 | 0.6276 | 0.4823 | 0.0535 | 0.3136 | 0.3836 | 0.7687 | 0.6347 | 0.6510 | 0.6615 | 0.6529 | 0.6795 | 0.0014 |
| 0.2625 | 1.04 | 520 | 0.2270 | 0.5000 | 0.6339 | 0.7411 | nan | 0.7844 | 0.8633 | 0.6442 | 0.8202 | 0.3913 | 0.6661 | 0.7393 | 0.0533 | 0.4684 | 0.5305 | 0.8686 | 0.6858 | 0.8024 | 0.7433 | 0.7895 | 0.8522 | 0.0729 | 0.0 | 0.6637 | 0.7685 | 0.5378 | 0.7150 | 0.3328 | 0.6169 | 0.4502 | 0.0468 | 0.3310 | 0.3732 | 0.7769 | 0.6214 | 0.6602 | 0.6614 | 0.6823 | 0.6913 | 0.0714 |
| 0.2871 | 1.08 | 540 | 0.2072 | 0.5091 | 0.6337 | 0.7630 | nan | 0.7427 | 0.8718 | 0.5674 | 0.8080 | 0.6131 | 0.7855 | 0.7672 | 0.0584 | 0.3031 | 0.4535 | 0.8750 | 0.6763 | 0.8457 | 0.8027 | 0.7491 | 0.7710 | 0.0820 | 0.0 | 0.6471 | 0.7706 | 0.5092 | 0.7250 | 0.4737 | 0.6887 | 0.5152 | 0.0507 | 0.2643 | 0.3623 | 0.7788 | 0.6085 | 0.6565 | 0.6659 | 0.6633 | 0.7025 | 0.0816 |
| 0.1481 | 1.12 | 560 | 0.2250 | 0.4824 | 0.5946 | 0.7494 | nan | 0.6480 | 0.8561 | 0.5148 | 0.8637 | 0.5174 | 0.7904 | 0.6671 | 0.0029 | 0.3782 | 0.2824 | 0.8794 | 0.6807 | 0.7755 | 0.6985 | 0.7431 | 0.8058 | 0.0039 | 0.0 | 0.6099 | 0.7755 | 0.4755 | 0.7081 | 0.4454 | 0.6483 | 0.4567 | 0.0029 | 0.2864 | 0.2456 | 0.7798 | 0.6012 | 0.6408 | 0.6339 | 0.6715 | 0.6978 | 0.0039 |
| 0.0995 | 1.16 | 580 | 0.2084 | 0.5218 | 0.6570 | 0.7698 | nan | 0.7706 | 0.8532 | 0.4978 | 0.7874 | 0.7761 | 0.8102 | 0.6761 | 0.0 | 0.4886 | 0.4884 | 0.9113 | 0.7646 | 0.8476 | 0.8129 | 0.7507 | 0.7485 | 0.1856 | 0.0 | 0.6194 | 0.7661 | 0.4641 | 0.7200 | 0.5843 | 0.6730 | 0.5042 | 0.0 | 0.3497 | 0.3711 | 0.7790 | 0.6542 | 0.6835 | 0.6823 | 0.6749 | 0.6959 | 0.1715 |
| 0.2912 | 1.2 | 600 | 0.2166 | 0.5136 | 0.6304 | 0.7632 | nan | 0.6870 | 0.8862 | 0.4891 | 0.7752 | 0.6264 | 0.8143 | 0.8202 | 0.0227 | 0.2578 | 0.4830 | 0.8932 | 0.7564 | 0.7366 | 0.7746 | 0.7678 | 0.7558 | 0.1712 | 0.0 | 0.6243 | 0.7791 | 0.4579 | 0.6983 | 0.5530 | 0.6676 | 0.5248 | 0.0222 | 0.2333 | 0.3786 | 0.7820 | 0.6438 | 0.6651 | 0.6773 | 0.6749 | 0.7018 | 0.1610 |
| 0.1874 | 1.24 | 620 | 0.2280 | 0.5053 | 0.6296 | 0.7525 | nan | 0.7070 | 0.8689 | 0.5348 | 0.8275 | 0.3452 | 0.8441 | 0.7748 | 0.0643 | 0.4207 | 0.4251 | 0.8840 | 0.7698 | 0.6921 | 0.7271 | 0.7322 | 0.7544 | 0.3318 | 0.0 | 0.6387 | 0.7766 | 0.4873 | 0.7210 | 0.3283 | 0.6163 | 0.5014 | 0.0600 | 0.3252 | 0.3434 | 0.7750 | 0.6349 | 0.6336 | 0.6531 | 0.6560 | 0.6995 | 0.2448 |
| 0.1634 | 1.28 | 640 | 0.2052 | 0.5100 | 0.6350 | 0.7638 | nan | 0.7069 | 0.8648 | 0.6021 | 0.8461 | 0.6408 | 0.8499 | 0.6889 | 0.0 | 0.3772 | 0.5718 | 0.8730 | 0.7073 | 0.5765 | 0.7283 | 0.7600 | 0.7655 | 0.2362 | 0.0 | 0.6105 | 0.7777 | 0.5233 | 0.7372 | 0.5287 | 0.6565 | 0.5185 | 0.0 | 0.3063 | 0.4062 | 0.7743 | 0.5688 | 0.5413 | 0.6500 | 0.6721 | 0.6956 | 0.2133 |
| 0.1894 | 1.32 | 660 | 0.2169 | 0.5104 | 0.6553 | 0.7601 | nan | 0.7721 | 0.8902 | 0.7412 | 0.8309 | 0.9266 | 0.6974 | 0.5353 | 0.0008 | 0.4742 | 0.4474 | 0.8442 | 0.8150 | 0.7319 | 0.7803 | 0.7767 | 0.7605 | 0.1160 | 0.0 | 0.6506 | 0.7883 | 0.5373 | 0.7116 | 0.5472 | 0.6493 | 0.4321 | 0.0008 | 0.3256 | 0.3422 | 0.7644 | 0.6199 | 0.6389 | 0.6849 | 0.6873 | 0.6919 | 0.1141 |
| 0.0769 | 1.36 | 680 | 0.1993 | 0.5250 | 0.6596 | 0.7756 | nan | 0.8044 | 0.8515 | 0.6711 | 0.8456 | 0.6474 | 0.7909 | 0.7083 | 0.0630 | 0.3173 | 0.6517 | 0.9003 | 0.6833 | 0.8527 | 0.8065 | 0.8162 | 0.7165 | 0.0872 | 0.0 | 0.6318 | 0.7755 | 0.5553 | 0.7207 | 0.5836 | 0.6787 | 0.5292 | 0.0625 | 0.2650 | 0.4130 | 0.7788 | 0.6131 | 0.6713 | 0.7043 | 0.7024 | 0.6790 | 0.0866 |
| 0.2145 | 1.4 | 700 | 0.2052 | 0.5114 | 0.6438 | 0.7630 | nan | 0.7518 | 0.8628 | 0.5961 | 0.8763 | 0.9097 | 0.7924 | 0.4449 | 0.0273 | 0.4497 | 0.3682 | 0.8965 | 0.8234 | 0.6068 | 0.8065 | 0.6396 | 0.8432 | 0.2497 | 0.0 | 0.6262 | 0.7776 | 0.5260 | 0.7240 | 0.6034 | 0.6991 | 0.4150 | 0.0270 | 0.3297 | 0.3073 | 0.7805 | 0.6198 | 0.5743 | 0.6511 | 0.6071 | 0.7187 | 0.2189 |
| 0.2162 | 1.44 | 720 | 0.2290 | 0.5246 | 0.6727 | 0.7519 | nan | 0.8003 | 0.8895 | 0.7155 | 0.7305 | 0.4570 | 0.8400 | 0.8071 | 0.0599 | 0.2933 | 0.5509 | 0.8700 | 0.7052 | 0.8386 | 0.7501 | 0.8070 | 0.8038 | 0.5178 | 0.0 | 0.7009 | 0.7910 | 0.5717 | 0.6618 | 0.4195 | 0.6924 | 0.4677 | 0.0587 | 0.2536 | 0.4050 | 0.7823 | 0.6246 | 0.6658 | 0.6718 | 0.6930 | 0.7369 | 0.2463 |
| 0.1751 | 1.48 | 740 | 0.2073 | 0.5376 | 0.6734 | 0.7847 | nan | 0.8054 | 0.8711 | 0.6506 | 0.8714 | 0.7615 | 0.7720 | 0.6263 | 0.1874 | 0.4293 | 0.4568 | 0.9023 | 0.8568 | 0.7712 | 0.7206 | 0.8132 | 0.8180 | 0.1342 | 0.0 | 0.7205 | 0.7976 | 0.5541 | 0.7385 | 0.5644 | 0.6886 | 0.4901 | 0.1510 | 0.3297 | 0.3632 | 0.7814 | 0.6510 | 0.6618 | 0.6457 | 0.6798 | 0.7289 | 0.1310 |
| 0.1175 | 1.52 | 760 | 0.2123 | 0.5114 | 0.6336 | 0.7694 | nan | 0.6736 | 0.8370 | 0.6304 | 0.8724 | 0.7794 | 0.7886 | 0.6708 | 0.0890 | 0.2305 | 0.6798 | 0.9045 | 0.5193 | 0.7556 | 0.7443 | 0.7395 | 0.7734 | 0.0836 | 0.0 | 0.6314 | 0.7744 | 0.5497 | 0.7306 | 0.5991 | 0.6411 | 0.5151 | 0.0705 | 0.2169 | 0.4380 | 0.7806 | 0.4983 | 0.6112 | 0.6768 | 0.6739 | 0.7150 | 0.0824 |
| 0.1317 | 1.56 | 780 | 0.2097 | 0.5035 | 0.6318 | 0.7713 | nan | 0.3686 | 0.9006 | 0.6208 | 0.8267 | 0.8135 | 0.7586 | 0.6929 | 0.0769 | 0.5944 | 0.2629 | 0.9171 | 0.8806 | 0.6178 | 0.7197 | 0.8212 | 0.7743 | 0.0936 | 0.0 | 0.3669 | 0.7756 | 0.5497 | 0.7150 | 0.6423 | 0.6759 | 0.5331 | 0.0657 | 0.3886 | 0.2448 | 0.7772 | 0.6177 | 0.5813 | 0.6439 | 0.6832 | 0.7088 | 0.0931 |
| 0.5482 | 1.6 | 800 | 0.2511 | 0.5037 | 0.6255 | 0.7414 | nan | 0.7498 | 0.8591 | 0.6984 | 0.7940 | 0.4886 | 0.7867 | 0.8255 | 0.0677 | 0.3048 | 0.4688 | 0.8573 | 0.6227 | 0.7895 | 0.7323 | 0.7148 | 0.6241 | 0.2496 | 0.0 | 0.6732 | 0.7722 | 0.5691 | 0.6858 | 0.4315 | 0.6297 | 0.4643 | 0.0620 | 0.2595 | 0.3642 | 0.7790 | 0.5765 | 0.6519 | 0.6686 | 0.6574 | 0.6024 | 0.2200 |
| 0.0895 | 1.64 | 820 | 0.1973 | 0.5191 | 0.6552 | 0.7673 | nan | 0.6921 | 0.8844 | 0.4919 | 0.8472 | 0.6608 | 0.7842 | 0.6546 | 0.2664 | 0.4594 | 0.4925 | 0.9224 | 0.8699 | 0.6010 | 0.8740 | 0.5805 | 0.8105 | 0.2468 | 0.0 | 0.6533 | 0.7801 | 0.4672 | 0.7328 | 0.5569 | 0.6945 | 0.5016 | 0.2105 | 0.3565 | 0.3858 | 0.7737 | 0.6031 | 0.5611 | 0.5950 | 0.5277 | 0.7232 | 0.2217 |
| 0.1804 | 1.68 | 840 | 0.2026 | 0.5308 | 0.6584 | 0.7736 | nan | 0.7891 | 0.8563 | 0.6565 | 0.8528 | 0.6089 | 0.7999 | 0.7005 | 0.0741 | 0.2858 | 0.6423 | 0.9035 | 0.7926 | 0.7474 | 0.7500 | 0.7516 | 0.7824 | 0.1997 | 0.0 | 0.6848 | 0.7815 | 0.5627 | 0.7391 | 0.5112 | 0.6788 | 0.4969 | 0.0673 | 0.2622 | 0.4456 | 0.7909 | 0.6476 | 0.6569 | 0.6618 | 0.6640 | 0.7139 | 0.1888 |
| 0.1271 | 1.72 | 860 | 0.2134 | 0.5227 | 0.6505 | 0.7693 | nan | 0.7656 | 0.8645 | 0.6724 | 0.9055 | 0.6357 | 0.7807 | 0.5336 | 0.0838 | 0.5199 | 0.4139 | 0.9021 | 0.8526 | 0.7135 | 0.7894 | 0.7737 | 0.7407 | 0.1103 | 0.0 | 0.6177 | 0.7821 | 0.5747 | 0.7212 | 0.5627 | 0.6421 | 0.4449 | 0.0762 | 0.3731 | 0.3486 | 0.7872 | 0.6535 | 0.6449 | 0.6892 | 0.6914 | 0.6913 | 0.1075 |
| 0.1344 | 1.76 | 880 | 0.2099 | 0.5269 | 0.6527 | 0.7711 | nan | 0.7985 | 0.8741 | 0.6237 | 0.8356 | 0.5284 | 0.8054 | 0.7358 | 0.0469 | 0.3616 | 0.5220 | 0.9019 | 0.6880 | 0.8126 | 0.8358 | 0.7745 | 0.7948 | 0.1563 | 0.0 | 0.6922 | 0.7886 | 0.5563 | 0.7230 | 0.4772 | 0.6475 | 0.5068 | 0.0436 | 0.3041 | 0.3968 | 0.7794 | 0.6338 | 0.6822 | 0.6952 | 0.6896 | 0.7182 | 0.1498 |
| 0.2751 | 1.8 | 900 | 0.2006 | 0.5334 | 0.6488 | 0.7806 | nan | 0.7400 | 0.8550 | 0.5263 | 0.8847 | 0.6187 | 0.8032 | 0.6862 | 0.0858 | 0.4811 | 0.4224 | 0.9162 | 0.7803 | 0.7360 | 0.7854 | 0.7527 | 0.7963 | 0.1590 | 0.0 | 0.6939 | 0.7836 | 0.4954 | 0.7498 | 0.5176 | 0.6805 | 0.5075 | 0.0725 | 0.3595 | 0.3539 | 0.7824 | 0.6646 | 0.6782 | 0.6886 | 0.6885 | 0.7303 | 0.1537 |
| 0.2685 | 1.84 | 920 | 0.2153 | 0.5265 | 0.6600 | 0.7598 | nan | 0.7896 | 0.8871 | 0.4589 | 0.8001 | 0.3307 | 0.8338 | 0.7796 | 0.2192 | 0.4367 | 0.4581 | 0.9048 | 0.8316 | 0.7681 | 0.8377 | 0.7482 | 0.7620 | 0.3733 | 0.0 | 0.6760 | 0.7832 | 0.4428 | 0.7128 | 0.3263 | 0.6632 | 0.5039 | 0.1754 | 0.3545 | 0.3853 | 0.7758 | 0.6553 | 0.6665 | 0.6908 | 0.6811 | 0.6933 | 0.2913 |
| 0.5729 | 1.88 | 940 | 0.2057 | 0.5343 | 0.6737 | 0.7641 | nan | 0.8351 | 0.8681 | 0.5588 | 0.7823 | 0.5378 | 0.8769 | 0.6844 | 0.2025 | 0.4204 | 0.5736 | 0.9000 | 0.6586 | 0.8633 | 0.7572 | 0.8501 | 0.8008 | 0.2837 | 0.0 | 0.6697 | 0.7834 | 0.5193 | 0.7093 | 0.4643 | 0.6734 | 0.4657 | 0.1703 | 0.3568 | 0.4435 | 0.7947 | 0.5896 | 0.6450 | 0.6871 | 0.7106 | 0.6983 | 0.2363 |
| 0.0862 | 1.92 | 960 | 0.2208 | 0.5155 | 0.6363 | 0.7593 | nan | 0.6683 | 0.8670 | 0.6014 | 0.8336 | 0.9151 | 0.7537 | 0.6623 | 0.0948 | 0.5015 | 0.4279 | 0.8643 | 0.5706 | 0.5450 | 0.7743 | 0.7484 | 0.7914 | 0.1971 | 0.0 | 0.6179 | 0.7799 | 0.5443 | 0.7211 | 0.5925 | 0.5910 | 0.5189 | 0.0850 | 0.3944 | 0.3678 | 0.7979 | 0.5061 | 0.4893 | 0.6992 | 0.6875 | 0.7094 | 0.1772 |
| 0.0793 | 1.96 | 980 | 0.2003 | 0.5467 | 0.6820 | 0.7890 | nan | 0.8868 | 0.8560 | 0.6296 | 0.8753 | 0.5087 | 0.8319 | 0.7202 | 0.2101 | 0.3960 | 0.5827 | 0.9140 | 0.6879 | 0.8781 | 0.7924 | 0.8308 | 0.8216 | 0.1713 | 0.0 | 0.7187 | 0.7865 | 0.5556 | 0.7705 | 0.4573 | 0.6863 | 0.5364 | 0.1786 | 0.3456 | 0.4445 | 0.7817 | 0.6192 | 0.6617 | 0.7112 | 0.7034 | 0.7258 | 0.1571 |
| 0.0881 | 2.0 | 1000 | 0.2026 | 0.5430 | 0.6696 | 0.7758 | nan | 0.8055 | 0.9034 | 0.6463 | 0.8711 | 0.5281 | 0.7951 | 0.6777 | 0.2288 | 0.4737 | 0.5184 | 0.8716 | 0.7001 | 0.7681 | 0.7600 | 0.7842 | 0.8391 | 0.2115 | 0.0 | 0.7040 | 0.7865 | 0.5595 | 0.7562 | 0.4646 | 0.6923 | 0.4893 | 0.1846 | 0.3773 | 0.4039 | 0.7844 | 0.6285 | 0.6595 | 0.6914 | 0.6785 | 0.7171 | 0.1954 |
| 0.164 | 2.04 | 1020 | 0.1894 | 0.5566 | 0.6935 | 0.7948 | nan | 0.8577 | 0.8451 | 0.6489 | 0.8534 | 0.6880 | 0.8749 | 0.7212 | 0.2222 | 0.3785 | 0.5106 | 0.8963 | 0.6640 | 0.8652 | 0.8502 | 0.7722 | 0.8177 | 0.3231 | 0.0 | 0.6855 | 0.7756 | 0.5673 | 0.7557 | 0.5883 | 0.7037 | 0.5489 | 0.1773 | 0.3318 | 0.4129 | 0.7889 | 0.6126 | 0.6769 | 0.7042 | 0.6960 | 0.7334 | 0.2598 |
| 0.158 | 2.08 | 1040 | 0.2104 | 0.5418 | 0.6749 | 0.7757 | nan | 0.8476 | 0.8642 | 0.6307 | 0.8318 | 0.4601 | 0.8279 | 0.7790 | 0.1855 | 0.4350 | 0.4771 | 0.9067 | 0.7989 | 0.7718 | 0.7935 | 0.8241 | 0.7621 | 0.2772 | 0.0 | 0.6748 | 0.7851 | 0.5636 | 0.7291 | 0.4187 | 0.6812 | 0.5001 | 0.1576 | 0.3579 | 0.3982 | 0.7805 | 0.6649 | 0.6787 | 0.7120 | 0.7232 | 0.7037 | 0.2224 |
| 0.0724 | 2.12 | 1060 | 0.1818 | 0.5813 | 0.7159 | 0.8143 | nan | 0.7836 | 0.8837 | 0.6726 | 0.8872 | 0.8685 | 0.7996 | 0.6764 | 0.3285 | 0.5280 | 0.5486 | 0.9054 | 0.7857 | 0.7742 | 0.8468 | 0.7965 | 0.8587 | 0.2266 | 0.0 | 0.7030 | 0.8008 | 0.5746 | 0.7651 | 0.7179 | 0.6962 | 0.5985 | 0.2603 | 0.3984 | 0.4226 | 0.7850 | 0.6685 | 0.6898 | 0.7073 | 0.7058 | 0.7649 | 0.2040 |
| 0.0906 | 2.16 | 1080 | 0.2052 | 0.5553 | 0.6875 | 0.7897 | nan | 0.8313 | 0.8956 | 0.6559 | 0.8275 | 0.7173 | 0.8116 | 0.7495 | 0.0605 | 0.4663 | 0.5563 | 0.8829 | 0.7184 | 0.8017 | 0.8431 | 0.7774 | 0.7582 | 0.3341 | 0.0 | 0.7110 | 0.7958 | 0.5638 | 0.7280 | 0.6074 | 0.6818 | 0.5526 | 0.0575 | 0.3893 | 0.4334 | 0.7886 | 0.6394 | 0.6823 | 0.6993 | 0.6912 | 0.7073 | 0.2664 |
| 0.119 | 2.2 | 1100 | 0.1916 | 0.5489 | 0.6809 | 0.7793 | nan | 0.8171 | 0.8442 | 0.7128 | 0.8296 | 0.7356 | 0.8236 | 0.6640 | 0.1341 | 0.5456 | 0.3609 | 0.8916 | 0.8015 | 0.8096 | 0.7653 | 0.7951 | 0.8119 | 0.2322 | 0.0 | 0.6733 | 0.7745 | 0.5803 | 0.7182 | 0.5975 | 0.6999 | 0.4996 | 0.1222 | 0.4036 | 0.3207 | 0.7971 | 0.6684 | 0.6861 | 0.6890 | 0.7078 | 0.7365 | 0.2050 |
| 0.1114 | 2.24 | 1120 | 0.1905 | 0.5526 | 0.6769 | 0.7941 | nan | 0.7955 | 0.8759 | 0.6366 | 0.8947 | 0.7813 | 0.7845 | 0.6508 | 0.0994 | 0.3162 | 0.6568 | 0.9211 | 0.7643 | 0.7050 | 0.7629 | 0.8151 | 0.7977 | 0.2493 | 0.0 | 0.7142 | 0.7945 | 0.5553 | 0.7484 | 0.6236 | 0.6722 | 0.5467 | 0.0970 | 0.2894 | 0.4530 | 0.7868 | 0.6591 | 0.6571 | 0.6901 | 0.7167 | 0.7352 | 0.2069 |
| 0.0757 | 2.28 | 1140 | 0.2216 | 0.5458 | 0.6760 | 0.7809 | nan | 0.7006 | 0.8731 | 0.6414 | 0.7872 | 0.6130 | 0.8828 | 0.8184 | 0.1886 | 0.5750 | 0.4180 | 0.9033 | 0.8910 | 0.6235 | 0.7955 | 0.7737 | 0.7658 | 0.2404 | 0.0 | 0.6697 | 0.7931 | 0.5672 | 0.7090 | 0.5666 | 0.7073 | 0.5092 | 0.1636 | 0.4196 | 0.3611 | 0.7910 | 0.6391 | 0.5870 | 0.7086 | 0.7117 | 0.7096 | 0.2109 |
| 0.0551 | 2.32 | 1160 | 0.2090 | 0.5627 | 0.7010 | 0.7837 | nan | 0.8745 | 0.9012 | 0.6052 | 0.7677 | 0.6776 | 0.8074 | 0.8089 | 0.2178 | 0.4269 | 0.6106 | 0.8998 | 0.7038 | 0.8525 | 0.8516 | 0.7745 | 0.8010 | 0.3363 | 0.0 | 0.7143 | 0.7934 | 0.5484 | 0.6976 | 0.5691 | 0.7044 | 0.5204 | 0.1995 | 0.3665 | 0.4422 | 0.7764 | 0.6567 | 0.7059 | 0.7163 | 0.7137 | 0.7323 | 0.2721 |
| 0.0936 | 2.36 | 1180 | 0.2165 | 0.5574 | 0.6867 | 0.7878 | nan | 0.7461 | 0.8914 | 0.5665 | 0.8649 | 0.6354 | 0.7483 | 0.7363 | 0.1586 | 0.5903 | 0.3687 | 0.9141 | 0.8447 | 0.7667 | 0.8507 | 0.7891 | 0.7414 | 0.4599 | 0.0 | 0.7022 | 0.7991 | 0.5241 | 0.7179 | 0.5839 | 0.6630 | 0.5364 | 0.1484 | 0.4303 | 0.3375 | 0.7782 | 0.6839 | 0.6968 | 0.7225 | 0.7219 | 0.7012 | 0.2853 |
| 0.2249 | 2.4 | 1200 | 0.1985 | 0.5576 | 0.6820 | 0.7858 | nan | 0.7479 | 0.8644 | 0.6423 | 0.8948 | 0.5762 | 0.7743 | 0.6383 | 0.2730 | 0.4054 | 0.5883 | 0.9116 | 0.8846 | 0.7431 | 0.8103 | 0.7955 | 0.8559 | 0.1886 | 0.0 | 0.6950 | 0.7889 | 0.5656 | 0.7334 | 0.5212 | 0.6682 | 0.4872 | 0.2366 | 0.3478 | 0.4438 | 0.7828 | 0.6917 | 0.6892 | 0.7223 | 0.7322 | 0.7515 | 0.1796 |
| 0.1143 | 2.44 | 1220 | 0.2132 | 0.5542 | 0.6838 | 0.7695 | nan | 0.7928 | 0.8792 | 0.6912 | 0.7460 | 0.6283 | 0.8408 | 0.7820 | 0.2448 | 0.4905 | 0.4794 | 0.8976 | 0.7917 | 0.8155 | 0.8065 | 0.8147 | 0.7629 | 0.1613 | 0.0 | 0.7049 | 0.7851 | 0.5858 | 0.6884 | 0.5133 | 0.7170 | 0.4776 | 0.2212 | 0.3929 | 0.3954 | 0.7848 | 0.6841 | 0.7051 | 0.7079 | 0.7274 | 0.7252 | 0.1587 |
| 0.2771 | 2.48 | 1240 | 0.2258 | 0.5580 | 0.6880 | 0.7782 | nan | 0.8725 | 0.8834 | 0.7124 | 0.8679 | 0.4498 | 0.7580 | 0.7352 | 0.2542 | 0.4660 | 0.5536 | 0.8802 | 0.8435 | 0.7798 | 0.8040 | 0.7906 | 0.7847 | 0.2596 | 0.0 | 0.7281 | 0.7984 | 0.5992 | 0.7209 | 0.4263 | 0.6651 | 0.4859 | 0.2339 | 0.3893 | 0.4403 | 0.7874 | 0.6971 | 0.7040 | 0.7042 | 0.7258 | 0.7388 | 0.1998 |
| 0.1988 | 2.52 | 1260 | 0.2129 | 0.5508 | 0.6813 | 0.7733 | nan | 0.8449 | 0.8465 | 0.6716 | 0.7666 | 0.7912 | 0.7598 | 0.7918 | 0.1262 | 0.4035 | 0.5711 | 0.9015 | 0.7580 | 0.8154 | 0.7535 | 0.8030 | 0.7797 | 0.1979 | 0.0 | 0.6909 | 0.7793 | 0.5838 | 0.6927 | 0.5898 | 0.6771 | 0.5041 | 0.1199 | 0.3521 | 0.4372 | 0.7785 | 0.6728 | 0.6947 | 0.6964 | 0.7248 | 0.7309 | 0.1903 |
| 0.0679 | 2.56 | 1280 | 0.1937 | 0.5683 | 0.6963 | 0.7955 | nan | 0.7422 | 0.9044 | 0.6691 | 0.8294 | 0.6163 | 0.8310 | 0.7917 | 0.3324 | 0.6376 | 0.3930 | 0.9014 | 0.8285 | 0.7713 | 0.8048 | 0.8271 | 0.7844 | 0.1731 | 0.0 | 0.6872 | 0.7986 | 0.5810 | 0.7385 | 0.5481 | 0.7185 | 0.5452 | 0.2847 | 0.4488 | 0.3568 | 0.7849 | 0.6938 | 0.6977 | 0.7127 | 0.7261 | 0.7367 | 0.1710 |
| 0.0815 | 2.6 | 1300 | 0.1993 | 0.5763 | 0.7156 | 0.7826 | nan | 0.7970 | 0.8772 | 0.7409 | 0.7964 | 0.5757 | 0.8128 | 0.8230 | 0.3708 | 0.4442 | 0.6099 | 0.8871 | 0.7767 | 0.7949 | 0.8140 | 0.8029 | 0.7646 | 0.4768 | 0.0 | 0.7016 | 0.7953 | 0.5979 | 0.7150 | 0.5049 | 0.7142 | 0.5156 | 0.3068 | 0.3891 | 0.4637 | 0.7945 | 0.6853 | 0.7042 | 0.7075 | 0.7254 | 0.7177 | 0.3345 |
| 0.0705 | 2.64 | 1320 | 0.1949 | 0.5713 | 0.7021 | 0.7976 | nan | 0.7553 | 0.8927 | 0.5885 | 0.8530 | 0.6004 | 0.8552 | 0.7297 | 0.4790 | 0.6650 | 0.3765 | 0.9130 | 0.8525 | 0.7707 | 0.8690 | 0.7700 | 0.7959 | 0.1701 | 0.0 | 0.7081 | 0.8047 | 0.5361 | 0.7416 | 0.5569 | 0.7221 | 0.5327 | 0.3904 | 0.4541 | 0.3455 | 0.7975 | 0.6906 | 0.6955 | 0.6991 | 0.7043 | 0.7369 | 0.1673 |
| 0.0785 | 2.68 | 1340 | 0.2041 | 0.5795 | 0.7097 | 0.7964 | nan | 0.8035 | 0.9029 | 0.6566 | 0.8325 | 0.5972 | 0.8503 | 0.7806 | 0.4603 | 0.4654 | 0.6184 | 0.8752 | 0.8377 | 0.6987 | 0.7804 | 0.8239 | 0.8514 | 0.2307 | 0.0 | 0.7323 | 0.8038 | 0.5765 | 0.7379 | 0.5414 | 0.7289 | 0.5339 | 0.3700 | 0.3978 | 0.4754 | 0.8028 | 0.6705 | 0.6539 | 0.7093 | 0.7269 | 0.7478 | 0.2222 |
| 0.1076 | 2.72 | 1360 | 0.1929 | 0.5838 | 0.7190 | 0.8072 | nan | 0.6902 | 0.8919 | 0.6362 | 0.8790 | 0.7117 | 0.8261 | 0.6784 | 0.4480 | 0.6431 | 0.4944 | 0.9088 | 0.8265 | 0.7479 | 0.8457 | 0.8242 | 0.8532 | 0.3170 | 0.0 | 0.6566 | 0.7966 | 0.5662 | 0.7594 | 0.6488 | 0.6928 | 0.5625 | 0.3419 | 0.4482 | 0.4200 | 0.7937 | 0.6759 | 0.6761 | 0.7319 | 0.7342 | 0.7486 | 0.2551 |
| 0.1436 | 2.76 | 1380 | 0.2300 | 0.5385 | 0.6686 | 0.7745 | nan | 0.7836 | 0.9007 | 0.6214 | 0.7997 | 0.6169 | 0.8014 | 0.8452 | 0.1419 | 0.3989 | 0.6709 | 0.8971 | 0.4475 | 0.9195 | 0.7890 | 0.8211 | 0.6318 | 0.2804 | 0.0 | 0.7015 | 0.8036 | 0.5603 | 0.7213 | 0.5128 | 0.7149 | 0.5244 | 0.1311 | 0.3619 | 0.4863 | 0.7927 | 0.4435 | 0.6090 | 0.7179 | 0.7295 | 0.6180 | 0.2642 |
| 0.1067 | 2.8 | 1400 | 0.1957 | 0.5652 | 0.7049 | 0.7881 | nan | 0.8524 | 0.8639 | 0.7524 | 0.8659 | 0.6098 | 0.8053 | 0.6721 | 0.2178 | 0.4882 | 0.5218 | 0.8987 | 0.8355 | 0.7302 | 0.8198 | 0.8127 | 0.8579 | 0.3791 | 0.0 | 0.6970 | 0.7926 | 0.6030 | 0.7407 | 0.5254 | 0.7052 | 0.4947 | 0.1865 | 0.4082 | 0.4450 | 0.7945 | 0.6695 | 0.6767 | 0.7171 | 0.7172 | 0.7042 | 0.2960 |
| 0.0719 | 2.84 | 1420 | 0.2357 | 0.5517 | 0.6760 | 0.7766 | nan | 0.8245 | 0.9166 | 0.6213 | 0.8075 | 0.5353 | 0.7805 | 0.8185 | 0.1425 | 0.4855 | 0.5586 | 0.8749 | 0.7612 | 0.7448 | 0.8053 | 0.8224 | 0.7441 | 0.2490 | 0.0 | 0.7198 | 0.8016 | 0.5629 | 0.7240 | 0.4794 | 0.6637 | 0.4917 | 0.1346 | 0.4047 | 0.4592 | 0.7837 | 0.6594 | 0.6719 | 0.7211 | 0.7227 | 0.6954 | 0.2352 |
| 0.1557 | 2.88 | 1440 | 0.2600 | 0.5491 | 0.6861 | 0.7593 | nan | 0.8334 | 0.8869 | 0.6552 | 0.7548 | 0.4025 | 0.7557 | 0.8423 | 0.1417 | 0.5662 | 0.5345 | 0.9121 | 0.8045 | 0.7816 | 0.8586 | 0.7752 | 0.7765 | 0.3824 | 0.0 | 0.7396 | 0.7964 | 0.5758 | 0.6832 | 0.3855 | 0.6560 | 0.4511 | 0.1362 | 0.4422 | 0.4574 | 0.7852 | 0.6753 | 0.6876 | 0.7167 | 0.7123 | 0.7135 | 0.2702 |
| 0.0667 | 2.92 | 1460 | 0.2077 | 0.5685 | 0.7011 | 0.7889 | nan | 0.8600 | 0.9046 | 0.7236 | 0.8549 | 0.4918 | 0.7826 | 0.7566 | 0.2867 | 0.5245 | 0.5654 | 0.8922 | 0.7801 | 0.8728 | 0.7829 | 0.8062 | 0.7907 | 0.2428 | 0.0 | 0.7300 | 0.7920 | 0.5978 | 0.7410 | 0.4591 | 0.6792 | 0.5235 | 0.2351 | 0.4322 | 0.4714 | 0.7826 | 0.6802 | 0.7142 | 0.7103 | 0.7247 | 0.7266 | 0.2322 |
| 0.0599 | 2.96 | 1480 | 0.1890 | 0.5706 | 0.7078 | 0.7904 | nan | 0.8265 | 0.8570 | 0.7718 | 0.8348 | 0.7044 | 0.8015 | 0.7367 | 0.2153 | 0.3547 | 0.6748 | 0.8968 | 0.8277 | 0.7836 | 0.8193 | 0.7976 | 0.7714 | 0.3590 | 0.0 | 0.7146 | 0.7867 | 0.6005 | 0.7420 | 0.5740 | 0.7028 | 0.5212 | 0.1847 | 0.3318 | 0.4857 | 0.7959 | 0.6741 | 0.6980 | 0.7252 | 0.7153 | 0.7289 | 0.2884 |
| 0.1253 | 3.0 | 1500 | 0.2008 | 0.5730 | 0.7009 | 0.7958 | nan | 0.7983 | 0.9092 | 0.6277 | 0.8403 | 0.5076 | 0.8389 | 0.8069 | 0.2118 | 0.5775 | 0.5092 | 0.8948 | 0.8165 | 0.7955 | 0.8217 | 0.7863 | 0.7737 | 0.3995 | 0.0 | 0.7192 | 0.8033 | 0.5639 | 0.7514 | 0.4760 | 0.7203 | 0.5251 | 0.2002 | 0.4440 | 0.4414 | 0.8016 | 0.6836 | 0.7215 | 0.7145 | 0.7223 | 0.7263 | 0.3001 |
| 0.0902 | 3.04 | 1520 | 0.2002 | 0.5771 | 0.7138 | 0.7951 | nan | 0.8105 | 0.8611 | 0.6681 | 0.8355 | 0.6470 | 0.8293 | 0.7263 | 0.2985 | 0.5198 | 0.6254 | 0.9141 | 0.8738 | 0.7614 | 0.8100 | 0.8081 | 0.8212 | 0.3252 | 0.0 | 0.6917 | 0.7907 | 0.5827 | 0.7466 | 0.5515 | 0.7143 | 0.5243 | 0.2417 | 0.4221 | 0.4795 | 0.7980 | 0.6762 | 0.6961 | 0.7176 | 0.7377 | 0.7402 | 0.2770 |
| 0.0793 | 3.08 | 1540 | 0.2097 | 0.5740 | 0.6960 | 0.7942 | nan | 0.7866 | 0.8973 | 0.5933 | 0.8581 | 0.5793 | 0.8686 | 0.7112 | 0.2830 | 0.5339 | 0.5274 | 0.9094 | 0.7455 | 0.8031 | 0.8050 | 0.7807 | 0.7956 | 0.3542 | 0.0 | 0.7338 | 0.8013 | 0.5453 | 0.7551 | 0.5228 | 0.7043 | 0.5216 | 0.2388 | 0.4344 | 0.4474 | 0.8099 | 0.6517 | 0.7028 | 0.7118 | 0.7277 | 0.7302 | 0.2923 |
| 0.1151 | 3.12 | 1560 | 0.2098 | 0.5839 | 0.7069 | 0.8009 | nan | 0.7985 | 0.8944 | 0.6654 | 0.8527 | 0.5810 | 0.8246 | 0.7654 | 0.2375 | 0.5160 | 0.5706 | 0.9016 | 0.7949 | 0.8408 | 0.8249 | 0.8197 | 0.8106 | 0.3179 | 0.0 | 0.7424 | 0.8056 | 0.5829 | 0.7540 | 0.5176 | 0.7170 | 0.5205 | 0.2154 | 0.4395 | 0.4741 | 0.8142 | 0.6893 | 0.7262 | 0.7221 | 0.7486 | 0.7490 | 0.2920 |
| 0.0521 | 3.16 | 1580 | 0.2137 | 0.5824 | 0.7149 | 0.7968 | nan | 0.8334 | 0.8909 | 0.7298 | 0.8236 | 0.5910 | 0.8047 | 0.7947 | 0.2071 | 0.6304 | 0.5506 | 0.8957 | 0.7867 | 0.8203 | 0.8369 | 0.8054 | 0.8381 | 0.3143 | 0.0 | 0.7455 | 0.8052 | 0.6026 | 0.7391 | 0.5304 | 0.7111 | 0.5198 | 0.1846 | 0.4810 | 0.4572 | 0.8158 | 0.6975 | 0.7236 | 0.7188 | 0.7349 | 0.7416 | 0.2748 |
| 0.0974 | 3.2 | 1600 | 0.2145 | 0.5750 | 0.7010 | 0.7944 | nan | 0.8038 | 0.8812 | 0.5595 | 0.8303 | 0.5730 | 0.8460 | 0.7588 | 0.2021 | 0.5587 | 0.5178 | 0.9135 | 0.8271 | 0.8278 | 0.8214 | 0.8236 | 0.7844 | 0.3874 | 0.0 | 0.7228 | 0.7942 | 0.5250 | 0.7341 | 0.5138 | 0.7236 | 0.5115 | 0.1847 | 0.4478 | 0.4420 | 0.8113 | 0.6973 | 0.7192 | 0.7389 | 0.7447 | 0.7376 | 0.3004 |
| 0.0535 | 3.24 | 1620 | 0.1986 | 0.5803 | 0.7191 | 0.8025 | nan | 0.8644 | 0.8970 | 0.7361 | 0.8454 | 0.7897 | 0.7807 | 0.7109 | 0.1309 | 0.5688 | 0.5623 | 0.8898 | 0.8323 | 0.7588 | 0.8089 | 0.8493 | 0.8091 | 0.3906 | 0.0 | 0.7053 | 0.7997 | 0.6082 | 0.7580 | 0.5811 | 0.6955 | 0.5477 | 0.1201 | 0.4516 | 0.4580 | 0.8204 | 0.6752 | 0.6925 | 0.7320 | 0.7468 | 0.7445 | 0.3084 |
| 0.072 | 3.28 | 1640 | 0.1961 | 0.5782 | 0.7140 | 0.8020 | nan | 0.8503 | 0.8473 | 0.7632 | 0.8730 | 0.6862 | 0.8199 | 0.7197 | 0.1571 | 0.5890 | 0.5258 | 0.8817 | 0.8225 | 0.7920 | 0.8056 | 0.8447 | 0.7937 | 0.3655 | 0.0 | 0.7110 | 0.7839 | 0.6097 | 0.7675 | 0.5405 | 0.7156 | 0.5373 | 0.1418 | 0.4611 | 0.4439 | 0.8183 | 0.6797 | 0.7040 | 0.7167 | 0.7379 | 0.7420 | 0.2963 |
| 0.0929 | 3.32 | 1660 | 0.2014 | 0.5753 | 0.7005 | 0.8059 | nan | 0.8069 | 0.9063 | 0.6184 | 0.8649 | 0.7200 | 0.8257 | 0.7258 | 0.1376 | 0.4722 | 0.6033 | 0.9044 | 0.8147 | 0.7698 | 0.8141 | 0.8313 | 0.7646 | 0.3288 | 0.0 | 0.7399 | 0.8079 | 0.5636 | 0.7677 | 0.5656 | 0.7075 | 0.5457 | 0.1288 | 0.4001 | 0.4691 | 0.8136 | 0.6855 | 0.6978 | 0.7241 | 0.7291 | 0.7303 | 0.2799 |
| 0.0883 | 3.36 | 1680 | 0.2020 | 0.5681 | 0.6953 | 0.8032 | nan | 0.6691 | 0.8898 | 0.7268 | 0.8802 | 0.6571 | 0.8365 | 0.7110 | 0.2121 | 0.4769 | 0.6395 | 0.9106 | 0.7869 | 0.8422 | 0.8619 | 0.7270 | 0.7651 | 0.2267 | 0.0 | 0.6504 | 0.7967 | 0.6055 | 0.7711 | 0.5475 | 0.7188 | 0.5390 | 0.1922 | 0.4080 | 0.4835 | 0.8028 | 0.6882 | 0.7258 | 0.6887 | 0.6628 | 0.7315 | 0.2127 |
| 0.0795 | 3.4 | 1700 | 0.2029 | 0.5795 | 0.7073 | 0.8019 | nan | 0.7438 | 0.8881 | 0.7527 | 0.8645 | 0.6712 | 0.8071 | 0.7493 | 0.2007 | 0.5927 | 0.5268 | 0.8968 | 0.8016 | 0.8051 | 0.8163 | 0.7442 | 0.8168 | 0.3461 | 0.0 | 0.7033 | 0.8013 | 0.6111 | 0.7618 | 0.5426 | 0.7030 | 0.5380 | 0.1790 | 0.4673 | 0.4503 | 0.8021 | 0.7002 | 0.7318 | 0.6986 | 0.6781 | 0.7602 | 0.3015 |
| 0.0773 | 3.44 | 1720 | 0.1989 | 0.5812 | 0.7117 | 0.8050 | nan | 0.8647 | 0.8811 | 0.6571 | 0.8473 | 0.7655 | 0.8081 | 0.7508 | 0.2 | 0.5806 | 0.5543 | 0.8992 | 0.8711 | 0.7839 | 0.8109 | 0.7591 | 0.7706 | 0.2941 | 0.0 | 0.7410 | 0.8039 | 0.5819 | 0.7591 | 0.5928 | 0.7198 | 0.5427 | 0.1720 | 0.4644 | 0.4652 | 0.8028 | 0.7036 | 0.7189 | 0.7045 | 0.6864 | 0.7301 | 0.2720 |
| 0.0627 | 3.48 | 1740 | 0.1922 | 0.5946 | 0.7326 | 0.8082 | nan | 0.8001 | 0.9026 | 0.7357 | 0.8662 | 0.7616 | 0.7701 | 0.7071 | 0.3307 | 0.5833 | 0.5425 | 0.8858 | 0.8232 | 0.8421 | 0.8466 | 0.7911 | 0.8314 | 0.4343 | 0.0 | 0.6934 | 0.8002 | 0.6045 | 0.7542 | 0.6357 | 0.6823 | 0.5510 | 0.2671 | 0.4622 | 0.4621 | 0.8064 | 0.7109 | 0.7429 | 0.7272 | 0.7122 | 0.7564 | 0.3336 |
| 0.0901 | 3.52 | 1760 | 0.1963 | 0.5834 | 0.7287 | 0.8048 | nan | 0.7844 | 0.8874 | 0.7435 | 0.8876 | 0.7874 | 0.7760 | 0.6757 | 0.5528 | 0.4646 | 0.6739 | 0.9074 | 0.8113 | 0.7329 | 0.8419 | 0.7806 | 0.8012 | 0.2792 | 0.0 | 0.7058 | 0.8024 | 0.6052 | 0.7672 | 0.6304 | 0.6697 | 0.5552 | 0.2771 | 0.4063 | 0.4888 | 0.8120 | 0.6742 | 0.6810 | 0.7174 | 0.7099 | 0.7422 | 0.2573 |
| 0.0945 | 3.56 | 1780 | 0.2033 | 0.5814 | 0.7128 | 0.8026 | nan | 0.7737 | 0.8804 | 0.7259 | 0.8444 | 0.7017 | 0.7875 | 0.7936 | 0.2431 | 0.5968 | 0.5278 | 0.8723 | 0.8753 | 0.7400 | 0.8484 | 0.7847 | 0.8230 | 0.2984 | 0.0 | 0.6802 | 0.7959 | 0.6064 | 0.7510 | 0.6027 | 0.6942 | 0.5622 | 0.2123 | 0.4806 | 0.4601 | 0.8139 | 0.6697 | 0.6731 | 0.7165 | 0.7166 | 0.7550 | 0.2749 |
| 0.0621 | 3.6 | 1800 | 0.2150 | 0.5739 | 0.7002 | 0.7936 | nan | 0.7455 | 0.8958 | 0.6267 | 0.8290 | 0.4667 | 0.8545 | 0.7940 | 0.2158 | 0.5564 | 0.5418 | 0.9127 | 0.7723 | 0.8698 | 0.8493 | 0.8622 | 0.7568 | 0.3538 | 0.0 | 0.6987 | 0.8035 | 0.5693 | 0.7468 | 0.4405 | 0.7120 | 0.5078 | 0.1976 | 0.4466 | 0.4550 | 0.8211 | 0.6854 | 0.7335 | 0.7358 | 0.7513 | 0.7141 | 0.3113 |
| 0.2598 | 3.64 | 1820 | 0.2038 | 0.5845 | 0.7150 | 0.7998 | nan | 0.7778 | 0.8901 | 0.7231 | 0.8247 | 0.6904 | 0.7825 | 0.8005 | 0.2124 | 0.6003 | 0.5248 | 0.8983 | 0.8224 | 0.8289 | 0.8407 | 0.8113 | 0.7780 | 0.3483 | 0.0 | 0.6945 | 0.8005 | 0.6083 | 0.7402 | 0.5578 | 0.7011 | 0.5394 | 0.1800 | 0.4688 | 0.4444 | 0.8234 | 0.7047 | 0.7372 | 0.7436 | 0.7471 | 0.7255 | 0.3038 |
| 0.0579 | 3.68 | 1840 | 0.2159 | 0.5795 | 0.7123 | 0.7900 | nan | 0.8404 | 0.8889 | 0.6393 | 0.8015 | 0.7077 | 0.7805 | 0.7668 | 0.2314 | 0.5816 | 0.5545 | 0.9067 | 0.7842 | 0.8706 | 0.8527 | 0.7892 | 0.7389 | 0.3750 | 0.0 | 0.7195 | 0.8002 | 0.5789 | 0.7270 | 0.5200 | 0.6983 | 0.5056 | 0.1995 | 0.4739 | 0.4656 | 0.8146 | 0.6987 | 0.7419 | 0.7428 | 0.7333 | 0.7015 | 0.3093 |
| 0.178 | 3.72 | 1860 | 0.2051 | 0.5807 | 0.7160 | 0.7960 | nan | 0.8871 | 0.8580 | 0.7123 | 0.8313 | 0.6923 | 0.8340 | 0.7196 | 0.2726 | 0.5479 | 0.5092 | 0.9005 | 0.7924 | 0.8467 | 0.8338 | 0.8060 | 0.8261 | 0.3020 | 0.0 | 0.7153 | 0.7931 | 0.6083 | 0.7428 | 0.5218 | 0.6966 | 0.5077 | 0.2297 | 0.4433 | 0.4389 | 0.8253 | 0.7020 | 0.7463 | 0.7383 | 0.7449 | 0.7425 | 0.2560 |
| 0.0652 | 3.76 | 1880 | 0.1907 | 0.5881 | 0.7163 | 0.8079 | nan | 0.7918 | 0.9170 | 0.6292 | 0.8550 | 0.7548 | 0.8023 | 0.7000 | 0.3581 | 0.4405 | 0.6354 | 0.9116 | 0.7540 | 0.8829 | 0.8521 | 0.8078 | 0.8326 | 0.2512 | 0.0 | 0.7321 | 0.8032 | 0.5730 | 0.7583 | 0.6172 | 0.6924 | 0.5500 | 0.2969 | 0.3963 | 0.4849 | 0.8110 | 0.6878 | 0.7372 | 0.7356 | 0.7367 | 0.7462 | 0.2273 |
| 0.0909 | 3.8 | 1900 | 0.2130 | 0.5773 | 0.7080 | 0.7958 | nan | 0.8645 | 0.8670 | 0.6606 | 0.8539 | 0.6938 | 0.7894 | 0.7331 | 0.3307 | 0.5893 | 0.5149 | 0.9035 | 0.7804 | 0.8136 | 0.8174 | 0.8344 | 0.7693 | 0.2204 | 0.0 | 0.7076 | 0.7923 | 0.5894 | 0.7520 | 0.5299 | 0.6777 | 0.5221 | 0.2841 | 0.4775 | 0.4505 | 0.8169 | 0.6857 | 0.7220 | 0.7303 | 0.7335 | 0.7171 | 0.2021 |
| 0.0961 | 3.84 | 1920 | 0.2318 | 0.5699 | 0.7032 | 0.7850 | nan | 0.8585 | 0.8814 | 0.7262 | 0.8201 | 0.4649 | 0.7840 | 0.8384 | 0.2209 | 0.5943 | 0.5827 | 0.9001 | 0.8247 | 0.8078 | 0.8476 | 0.7852 | 0.7388 | 0.2795 | 0.0 | 0.7093 | 0.8043 | 0.6152 | 0.7333 | 0.4218 | 0.6994 | 0.5020 | 0.2123 | 0.4828 | 0.4840 | 0.8139 | 0.6860 | 0.7119 | 0.7325 | 0.7223 | 0.6961 | 0.2304 |
| 0.0786 | 3.88 | 1940 | 0.2128 | 0.5738 | 0.7009 | 0.7950 | nan | 0.8275 | 0.8709 | 0.7395 | 0.8610 | 0.4952 | 0.8088 | 0.7840 | 0.1940 | 0.5403 | 0.5177 | 0.9014 | 0.8490 | 0.8128 | 0.8428 | 0.7945 | 0.8037 | 0.2714 | 0.0 | 0.7236 | 0.8014 | 0.6126 | 0.7543 | 0.4507 | 0.7059 | 0.5309 | 0.1864 | 0.4458 | 0.4492 | 0.8150 | 0.6890 | 0.7151 | 0.7352 | 0.7267 | 0.7343 | 0.2527 |
| 0.0636 | 3.92 | 1960 | 0.2003 | 0.5833 | 0.7262 | 0.7998 | nan | 0.8600 | 0.9029 | 0.7461 | 0.8230 | 0.7772 | 0.7915 | 0.7836 | 0.2790 | 0.6805 | 0.5158 | 0.8845 | 0.9083 | 0.5324 | 0.8158 | 0.8110 | 0.8367 | 0.3969 | 0.0 | 0.7663 | 0.8098 | 0.6200 | 0.7428 | 0.6096 | 0.7033 | 0.5636 | 0.2286 | 0.5014 | 0.4624 | 0.8116 | 0.6112 | 0.5186 | 0.7507 | 0.7531 | 0.7431 | 0.3027 |
| 0.0589 | 3.96 | 1980 | 0.1973 | 0.5911 | 0.7251 | 0.8140 | nan | 0.8461 | 0.8977 | 0.7605 | 0.8543 | 0.7629 | 0.8871 | 0.7317 | 0.2834 | 0.4014 | 0.6770 | 0.8954 | 0.6367 | 0.8749 | 0.8640 | 0.8419 | 0.7840 | 0.3271 | 0.0 | 0.7618 | 0.8090 | 0.6166 | 0.7608 | 0.6512 | 0.7371 | 0.5648 | 0.2335 | 0.3683 | 0.4960 | 0.8055 | 0.6120 | 0.6862 | 0.7559 | 0.7535 | 0.7329 | 0.2949 |
| 0.0517 | 4.0 | 2000 | 0.1941 | 0.5891 | 0.7204 | 0.8118 | nan | 0.8225 | 0.8958 | 0.7789 | 0.8578 | 0.7435 | 0.8709 | 0.7380 | 0.2309 | 0.4791 | 0.6296 | 0.9095 | 0.6344 | 0.8537 | 0.8293 | 0.8547 | 0.7902 | 0.3280 | 0.0 | 0.7503 | 0.8103 | 0.6221 | 0.7556 | 0.6648 | 0.7287 | 0.5669 | 0.1981 | 0.4191 | 0.4888 | 0.8081 | 0.6006 | 0.6729 | 0.7420 | 0.7530 | 0.7366 | 0.2853 |
| 0.0422 | 4.04 | 2020 | 0.2032 | 0.5913 | 0.7192 | 0.8093 | nan | 0.8231 | 0.9095 | 0.7218 | 0.8538 | 0.6817 | 0.8363 | 0.7633 | 0.2917 | 0.6304 | 0.5313 | 0.8938 | 0.8721 | 0.7443 | 0.8296 | 0.8005 | 0.7821 | 0.2613 | 0.0 | 0.7468 | 0.8084 | 0.6122 | 0.7520 | 0.6243 | 0.7129 | 0.5594 | 0.2464 | 0.4930 | 0.4699 | 0.8102 | 0.6812 | 0.6865 | 0.7350 | 0.7349 | 0.7280 | 0.2428 |
| 0.0861 | 4.08 | 2040 | 0.1949 | 0.6051 | 0.7314 | 0.8172 | nan | 0.8581 | 0.8851 | 0.6496 | 0.8789 | 0.7340 | 0.8261 | 0.7216 | 0.3758 | 0.5946 | 0.6085 | 0.9150 | 0.7740 | 0.8651 | 0.8405 | 0.8456 | 0.7810 | 0.2805 | 0.0 | 0.7568 | 0.8076 | 0.5824 | 0.7632 | 0.6593 | 0.7058 | 0.5758 | 0.3100 | 0.4879 | 0.5035 | 0.8131 | 0.6936 | 0.7382 | 0.7537 | 0.7513 | 0.7339 | 0.2559 |
| 0.1004 | 4.12 | 2060 | 0.1849 | 0.6016 | 0.7348 | 0.8130 | nan | 0.8772 | 0.8872 | 0.7109 | 0.8664 | 0.7335 | 0.8124 | 0.7212 | 0.3150 | 0.5658 | 0.5974 | 0.8978 | 0.8494 | 0.8242 | 0.8454 | 0.7727 | 0.8369 | 0.3779 | 0.0 | 0.7377 | 0.8023 | 0.6101 | 0.7663 | 0.6085 | 0.7008 | 0.5652 | 0.2773 | 0.4760 | 0.5018 | 0.8146 | 0.7021 | 0.7407 | 0.7424 | 0.7256 | 0.7571 | 0.2995 |
| 0.0719 | 4.16 | 2080 | 0.1912 | 0.6032 | 0.7298 | 0.8135 | nan | 0.8346 | 0.8875 | 0.7111 | 0.8822 | 0.6972 | 0.8197 | 0.7397 | 0.3803 | 0.4940 | 0.6159 | 0.8967 | 0.7861 | 0.8263 | 0.8352 | 0.8367 | 0.7981 | 0.3657 | 0.0 | 0.7349 | 0.8040 | 0.6079 | 0.7695 | 0.6152 | 0.7048 | 0.5781 | 0.3232 | 0.4266 | 0.4933 | 0.8114 | 0.7068 | 0.7369 | 0.7475 | 0.7395 | 0.7458 | 0.3123 |
| 0.224 | 4.2 | 2100 | 0.1948 | 0.6021 | 0.7505 | 0.8035 | nan | 0.8737 | 0.8728 | 0.7274 | 0.8104 | 0.6621 | 0.8323 | 0.7839 | 0.3911 | 0.5970 | 0.5556 | 0.9130 | 0.8385 | 0.8260 | 0.8199 | 0.8032 | 0.8605 | 0.5910 | 0.0 | 0.7477 | 0.7968 | 0.6154 | 0.7411 | 0.5771 | 0.7240 | 0.5406 | 0.3181 | 0.4838 | 0.4865 | 0.8125 | 0.7163 | 0.7370 | 0.7422 | 0.7408 | 0.7673 | 0.2905 |
| 0.0466 | 4.24 | 2120 | 0.2434 | 0.5946 | 0.7268 | 0.7963 | nan | 0.8764 | 0.9095 | 0.6823 | 0.8218 | 0.4696 | 0.7933 | 0.8337 | 0.3116 | 0.5430 | 0.6394 | 0.8914 | 0.8331 | 0.8339 | 0.8381 | 0.8504 | 0.7937 | 0.4342 | 0.0 | 0.7687 | 0.8141 | 0.6015 | 0.7469 | 0.4352 | 0.7082 | 0.4933 | 0.2877 | 0.4605 | 0.5188 | 0.8125 | 0.7242 | 0.7473 | 0.7572 | 0.7617 | 0.7461 | 0.3184 |
| 0.0539 | 4.28 | 2140 | 0.1896 | 0.6050 | 0.7340 | 0.8169 | nan | 0.8388 | 0.9077 | 0.6648 | 0.8533 | 0.6652 | 0.8309 | 0.7608 | 0.3731 | 0.5600 | 0.6177 | 0.9098 | 0.8182 | 0.8691 | 0.8359 | 0.8473 | 0.8432 | 0.2830 | 0.0 | 0.7588 | 0.8153 | 0.5957 | 0.7674 | 0.5456 | 0.7155 | 0.5559 | 0.2860 | 0.4728 | 0.5089 | 0.8094 | 0.7313 | 0.7640 | 0.7594 | 0.7571 | 0.7767 | 0.2705 |
| 0.059 | 4.32 | 2160 | 0.1847 | 0.6109 | 0.7484 | 0.8196 | nan | 0.8403 | 0.8857 | 0.7280 | 0.8728 | 0.8208 | 0.8416 | 0.6962 | 0.5104 | 0.5866 | 0.5678 | 0.9112 | 0.8835 | 0.7349 | 0.8507 | 0.8213 | 0.8171 | 0.3544 | 0.0 | 0.7478 | 0.8066 | 0.6136 | 0.7724 | 0.6560 | 0.7165 | 0.5754 | 0.3698 | 0.4771 | 0.4890 | 0.8076 | 0.6971 | 0.6900 | 0.7560 | 0.7475 | 0.7570 | 0.3171 |
| 0.1197 | 4.36 | 2180 | 0.1876 | 0.6047 | 0.7393 | 0.8149 | nan | 0.8044 | 0.8933 | 0.7389 | 0.8448 | 0.6778 | 0.8412 | 0.7902 | 0.3160 | 0.5677 | 0.6155 | 0.9092 | 0.8380 | 0.8052 | 0.8398 | 0.8433 | 0.8004 | 0.4429 | 0.0 | 0.7342 | 0.8048 | 0.6188 | 0.7600 | 0.6143 | 0.7251 | 0.5925 | 0.2804 | 0.4754 | 0.5111 | 0.7982 | 0.7126 | 0.7249 | 0.7478 | 0.7272 | 0.7579 | 0.2998 |
| 0.0465 | 4.4 | 2200 | 0.1911 | 0.6054 | 0.7314 | 0.8183 | nan | 0.8259 | 0.8737 | 0.7163 | 0.8957 | 0.6328 | 0.8381 | 0.7482 | 0.3173 | 0.6658 | 0.5310 | 0.9127 | 0.8460 | 0.8064 | 0.8194 | 0.8513 | 0.7996 | 0.3532 | 0.0 | 0.7469 | 0.8076 | 0.6081 | 0.7664 | 0.5869 | 0.7234 | 0.5681 | 0.2813 | 0.5096 | 0.4736 | 0.8098 | 0.7253 | 0.7382 | 0.7474 | 0.7536 | 0.7591 | 0.2918 |
| 0.0487 | 4.44 | 2220 | 0.1965 | 0.6013 | 0.7315 | 0.8136 | nan | 0.7788 | 0.8986 | 0.7435 | 0.8289 | 0.6291 | 0.8804 | 0.8127 | 0.2571 | 0.6768 | 0.5054 | 0.9008 | 0.8404 | 0.7823 | 0.8593 | 0.8272 | 0.8242 | 0.3893 | 0.0 | 0.7376 | 0.8085 | 0.6166 | 0.7574 | 0.5702 | 0.7369 | 0.5632 | 0.2343 | 0.5060 | 0.4531 | 0.8089 | 0.7150 | 0.7207 | 0.7511 | 0.7581 | 0.7700 | 0.3161 |
| 0.1179 | 4.48 | 2240 | 0.1887 | 0.5990 | 0.7318 | 0.8132 | nan | 0.8549 | 0.8896 | 0.7258 | 0.8461 | 0.7417 | 0.8238 | 0.7644 | 0.2442 | 0.5182 | 0.6746 | 0.8932 | 0.7816 | 0.8325 | 0.8215 | 0.8220 | 0.8357 | 0.3714 | 0.0 | 0.7284 | 0.8028 | 0.6163 | 0.7562 | 0.6044 | 0.7211 | 0.5610 | 0.2192 | 0.4385 | 0.5071 | 0.8120 | 0.7167 | 0.7340 | 0.7441 | 0.7553 | 0.7684 | 0.2975 |
| 0.0534 | 4.52 | 2260 | 0.2019 | 0.5961 | 0.7289 | 0.7971 | nan | 0.7750 | 0.8870 | 0.6503 | 0.8138 | 0.6035 | 0.7839 | 0.8024 | 0.3672 | 0.6275 | 0.5181 | 0.9029 | 0.8397 | 0.8378 | 0.8522 | 0.8529 | 0.8193 | 0.4577 | 0.0 | 0.7304 | 0.8049 | 0.5836 | 0.7364 | 0.4990 | 0.6986 | 0.5223 | 0.3085 | 0.4876 | 0.4604 | 0.8131 | 0.7311 | 0.7468 | 0.7495 | 0.7642 | 0.7595 | 0.3334 |
| 0.0893 | 4.56 | 2280 | 0.2143 | 0.5987 | 0.7251 | 0.7975 | nan | 0.7382 | 0.8807 | 0.7100 | 0.8223 | 0.5582 | 0.8206 | 0.8070 | 0.4127 | 0.5589 | 0.5561 | 0.9109 | 0.8181 | 0.8803 | 0.8305 | 0.8518 | 0.7708 | 0.4003 | 0.0 | 0.6998 | 0.7978 | 0.6118 | 0.7331 | 0.5165 | 0.7194 | 0.5223 | 0.3504 | 0.4649 | 0.4763 | 0.8118 | 0.7273 | 0.7508 | 0.7484 | 0.7669 | 0.7286 | 0.3511 |
| 0.0443 | 4.6 | 2300 | 0.2107 | 0.6088 | 0.7451 | 0.8079 | nan | 0.8517 | 0.9117 | 0.7681 | 0.7944 | 0.6344 | 0.8661 | 0.8579 | 0.4570 | 0.6486 | 0.5666 | 0.8783 | 0.7970 | 0.7842 | 0.8453 | 0.8396 | 0.8066 | 0.3593 | 0.0 | 0.7495 | 0.8123 | 0.6290 | 0.7319 | 0.5771 | 0.7430 | 0.5452 | 0.3799 | 0.5021 | 0.4816 | 0.8129 | 0.6993 | 0.7201 | 0.7506 | 0.7543 | 0.7490 | 0.3210 |
| 0.0433 | 4.64 | 2320 | 0.1912 | 0.6129 | 0.7392 | 0.8284 | nan | 0.7361 | 0.8932 | 0.6950 | 0.8864 | 0.7410 | 0.8718 | 0.7345 | 0.3977 | 0.5824 | 0.6076 | 0.9056 | 0.8344 | 0.8280 | 0.8070 | 0.8582 | 0.8404 | 0.3467 | 0.0 | 0.6949 | 0.8102 | 0.6119 | 0.7813 | 0.6735 | 0.7293 | 0.6042 | 0.3380 | 0.4804 | 0.4994 | 0.8156 | 0.7139 | 0.7324 | 0.7331 | 0.7432 | 0.7583 | 0.3130 |
| 0.0651 | 4.68 | 2340 | 0.1955 | 0.5984 | 0.7331 | 0.8145 | nan | 0.7781 | 0.8997 | 0.6854 | 0.8605 | 0.7560 | 0.8705 | 0.7164 | 0.3448 | 0.4754 | 0.6191 | 0.9088 | 0.8595 | 0.7697 | 0.8969 | 0.7732 | 0.7595 | 0.4887 | 0.0 | 0.7105 | 0.8075 | 0.6069 | 0.7669 | 0.6593 | 0.7214 | 0.5752 | 0.3071 | 0.4179 | 0.4920 | 0.8140 | 0.6969 | 0.6987 | 0.7080 | 0.7072 | 0.7070 | 0.3752 |
| 0.047 | 4.72 | 2360 | 0.1974 | 0.6030 | 0.7384 | 0.8122 | nan | 0.8279 | 0.8898 | 0.7517 | 0.8304 | 0.7763 | 0.8685 | 0.7752 | 0.3255 | 0.6484 | 0.5347 | 0.9093 | 0.8206 | 0.7810 | 0.7968 | 0.7843 | 0.7683 | 0.4647 | 0.0 | 0.7301 | 0.8074 | 0.6251 | 0.7479 | 0.6533 | 0.7407 | 0.5601 | 0.2951 | 0.4976 | 0.4673 | 0.8199 | 0.6923 | 0.7070 | 0.6976 | 0.7268 | 0.7155 | 0.3707 |
| 0.0631 | 4.76 | 2380 | 0.1954 | 0.5960 | 0.7307 | 0.8121 | nan | 0.8168 | 0.8874 | 0.7811 | 0.8587 | 0.6200 | 0.8873 | 0.7910 | 0.3364 | 0.5003 | 0.5346 | 0.8992 | 0.7987 | 0.8182 | 0.8688 | 0.7974 | 0.7612 | 0.4653 | 0.0 | 0.7194 | 0.8007 | 0.6240 | 0.7744 | 0.5822 | 0.7310 | 0.5696 | 0.3095 | 0.4293 | 0.4671 | 0.8212 | 0.6866 | 0.7134 | 0.7140 | 0.7220 | 0.7142 | 0.3493 |
| 0.1457 | 4.8 | 2400 | 0.1905 | 0.6017 | 0.7349 | 0.8122 | nan | 0.8354 | 0.8926 | 0.6969 | 0.8269 | 0.7461 | 0.8505 | 0.8060 | 0.2994 | 0.5935 | 0.6066 | 0.9038 | 0.7462 | 0.7689 | 0.8211 | 0.8379 | 0.8154 | 0.4459 | 0.0 | 0.7296 | 0.8007 | 0.6096 | 0.7530 | 0.6517 | 0.7186 | 0.5810 | 0.2758 | 0.4734 | 0.4956 | 0.8201 | 0.6783 | 0.6944 | 0.7232 | 0.7516 | 0.7421 | 0.3313 |
| 0.096 | 4.84 | 2420 | 0.1839 | 0.6017 | 0.7401 | 0.8149 | nan | 0.7803 | 0.9063 | 0.6768 | 0.8360 | 0.7918 | 0.8266 | 0.7649 | 0.3966 | 0.4742 | 0.5942 | 0.9145 | 0.8588 | 0.7922 | 0.8473 | 0.8116 | 0.8137 | 0.4953 | 0.0 | 0.7268 | 0.8094 | 0.6010 | 0.7528 | 0.6775 | 0.7149 | 0.5818 | 0.3183 | 0.4211 | 0.4933 | 0.8070 | 0.7010 | 0.7037 | 0.7242 | 0.7304 | 0.7427 | 0.3250 |
| 0.1249 | 4.88 | 2440 | 0.1843 | 0.6077 | 0.7428 | 0.8183 | nan | 0.7991 | 0.8892 | 0.7353 | 0.8558 | 0.7765 | 0.8298 | 0.7553 | 0.3874 | 0.6074 | 0.5186 | 0.8991 | 0.8337 | 0.8211 | 0.8479 | 0.8120 | 0.8344 | 0.4250 | 0.0 | 0.7245 | 0.8070 | 0.6209 | 0.7615 | 0.6935 | 0.7093 | 0.5903 | 0.3295 | 0.4814 | 0.4554 | 0.8175 | 0.7059 | 0.7231 | 0.7149 | 0.7316 | 0.7606 | 0.3115 |
| 0.0401 | 4.92 | 2460 | 0.1957 | 0.5969 | 0.7328 | 0.8131 | nan | 0.8428 | 0.8672 | 0.7114 | 0.8465 | 0.7447 | 0.8701 | 0.7830 | 0.3845 | 0.4677 | 0.5891 | 0.9165 | 0.8389 | 0.7478 | 0.8294 | 0.8362 | 0.7763 | 0.4048 | 0.0 | 0.7000 | 0.7963 | 0.6113 | 0.7632 | 0.6725 | 0.7203 | 0.5890 | 0.3243 | 0.4029 | 0.4698 | 0.8106 | 0.6811 | 0.6832 | 0.7295 | 0.7424 | 0.7313 | 0.3166 |
| 0.0957 | 4.96 | 2480 | 0.1954 | 0.5970 | 0.7327 | 0.8071 | nan | 0.7625 | 0.9070 | 0.7343 | 0.8071 | 0.7656 | 0.8036 | 0.8320 | 0.3442 | 0.6363 | 0.5262 | 0.8882 | 0.8642 | 0.7561 | 0.8266 | 0.8168 | 0.7836 | 0.4017 | 0.0 | 0.7029 | 0.8052 | 0.6222 | 0.7440 | 0.6464 | 0.7212 | 0.5705 | 0.2782 | 0.4840 | 0.4610 | 0.8116 | 0.6883 | 0.6958 | 0.7341 | 0.7438 | 0.7305 | 0.3055 |
| 0.0839 | 5.0 | 2500 | 0.1927 | 0.5988 | 0.7278 | 0.8200 | nan | 0.8173 | 0.8802 | 0.6631 | 0.8705 | 0.7154 | 0.8477 | 0.7848 | 0.3481 | 0.5379 | 0.5904 | 0.9287 | 0.8472 | 0.7912 | 0.8622 | 0.7959 | 0.7803 | 0.3110 | 0.0 | 0.7022 | 0.7997 | 0.5917 | 0.7852 | 0.6572 | 0.7213 | 0.6105 | 0.3032 | 0.4454 | 0.4850 | 0.8044 | 0.6982 | 0.7167 | 0.7343 | 0.7337 | 0.7242 | 0.2656 |
| 0.0441 | 5.04 | 2520 | 0.1921 | 0.6079 | 0.7363 | 0.8239 | nan | 0.7877 | 0.9069 | 0.6990 | 0.8730 | 0.6964 | 0.8387 | 0.7980 | 0.3814 | 0.5382 | 0.6421 | 0.8931 | 0.7990 | 0.8441 | 0.8362 | 0.7911 | 0.8295 | 0.3623 | 0.0 | 0.7204 | 0.8072 | 0.6099 | 0.7831 | 0.6568 | 0.7206 | 0.6074 | 0.3140 | 0.4512 | 0.5082 | 0.8085 | 0.7050 | 0.7430 | 0.7261 | 0.7320 | 0.7559 | 0.2924 |
| 0.0679 | 5.08 | 2540 | 0.1925 | 0.6096 | 0.7439 | 0.8232 | nan | 0.8173 | 0.8865 | 0.7275 | 0.8745 | 0.7319 | 0.8373 | 0.7785 | 0.4078 | 0.6311 | 0.5003 | 0.9109 | 0.8146 | 0.8512 | 0.8179 | 0.8481 | 0.7909 | 0.4206 | 0.0 | 0.7017 | 0.7981 | 0.6187 | 0.7817 | 0.6650 | 0.7292 | 0.6078 | 0.3298 | 0.4797 | 0.4434 | 0.8036 | 0.7140 | 0.7518 | 0.7390 | 0.7513 | 0.7401 | 0.3181 |
| 0.0762 | 5.12 | 2560 | 0.1966 | 0.5916 | 0.7179 | 0.8151 | nan | 0.8240 | 0.8840 | 0.7232 | 0.8917 | 0.7024 | 0.8440 | 0.7422 | 0.2452 | 0.5112 | 0.5410 | 0.8962 | 0.8666 | 0.7568 | 0.8129 | 0.7840 | 0.8040 | 0.3755 | 0.0 | 0.7137 | 0.8025 | 0.6176 | 0.7807 | 0.6263 | 0.7113 | 0.5895 | 0.2326 | 0.4191 | 0.4490 | 0.8085 | 0.6947 | 0.6996 | 0.7263 | 0.7315 | 0.7389 | 0.3072 |
| 0.0812 | 5.16 | 2580 | 0.2026 | 0.6001 | 0.7320 | 0.8174 | nan | 0.8212 | 0.8860 | 0.7650 | 0.8756 | 0.6950 | 0.8321 | 0.7693 | 0.2653 | 0.5681 | 0.6025 | 0.8839 | 0.7922 | 0.8607 | 0.8671 | 0.8006 | 0.7756 | 0.3841 | 0.0 | 0.7167 | 0.8025 | 0.6292 | 0.7705 | 0.6289 | 0.7126 | 0.5880 | 0.2479 | 0.4657 | 0.4925 | 0.8058 | 0.7027 | 0.7396 | 0.7394 | 0.7389 | 0.7249 | 0.2954 |
| 0.0444 | 5.2 | 2600 | 0.1922 | 0.6073 | 0.7353 | 0.8240 | nan | 0.8309 | 0.8819 | 0.7276 | 0.8846 | 0.7038 | 0.8672 | 0.7492 | 0.3170 | 0.5291 | 0.6013 | 0.9216 | 0.7891 | 0.8462 | 0.8551 | 0.8235 | 0.8115 | 0.3607 | 0.0 | 0.7482 | 0.8089 | 0.6214 | 0.7816 | 0.6365 | 0.7228 | 0.5935 | 0.2867 | 0.4451 | 0.4850 | 0.8089 | 0.7069 | 0.7373 | 0.7486 | 0.7520 | 0.7531 | 0.2952 |
| 0.0723 | 5.24 | 2620 | 0.1927 | 0.6121 | 0.7415 | 0.8252 | nan | 0.8155 | 0.9101 | 0.7610 | 0.8830 | 0.7283 | 0.8631 | 0.7346 | 0.3833 | 0.5606 | 0.6069 | 0.8925 | 0.8546 | 0.7885 | 0.8422 | 0.8172 | 0.8209 | 0.3426 | 0.0 | 0.7512 | 0.8134 | 0.6279 | 0.7795 | 0.6473 | 0.7385 | 0.5807 | 0.3154 | 0.4708 | 0.5069 | 0.8119 | 0.7036 | 0.7149 | 0.7469 | 0.7491 | 0.7647 | 0.2952 |
| 0.038 | 5.28 | 2640 | 0.2019 | 0.6074 | 0.7386 | 0.8191 | nan | 0.8442 | 0.8776 | 0.6959 | 0.8620 | 0.6979 | 0.8641 | 0.7660 | 0.3409 | 0.5926 | 0.5682 | 0.9181 | 0.8056 | 0.8347 | 0.8304 | 0.8502 | 0.7998 | 0.4073 | 0.0 | 0.7348 | 0.8067 | 0.6034 | 0.7649 | 0.6384 | 0.7362 | 0.5644 | 0.2843 | 0.4902 | 0.4999 | 0.8107 | 0.7004 | 0.7260 | 0.7447 | 0.7476 | 0.7535 | 0.3277 |
| 0.0545 | 5.32 | 2660 | 0.2016 | 0.6004 | 0.7302 | 0.8180 | nan | 0.8631 | 0.8974 | 0.7166 | 0.8660 | 0.7245 | 0.8718 | 0.7548 | 0.2667 | 0.5677 | 0.6003 | 0.8980 | 0.8759 | 0.6811 | 0.8429 | 0.8213 | 0.8017 | 0.3629 | 0.0 | 0.7388 | 0.8079 | 0.6163 | 0.7700 | 0.6512 | 0.7397 | 0.5754 | 0.2448 | 0.4684 | 0.5051 | 0.8088 | 0.6704 | 0.6398 | 0.7464 | 0.7525 | 0.7572 | 0.3150 |
| 0.0644 | 5.36 | 2680 | 0.1983 | 0.6148 | 0.7467 | 0.8243 | nan | 0.8191 | 0.9042 | 0.7854 | 0.8634 | 0.7273 | 0.8680 | 0.7522 | 0.3414 | 0.5216 | 0.6624 | 0.9161 | 0.8504 | 0.7786 | 0.8585 | 0.8159 | 0.8329 | 0.3973 | 0.0 | 0.7561 | 0.8158 | 0.6249 | 0.7688 | 0.6561 | 0.7506 | 0.5695 | 0.3067 | 0.4492 | 0.5257 | 0.8140 | 0.7002 | 0.7042 | 0.7520 | 0.7539 | 0.7789 | 0.3397 |
| 0.0814 | 5.4 | 2700 | 0.2007 | 0.6073 | 0.7347 | 0.8188 | nan | 0.8194 | 0.8470 | 0.7055 | 0.8634 | 0.7134 | 0.8847 | 0.7546 | 0.3835 | 0.5528 | 0.6093 | 0.9166 | 0.8344 | 0.8307 | 0.8395 | 0.8268 | 0.8139 | 0.2941 | 0.0 | 0.7186 | 0.7897 | 0.6077 | 0.7645 | 0.6524 | 0.7458 | 0.5671 | 0.3165 | 0.4585 | 0.4999 | 0.8149 | 0.7195 | 0.7399 | 0.7455 | 0.7569 | 0.7621 | 0.2722 |
| 0.0437 | 5.44 | 2720 | 0.1966 | 0.5950 | 0.7244 | 0.8125 | nan | 0.8239 | 0.9001 | 0.7067 | 0.8549 | 0.6844 | 0.8617 | 0.7482 | 0.3604 | 0.3834 | 0.7186 | 0.8956 | 0.7357 | 0.8750 | 0.8170 | 0.8544 | 0.8115 | 0.2840 | 0.0 | 0.7154 | 0.8097 | 0.6147 | 0.7641 | 0.6176 | 0.7480 | 0.5478 | 0.3101 | 0.3551 | 0.5117 | 0.8145 | 0.6718 | 0.7199 | 0.7336 | 0.7494 | 0.7618 | 0.2643 |
| 0.0536 | 5.48 | 2740 | 0.2150 | 0.5843 | 0.7165 | 0.7959 | nan | 0.7963 | 0.8867 | 0.7123 | 0.8105 | 0.5821 | 0.8255 | 0.8201 | 0.1755 | 0.6811 | 0.4980 | 0.9111 | 0.8575 | 0.7585 | 0.8623 | 0.7805 | 0.7913 | 0.4308 | 0.0 | 0.7054 | 0.8026 | 0.6155 | 0.7356 | 0.5335 | 0.7356 | 0.5247 | 0.1583 | 0.5013 | 0.4513 | 0.8245 | 0.6981 | 0.7006 | 0.7356 | 0.7260 | 0.7410 | 0.3277 |
| 0.0715 | 5.52 | 2760 | 0.2088 | 0.6012 | 0.7312 | 0.8127 | nan | 0.8138 | 0.9035 | 0.7080 | 0.8064 | 0.6314 | 0.8808 | 0.8267 | 0.2183 | 0.5328 | 0.6335 | 0.9009 | 0.8449 | 0.8147 | 0.8598 | 0.8543 | 0.8246 | 0.3757 | 0.0 | 0.7301 | 0.8171 | 0.6143 | 0.7385 | 0.6004 | 0.7536 | 0.5403 | 0.2052 | 0.4497 | 0.5130 | 0.8184 | 0.7211 | 0.7285 | 0.7539 | 0.7559 | 0.7625 | 0.3198 |
| 0.091 | 5.56 | 2780 | 0.2041 | 0.6034 | 0.7423 | 0.8110 | nan | 0.8689 | 0.8771 | 0.7109 | 0.8244 | 0.6929 | 0.8958 | 0.7644 | 0.3538 | 0.5529 | 0.6557 | 0.9130 | 0.7627 | 0.8228 | 0.8463 | 0.8492 | 0.7885 | 0.4405 | 0.0 | 0.7032 | 0.8010 | 0.6166 | 0.7454 | 0.6173 | 0.7461 | 0.5405 | 0.2925 | 0.4647 | 0.5157 | 0.8187 | 0.6948 | 0.7173 | 0.7534 | 0.7638 | 0.7432 | 0.3271 |
| 0.0393 | 5.6 | 2800 | 0.2226 | 0.6045 | 0.7396 | 0.8036 | nan | 0.8102 | 0.8913 | 0.7321 | 0.7656 | 0.6763 | 0.8691 | 0.8480 | 0.2555 | 0.6074 | 0.6081 | 0.9126 | 0.8450 | 0.8172 | 0.8242 | 0.8333 | 0.7906 | 0.4864 | 0.0 | 0.7332 | 0.8077 | 0.6235 | 0.7098 | 0.6315 | 0.7585 | 0.5299 | 0.2295 | 0.4953 | 0.5149 | 0.8173 | 0.7228 | 0.7343 | 0.7428 | 0.7567 | 0.7462 | 0.3268 |
| 0.0414 | 5.64 | 2820 | 0.2097 | 0.6077 | 0.7418 | 0.8162 | nan | 0.8296 | 0.8941 | 0.7577 | 0.8453 | 0.6405 | 0.8695 | 0.7839 | 0.2478 | 0.5981 | 0.6425 | 0.9007 | 0.8282 | 0.8185 | 0.8512 | 0.8185 | 0.8026 | 0.4819 | 0.0 | 0.7503 | 0.8152 | 0.6313 | 0.7578 | 0.6115 | 0.7246 | 0.5618 | 0.2221 | 0.4853 | 0.5175 | 0.8186 | 0.7245 | 0.7450 | 0.7400 | 0.7506 | 0.7550 | 0.3278 |
| 0.1061 | 5.68 | 2840 | 0.2079 | 0.6085 | 0.7396 | 0.8139 | nan | 0.8036 | 0.8906 | 0.7229 | 0.8454 | 0.6381 | 0.8610 | 0.7658 | 0.3532 | 0.5529 | 0.6432 | 0.9175 | 0.8227 | 0.8296 | 0.8678 | 0.8142 | 0.8296 | 0.4152 | 0.0 | 0.7403 | 0.8125 | 0.6203 | 0.7558 | 0.6054 | 0.7119 | 0.5590 | 0.2992 | 0.4675 | 0.5195 | 0.8170 | 0.7175 | 0.7413 | 0.7384 | 0.7399 | 0.7671 | 0.3402 |
| 0.044 | 5.72 | 2860 | 0.2129 | 0.5955 | 0.7281 | 0.8073 | nan | 0.8760 | 0.8817 | 0.7239 | 0.8369 | 0.6680 | 0.8184 | 0.7773 | 0.1578 | 0.5715 | 0.6299 | 0.8995 | 0.8182 | 0.8421 | 0.8418 | 0.8206 | 0.7976 | 0.4171 | 0.0 | 0.7150 | 0.8070 | 0.6213 | 0.7422 | 0.5868 | 0.7250 | 0.5270 | 0.1529 | 0.4774 | 0.5211 | 0.8188 | 0.7080 | 0.7371 | 0.7410 | 0.7502 | 0.7567 | 0.3316 |
| 0.0832 | 5.76 | 2880 | 0.2060 | 0.6030 | 0.7359 | 0.8107 | nan | 0.8445 | 0.8972 | 0.7264 | 0.8434 | 0.6797 | 0.8604 | 0.7604 | 0.3486 | 0.6110 | 0.5234 | 0.9062 | 0.8506 | 0.7577 | 0.8396 | 0.7971 | 0.8256 | 0.4393 | 0.0 | 0.7388 | 0.8133 | 0.6226 | 0.7478 | 0.6102 | 0.7332 | 0.5351 | 0.2822 | 0.4757 | 0.4633 | 0.8212 | 0.7096 | 0.7075 | 0.7428 | 0.7475 | 0.7665 | 0.3362 |
| 0.0458 | 5.8 | 2900 | 0.2080 | 0.6049 | 0.7418 | 0.8100 | nan | 0.8212 | 0.8851 | 0.7796 | 0.8234 | 0.6697 | 0.8497 | 0.7741 | 0.3276 | 0.5372 | 0.6118 | 0.9123 | 0.8514 | 0.8086 | 0.8501 | 0.8600 | 0.8373 | 0.4115 | 0.0 | 0.7295 | 0.8059 | 0.6272 | 0.7408 | 0.6093 | 0.7425 | 0.5317 | 0.2670 | 0.4552 | 0.5113 | 0.8183 | 0.7212 | 0.7323 | 0.7519 | 0.7597 | 0.7728 | 0.3115 |
| 0.0429 | 5.84 | 2920 | 0.2081 | 0.6025 | 0.7436 | 0.8059 | nan | 0.8457 | 0.8600 | 0.7882 | 0.8348 | 0.7078 | 0.8311 | 0.7521 | 0.3579 | 0.6167 | 0.6247 | 0.9036 | 0.8151 | 0.8271 | 0.8229 | 0.8037 | 0.8150 | 0.4357 | 0.0 | 0.6773 | 0.7914 | 0.6201 | 0.7399 | 0.6141 | 0.7345 | 0.5253 | 0.2743 | 0.4960 | 0.5209 | 0.8174 | 0.7162 | 0.7385 | 0.7401 | 0.7466 | 0.7628 | 0.3298 |
| 0.054 | 5.88 | 2940 | 0.2204 | 0.5966 | 0.7370 | 0.8051 | nan | 0.7878 | 0.8990 | 0.6791 | 0.8110 | 0.6541 | 0.8227 | 0.7956 | 0.3752 | 0.5920 | 0.5842 | 0.9142 | 0.8651 | 0.7815 | 0.8965 | 0.8251 | 0.8181 | 0.4275 | 0.0 | 0.7110 | 0.8108 | 0.5928 | 0.7351 | 0.5910 | 0.7252 | 0.5343 | 0.2705 | 0.4730 | 0.4895 | 0.8139 | 0.7148 | 0.7219 | 0.7288 | 0.7308 | 0.7629 | 0.3323 |
| 0.0526 | 5.92 | 2960 | 0.2271 | 0.5921 | 0.7137 | 0.8074 | nan | 0.7305 | 0.8986 | 0.6791 | 0.8207 | 0.6357 | 0.8230 | 0.8263 | 0.1921 | 0.5933 | 0.5993 | 0.9000 | 0.7991 | 0.8748 | 0.8311 | 0.8310 | 0.8173 | 0.2809 | 0.0 | 0.7011 | 0.8120 | 0.5975 | 0.7376 | 0.5800 | 0.7360 | 0.5299 | 0.1707 | 0.4862 | 0.5073 | 0.8141 | 0.7211 | 0.7529 | 0.7340 | 0.7601 | 0.7582 | 0.2582 |
| 0.0787 | 5.96 | 2980 | 0.1975 | 0.6112 | 0.7550 | 0.8154 | nan | 0.8712 | 0.8549 | 0.7621 | 0.8253 | 0.7788 | 0.8781 | 0.7424 | 0.3999 | 0.5312 | 0.6642 | 0.8947 | 0.8300 | 0.8439 | 0.8626 | 0.8529 | 0.8194 | 0.4234 | 0.0 | 0.7091 | 0.7942 | 0.6226 | 0.7461 | 0.6634 | 0.7555 | 0.5392 | 0.2870 | 0.4502 | 0.5253 | 0.8142 | 0.7330 | 0.7496 | 0.7555 | 0.7663 | 0.7618 | 0.3277 |
| 0.077 | 6.0 | 3000 | 0.1916 | 0.6131 | 0.7349 | 0.8314 | nan | 0.7940 | 0.9065 | 0.6260 | 0.9004 | 0.8101 | 0.8706 | 0.6719 | 0.3622 | 0.5013 | 0.6468 | 0.9126 | 0.8364 | 0.8394 | 0.8486 | 0.8284 | 0.8337 | 0.3050 | 0.0 | 0.7254 | 0.8176 | 0.5706 | 0.7962 | 0.6645 | 0.7580 | 0.5719 | 0.3001 | 0.4435 | 0.5239 | 0.8170 | 0.7344 | 0.7520 | 0.7461 | 0.7545 | 0.7748 | 0.2853 |
| 0.0346 | 6.04 | 3020 | 0.2012 | 0.6083 | 0.7380 | 0.8188 | nan | 0.7745 | 0.9022 | 0.7231 | 0.8575 | 0.8261 | 0.8445 | 0.6999 | 0.3096 | 0.6325 | 0.5564 | 0.9167 | 0.8575 | 0.7878 | 0.8419 | 0.8112 | 0.8105 | 0.3936 | 0.0 | 0.7344 | 0.8100 | 0.6167 | 0.7698 | 0.6416 | 0.7527 | 0.5464 | 0.2616 | 0.5020 | 0.4926 | 0.8105 | 0.7176 | 0.7237 | 0.7446 | 0.7461 | 0.7632 | 0.3165 |
| 0.1209 | 6.08 | 3040 | 0.1980 | 0.6079 | 0.7360 | 0.8205 | nan | 0.7869 | 0.9241 | 0.7542 | 0.8579 | 0.8112 | 0.8485 | 0.7041 | 0.2721 | 0.5967 | 0.5987 | 0.8841 | 0.8261 | 0.8375 | 0.7873 | 0.8708 | 0.8015 | 0.3504 | 0.0 | 0.7410 | 0.8122 | 0.6182 | 0.7677 | 0.6410 | 0.7500 | 0.5438 | 0.2397 | 0.4894 | 0.5063 | 0.8078 | 0.7253 | 0.7425 | 0.7332 | 0.7581 | 0.7582 | 0.3084 |
| 0.0416 | 6.12 | 3060 | 0.1973 | 0.6151 | 0.7489 | 0.8206 | nan | 0.8262 | 0.8939 | 0.7506 | 0.8571 | 0.8057 | 0.8401 | 0.7037 | 0.3972 | 0.5672 | 0.6363 | 0.9234 | 0.8370 | 0.8145 | 0.8586 | 0.8284 | 0.8339 | 0.3578 | 0.0 | 0.7489 | 0.8125 | 0.6259 | 0.7666 | 0.6410 | 0.7477 | 0.5412 | 0.3161 | 0.4825 | 0.5207 | 0.8096 | 0.7224 | 0.7329 | 0.7565 | 0.7594 | 0.7769 | 0.3103 |
| 0.0439 | 6.16 | 3080 | 0.1961 | 0.6118 | 0.7440 | 0.8172 | nan | 0.7941 | 0.9156 | 0.7294 | 0.8416 | 0.8139 | 0.8435 | 0.7159 | 0.4061 | 0.5151 | 0.6792 | 0.8770 | 0.8128 | 0.8503 | 0.8483 | 0.8207 | 0.8163 | 0.3677 | 0.0 | 0.7441 | 0.8094 | 0.6217 | 0.7562 | 0.6516 | 0.7470 | 0.5382 | 0.3008 | 0.4542 | 0.5300 | 0.8056 | 0.7234 | 0.7458 | 0.7501 | 0.7595 | 0.7641 | 0.3111 |
| 0.0467 | 6.2 | 3100 | 0.1993 | 0.6138 | 0.7460 | 0.8209 | nan | 0.8212 | 0.8919 | 0.6869 | 0.8580 | 0.8067 | 0.8439 | 0.7093 | 0.4469 | 0.6316 | 0.5251 | 0.9193 | 0.8579 | 0.8226 | 0.8563 | 0.8425 | 0.8178 | 0.3439 | 0.0 | 0.7509 | 0.8102 | 0.6060 | 0.7639 | 0.6560 | 0.7453 | 0.5469 | 0.3408 | 0.4853 | 0.4688 | 0.8130 | 0.7281 | 0.7425 | 0.7528 | 0.7666 | 0.7698 | 0.3011 |
| 0.0639 | 6.24 | 3120 | 0.1939 | 0.6192 | 0.7579 | 0.8265 | nan | 0.8742 | 0.8965 | 0.7917 | 0.8737 | 0.8232 | 0.8609 | 0.6932 | 0.4729 | 0.6036 | 0.5774 | 0.8927 | 0.8442 | 0.8251 | 0.8449 | 0.8313 | 0.8289 | 0.3502 | 0.0 | 0.7351 | 0.8098 | 0.6319 | 0.7757 | 0.6619 | 0.7524 | 0.5602 | 0.3486 | 0.4854 | 0.4994 | 0.8139 | 0.7307 | 0.7493 | 0.7511 | 0.7647 | 0.7767 | 0.2985 |
| 0.051 | 6.28 | 3140 | 0.1950 | 0.6220 | 0.7483 | 0.8331 | nan | 0.7659 | 0.9159 | 0.7107 | 0.8991 | 0.8370 | 0.8677 | 0.6572 | 0.4390 | 0.5374 | 0.6454 | 0.9061 | 0.8271 | 0.8608 | 0.8353 | 0.8573 | 0.8176 | 0.3415 | 0.0 | 0.7207 | 0.8189 | 0.6197 | 0.7846 | 0.6857 | 0.7521 | 0.5636 | 0.3327 | 0.4680 | 0.5305 | 0.8165 | 0.7409 | 0.7586 | 0.7565 | 0.7750 | 0.7733 | 0.2979 |
| 0.0594 | 6.32 | 3160 | 0.1999 | 0.6118 | 0.7459 | 0.8225 | nan | 0.8510 | 0.9022 | 0.7170 | 0.8657 | 0.8162 | 0.8436 | 0.7059 | 0.3287 | 0.6434 | 0.5611 | 0.9120 | 0.8567 | 0.7685 | 0.8446 | 0.8253 | 0.8281 | 0.4108 | 0.0 | 0.7467 | 0.8156 | 0.6191 | 0.7684 | 0.6833 | 0.7346 | 0.5523 | 0.2637 | 0.4770 | 0.4749 | 0.8154 | 0.7191 | 0.7192 | 0.7495 | 0.7587 | 0.7786 | 0.3354 |
| 0.0409 | 6.36 | 3180 | 0.1963 | 0.6192 | 0.7575 | 0.8254 | nan | 0.8534 | 0.8970 | 0.7831 | 0.8714 | 0.8042 | 0.8622 | 0.6865 | 0.3991 | 0.5463 | 0.6052 | 0.8979 | 0.8318 | 0.8446 | 0.8594 | 0.8434 | 0.8354 | 0.4559 | 0.0 | 0.7419 | 0.8124 | 0.6315 | 0.7739 | 0.6809 | 0.7405 | 0.5644 | 0.3053 | 0.4624 | 0.5117 | 0.8150 | 0.7316 | 0.7465 | 0.7526 | 0.7583 | 0.7718 | 0.3453 |
| 0.0484 | 6.4 | 3200 | 0.1987 | 0.6111 | 0.7424 | 0.8209 | nan | 0.8281 | 0.9024 | 0.6257 | 0.8620 | 0.7811 | 0.8600 | 0.7204 | 0.3944 | 0.6037 | 0.5542 | 0.9109 | 0.8334 | 0.7980 | 0.8483 | 0.8021 | 0.8282 | 0.4678 | 0.0 | 0.7514 | 0.8125 | 0.5716 | 0.7692 | 0.6594 | 0.7495 | 0.5607 | 0.3106 | 0.4874 | 0.4876 | 0.8123 | 0.7212 | 0.7319 | 0.7363 | 0.7409 | 0.7658 | 0.3315 |
| 0.0487 | 6.44 | 3220 | 0.2036 | 0.6149 | 0.7462 | 0.8220 | nan | 0.8514 | 0.8878 | 0.6876 | 0.8779 | 0.7743 | 0.8645 | 0.7127 | 0.4503 | 0.6008 | 0.6170 | 0.8930 | 0.8475 | 0.7827 | 0.8425 | 0.7648 | 0.8298 | 0.4014 | 0.0 | 0.7369 | 0.8084 | 0.6070 | 0.7732 | 0.6437 | 0.7516 | 0.5569 | 0.3440 | 0.4941 | 0.5205 | 0.8114 | 0.7216 | 0.7223 | 0.7360 | 0.7266 | 0.7781 | 0.3354 |
| 0.0718 | 6.48 | 3240 | 0.2046 | 0.6133 | 0.7454 | 0.8194 | nan | 0.8476 | 0.8742 | 0.7364 | 0.8526 | 0.7709 | 0.8615 | 0.7423 | 0.3505 | 0.5951 | 0.6241 | 0.9139 | 0.8710 | 0.7696 | 0.8505 | 0.8137 | 0.8146 | 0.3840 | 0.0 | 0.7315 | 0.8026 | 0.6207 | 0.7617 | 0.6362 | 0.7511 | 0.5496 | 0.2920 | 0.4927 | 0.5264 | 0.8121 | 0.7279 | 0.7215 | 0.7561 | 0.7537 | 0.7749 | 0.3295 |
| 0.0666 | 6.52 | 3260 | 0.2018 | 0.6103 | 0.7363 | 0.8237 | nan | 0.8582 | 0.8781 | 0.6627 | 0.8734 | 0.7564 | 0.8542 | 0.7235 | 0.2790 | 0.5671 | 0.6371 | 0.9218 | 0.8576 | 0.8130 | 0.8377 | 0.8483 | 0.8246 | 0.3251 | 0.0 | 0.7225 | 0.8045 | 0.5912 | 0.7707 | 0.6436 | 0.7516 | 0.5589 | 0.2490 | 0.4777 | 0.5257 | 0.8117 | 0.7423 | 0.7456 | 0.7587 | 0.7612 | 0.7767 | 0.2931 |
| 0.055 | 6.56 | 3280 | 0.1966 | 0.6189 | 0.7470 | 0.8300 | nan | 0.8568 | 0.8922 | 0.7653 | 0.8824 | 0.7941 | 0.8632 | 0.7250 | 0.2978 | 0.5364 | 0.6410 | 0.9050 | 0.8366 | 0.8240 | 0.8570 | 0.8350 | 0.8158 | 0.3706 | 0.0 | 0.7414 | 0.8117 | 0.6337 | 0.7806 | 0.6754 | 0.7565 | 0.5760 | 0.2545 | 0.4678 | 0.5268 | 0.8145 | 0.7382 | 0.7441 | 0.7636 | 0.7652 | 0.7718 | 0.3177 |
| 0.0586 | 6.6 | 3300 | 0.1984 | 0.6196 | 0.7496 | 0.8243 | nan | 0.8386 | 0.8967 | 0.7340 | 0.8547 | 0.7187 | 0.8721 | 0.7726 | 0.3753 | 0.5738 | 0.6503 | 0.8946 | 0.8357 | 0.8508 | 0.8480 | 0.8219 | 0.8012 | 0.4052 | 0.0 | 0.7402 | 0.8120 | 0.6273 | 0.7598 | 0.6449 | 0.7617 | 0.5580 | 0.3214 | 0.4871 | 0.5336 | 0.8142 | 0.7362 | 0.7574 | 0.7550 | 0.7624 | 0.7641 | 0.3178 |
| 0.054 | 6.64 | 3320 | 0.1945 | 0.6176 | 0.7460 | 0.8294 | nan | 0.8253 | 0.8945 | 0.7383 | 0.8571 | 0.7803 | 0.8766 | 0.7617 | 0.3174 | 0.5509 | 0.6698 | 0.9057 | 0.8345 | 0.8537 | 0.8654 | 0.8013 | 0.8261 | 0.3228 | 0.0 | 0.7363 | 0.8137 | 0.6226 | 0.7705 | 0.6833 | 0.7702 | 0.5751 | 0.2722 | 0.4787 | 0.5382 | 0.8145 | 0.7380 | 0.7596 | 0.7456 | 0.7416 | 0.7759 | 0.2810 |
| 0.0918 | 6.68 | 3340 | 0.1977 | 0.6178 | 0.7486 | 0.8289 | nan | 0.8353 | 0.8952 | 0.7535 | 0.8468 | 0.7779 | 0.8714 | 0.7888 | 0.2920 | 0.6281 | 0.6273 | 0.9077 | 0.8633 | 0.8127 | 0.8589 | 0.7952 | 0.8256 | 0.3471 | 0.0 | 0.7390 | 0.8108 | 0.6278 | 0.7660 | 0.6963 | 0.7715 | 0.5818 | 0.2559 | 0.5158 | 0.5280 | 0.8138 | 0.7307 | 0.7471 | 0.7388 | 0.7326 | 0.7751 | 0.2890 |
| 0.0485 | 6.72 | 3360 | 0.1935 | 0.6151 | 0.7438 | 0.8303 | nan | 0.8458 | 0.8932 | 0.7397 | 0.8770 | 0.8135 | 0.8903 | 0.7165 | 0.3140 | 0.5889 | 0.5917 | 0.9073 | 0.8082 | 0.8552 | 0.8702 | 0.8096 | 0.7906 | 0.3327 | 0.0 | 0.7394 | 0.8087 | 0.6186 | 0.7824 | 0.6935 | 0.7730 | 0.5854 | 0.2679 | 0.4889 | 0.5122 | 0.8123 | 0.7277 | 0.7524 | 0.7443 | 0.7412 | 0.7485 | 0.2754 |
| 0.0707 | 6.76 | 3380 | 0.1956 | 0.6135 | 0.7441 | 0.8298 | nan | 0.8640 | 0.8860 | 0.7093 | 0.8739 | 0.7835 | 0.8753 | 0.7555 | 0.2561 | 0.5847 | 0.6261 | 0.9060 | 0.8611 | 0.7900 | 0.8629 | 0.7686 | 0.8284 | 0.4190 | 0.0 | 0.7419 | 0.8129 | 0.6096 | 0.7736 | 0.6967 | 0.7596 | 0.5906 | 0.2294 | 0.4890 | 0.5329 | 0.8141 | 0.7393 | 0.7399 | 0.7283 | 0.7234 | 0.7732 | 0.2894 |
| 0.0479 | 6.8 | 3400 | 0.2023 | 0.6173 | 0.7511 | 0.8284 | nan | 0.8060 | 0.8994 | 0.7386 | 0.8636 | 0.7464 | 0.8888 | 0.7598 | 0.4561 | 0.4873 | 0.6764 | 0.9131 | 0.8034 | 0.8738 | 0.8118 | 0.8396 | 0.8131 | 0.3915 | 0.0 | 0.7375 | 0.8162 | 0.6257 | 0.7735 | 0.6701 | 0.7588 | 0.5810 | 0.3186 | 0.4419 | 0.5425 | 0.8176 | 0.7365 | 0.7567 | 0.7342 | 0.7566 | 0.7620 | 0.2826 |
| 0.0681 | 6.84 | 3420 | 0.1910 | 0.6193 | 0.7555 | 0.8259 | nan | 0.8415 | 0.9146 | 0.7535 | 0.8504 | 0.8153 | 0.8551 | 0.7497 | 0.4178 | 0.6103 | 0.6438 | 0.8894 | 0.8482 | 0.8158 | 0.8471 | 0.7817 | 0.8164 | 0.3937 | 0.0 | 0.7503 | 0.8117 | 0.6351 | 0.7665 | 0.6840 | 0.7704 | 0.5730 | 0.3150 | 0.4980 | 0.5348 | 0.8161 | 0.7367 | 0.7468 | 0.7341 | 0.7374 | 0.7620 | 0.2755 |
| 0.0527 | 6.88 | 3440 | 0.2485 | 0.5992 | 0.7385 | 0.7956 | nan | 0.8583 | 0.9012 | 0.6970 | 0.8161 | 0.4887 | 0.7942 | 0.8130 | 0.4627 | 0.5456 | 0.6360 | 0.9041 | 0.8325 | 0.8547 | 0.8560 | 0.8318 | 0.8158 | 0.4471 | 0.0 | 0.7482 | 0.8062 | 0.6126 | 0.7252 | 0.4562 | 0.7181 | 0.5111 | 0.3480 | 0.4828 | 0.5308 | 0.8197 | 0.7248 | 0.7482 | 0.7423 | 0.7568 | 0.7627 | 0.2918 |
| 0.0552 | 6.92 | 3460 | 0.2340 | 0.6095 | 0.7488 | 0.8068 | nan | 0.8834 | 0.8760 | 0.7525 | 0.8465 | 0.5447 | 0.8179 | 0.7830 | 0.4823 | 0.6262 | 0.6107 | 0.9227 | 0.8547 | 0.8231 | 0.8487 | 0.8352 | 0.8306 | 0.3909 | 0.0 | 0.7352 | 0.8068 | 0.6311 | 0.7391 | 0.5054 | 0.7189 | 0.5285 | 0.3720 | 0.5219 | 0.5261 | 0.8197 | 0.7314 | 0.7472 | 0.7522 | 0.7705 | 0.7766 | 0.2888 |
| 0.0467 | 6.96 | 3480 | 0.2203 | 0.6069 | 0.7367 | 0.8145 | nan | 0.8406 | 0.8867 | 0.7886 | 0.8672 | 0.6168 | 0.8327 | 0.7707 | 0.4004 | 0.5789 | 0.6595 | 0.8940 | 0.8545 | 0.8098 | 0.8402 | 0.8144 | 0.8331 | 0.2364 | 0.0 | 0.7277 | 0.8133 | 0.6357 | 0.7570 | 0.5657 | 0.7190 | 0.5524 | 0.3152 | 0.5036 | 0.5464 | 0.8177 | 0.7252 | 0.7368 | 0.7496 | 0.7611 | 0.7712 | 0.2260 |
| 0.0439 | 7.0 | 3500 | 0.2275 | 0.6051 | 0.7303 | 0.8110 | nan | 0.8470 | 0.8943 | 0.6942 | 0.8549 | 0.6545 | 0.8176 | 0.7530 | 0.3131 | 0.6298 | 0.6255 | 0.9062 | 0.8398 | 0.8313 | 0.8247 | 0.8425 | 0.7976 | 0.2892 | 0.0 | 0.7388 | 0.8097 | 0.6109 | 0.7479 | 0.5758 | 0.7290 | 0.5326 | 0.2652 | 0.5192 | 0.5317 | 0.8174 | 0.7297 | 0.7445 | 0.7506 | 0.7710 | 0.7548 | 0.2632 |
| 0.0521 | 7.04 | 3520 | 0.2251 | 0.6088 | 0.7420 | 0.8137 | nan | 0.8732 | 0.8794 | 0.7645 | 0.8523 | 0.7060 | 0.8313 | 0.7457 | 0.3072 | 0.5490 | 0.6194 | 0.9096 | 0.7940 | 0.8878 | 0.8470 | 0.8630 | 0.7804 | 0.4046 | 0.0 | 0.7474 | 0.8070 | 0.6354 | 0.7500 | 0.6009 | 0.7335 | 0.5409 | 0.2459 | 0.4823 | 0.5253 | 0.8200 | 0.7260 | 0.7482 | 0.7637 | 0.7731 | 0.7381 | 0.3209 |
| 0.0309 | 7.08 | 3540 | 0.2404 | 0.6004 | 0.7310 | 0.8055 | nan | 0.8285 | 0.8969 | 0.7766 | 0.8295 | 0.6323 | 0.8245 | 0.7835 | 0.2006 | 0.6407 | 0.5665 | 0.9032 | 0.8318 | 0.8426 | 0.8452 | 0.8229 | 0.7760 | 0.4249 | 0.0 | 0.7453 | 0.8156 | 0.6395 | 0.7323 | 0.5505 | 0.7299 | 0.5171 | 0.1760 | 0.5113 | 0.4996 | 0.8199 | 0.7356 | 0.7584 | 0.7586 | 0.7658 | 0.7337 | 0.3173 |
| 0.041 | 7.12 | 3560 | 0.2270 | 0.6036 | 0.7300 | 0.8090 | nan | 0.8632 | 0.8931 | 0.6576 | 0.8435 | 0.6410 | 0.8345 | 0.7614 | 0.2645 | 0.5828 | 0.6233 | 0.9111 | 0.8093 | 0.8429 | 0.8509 | 0.8402 | 0.7893 | 0.4015 | 0.0 | 0.7552 | 0.8082 | 0.5947 | 0.7412 | 0.5704 | 0.7325 | 0.5289 | 0.2354 | 0.4928 | 0.5234 | 0.8194 | 0.7224 | 0.7475 | 0.7582 | 0.7656 | 0.7445 | 0.3243 |
| 0.0516 | 7.16 | 3580 | 0.2235 | 0.6068 | 0.7352 | 0.8144 | nan | 0.8617 | 0.8936 | 0.6386 | 0.8380 | 0.7164 | 0.8518 | 0.7569 | 0.3071 | 0.5462 | 0.6456 | 0.9117 | 0.8011 | 0.8581 | 0.8647 | 0.8250 | 0.7942 | 0.3875 | 0.0 | 0.7505 | 0.8082 | 0.5835 | 0.7456 | 0.6204 | 0.7463 | 0.5376 | 0.2546 | 0.4747 | 0.5257 | 0.8182 | 0.7202 | 0.7438 | 0.7604 | 0.7633 | 0.7480 | 0.3215 |
| 0.0444 | 7.2 | 3600 | 0.2259 | 0.6113 | 0.7438 | 0.8127 | nan | 0.8235 | 0.8932 | 0.7367 | 0.8187 | 0.6444 | 0.8665 | 0.8099 | 0.3617 | 0.6273 | 0.6339 | 0.9160 | 0.8431 | 0.8102 | 0.8794 | 0.7815 | 0.8072 | 0.3914 | 0.0 | 0.7410 | 0.8093 | 0.6299 | 0.7389 | 0.5965 | 0.7561 | 0.5393 | 0.2970 | 0.5100 | 0.5292 | 0.8202 | 0.7342 | 0.7461 | 0.7426 | 0.7365 | 0.7587 | 0.3185 |
| 0.0443 | 7.24 | 3620 | 0.2187 | 0.6184 | 0.7525 | 0.8190 | nan | 0.8530 | 0.8955 | 0.7771 | 0.8274 | 0.6900 | 0.8704 | 0.8047 | 0.4150 | 0.5997 | 0.6314 | 0.9052 | 0.8460 | 0.8180 | 0.8637 | 0.8151 | 0.8124 | 0.3677 | 0.0 | 0.7525 | 0.8098 | 0.6386 | 0.7475 | 0.6305 | 0.7658 | 0.5575 | 0.3230 | 0.4993 | 0.5302 | 0.8209 | 0.7393 | 0.7484 | 0.7495 | 0.7537 | 0.7600 | 0.3047 |
| 0.0773 | 7.28 | 3640 | 0.2119 | 0.6199 | 0.7516 | 0.8210 | nan | 0.8772 | 0.9028 | 0.7443 | 0.8270 | 0.7095 | 0.8537 | 0.8093 | 0.3872 | 0.6059 | 0.6146 | 0.9135 | 0.8322 | 0.8508 | 0.8241 | 0.8498 | 0.8167 | 0.3585 | 0.0 | 0.7556 | 0.8096 | 0.6315 | 0.7483 | 0.6378 | 0.7640 | 0.5590 | 0.3153 | 0.5032 | 0.5233 | 0.8201 | 0.7369 | 0.7544 | 0.7562 | 0.7717 | 0.7639 | 0.3068 |
| 0.0381 | 7.32 | 3660 | 0.2086 | 0.6088 | 0.7409 | 0.8124 | nan | 0.8592 | 0.8914 | 0.7294 | 0.8354 | 0.7693 | 0.8301 | 0.7288 | 0.3523 | 0.5901 | 0.6420 | 0.9119 | 0.8092 | 0.8492 | 0.8283 | 0.8480 | 0.8010 | 0.3202 | 0.0 | 0.7428 | 0.8083 | 0.6265 | 0.7509 | 0.6160 | 0.7504 | 0.5294 | 0.2703 | 0.4945 | 0.5303 | 0.8220 | 0.7244 | 0.7482 | 0.7515 | 0.7664 | 0.7466 | 0.2808 |
| 0.0464 | 7.36 | 3680 | 0.2155 | 0.6097 | 0.7379 | 0.8135 | nan | 0.8474 | 0.8975 | 0.7075 | 0.8456 | 0.7282 | 0.8638 | 0.7149 | 0.3864 | 0.5974 | 0.5819 | 0.9084 | 0.8256 | 0.8455 | 0.8365 | 0.8537 | 0.7817 | 0.3218 | 0.0 | 0.7408 | 0.8088 | 0.6178 | 0.7546 | 0.5922 | 0.7590 | 0.5152 | 0.3069 | 0.4931 | 0.5063 | 0.8208 | 0.7335 | 0.7535 | 0.7598 | 0.7728 | 0.7445 | 0.2955 |
| 0.0614 | 7.4 | 3700 | 0.2195 | 0.6135 | 0.7500 | 0.8110 | nan | 0.8656 | 0.8814 | 0.7297 | 0.8356 | 0.7074 | 0.8448 | 0.7365 | 0.4880 | 0.5984 | 0.5838 | 0.9176 | 0.8240 | 0.8345 | 0.8315 | 0.8677 | 0.8213 | 0.3814 | 0.0 | 0.7419 | 0.8070 | 0.6230 | 0.7469 | 0.6014 | 0.7525 | 0.5221 | 0.3509 | 0.4926 | 0.5007 | 0.8195 | 0.7314 | 0.7503 | 0.7538 | 0.7739 | 0.7641 | 0.3112 |
| 0.0387 | 7.44 | 3720 | 0.2203 | 0.6204 | 0.7548 | 0.8177 | nan | 0.8613 | 0.8878 | 0.7302 | 0.8424 | 0.7072 | 0.8624 | 0.7557 | 0.4943 | 0.6047 | 0.6229 | 0.8990 | 0.8379 | 0.8324 | 0.8634 | 0.8426 | 0.8073 | 0.3807 | 0.0 | 0.7446 | 0.8094 | 0.6272 | 0.7534 | 0.6154 | 0.7665 | 0.5337 | 0.3675 | 0.5036 | 0.5203 | 0.8211 | 0.7351 | 0.7515 | 0.7663 | 0.7764 | 0.7584 | 0.3162 |
| 0.0756 | 7.48 | 3740 | 0.2238 | 0.6159 | 0.7463 | 0.8187 | nan | 0.8548 | 0.8948 | 0.7299 | 0.8325 | 0.7072 | 0.8686 | 0.7847 | 0.3186 | 0.5954 | 0.6298 | 0.9106 | 0.8341 | 0.8262 | 0.8541 | 0.8236 | 0.8073 | 0.4144 | 0.0 | 0.7526 | 0.8121 | 0.6257 | 0.7509 | 0.6249 | 0.7643 | 0.5441 | 0.2633 | 0.5015 | 0.5210 | 0.8226 | 0.7318 | 0.7506 | 0.7612 | 0.7694 | 0.7608 | 0.3291 |
| 0.0442 | 7.52 | 3760 | 0.2139 | 0.6150 | 0.7454 | 0.8186 | nan | 0.8580 | 0.9114 | 0.7052 | 0.8456 | 0.6986 | 0.8814 | 0.7237 | 0.3424 | 0.6381 | 0.5776 | 0.9101 | 0.8323 | 0.8491 | 0.8561 | 0.8353 | 0.8024 | 0.4048 | 0.0 | 0.7541 | 0.8137 | 0.6187 | 0.7590 | 0.5916 | 0.7691 | 0.5252 | 0.2908 | 0.5133 | 0.4968 | 0.8226 | 0.7350 | 0.7548 | 0.7660 | 0.7775 | 0.7583 | 0.3228 |
| 0.0539 | 7.56 | 3780 | 0.2026 | 0.6198 | 0.7487 | 0.8260 | nan | 0.8731 | 0.8995 | 0.7449 | 0.8710 | 0.7200 | 0.8849 | 0.7157 | 0.3682 | 0.6338 | 0.6196 | 0.9113 | 0.7938 | 0.8676 | 0.8560 | 0.8503 | 0.8035 | 0.3142 | 0.0 | 0.7541 | 0.8119 | 0.6326 | 0.7762 | 0.6140 | 0.7747 | 0.5466 | 0.3147 | 0.5172 | 0.5266 | 0.8235 | 0.7179 | 0.7479 | 0.7624 | 0.7809 | 0.7632 | 0.2924 |
| 0.047 | 7.6 | 3800 | 0.2024 | 0.6212 | 0.7475 | 0.8296 | nan | 0.8603 | 0.8992 | 0.7020 | 0.8756 | 0.7303 | 0.8862 | 0.7304 | 0.3776 | 0.6126 | 0.5955 | 0.9141 | 0.8511 | 0.8107 | 0.8579 | 0.8407 | 0.8378 | 0.3254 | 0.0 | 0.7505 | 0.8158 | 0.6163 | 0.7818 | 0.6228 | 0.7744 | 0.5596 | 0.3137 | 0.5023 | 0.5141 | 0.8244 | 0.7330 | 0.7436 | 0.7663 | 0.7774 | 0.7821 | 0.3034 |
| 0.0467 | 7.64 | 3820 | 0.2028 | 0.6129 | 0.7373 | 0.8199 | nan | 0.8027 | 0.8986 | 0.6825 | 0.8596 | 0.7446 | 0.8921 | 0.7136 | 0.3488 | 0.5648 | 0.6284 | 0.8980 | 0.8360 | 0.7928 | 0.8416 | 0.8354 | 0.8113 | 0.3827 | 0.0 | 0.7326 | 0.8131 | 0.6084 | 0.7703 | 0.6213 | 0.7694 | 0.5378 | 0.2919 | 0.4774 | 0.5175 | 0.8227 | 0.7184 | 0.7291 | 0.7620 | 0.7710 | 0.7670 | 0.3217 |
| 0.0385 | 7.68 | 3840 | 0.2022 | 0.6145 | 0.7447 | 0.8220 | nan | 0.8519 | 0.8908 | 0.7347 | 0.8602 | 0.7322 | 0.8846 | 0.7235 | 0.3646 | 0.5684 | 0.5708 | 0.9190 | 0.8485 | 0.8332 | 0.8654 | 0.8127 | 0.8194 | 0.3794 | 0.0 | 0.7498 | 0.8106 | 0.6242 | 0.7719 | 0.6280 | 0.7682 | 0.5460 | 0.3105 | 0.4718 | 0.4958 | 0.8232 | 0.7229 | 0.7411 | 0.7460 | 0.7484 | 0.7711 | 0.3320 |
| 0.082 | 7.72 | 3860 | 0.2047 | 0.6180 | 0.7498 | 0.8261 | nan | 0.8602 | 0.9006 | 0.7283 | 0.8621 | 0.7385 | 0.9008 | 0.7200 | 0.3629 | 0.6560 | 0.5607 | 0.9057 | 0.8369 | 0.8220 | 0.8445 | 0.8385 | 0.8283 | 0.3802 | 0.0 | 0.7502 | 0.8141 | 0.6240 | 0.7764 | 0.6321 | 0.7699 | 0.5491 | 0.3007 | 0.5019 | 0.4872 | 0.8222 | 0.7280 | 0.7474 | 0.7510 | 0.7594 | 0.7764 | 0.3344 |
| 0.0452 | 7.76 | 3880 | 0.2026 | 0.6187 | 0.7544 | 0.8228 | nan | 0.8522 | 0.8847 | 0.7730 | 0.8698 | 0.7117 | 0.8773 | 0.7253 | 0.4656 | 0.5983 | 0.6178 | 0.9034 | 0.8591 | 0.8158 | 0.8700 | 0.7850 | 0.8353 | 0.3805 | 0.0 | 0.7390 | 0.8077 | 0.6320 | 0.7788 | 0.6067 | 0.7798 | 0.5474 | 0.3492 | 0.4907 | 0.5241 | 0.8225 | 0.7265 | 0.7491 | 0.7399 | 0.7383 | 0.7763 | 0.3284 |
| 0.0709 | 7.8 | 3900 | 0.2129 | 0.6168 | 0.7514 | 0.8228 | nan | 0.8691 | 0.8992 | 0.7177 | 0.8494 | 0.7060 | 0.8733 | 0.7717 | 0.3807 | 0.6129 | 0.5954 | 0.8941 | 0.8474 | 0.8247 | 0.8548 | 0.8000 | 0.8376 | 0.4392 | 0.0 | 0.7570 | 0.8118 | 0.6217 | 0.7666 | 0.6198 | 0.7782 | 0.5532 | 0.3023 | 0.4885 | 0.5096 | 0.8215 | 0.7249 | 0.7523 | 0.7414 | 0.7392 | 0.7806 | 0.3340 |
| 0.0445 | 7.84 | 3920 | 0.2112 | 0.6152 | 0.7479 | 0.8208 | nan | 0.8354 | 0.8968 | 0.7225 | 0.8596 | 0.7025 | 0.8762 | 0.7309 | 0.4132 | 0.5801 | 0.6012 | 0.9090 | 0.8403 | 0.8277 | 0.8304 | 0.8310 | 0.8418 | 0.4157 | 0.0 | 0.7408 | 0.8104 | 0.6227 | 0.7721 | 0.5956 | 0.7748 | 0.5390 | 0.3149 | 0.4730 | 0.5026 | 0.8231 | 0.7298 | 0.7588 | 0.7489 | 0.7601 | 0.7798 | 0.3279 |
| 0.0684 | 7.88 | 3940 | 0.2073 | 0.6162 | 0.7520 | 0.8212 | nan | 0.8597 | 0.8945 | 0.7100 | 0.8620 | 0.7031 | 0.8764 | 0.7234 | 0.4659 | 0.6066 | 0.6061 | 0.9092 | 0.8544 | 0.8132 | 0.8451 | 0.8228 | 0.8359 | 0.3964 | 0.0 | 0.7482 | 0.8133 | 0.6172 | 0.7733 | 0.5902 | 0.7734 | 0.5329 | 0.3347 | 0.4877 | 0.5064 | 0.8232 | 0.7360 | 0.7534 | 0.7511 | 0.7568 | 0.7794 | 0.3151 |
| 0.0461 | 7.92 | 3960 | 0.2076 | 0.6157 | 0.7469 | 0.8250 | nan | 0.8594 | 0.8986 | 0.6659 | 0.8770 | 0.7159 | 0.8692 | 0.7100 | 0.4604 | 0.5639 | 0.5988 | 0.9099 | 0.8512 | 0.8546 | 0.8655 | 0.8396 | 0.8200 | 0.3381 | 0.0 | 0.7589 | 0.8132 | 0.5961 | 0.7836 | 0.5913 | 0.7689 | 0.5409 | 0.3507 | 0.4729 | 0.5124 | 0.8228 | 0.7347 | 0.7600 | 0.7532 | 0.7589 | 0.7715 | 0.2926 |
| 0.053 | 7.96 | 3980 | 0.2174 | 0.6106 | 0.7430 | 0.8218 | nan | 0.8738 | 0.8890 | 0.7214 | 0.8702 | 0.7303 | 0.8785 | 0.7177 | 0.3748 | 0.5630 | 0.5626 | 0.9187 | 0.8729 | 0.7903 | 0.8706 | 0.8151 | 0.8118 | 0.3701 | 0.0 | 0.7605 | 0.8134 | 0.6223 | 0.7789 | 0.6070 | 0.7638 | 0.5417 | 0.3003 | 0.4682 | 0.4870 | 0.8225 | 0.7172 | 0.7317 | 0.7506 | 0.7546 | 0.7626 | 0.3087 |
| 0.063 | 8.0 | 4000 | 0.2192 | 0.6122 | 0.7454 | 0.8158 | nan | 0.8402 | 0.9083 | 0.7397 | 0.8477 | 0.6991 | 0.8612 | 0.7566 | 0.4382 | 0.5439 | 0.5893 | 0.8825 | 0.8527 | 0.8119 | 0.8538 | 0.8192 | 0.8023 | 0.4255 | 0.0 | 0.7532 | 0.8109 | 0.6301 | 0.7640 | 0.6155 | 0.7572 | 0.5442 | 0.3352 | 0.4609 | 0.5009 | 0.8170 | 0.7196 | 0.7373 | 0.7428 | 0.7510 | 0.7598 | 0.3202 |
| 0.0696 | 8.04 | 4020 | 0.2176 | 0.6092 | 0.7437 | 0.8174 | nan | 0.8501 | 0.8994 | 0.7617 | 0.8430 | 0.7154 | 0.8691 | 0.7603 | 0.3024 | 0.5760 | 0.6084 | 0.9050 | 0.7923 | 0.8546 | 0.8203 | 0.8350 | 0.8042 | 0.4453 | 0.0 | 0.7502 | 0.8153 | 0.6318 | 0.7643 | 0.6147 | 0.7635 | 0.5416 | 0.2431 | 0.4767 | 0.5068 | 0.8239 | 0.7155 | 0.7448 | 0.7377 | 0.7574 | 0.7632 | 0.3147 |
| 0.0716 | 8.08 | 4040 | 0.2081 | 0.6164 | 0.7460 | 0.8256 | nan | 0.8457 | 0.8875 | 0.7553 | 0.8637 | 0.7370 | 0.8820 | 0.7645 | 0.3343 | 0.6189 | 0.5919 | 0.9100 | 0.8438 | 0.8032 | 0.8669 | 0.7875 | 0.8119 | 0.3787 | 0.0 | 0.7475 | 0.8098 | 0.6328 | 0.7769 | 0.6563 | 0.7717 | 0.5780 | 0.2759 | 0.4884 | 0.5018 | 0.8258 | 0.7273 | 0.7430 | 0.7411 | 0.7404 | 0.7682 | 0.3097 |
| 0.0476 | 8.12 | 4060 | 0.2121 | 0.6152 | 0.7445 | 0.8213 | nan | 0.8776 | 0.8912 | 0.7376 | 0.8673 | 0.7077 | 0.8765 | 0.7191 | 0.3780 | 0.5497 | 0.6293 | 0.9055 | 0.8189 | 0.8572 | 0.8369 | 0.8284 | 0.8291 | 0.3461 | 0.0 | 0.7476 | 0.8102 | 0.6290 | 0.7731 | 0.6066 | 0.7692 | 0.5422 | 0.3104 | 0.4700 | 0.5254 | 0.8235 | 0.7342 | 0.7590 | 0.7401 | 0.7570 | 0.7771 | 0.2989 |
| 0.0282 | 8.16 | 4080 | 0.2227 | 0.6179 | 0.7503 | 0.8233 | nan | 0.8493 | 0.8953 | 0.7243 | 0.8609 | 0.7054 | 0.8850 | 0.7402 | 0.4689 | 0.5992 | 0.6032 | 0.9098 | 0.8674 | 0.8176 | 0.8304 | 0.8224 | 0.8261 | 0.3496 | 0.0 | 0.7464 | 0.8135 | 0.6221 | 0.7722 | 0.6173 | 0.7711 | 0.5455 | 0.3437 | 0.4873 | 0.5114 | 0.8242 | 0.7384 | 0.7545 | 0.7427 | 0.7597 | 0.7755 | 0.2974 |
| 0.066 | 8.2 | 4100 | 0.2196 | 0.6178 | 0.7515 | 0.8234 | nan | 0.8605 | 0.8867 | 0.7520 | 0.8588 | 0.6987 | 0.8821 | 0.7467 | 0.3982 | 0.5296 | 0.7016 | 0.9118 | 0.8113 | 0.8563 | 0.8405 | 0.8277 | 0.8350 | 0.3778 | 0.0 | 0.7526 | 0.8116 | 0.6271 | 0.7691 | 0.6182 | 0.7677 | 0.5441 | 0.3201 | 0.4636 | 0.5442 | 0.8241 | 0.7320 | 0.7581 | 0.7477 | 0.7625 | 0.7792 | 0.2986 |
| 0.0778 | 8.24 | 4120 | 0.2207 | 0.6158 | 0.7519 | 0.8196 | nan | 0.8662 | 0.8984 | 0.7375 | 0.8417 | 0.7046 | 0.8827 | 0.7453 | 0.4193 | 0.5823 | 0.6251 | 0.9098 | 0.8391 | 0.8376 | 0.8596 | 0.8218 | 0.8180 | 0.3927 | 0.0 | 0.7475 | 0.8082 | 0.6272 | 0.7637 | 0.6183 | 0.7644 | 0.5440 | 0.3164 | 0.4880 | 0.5196 | 0.8225 | 0.7363 | 0.7576 | 0.7433 | 0.7527 | 0.7708 | 0.3040 |
| 0.0467 | 8.28 | 4140 | 0.2348 | 0.6066 | 0.7388 | 0.8137 | nan | 0.8778 | 0.8864 | 0.7390 | 0.8421 | 0.6967 | 0.8328 | 0.7716 | 0.2713 | 0.5635 | 0.6553 | 0.9114 | 0.8487 | 0.8293 | 0.8234 | 0.8276 | 0.8004 | 0.3817 | 0.0 | 0.7537 | 0.8105 | 0.6265 | 0.7509 | 0.5995 | 0.7384 | 0.5331 | 0.2300 | 0.4803 | 0.5344 | 0.8265 | 0.7321 | 0.7541 | 0.7356 | 0.7555 | 0.7611 | 0.2958 |
| 0.0729 | 8.32 | 4160 | 0.2377 | 0.6016 | 0.7342 | 0.8092 | nan | 0.8659 | 0.9055 | 0.7306 | 0.8257 | 0.6606 | 0.8228 | 0.7871 | 0.2538 | 0.5477 | 0.6017 | 0.9047 | 0.8374 | 0.8502 | 0.8598 | 0.8237 | 0.8064 | 0.3972 | 0.0 | 0.7492 | 0.8113 | 0.6273 | 0.7462 | 0.5713 | 0.7264 | 0.5335 | 0.2263 | 0.4677 | 0.5076 | 0.8252 | 0.7278 | 0.7542 | 0.7386 | 0.7492 | 0.7609 | 0.3055 |
| 0.0314 | 8.36 | 4180 | 0.2331 | 0.6053 | 0.7385 | 0.8127 | nan | 0.8451 | 0.9049 | 0.7290 | 0.8338 | 0.6926 | 0.8417 | 0.7630 | 0.2421 | 0.5876 | 0.6142 | 0.8928 | 0.8661 | 0.8179 | 0.8467 | 0.7945 | 0.8287 | 0.4544 | 0.0 | 0.7498 | 0.8132 | 0.6277 | 0.7472 | 0.6012 | 0.7386 | 0.5316 | 0.2206 | 0.4866 | 0.5158 | 0.8222 | 0.7240 | 0.7455 | 0.7416 | 0.7438 | 0.7740 | 0.3121 |
| 0.0417 | 8.4 | 4200 | 0.2297 | 0.6117 | 0.7444 | 0.8154 | nan | 0.8657 | 0.8996 | 0.7438 | 0.8327 | 0.6827 | 0.8573 | 0.7638 | 0.3149 | 0.5832 | 0.6047 | 0.9116 | 0.8488 | 0.8428 | 0.8714 | 0.8068 | 0.8253 | 0.3989 | 0.0 | 0.7633 | 0.8123 | 0.6302 | 0.7487 | 0.6098 | 0.7502 | 0.5344 | 0.2728 | 0.4839 | 0.5104 | 0.8265 | 0.7317 | 0.7573 | 0.7467 | 0.7452 | 0.7725 | 0.3153 |
| 0.05 | 8.44 | 4220 | 0.2271 | 0.6161 | 0.7455 | 0.8215 | nan | 0.8631 | 0.9026 | 0.7511 | 0.8575 | 0.6986 | 0.8655 | 0.7491 | 0.3346 | 0.5949 | 0.6104 | 0.8962 | 0.8472 | 0.8347 | 0.8632 | 0.8054 | 0.8265 | 0.3734 | 0.0 | 0.7625 | 0.8138 | 0.6335 | 0.7622 | 0.6207 | 0.7495 | 0.5443 | 0.2922 | 0.4888 | 0.5166 | 0.8246 | 0.7395 | 0.7607 | 0.7435 | 0.7497 | 0.7785 | 0.3096 |
| 0.0541 | 8.48 | 4240 | 0.2227 | 0.6164 | 0.7388 | 0.8272 | nan | 0.8478 | 0.9055 | 0.7101 | 0.8879 | 0.6953 | 0.8455 | 0.7449 | 0.2957 | 0.6119 | 0.6019 | 0.9073 | 0.8250 | 0.8470 | 0.8558 | 0.8319 | 0.8216 | 0.3246 | 0.0 | 0.7695 | 0.8174 | 0.6182 | 0.7706 | 0.6331 | 0.7388 | 0.5698 | 0.2683 | 0.4955 | 0.5107 | 0.8253 | 0.7389 | 0.7609 | 0.7467 | 0.7556 | 0.7774 | 0.2987 |
| 0.0361 | 8.52 | 4260 | 0.2275 | 0.6168 | 0.7421 | 0.8272 | nan | 0.8536 | 0.8995 | 0.7183 | 0.8799 | 0.7048 | 0.8417 | 0.7611 | 0.3506 | 0.5552 | 0.6506 | 0.9142 | 0.8481 | 0.8468 | 0.8534 | 0.8210 | 0.8173 | 0.2988 | 0.0 | 0.7541 | 0.8131 | 0.6184 | 0.7697 | 0.6383 | 0.7402 | 0.5791 | 0.2963 | 0.4795 | 0.5348 | 0.8234 | 0.7439 | 0.7606 | 0.7444 | 0.7527 | 0.7714 | 0.2818 |
| 0.0389 | 8.56 | 4280 | 0.2229 | 0.6198 | 0.7505 | 0.8290 | nan | 0.8848 | 0.8979 | 0.7303 | 0.8820 | 0.6991 | 0.8480 | 0.7562 | 0.4229 | 0.6257 | 0.6414 | 0.9137 | 0.8404 | 0.8390 | 0.8373 | 0.8252 | 0.8380 | 0.2764 | 0.0 | 0.7545 | 0.8152 | 0.6212 | 0.7709 | 0.6410 | 0.7464 | 0.5771 | 0.3138 | 0.5133 | 0.5295 | 0.8244 | 0.7366 | 0.7597 | 0.7498 | 0.7575 | 0.7848 | 0.2609 |
| 0.0558 | 8.6 | 4300 | 0.2195 | 0.6148 | 0.7425 | 0.8239 | nan | 0.8746 | 0.8951 | 0.7349 | 0.8719 | 0.7043 | 0.8426 | 0.7614 | 0.3675 | 0.5751 | 0.6383 | 0.9055 | 0.8457 | 0.8271 | 0.8390 | 0.8284 | 0.8273 | 0.2837 | 0.0 | 0.7525 | 0.8152 | 0.6213 | 0.7658 | 0.6393 | 0.7416 | 0.5705 | 0.2937 | 0.4901 | 0.5255 | 0.8239 | 0.7295 | 0.7502 | 0.7522 | 0.7592 | 0.7772 | 0.2592 |
| 0.0518 | 8.64 | 4320 | 0.2243 | 0.6100 | 0.7395 | 0.8187 | nan | 0.8573 | 0.8882 | 0.6744 | 0.8370 | 0.7125 | 0.8549 | 0.7943 | 0.3636 | 0.5806 | 0.6465 | 0.9170 | 0.8424 | 0.8206 | 0.8424 | 0.8282 | 0.8064 | 0.3046 | 0.0 | 0.7494 | 0.8109 | 0.5947 | 0.7505 | 0.6412 | 0.7541 | 0.5576 | 0.2835 | 0.4915 | 0.5322 | 0.8231 | 0.7243 | 0.7405 | 0.7508 | 0.7564 | 0.7662 | 0.2525 |
| 0.0494 | 8.68 | 4340 | 0.2253 | 0.6195 | 0.7551 | 0.8216 | nan | 0.8610 | 0.8936 | 0.7012 | 0.8349 | 0.7050 | 0.8833 | 0.7699 | 0.4646 | 0.6088 | 0.6337 | 0.9047 | 0.8290 | 0.8393 | 0.8325 | 0.8498 | 0.8475 | 0.3772 | 0.0 | 0.7665 | 0.8150 | 0.6144 | 0.7542 | 0.6231 | 0.7692 | 0.5457 | 0.3459 | 0.5041 | 0.5377 | 0.8237 | 0.7256 | 0.7486 | 0.7537 | 0.7631 | 0.7836 | 0.2767 |
| 0.0383 | 8.72 | 4360 | 0.2340 | 0.6198 | 0.7559 | 0.8203 | nan | 0.8520 | 0.9032 | 0.6900 | 0.8180 | 0.7041 | 0.8829 | 0.7936 | 0.4585 | 0.5947 | 0.6318 | 0.9162 | 0.8363 | 0.8426 | 0.8445 | 0.8350 | 0.8253 | 0.4223 | 0.0 | 0.7709 | 0.8145 | 0.6086 | 0.7455 | 0.6360 | 0.7683 | 0.5511 | 0.3486 | 0.4953 | 0.5325 | 0.8247 | 0.7336 | 0.7517 | 0.7556 | 0.7600 | 0.7761 | 0.2841 |
| 0.0375 | 8.76 | 4380 | 0.2217 | 0.6190 | 0.7508 | 0.8206 | nan | 0.8522 | 0.8948 | 0.7449 | 0.8423 | 0.7028 | 0.8788 | 0.7530 | 0.3981 | 0.5796 | 0.6369 | 0.9089 | 0.8378 | 0.8432 | 0.8509 | 0.8432 | 0.8251 | 0.3711 | 0.0 | 0.7654 | 0.8135 | 0.6285 | 0.7568 | 0.6153 | 0.7698 | 0.5412 | 0.3309 | 0.4905 | 0.5324 | 0.8261 | 0.7353 | 0.7564 | 0.7579 | 0.7658 | 0.7739 | 0.2821 |
| 0.0367 | 8.8 | 4400 | 0.2246 | 0.6145 | 0.7416 | 0.8197 | nan | 0.8334 | 0.9068 | 0.7256 | 0.8322 | 0.7058 | 0.8781 | 0.7749 | 0.3536 | 0.6074 | 0.5935 | 0.9129 | 0.8687 | 0.8181 | 0.8378 | 0.8418 | 0.8087 | 0.3076 | 0.0 | 0.7557 | 0.8191 | 0.6192 | 0.7533 | 0.6236 | 0.7658 | 0.5453 | 0.3045 | 0.4992 | 0.5132 | 0.8244 | 0.7292 | 0.7469 | 0.7588 | 0.7727 | 0.7672 | 0.2636 |
| 0.074 | 8.84 | 4420 | 0.2326 | 0.6138 | 0.7419 | 0.8193 | nan | 0.8483 | 0.8924 | 0.7183 | 0.8400 | 0.7080 | 0.8732 | 0.7632 | 0.3716 | 0.5848 | 0.6264 | 0.9149 | 0.8326 | 0.8520 | 0.8216 | 0.8525 | 0.8141 | 0.2978 | 0.0 | 0.7572 | 0.8164 | 0.6165 | 0.7537 | 0.6143 | 0.7643 | 0.5398 | 0.2985 | 0.4928 | 0.5247 | 0.8242 | 0.7314 | 0.7556 | 0.7516 | 0.7737 | 0.7704 | 0.2632 |
| 0.038 | 8.88 | 4440 | 0.2314 | 0.6220 | 0.7566 | 0.8234 | nan | 0.8469 | 0.9163 | 0.7150 | 0.8502 | 0.6724 | 0.8791 | 0.7627 | 0.5999 | 0.6023 | 0.6458 | 0.9025 | 0.8408 | 0.8365 | 0.8592 | 0.8411 | 0.8110 | 0.2815 | 0.0 | 0.7603 | 0.8159 | 0.6218 | 0.7619 | 0.6140 | 0.7485 | 0.5529 | 0.4128 | 0.5023 | 0.5385 | 0.8229 | 0.7336 | 0.7566 | 0.7688 | 0.7776 | 0.7600 | 0.2481 |
| 0.0486 | 8.92 | 4460 | 0.2265 | 0.6176 | 0.7471 | 0.8218 | nan | 0.8489 | 0.8824 | 0.7234 | 0.8589 | 0.6716 | 0.8823 | 0.7616 | 0.4996 | 0.5337 | 0.6612 | 0.9079 | 0.8436 | 0.8342 | 0.8490 | 0.8480 | 0.8212 | 0.2740 | 0.0 | 0.7505 | 0.8106 | 0.6248 | 0.7667 | 0.6140 | 0.7534 | 0.5585 | 0.3704 | 0.4673 | 0.5368 | 0.8259 | 0.7315 | 0.7565 | 0.7639 | 0.7729 | 0.7609 | 0.2529 |
| 0.0589 | 8.96 | 4480 | 0.2335 | 0.6140 | 0.7404 | 0.8184 | nan | 0.8318 | 0.9004 | 0.7298 | 0.8342 | 0.6780 | 0.8726 | 0.7916 | 0.3401 | 0.5608 | 0.6654 | 0.9077 | 0.8507 | 0.8166 | 0.8645 | 0.8000 | 0.8166 | 0.3265 | 0.0 | 0.7470 | 0.8131 | 0.6265 | 0.7503 | 0.6308 | 0.7604 | 0.5579 | 0.2867 | 0.4791 | 0.5382 | 0.8258 | 0.7323 | 0.7529 | 0.7567 | 0.7570 | 0.7584 | 0.2784 |
| 0.0928 | 9.0 | 4500 | 0.2234 | 0.6170 | 0.7451 | 0.8261 | nan | 0.8674 | 0.8965 | 0.7326 | 0.8676 | 0.6852 | 0.8826 | 0.7584 | 0.2819 | 0.6002 | 0.6321 | 0.9084 | 0.8186 | 0.8459 | 0.8650 | 0.8278 | 0.8071 | 0.3889 | 0.0 | 0.7652 | 0.8184 | 0.6286 | 0.7709 | 0.6255 | 0.7565 | 0.5666 | 0.2459 | 0.4963 | 0.5297 | 0.8279 | 0.7332 | 0.7606 | 0.7590 | 0.7643 | 0.7585 | 0.2994 |
| 0.0573 | 9.04 | 4520 | 0.2235 | 0.6203 | 0.7464 | 0.8278 | nan | 0.8441 | 0.9048 | 0.7557 | 0.8764 | 0.6927 | 0.8730 | 0.7553 | 0.3351 | 0.5800 | 0.6431 | 0.8976 | 0.8401 | 0.8388 | 0.8349 | 0.8396 | 0.8132 | 0.3647 | 0.0 | 0.7572 | 0.8168 | 0.6361 | 0.7754 | 0.6289 | 0.7582 | 0.5684 | 0.2740 | 0.4915 | 0.5384 | 0.8271 | 0.7325 | 0.7539 | 0.7550 | 0.7734 | 0.7672 | 0.3111 |
| 0.0523 | 9.08 | 4540 | 0.2217 | 0.6225 | 0.7516 | 0.8277 | nan | 0.8399 | 0.8935 | 0.7553 | 0.8741 | 0.6888 | 0.8867 | 0.7466 | 0.4573 | 0.5676 | 0.6488 | 0.9148 | 0.8437 | 0.8369 | 0.8397 | 0.8095 | 0.8470 | 0.3272 | 0.0 | 0.7538 | 0.8140 | 0.6335 | 0.7796 | 0.6226 | 0.7658 | 0.5625 | 0.3275 | 0.4876 | 0.5414 | 0.8296 | 0.7301 | 0.7501 | 0.7519 | 0.7637 | 0.7855 | 0.3064 |
| 0.0372 | 9.12 | 4560 | 0.2219 | 0.6164 | 0.7455 | 0.8271 | nan | 0.8473 | 0.9010 | 0.7986 | 0.8733 | 0.7194 | 0.8896 | 0.7262 | 0.2736 | 0.6386 | 0.5583 | 0.9006 | 0.8329 | 0.8349 | 0.8477 | 0.8408 | 0.8291 | 0.3614 | 0.0 | 0.7641 | 0.8176 | 0.6378 | 0.7793 | 0.6240 | 0.7654 | 0.5526 | 0.2364 | 0.5000 | 0.4922 | 0.8266 | 0.7301 | 0.7500 | 0.7622 | 0.7750 | 0.7774 | 0.3053 |
| 0.0338 | 9.16 | 4580 | 0.2194 | 0.6151 | 0.7444 | 0.8235 | nan | 0.8565 | 0.9045 | 0.7748 | 0.8561 | 0.6996 | 0.8831 | 0.7412 | 0.2413 | 0.5597 | 0.6618 | 0.9050 | 0.8354 | 0.8398 | 0.8621 | 0.8231 | 0.8231 | 0.3871 | 0.0 | 0.7564 | 0.8160 | 0.6372 | 0.7708 | 0.6168 | 0.7642 | 0.5501 | 0.2192 | 0.4849 | 0.5388 | 0.8262 | 0.7314 | 0.7486 | 0.7605 | 0.7652 | 0.7703 | 0.3151 |
| 0.0257 | 9.2 | 4600 | 0.2310 | 0.6161 | 0.7447 | 0.8228 | nan | 0.8637 | 0.9010 | 0.7017 | 0.8463 | 0.6798 | 0.8983 | 0.7594 | 0.3465 | 0.5853 | 0.6059 | 0.9181 | 0.8553 | 0.8271 | 0.8657 | 0.8445 | 0.8027 | 0.3584 | 0.0 | 0.7591 | 0.8155 | 0.6141 | 0.7665 | 0.6172 | 0.7607 | 0.5539 | 0.2841 | 0.4879 | 0.5133 | 0.8245 | 0.7351 | 0.7456 | 0.7654 | 0.7720 | 0.7611 | 0.3139 |
| 0.0361 | 9.24 | 4620 | 0.2252 | 0.6177 | 0.7411 | 0.8252 | nan | 0.8602 | 0.8865 | 0.7017 | 0.8594 | 0.6979 | 0.8903 | 0.7653 | 0.2889 | 0.5940 | 0.6255 | 0.9065 | 0.8491 | 0.8159 | 0.8514 | 0.8225 | 0.8356 | 0.3481 | 0.0 | 0.7640 | 0.8156 | 0.6161 | 0.7685 | 0.6218 | 0.7700 | 0.5514 | 0.2470 | 0.4947 | 0.5280 | 0.8262 | 0.7354 | 0.7478 | 0.7640 | 0.7766 | 0.7753 | 0.3158 |
| 0.0347 | 9.28 | 4640 | 0.2147 | 0.6200 | 0.7443 | 0.8232 | nan | 0.8352 | 0.9015 | 0.6848 | 0.8728 | 0.6870 | 0.8730 | 0.7260 | 0.4264 | 0.5880 | 0.6143 | 0.9147 | 0.8463 | 0.8288 | 0.8560 | 0.8371 | 0.8136 | 0.3471 | 0.0 | 0.7601 | 0.8139 | 0.6094 | 0.7736 | 0.6179 | 0.7552 | 0.5541 | 0.3273 | 0.4945 | 0.5242 | 0.8248 | 0.7396 | 0.7573 | 0.7674 | 0.7783 | 0.7595 | 0.3036 |
| 0.0448 | 9.32 | 4660 | 0.2202 | 0.6206 | 0.7493 | 0.8224 | nan | 0.8721 | 0.8928 | 0.7461 | 0.8527 | 0.6907 | 0.8672 | 0.7654 | 0.3517 | 0.5951 | 0.6236 | 0.9228 | 0.8334 | 0.8348 | 0.8474 | 0.8318 | 0.8255 | 0.3839 | 0.0 | 0.7636 | 0.8125 | 0.6291 | 0.7633 | 0.6285 | 0.7545 | 0.5555 | 0.2887 | 0.4987 | 0.5293 | 0.8243 | 0.7380 | 0.7602 | 0.7629 | 0.7738 | 0.7699 | 0.3173 |
| 0.0461 | 9.36 | 4680 | 0.2219 | 0.6224 | 0.7525 | 0.8226 | nan | 0.8586 | 0.8968 | 0.7592 | 0.8534 | 0.6851 | 0.8649 | 0.7606 | 0.4322 | 0.5740 | 0.6244 | 0.9118 | 0.8247 | 0.8462 | 0.8574 | 0.8488 | 0.8434 | 0.3512 | 0.0 | 0.7621 | 0.8184 | 0.6386 | 0.7572 | 0.6231 | 0.7441 | 0.5521 | 0.3460 | 0.4897 | 0.5255 | 0.8259 | 0.7370 | 0.7613 | 0.7627 | 0.7814 | 0.7692 | 0.3093 |
| 0.0426 | 9.4 | 4700 | 0.2204 | 0.6179 | 0.7414 | 0.8235 | nan | 0.8537 | 0.8979 | 0.7061 | 0.8604 | 0.7016 | 0.8757 | 0.7515 | 0.3451 | 0.5808 | 0.6057 | 0.9052 | 0.8406 | 0.8397 | 0.8718 | 0.8247 | 0.8201 | 0.3240 | 0.0 | 0.7597 | 0.8162 | 0.6196 | 0.7614 | 0.6139 | 0.7480 | 0.5505 | 0.2937 | 0.4912 | 0.5175 | 0.8257 | 0.7415 | 0.7624 | 0.7689 | 0.7782 | 0.7715 | 0.3032 |
| 0.0298 | 9.44 | 4720 | 0.2229 | 0.6186 | 0.7430 | 0.8269 | nan | 0.8791 | 0.8981 | 0.6689 | 0.8638 | 0.6958 | 0.8800 | 0.7490 | 0.3231 | 0.5789 | 0.6243 | 0.9209 | 0.8405 | 0.8507 | 0.8610 | 0.8479 | 0.8245 | 0.3249 | 0.0 | 0.7687 | 0.8212 | 0.5974 | 0.7684 | 0.6145 | 0.7596 | 0.5552 | 0.2785 | 0.4865 | 0.5197 | 0.8278 | 0.7435 | 0.7616 | 0.7728 | 0.7830 | 0.7728 | 0.3035 |
| 0.0396 | 9.48 | 4740 | 0.2194 | 0.6178 | 0.7451 | 0.8249 | nan | 0.8558 | 0.8985 | 0.7329 | 0.8603 | 0.6917 | 0.8656 | 0.7544 | 0.2961 | 0.5915 | 0.6101 | 0.9182 | 0.8229 | 0.8528 | 0.8644 | 0.8321 | 0.8544 | 0.3656 | 0.0 | 0.7584 | 0.8118 | 0.6254 | 0.7689 | 0.6216 | 0.7592 | 0.5630 | 0.2490 | 0.4927 | 0.5189 | 0.8270 | 0.7312 | 0.7581 | 0.7654 | 0.7742 | 0.7813 | 0.3152 |
| 0.0376 | 9.52 | 4760 | 0.2246 | 0.6190 | 0.7453 | 0.8293 | nan | 0.8531 | 0.9008 | 0.7675 | 0.8879 | 0.6756 | 0.8653 | 0.7463 | 0.3321 | 0.5628 | 0.6402 | 0.9072 | 0.8465 | 0.8313 | 0.8571 | 0.8365 | 0.8420 | 0.3171 | 0.0 | 0.7661 | 0.8215 | 0.6346 | 0.7783 | 0.6147 | 0.7502 | 0.5700 | 0.2799 | 0.4806 | 0.5286 | 0.8280 | 0.7331 | 0.7529 | 0.7601 | 0.7741 | 0.7820 | 0.2880 |
| 0.0352 | 9.56 | 4780 | 0.2257 | 0.6170 | 0.7451 | 0.8236 | nan | 0.8482 | 0.8993 | 0.7699 | 0.8593 | 0.6632 | 0.8646 | 0.7753 | 0.3683 | 0.5849 | 0.6340 | 0.9119 | 0.8564 | 0.8098 | 0.8549 | 0.8404 | 0.8405 | 0.2851 | 0.0 | 0.7635 | 0.8183 | 0.6363 | 0.7651 | 0.6148 | 0.7525 | 0.5637 | 0.3001 | 0.4872 | 0.5264 | 0.8264 | 0.7286 | 0.7449 | 0.7577 | 0.7713 | 0.7812 | 0.2675 |
| 0.0542 | 9.6 | 4800 | 0.2272 | 0.6175 | 0.7445 | 0.8233 | nan | 0.8529 | 0.9084 | 0.7263 | 0.8714 | 0.6360 | 0.8556 | 0.7600 | 0.4009 | 0.5835 | 0.6507 | 0.9122 | 0.8492 | 0.8174 | 0.8589 | 0.8306 | 0.8385 | 0.3039 | 0.0 | 0.7682 | 0.8175 | 0.6278 | 0.7656 | 0.5900 | 0.7477 | 0.5562 | 0.3268 | 0.4917 | 0.5386 | 0.8276 | 0.7303 | 0.7475 | 0.7591 | 0.7672 | 0.7832 | 0.2697 |
| 0.0597 | 9.64 | 4820 | 0.2243 | 0.6173 | 0.7459 | 0.8209 | nan | 0.8581 | 0.8975 | 0.7392 | 0.8623 | 0.6479 | 0.8756 | 0.7467 | 0.4048 | 0.5571 | 0.6483 | 0.9147 | 0.8412 | 0.8386 | 0.8492 | 0.8357 | 0.8250 | 0.3387 | 0.0 | 0.7632 | 0.8103 | 0.6294 | 0.7655 | 0.5914 | 0.7578 | 0.5482 | 0.3298 | 0.4798 | 0.5331 | 0.8269 | 0.7378 | 0.7562 | 0.7535 | 0.7642 | 0.7758 | 0.2888 |
| 0.0855 | 9.68 | 4840 | 0.2361 | 0.6083 | 0.7346 | 0.8123 | nan | 0.8613 | 0.8959 | 0.7404 | 0.8304 | 0.6354 | 0.8824 | 0.7803 | 0.2968 | 0.5771 | 0.6293 | 0.9045 | 0.8358 | 0.8301 | 0.8307 | 0.8167 | 0.8049 | 0.3358 | 0.0 | 0.7646 | 0.8139 | 0.6307 | 0.7473 | 0.5705 | 0.7638 | 0.5246 | 0.2614 | 0.4867 | 0.5266 | 0.8259 | 0.7308 | 0.7483 | 0.7451 | 0.7598 | 0.7597 | 0.2898 |
| 0.0563 | 9.72 | 4860 | 0.2289 | 0.6154 | 0.7473 | 0.8178 | nan | 0.8695 | 0.9057 | 0.7158 | 0.8294 | 0.6774 | 0.8696 | 0.7678 | 0.3771 | 0.6135 | 0.5997 | 0.9082 | 0.8485 | 0.8368 | 0.8476 | 0.8450 | 0.8416 | 0.3509 | 0.0 | 0.7647 | 0.8150 | 0.6206 | 0.7501 | 0.6023 | 0.7646 | 0.5346 | 0.3071 | 0.4981 | 0.5153 | 0.8249 | 0.7351 | 0.7524 | 0.7541 | 0.7661 | 0.7764 | 0.2950 |
| 0.0694 | 9.76 | 4880 | 0.2276 | 0.6139 | 0.7427 | 0.8186 | nan | 0.8687 | 0.9006 | 0.7177 | 0.8340 | 0.7027 | 0.8921 | 0.7562 | 0.3572 | 0.6075 | 0.5876 | 0.9079 | 0.8441 | 0.8309 | 0.8355 | 0.8477 | 0.8100 | 0.3259 | 0.0 | 0.7621 | 0.8153 | 0.6212 | 0.7563 | 0.6080 | 0.7695 | 0.5397 | 0.2979 | 0.4909 | 0.5043 | 0.8247 | 0.7374 | 0.7541 | 0.7512 | 0.7699 | 0.7609 | 0.2868 |
| 0.0377 | 9.8 | 4900 | 0.2148 | 0.6199 | 0.7466 | 0.8302 | nan | 0.8704 | 0.8920 | 0.7402 | 0.8967 | 0.7284 | 0.8958 | 0.6951 | 0.3935 | 0.5583 | 0.6585 | 0.9177 | 0.8135 | 0.8469 | 0.8450 | 0.8428 | 0.8031 | 0.2944 | 0.0 | 0.7683 | 0.8178 | 0.6249 | 0.7924 | 0.6244 | 0.7652 | 0.5623 | 0.3204 | 0.4778 | 0.5333 | 0.8260 | 0.7276 | 0.7532 | 0.7546 | 0.7684 | 0.7598 | 0.2823 |
| 0.0534 | 9.84 | 4920 | 0.2119 | 0.6209 | 0.7478 | 0.8312 | nan | 0.8586 | 0.9098 | 0.7091 | 0.8895 | 0.7283 | 0.8786 | 0.7104 | 0.4140 | 0.6087 | 0.6257 | 0.9178 | 0.8457 | 0.8222 | 0.8478 | 0.8429 | 0.8212 | 0.2815 | 0.0 | 0.7662 | 0.8146 | 0.6182 | 0.7906 | 0.6364 | 0.7656 | 0.5698 | 0.3339 | 0.4983 | 0.5214 | 0.8250 | 0.7333 | 0.7485 | 0.7513 | 0.7668 | 0.7670 | 0.2699 |
| 0.0596 | 9.88 | 4940 | 0.2095 | 0.6206 | 0.7466 | 0.8317 | nan | 0.8512 | 0.9009 | 0.7502 | 0.8952 | 0.7235 | 0.8842 | 0.7147 | 0.3887 | 0.5872 | 0.6461 | 0.8986 | 0.8318 | 0.8380 | 0.8639 | 0.8334 | 0.8172 | 0.2676 | 0.0 | 0.7584 | 0.8165 | 0.6355 | 0.7917 | 0.6305 | 0.7697 | 0.5682 | 0.3181 | 0.4964 | 0.5364 | 0.8242 | 0.7291 | 0.7487 | 0.7529 | 0.7690 | 0.7622 | 0.2628 |
| 0.0443 | 9.92 | 4960 | 0.2174 | 0.6185 | 0.7482 | 0.8271 | nan | 0.8366 | 0.8982 | 0.7238 | 0.8692 | 0.6983 | 0.8825 | 0.7496 | 0.4489 | 0.5994 | 0.6071 | 0.9190 | 0.8424 | 0.8391 | 0.8726 | 0.8129 | 0.8225 | 0.2967 | 0.0 | 0.7460 | 0.8164 | 0.6239 | 0.7827 | 0.6206 | 0.7661 | 0.5694 | 0.3445 | 0.4996 | 0.5204 | 0.8233 | 0.7275 | 0.7472 | 0.7485 | 0.7583 | 0.7631 | 0.2748 |
| 0.0366 | 9.96 | 4980 | 0.2141 | 0.6158 | 0.7455 | 0.8229 | nan | 0.8576 | 0.8926 | 0.7784 | 0.8813 | 0.7318 | 0.8717 | 0.7171 | 0.3805 | 0.5959 | 0.6243 | 0.8987 | 0.8323 | 0.8288 | 0.8452 | 0.7942 | 0.7856 | 0.3574 | 0.0 | 0.7498 | 0.8127 | 0.6371 | 0.7817 | 0.6057 | 0.7667 | 0.5537 | 0.3075 | 0.4946 | 0.5219 | 0.8239 | 0.7303 | 0.7494 | 0.7416 | 0.7523 | 0.7455 | 0.3103 |
| 0.0378 | 10.0 | 5000 | 0.2255 | 0.6146 | 0.7467 | 0.8205 | nan | 0.8623 | 0.8960 | 0.7348 | 0.8527 | 0.7228 | 0.8557 | 0.7479 | 0.3292 | 0.6004 | 0.6126 | 0.9190 | 0.8466 | 0.8337 | 0.8469 | 0.8429 | 0.7933 | 0.3966 | 0.0 | 0.7603 | 0.8111 | 0.6260 | 0.7673 | 0.6062 | 0.7592 | 0.5469 | 0.2756 | 0.4944 | 0.5214 | 0.8248 | 0.7310 | 0.7492 | 0.7548 | 0.7687 | 0.7511 | 0.3148 |
| 0.0412 | 10.04 | 5020 | 0.2159 | 0.6145 | 0.7431 | 0.8224 | nan | 0.8334 | 0.9106 | 0.7136 | 0.8595 | 0.7208 | 0.8631 | 0.7485 | 0.3142 | 0.5852 | 0.6161 | 0.9079 | 0.8300 | 0.8400 | 0.8357 | 0.8431 | 0.7875 | 0.4234 | 0.0 | 0.7569 | 0.8186 | 0.6197 | 0.7697 | 0.6115 | 0.7634 | 0.5506 | 0.2716 | 0.4897 | 0.5235 | 0.8262 | 0.7264 | 0.7453 | 0.7509 | 0.7665 | 0.7481 | 0.3230 |
| 0.1179 | 10.08 | 5040 | 0.2071 | 0.6180 | 0.7496 | 0.8239 | nan | 0.8613 | 0.9001 | 0.7407 | 0.8686 | 0.7187 | 0.8611 | 0.7420 | 0.3679 | 0.5785 | 0.6314 | 0.9041 | 0.8371 | 0.8376 | 0.8479 | 0.8274 | 0.8013 | 0.4174 | 0.0 | 0.7594 | 0.8119 | 0.6309 | 0.7763 | 0.6182 | 0.7628 | 0.5625 | 0.2990 | 0.4925 | 0.5347 | 0.8260 | 0.7251 | 0.7413 | 0.7540 | 0.7641 | 0.7537 | 0.3123 |
| 0.0377 | 10.12 | 5060 | 0.2216 | 0.6169 | 0.7470 | 0.8237 | nan | 0.8673 | 0.8996 | 0.6967 | 0.8612 | 0.7010 | 0.8703 | 0.7586 | 0.3511 | 0.6051 | 0.6281 | 0.9198 | 0.8355 | 0.8233 | 0.8483 | 0.8428 | 0.7845 | 0.4051 | 0.0 | 0.7629 | 0.8188 | 0.6104 | 0.7721 | 0.6135 | 0.7628 | 0.5605 | 0.2929 | 0.5016 | 0.5304 | 0.8264 | 0.7279 | 0.7409 | 0.7580 | 0.7689 | 0.7454 | 0.3103 |
| 0.0445 | 10.16 | 5080 | 0.2239 | 0.6179 | 0.7467 | 0.8240 | nan | 0.8545 | 0.8958 | 0.7701 | 0.8630 | 0.7007 | 0.8702 | 0.7605 | 0.3334 | 0.6025 | 0.6255 | 0.9208 | 0.8364 | 0.8213 | 0.8593 | 0.8240 | 0.7971 | 0.3595 | 0.0 | 0.7640 | 0.8170 | 0.6357 | 0.7734 | 0.6157 | 0.7643 | 0.5647 | 0.2889 | 0.4980 | 0.5305 | 0.8266 | 0.7283 | 0.7441 | 0.7552 | 0.7653 | 0.7550 | 0.2959 |
| 0.0397 | 10.2 | 5100 | 0.2256 | 0.6182 | 0.7471 | 0.8257 | nan | 0.8602 | 0.8983 | 0.7746 | 0.8704 | 0.7085 | 0.8777 | 0.7589 | 0.3473 | 0.6178 | 0.5808 | 0.9051 | 0.8427 | 0.8164 | 0.8588 | 0.8123 | 0.7980 | 0.3731 | 0.0 | 0.7645 | 0.8199 | 0.6395 | 0.7753 | 0.6197 | 0.7651 | 0.5659 | 0.2990 | 0.4985 | 0.5049 | 0.8273 | 0.7302 | 0.7465 | 0.7551 | 0.7643 | 0.7549 | 0.2975 |
| 0.0335 | 10.24 | 5120 | 0.2156 | 0.6217 | 0.7500 | 0.8290 | nan | 0.8619 | 0.8925 | 0.7266 | 0.8851 | 0.7115 | 0.8604 | 0.7429 | 0.4009 | 0.6091 | 0.6095 | 0.9262 | 0.8338 | 0.8409 | 0.8507 | 0.8471 | 0.8052 | 0.3459 | 0.0 | 0.7638 | 0.8206 | 0.6234 | 0.7827 | 0.6255 | 0.7603 | 0.5746 | 0.3377 | 0.5021 | 0.5211 | 0.8260 | 0.7300 | 0.7501 | 0.7550 | 0.7683 | 0.7577 | 0.2923 |
| 0.048 | 10.28 | 5140 | 0.2195 | 0.6206 | 0.7457 | 0.8280 | nan | 0.8531 | 0.9014 | 0.6939 | 0.8842 | 0.7175 | 0.8655 | 0.7404 | 0.4071 | 0.6059 | 0.6196 | 0.9035 | 0.8571 | 0.8085 | 0.8516 | 0.8397 | 0.7988 | 0.3285 | 0.0 | 0.7606 | 0.8163 | 0.6127 | 0.7841 | 0.6295 | 0.7633 | 0.5770 | 0.3358 | 0.5014 | 0.5297 | 0.8262 | 0.7284 | 0.7393 | 0.7531 | 0.7629 | 0.7543 | 0.2961 |
| 0.0518 | 10.32 | 5160 | 0.2107 | 0.6254 | 0.7515 | 0.8318 | nan | 0.8493 | 0.8991 | 0.7409 | 0.8845 | 0.7223 | 0.8681 | 0.7451 | 0.3741 | 0.5943 | 0.6483 | 0.9188 | 0.8404 | 0.8384 | 0.8459 | 0.8475 | 0.8103 | 0.3483 | 0.0 | 0.7630 | 0.8202 | 0.6315 | 0.7845 | 0.6292 | 0.7674 | 0.5743 | 0.3200 | 0.5017 | 0.5441 | 0.8304 | 0.7308 | 0.7501 | 0.7621 | 0.7759 | 0.7625 | 0.3086 |
| 0.0362 | 10.36 | 5180 | 0.2180 | 0.6204 | 0.7522 | 0.8271 | nan | 0.8772 | 0.8998 | 0.7279 | 0.8720 | 0.7247 | 0.8705 | 0.7520 | 0.3289 | 0.5850 | 0.6485 | 0.9086 | 0.8084 | 0.8411 | 0.8353 | 0.8401 | 0.7921 | 0.4761 | 0.0 | 0.7615 | 0.8145 | 0.6294 | 0.7781 | 0.6348 | 0.7684 | 0.5729 | 0.2863 | 0.4947 | 0.5348 | 0.8298 | 0.7204 | 0.7510 | 0.7587 | 0.7739 | 0.7521 | 0.3060 |
| 0.053 | 10.4 | 5200 | 0.2110 | 0.6238 | 0.7492 | 0.8305 | nan | 0.8493 | 0.9017 | 0.7544 | 0.8845 | 0.7309 | 0.8746 | 0.7392 | 0.3401 | 0.5799 | 0.6198 | 0.9038 | 0.8354 | 0.8265 | 0.8521 | 0.8394 | 0.8169 | 0.3874 | 0.0 | 0.7631 | 0.8175 | 0.6393 | 0.7849 | 0.6409 | 0.7671 | 0.5779 | 0.2954 | 0.4893 | 0.5222 | 0.8297 | 0.7329 | 0.7528 | 0.7644 | 0.7747 | 0.7652 | 0.3116 |
| 0.0626 | 10.44 | 5220 | 0.2206 | 0.6222 | 0.7489 | 0.8291 | nan | 0.8490 | 0.9027 | 0.7750 | 0.8726 | 0.7048 | 0.8677 | 0.7555 | 0.2887 | 0.5839 | 0.6412 | 0.9092 | 0.8312 | 0.8575 | 0.8582 | 0.8417 | 0.8173 | 0.3746 | 0.0 | 0.7695 | 0.8209 | 0.6442 | 0.7780 | 0.6199 | 0.7659 | 0.5642 | 0.2613 | 0.4979 | 0.5377 | 0.8304 | 0.7308 | 0.7592 | 0.7671 | 0.7764 | 0.7675 | 0.3092 |
| 0.0327 | 10.48 | 5240 | 0.2259 | 0.6213 | 0.7494 | 0.8227 | nan | 0.8680 | 0.8990 | 0.7714 | 0.8542 | 0.6356 | 0.8630 | 0.8026 | 0.3758 | 0.5874 | 0.6414 | 0.9155 | 0.8420 | 0.8452 | 0.8468 | 0.8367 | 0.7930 | 0.3618 | 0.0 | 0.7686 | 0.8182 | 0.6428 | 0.7656 | 0.6033 | 0.7590 | 0.5645 | 0.3215 | 0.5024 | 0.5408 | 0.8284 | 0.7342 | 0.7579 | 0.7564 | 0.7711 | 0.7505 | 0.2988 |
| 0.0502 | 10.52 | 5260 | 0.2303 | 0.6205 | 0.7532 | 0.8192 | nan | 0.8599 | 0.9073 | 0.7546 | 0.8278 | 0.6260 | 0.8672 | 0.8299 | 0.4034 | 0.6101 | 0.6381 | 0.9083 | 0.8542 | 0.8286 | 0.8677 | 0.8222 | 0.7866 | 0.4117 | 0.0 | 0.7654 | 0.8201 | 0.6399 | 0.7542 | 0.5932 | 0.7602 | 0.5554 | 0.3344 | 0.5066 | 0.5406 | 0.8287 | 0.7359 | 0.7540 | 0.7616 | 0.7674 | 0.7443 | 0.3081 |
| 0.0261 | 10.56 | 5280 | 0.2100 | 0.6276 | 0.7585 | 0.8288 | nan | 0.8454 | 0.8949 | 0.7216 | 0.8499 | 0.7262 | 0.8815 | 0.7873 | 0.4518 | 0.5732 | 0.6507 | 0.9106 | 0.8435 | 0.8412 | 0.8713 | 0.8251 | 0.8197 | 0.4006 | 0.0 | 0.7584 | 0.8135 | 0.6246 | 0.7698 | 0.6606 | 0.7626 | 0.5794 | 0.3609 | 0.4907 | 0.5444 | 0.8275 | 0.7360 | 0.7576 | 0.7629 | 0.7689 | 0.7684 | 0.3100 |
| 0.0367 | 10.6 | 5300 | 0.2105 | 0.6286 | 0.7600 | 0.8295 | nan | 0.8311 | 0.9008 | 0.7109 | 0.8554 | 0.7369 | 0.8848 | 0.7620 | 0.4867 | 0.6178 | 0.6341 | 0.9151 | 0.8242 | 0.8420 | 0.8563 | 0.8457 | 0.8271 | 0.3897 | 0.0 | 0.7560 | 0.8176 | 0.6200 | 0.7720 | 0.6602 | 0.7608 | 0.5730 | 0.3741 | 0.5059 | 0.5350 | 0.8270 | 0.7342 | 0.7568 | 0.7657 | 0.7747 | 0.7741 | 0.3087 |
| 0.0494 | 10.64 | 5320 | 0.2101 | 0.6297 | 0.7626 | 0.8293 | nan | 0.8543 | 0.8998 | 0.7747 | 0.8539 | 0.7431 | 0.8798 | 0.7701 | 0.4706 | 0.5727 | 0.6555 | 0.9018 | 0.8355 | 0.8481 | 0.8455 | 0.8512 | 0.8174 | 0.3906 | 0.0 | 0.7598 | 0.8179 | 0.6454 | 0.7712 | 0.6626 | 0.7614 | 0.5729 | 0.3685 | 0.4892 | 0.5435 | 0.8264 | 0.7346 | 0.7580 | 0.7642 | 0.7773 | 0.7698 | 0.3125 |
| 0.032 | 10.68 | 5340 | 0.2092 | 0.6256 | 0.7525 | 0.8288 | nan | 0.8394 | 0.9041 | 0.7387 | 0.8624 | 0.7439 | 0.8801 | 0.7531 | 0.4074 | 0.5851 | 0.6353 | 0.9099 | 0.8306 | 0.8395 | 0.8385 | 0.8394 | 0.8221 | 0.3637 | 0.0 | 0.7606 | 0.8164 | 0.6359 | 0.7755 | 0.6571 | 0.7609 | 0.5714 | 0.3418 | 0.4900 | 0.5332 | 0.8272 | 0.7302 | 0.7549 | 0.7582 | 0.7714 | 0.7749 | 0.3020 |
| 0.0815 | 10.72 | 5360 | 0.2096 | 0.6262 | 0.7539 | 0.8322 | nan | 0.8455 | 0.8997 | 0.7519 | 0.8693 | 0.7435 | 0.8937 | 0.7511 | 0.3924 | 0.6073 | 0.5934 | 0.9148 | 0.8577 | 0.8196 | 0.8589 | 0.8448 | 0.8204 | 0.3518 | 0.0 | 0.7650 | 0.8207 | 0.6388 | 0.7816 | 0.6572 | 0.7617 | 0.5773 | 0.3307 | 0.4985 | 0.5189 | 0.8281 | 0.7326 | 0.7490 | 0.7657 | 0.7760 | 0.7720 | 0.2975 |
| 0.0529 | 10.76 | 5380 | 0.2130 | 0.6261 | 0.7532 | 0.8287 | nan | 0.8682 | 0.8954 | 0.7341 | 0.8578 | 0.7345 | 0.8630 | 0.7909 | 0.4212 | 0.5998 | 0.6059 | 0.9135 | 0.8545 | 0.8225 | 0.8491 | 0.8459 | 0.8118 | 0.3364 | 0.0 | 0.7678 | 0.8209 | 0.6332 | 0.7739 | 0.6654 | 0.7521 | 0.5824 | 0.3451 | 0.4929 | 0.5194 | 0.8284 | 0.7403 | 0.7554 | 0.7608 | 0.7780 | 0.7618 | 0.2918 |
| 0.0348 | 10.8 | 5400 | 0.2174 | 0.6254 | 0.7535 | 0.8270 | nan | 0.8603 | 0.8988 | 0.6850 | 0.8541 | 0.7227 | 0.8434 | 0.7972 | 0.4412 | 0.5788 | 0.6221 | 0.9185 | 0.8593 | 0.8188 | 0.8499 | 0.8463 | 0.8332 | 0.3798 | 0.0 | 0.7677 | 0.8190 | 0.6110 | 0.7707 | 0.6526 | 0.7469 | 0.5817 | 0.3509 | 0.4876 | 0.5275 | 0.8273 | 0.7360 | 0.7504 | 0.7609 | 0.7770 | 0.7691 | 0.3200 |
| 0.0424 | 10.84 | 5420 | 0.2128 | 0.6286 | 0.7594 | 0.8323 | nan | 0.8541 | 0.8904 | 0.7261 | 0.8671 | 0.7348 | 0.8700 | 0.7783 | 0.3729 | 0.5723 | 0.6372 | 0.9230 | 0.8561 | 0.8202 | 0.8570 | 0.8394 | 0.8370 | 0.4743 | 0.0 | 0.7685 | 0.8167 | 0.6291 | 0.7790 | 0.6736 | 0.7597 | 0.5928 | 0.3156 | 0.4897 | 0.5383 | 0.8277 | 0.7348 | 0.7485 | 0.7624 | 0.7729 | 0.7761 | 0.3302 |
| 0.0443 | 10.88 | 5440 | 0.2127 | 0.6280 | 0.7551 | 0.8318 | nan | 0.8285 | 0.9077 | 0.7122 | 0.8713 | 0.7365 | 0.8675 | 0.7681 | 0.3680 | 0.6071 | 0.6288 | 0.9094 | 0.8384 | 0.8312 | 0.8476 | 0.8344 | 0.8200 | 0.4596 | 0.0 | 0.7680 | 0.8184 | 0.6258 | 0.7799 | 0.6731 | 0.7608 | 0.5919 | 0.3159 | 0.5004 | 0.5312 | 0.8275 | 0.7353 | 0.7551 | 0.7588 | 0.7722 | 0.7686 | 0.3203 |
| 0.0725 | 10.92 | 5460 | 0.2146 | 0.6300 | 0.7579 | 0.8328 | nan | 0.8521 | 0.8993 | 0.7243 | 0.8694 | 0.7051 | 0.8731 | 0.7830 | 0.3837 | 0.6255 | 0.6155 | 0.9131 | 0.8557 | 0.8331 | 0.8509 | 0.8339 | 0.8381 | 0.4290 | 0.0 | 0.7717 | 0.8195 | 0.6304 | 0.7799 | 0.6599 | 0.7633 | 0.5904 | 0.3339 | 0.5067 | 0.5259 | 0.8285 | 0.7402 | 0.7604 | 0.7598 | 0.7730 | 0.7798 | 0.3168 |
| 0.0516 | 10.96 | 5480 | 0.2144 | 0.6324 | 0.7604 | 0.8355 | nan | 0.8486 | 0.9148 | 0.7692 | 0.8722 | 0.7175 | 0.8743 | 0.7817 | 0.3988 | 0.5847 | 0.6573 | 0.9090 | 0.8564 | 0.8315 | 0.8598 | 0.8257 | 0.8307 | 0.3950 | 0.0 | 0.7761 | 0.8266 | 0.6443 | 0.7816 | 0.6665 | 0.7638 | 0.5937 | 0.3506 | 0.4985 | 0.5469 | 0.8267 | 0.7378 | 0.7569 | 0.7599 | 0.7671 | 0.7812 | 0.3043 |
| 0.0542 | 11.0 | 5500 | 0.2133 | 0.6298 | 0.7572 | 0.8331 | nan | 0.8333 | 0.9010 | 0.7820 | 0.8751 | 0.7279 | 0.8879 | 0.7564 | 0.4034 | 0.5703 | 0.6596 | 0.9128 | 0.8320 | 0.8518 | 0.8707 | 0.8125 | 0.8182 | 0.3773 | 0.0 | 0.7640 | 0.8179 | 0.6455 | 0.7836 | 0.6643 | 0.7653 | 0.5916 | 0.3499 | 0.4914 | 0.5451 | 0.8265 | 0.7416 | 0.7649 | 0.7560 | 0.7595 | 0.7752 | 0.2944 |
| 0.0404 | 11.04 | 5520 | 0.2140 | 0.6325 | 0.7596 | 0.8365 | nan | 0.8663 | 0.8999 | 0.7718 | 0.8849 | 0.7341 | 0.8879 | 0.7504 | 0.4153 | 0.5794 | 0.6610 | 0.9106 | 0.8534 | 0.8390 | 0.8535 | 0.8246 | 0.8299 | 0.3507 | 0.0 | 0.7760 | 0.8215 | 0.6441 | 0.7857 | 0.6680 | 0.7666 | 0.5918 | 0.3588 | 0.4958 | 0.5472 | 0.8283 | 0.7478 | 0.7633 | 0.7584 | 0.7669 | 0.7815 | 0.2824 |
| 0.0451 | 11.08 | 5540 | 0.2135 | 0.6290 | 0.7568 | 0.8327 | nan | 0.8767 | 0.9029 | 0.7418 | 0.8730 | 0.7319 | 0.8768 | 0.7688 | 0.4331 | 0.5868 | 0.6178 | 0.9193 | 0.8594 | 0.8246 | 0.8577 | 0.8235 | 0.8097 | 0.3623 | 0.0 | 0.7778 | 0.8237 | 0.6354 | 0.7786 | 0.6702 | 0.7645 | 0.5908 | 0.3712 | 0.4864 | 0.5227 | 0.8254 | 0.7392 | 0.7573 | 0.7583 | 0.7652 | 0.7654 | 0.2896 |
| 0.0477 | 11.12 | 5560 | 0.2149 | 0.6277 | 0.7547 | 0.8314 | nan | 0.8641 | 0.8961 | 0.7527 | 0.8823 | 0.7351 | 0.8723 | 0.7534 | 0.4310 | 0.5857 | 0.6364 | 0.9045 | 0.8509 | 0.8218 | 0.8473 | 0.8141 | 0.8222 | 0.3595 | 0.0 | 0.7712 | 0.8169 | 0.6389 | 0.7823 | 0.6654 | 0.7653 | 0.5867 | 0.3619 | 0.4893 | 0.5323 | 0.8250 | 0.7381 | 0.7556 | 0.7541 | 0.7625 | 0.7697 | 0.2840 |
| 0.0373 | 11.16 | 5580 | 0.2104 | 0.6275 | 0.7564 | 0.8315 | nan | 0.8625 | 0.8935 | 0.7551 | 0.8727 | 0.7091 | 0.8845 | 0.7628 | 0.4085 | 0.5838 | 0.6345 | 0.9158 | 0.8496 | 0.8422 | 0.8586 | 0.8232 | 0.8257 | 0.3760 | 0.0 | 0.7754 | 0.8146 | 0.6345 | 0.7790 | 0.6502 | 0.7704 | 0.5822 | 0.3509 | 0.4897 | 0.5328 | 0.8257 | 0.7402 | 0.7627 | 0.7564 | 0.7639 | 0.7744 | 0.2914 |
| 0.0359 | 11.2 | 5600 | 0.2093 | 0.6279 | 0.7592 | 0.8310 | nan | 0.8657 | 0.8938 | 0.7299 | 0.8674 | 0.7094 | 0.8825 | 0.7700 | 0.4404 | 0.5819 | 0.6408 | 0.9095 | 0.8462 | 0.8487 | 0.8587 | 0.8144 | 0.8360 | 0.4117 | 0.0 | 0.7685 | 0.8183 | 0.6283 | 0.7763 | 0.6471 | 0.7696 | 0.5786 | 0.3624 | 0.4902 | 0.5349 | 0.8256 | 0.7377 | 0.7633 | 0.7569 | 0.7626 | 0.7809 | 0.3001 |
| 0.0549 | 11.24 | 5620 | 0.2080 | 0.6231 | 0.7515 | 0.8279 | nan | 0.8614 | 0.9001 | 0.7025 | 0.8620 | 0.7041 | 0.8777 | 0.7664 | 0.3873 | 0.5975 | 0.6150 | 0.9117 | 0.8499 | 0.8352 | 0.8384 | 0.8368 | 0.8320 | 0.3974 | 0.0 | 0.7629 | 0.8166 | 0.6182 | 0.7750 | 0.6366 | 0.7677 | 0.5736 | 0.3337 | 0.4940 | 0.5205 | 0.8246 | 0.7360 | 0.7591 | 0.7550 | 0.7669 | 0.7764 | 0.2982 |
| 0.0512 | 11.28 | 5640 | 0.2108 | 0.6251 | 0.7541 | 0.8314 | nan | 0.8632 | 0.9005 | 0.7296 | 0.8754 | 0.6961 | 0.8890 | 0.7573 | 0.3910 | 0.6054 | 0.6270 | 0.9131 | 0.8557 | 0.8332 | 0.8487 | 0.8269 | 0.8212 | 0.3856 | 0.0 | 0.7650 | 0.8158 | 0.6289 | 0.7828 | 0.6318 | 0.7657 | 0.5804 | 0.3362 | 0.4984 | 0.5274 | 0.8258 | 0.7400 | 0.7589 | 0.7562 | 0.7671 | 0.7733 | 0.2974 |
| 0.0329 | 11.32 | 5660 | 0.2129 | 0.6243 | 0.7561 | 0.8279 | nan | 0.8647 | 0.8870 | 0.7665 | 0.8815 | 0.6828 | 0.8908 | 0.7336 | 0.4715 | 0.5886 | 0.6307 | 0.9125 | 0.8491 | 0.8272 | 0.8533 | 0.8241 | 0.8292 | 0.3601 | 0.0 | 0.7595 | 0.8118 | 0.6378 | 0.7854 | 0.6189 | 0.7576 | 0.5749 | 0.3751 | 0.4922 | 0.5265 | 0.8249 | 0.7381 | 0.7567 | 0.7558 | 0.7647 | 0.7755 | 0.2824 |
| 0.0624 | 11.36 | 5680 | 0.2176 | 0.6276 | 0.7592 | 0.8322 | nan | 0.8666 | 0.9038 | 0.7484 | 0.8798 | 0.6784 | 0.8929 | 0.7404 | 0.4572 | 0.5800 | 0.6500 | 0.9101 | 0.8476 | 0.8426 | 0.8579 | 0.8419 | 0.8432 | 0.3653 | 0.0 | 0.7675 | 0.8213 | 0.6343 | 0.7865 | 0.6190 | 0.7568 | 0.5758 | 0.3717 | 0.4907 | 0.5365 | 0.8250 | 0.7409 | 0.7612 | 0.7636 | 0.7735 | 0.7825 | 0.2902 |
| 0.0438 | 11.4 | 5700 | 0.2145 | 0.6197 | 0.7470 | 0.8276 | nan | 0.8583 | 0.8946 | 0.7420 | 0.8716 | 0.7013 | 0.8881 | 0.7458 | 0.3413 | 0.5784 | 0.6286 | 0.9070 | 0.8443 | 0.8230 | 0.8482 | 0.8484 | 0.8255 | 0.3524 | 0.0 | 0.7606 | 0.8171 | 0.6299 | 0.7809 | 0.6282 | 0.7606 | 0.5730 | 0.2992 | 0.4899 | 0.5293 | 0.8233 | 0.7329 | 0.7486 | 0.7557 | 0.7704 | 0.7716 | 0.2840 |
| 0.0357 | 11.44 | 5720 | 0.2165 | 0.6224 | 0.7510 | 0.8290 | nan | 0.8549 | 0.9050 | 0.7354 | 0.8677 | 0.7007 | 0.8893 | 0.7488 | 0.3664 | 0.6073 | 0.6288 | 0.9029 | 0.8525 | 0.8212 | 0.8488 | 0.8396 | 0.8376 | 0.3607 | 0.0 | 0.7648 | 0.8193 | 0.6297 | 0.7792 | 0.6292 | 0.7660 | 0.5687 | 0.3147 | 0.5002 | 0.5310 | 0.8234 | 0.7338 | 0.7487 | 0.7549 | 0.7688 | 0.7767 | 0.2935 |
| 0.0476 | 11.48 | 5740 | 0.2198 | 0.6246 | 0.7552 | 0.8284 | nan | 0.8697 | 0.9019 | 0.7674 | 0.8673 | 0.6945 | 0.8877 | 0.7538 | 0.4138 | 0.5647 | 0.6587 | 0.9082 | 0.8418 | 0.8337 | 0.8504 | 0.8338 | 0.8250 | 0.3658 | 0.0 | 0.7700 | 0.8182 | 0.6393 | 0.7769 | 0.6309 | 0.7648 | 0.5706 | 0.3502 | 0.4808 | 0.5358 | 0.8261 | 0.7391 | 0.7571 | 0.7529 | 0.7638 | 0.7699 | 0.2964 |
| 0.0467 | 11.52 | 5760 | 0.2185 | 0.6216 | 0.7517 | 0.8282 | nan | 0.8730 | 0.8975 | 0.7627 | 0.8608 | 0.7052 | 0.8941 | 0.7595 | 0.3479 | 0.5988 | 0.6071 | 0.9060 | 0.8564 | 0.8250 | 0.8546 | 0.8256 | 0.8349 | 0.3691 | 0.0 | 0.7690 | 0.8174 | 0.6378 | 0.7752 | 0.6320 | 0.7646 | 0.5660 | 0.3006 | 0.4899 | 0.5149 | 0.8273 | 0.7414 | 0.7564 | 0.7554 | 0.7662 | 0.7761 | 0.2982 |
| 0.0433 | 11.56 | 5780 | 0.2111 | 0.6208 | 0.7480 | 0.8278 | nan | 0.8661 | 0.8986 | 0.7574 | 0.8706 | 0.7196 | 0.8946 | 0.7398 | 0.3789 | 0.5838 | 0.5903 | 0.9081 | 0.8516 | 0.8256 | 0.8466 | 0.8307 | 0.8173 | 0.3367 | 0.0 | 0.7611 | 0.8168 | 0.6375 | 0.7805 | 0.6338 | 0.7664 | 0.5661 | 0.3274 | 0.4832 | 0.5056 | 0.8262 | 0.7368 | 0.7542 | 0.7568 | 0.7669 | 0.7684 | 0.2871 |
| 0.0304 | 11.6 | 5800 | 0.2154 | 0.6191 | 0.7436 | 0.8277 | nan | 0.8618 | 0.8979 | 0.7209 | 0.8716 | 0.7157 | 0.8946 | 0.7407 | 0.3319 | 0.5662 | 0.6205 | 0.9098 | 0.8442 | 0.8295 | 0.8469 | 0.8375 | 0.8093 | 0.3416 | 0.0 | 0.7636 | 0.8199 | 0.6260 | 0.7789 | 0.6300 | 0.7689 | 0.5623 | 0.2928 | 0.4787 | 0.5193 | 0.8260 | 0.7348 | 0.7550 | 0.7615 | 0.7725 | 0.7631 | 0.2904 |
| 0.0456 | 11.64 | 5820 | 0.2215 | 0.6230 | 0.7521 | 0.8266 | nan | 0.8554 | 0.9081 | 0.7498 | 0.8582 | 0.7027 | 0.8900 | 0.7501 | 0.3789 | 0.5846 | 0.6315 | 0.9070 | 0.8620 | 0.8103 | 0.8540 | 0.8338 | 0.8297 | 0.3791 | 0.0 | 0.7671 | 0.8182 | 0.6374 | 0.7732 | 0.6303 | 0.7704 | 0.5589 | 0.3259 | 0.4920 | 0.5315 | 0.8259 | 0.7282 | 0.7434 | 0.7636 | 0.7698 | 0.7745 | 0.3035 |
| 0.0395 | 11.68 | 5840 | 0.2156 | 0.6267 | 0.7571 | 0.8288 | nan | 0.8395 | 0.9011 | 0.7391 | 0.8638 | 0.7053 | 0.8887 | 0.7445 | 0.4443 | 0.6131 | 0.6206 | 0.9123 | 0.8457 | 0.8456 | 0.8584 | 0.8299 | 0.8410 | 0.3778 | 0.0 | 0.7617 | 0.8185 | 0.6350 | 0.7767 | 0.6294 | 0.7724 | 0.5599 | 0.3643 | 0.5046 | 0.5287 | 0.8268 | 0.7346 | 0.7577 | 0.7628 | 0.7672 | 0.7783 | 0.3018 |
| 0.0391 | 11.72 | 5860 | 0.2238 | 0.6280 | 0.7600 | 0.8292 | nan | 0.8536 | 0.9013 | 0.7666 | 0.8641 | 0.7047 | 0.8927 | 0.7430 | 0.4564 | 0.6096 | 0.6249 | 0.9133 | 0.8358 | 0.8507 | 0.8643 | 0.8406 | 0.8269 | 0.3712 | 0.0 | 0.7668 | 0.8178 | 0.6427 | 0.7769 | 0.6300 | 0.7726 | 0.5607 | 0.3792 | 0.5012 | 0.5286 | 0.8268 | 0.7357 | 0.7595 | 0.7659 | 0.7694 | 0.7724 | 0.2980 |
| 0.0346 | 11.76 | 5880 | 0.2191 | 0.6239 | 0.7533 | 0.8262 | nan | 0.8605 | 0.9009 | 0.7339 | 0.8621 | 0.7032 | 0.8922 | 0.7436 | 0.4405 | 0.6021 | 0.6003 | 0.9150 | 0.8546 | 0.8185 | 0.8389 | 0.8408 | 0.8256 | 0.3724 | 0.0 | 0.7648 | 0.8168 | 0.6315 | 0.7751 | 0.6285 | 0.7713 | 0.5581 | 0.3704 | 0.4912 | 0.5119 | 0.8274 | 0.7354 | 0.7498 | 0.7582 | 0.7679 | 0.7729 | 0.2998 |
| 0.0428 | 11.8 | 5900 | 0.2230 | 0.6226 | 0.7544 | 0.8254 | nan | 0.8661 | 0.9018 | 0.7239 | 0.8575 | 0.7139 | 0.8850 | 0.7410 | 0.4345 | 0.5995 | 0.6129 | 0.9190 | 0.8587 | 0.8062 | 0.8652 | 0.8263 | 0.8313 | 0.3829 | 0.0 | 0.7703 | 0.8180 | 0.6275 | 0.7721 | 0.6201 | 0.7767 | 0.5547 | 0.3585 | 0.4955 | 0.5214 | 0.8283 | 0.7276 | 0.7427 | 0.7600 | 0.7599 | 0.7759 | 0.2983 |
| 0.0376 | 11.84 | 5920 | 0.2248 | 0.6199 | 0.7497 | 0.8238 | nan | 0.8727 | 0.8903 | 0.7110 | 0.8552 | 0.7067 | 0.8816 | 0.7558 | 0.4013 | 0.6114 | 0.6214 | 0.9192 | 0.8479 | 0.8203 | 0.8553 | 0.8205 | 0.8192 | 0.3547 | 0.0 | 0.7625 | 0.8181 | 0.6212 | 0.7665 | 0.6213 | 0.7749 | 0.5510 | 0.3346 | 0.5040 | 0.5291 | 0.8278 | 0.7265 | 0.7457 | 0.7574 | 0.7599 | 0.7695 | 0.2881 |
| 0.0359 | 11.88 | 5940 | 0.2267 | 0.6204 | 0.7485 | 0.8251 | nan | 0.8528 | 0.9020 | 0.7108 | 0.8586 | 0.6962 | 0.8801 | 0.7549 | 0.3779 | 0.5934 | 0.6442 | 0.9122 | 0.8469 | 0.8411 | 0.8614 | 0.8156 | 0.8121 | 0.3645 | 0.0 | 0.7618 | 0.8199 | 0.6232 | 0.7681 | 0.6200 | 0.7714 | 0.5553 | 0.3211 | 0.4962 | 0.5359 | 0.8260 | 0.7373 | 0.7558 | 0.7539 | 0.7591 | 0.7666 | 0.2956 |
| 0.0345 | 11.92 | 5960 | 0.2250 | 0.6230 | 0.7505 | 0.8262 | nan | 0.8300 | 0.9085 | 0.7175 | 0.8635 | 0.7003 | 0.8771 | 0.7477 | 0.4255 | 0.5867 | 0.6400 | 0.9049 | 0.8476 | 0.8444 | 0.8481 | 0.8222 | 0.8292 | 0.3651 | 0.0 | 0.7581 | 0.8192 | 0.6272 | 0.7707 | 0.6217 | 0.7718 | 0.5576 | 0.3485 | 0.4925 | 0.5330 | 0.8258 | 0.7390 | 0.7586 | 0.7542 | 0.7623 | 0.7761 | 0.2974 |
| 0.0374 | 11.96 | 5980 | 0.2186 | 0.6238 | 0.7521 | 0.8256 | nan | 0.8399 | 0.9082 | 0.7109 | 0.8621 | 0.7026 | 0.8810 | 0.7414 | 0.4934 | 0.6159 | 0.5969 | 0.9150 | 0.8529 | 0.8370 | 0.8347 | 0.8388 | 0.8225 | 0.3330 | 0.0 | 0.7612 | 0.8185 | 0.6248 | 0.7701 | 0.6254 | 0.7705 | 0.5559 | 0.3824 | 0.5027 | 0.5153 | 0.8279 | 0.7365 | 0.7563 | 0.7553 | 0.7685 | 0.7736 | 0.2826 |
| 0.055 | 12.0 | 6000 | 0.2175 | 0.6251 | 0.7562 | 0.8254 | nan | 0.8404 | 0.9083 | 0.6946 | 0.8566 | 0.7138 | 0.8827 | 0.7373 | 0.4973 | 0.5873 | 0.6403 | 0.9124 | 0.8417 | 0.8445 | 0.8313 | 0.8508 | 0.8241 | 0.3917 | 0.0 | 0.7637 | 0.8192 | 0.6178 | 0.7687 | 0.6261 | 0.7699 | 0.5516 | 0.3656 | 0.4957 | 0.5332 | 0.8288 | 0.7396 | 0.7604 | 0.7583 | 0.7731 | 0.7739 | 0.3052 |
| 0.0336 | 12.04 | 6020 | 0.2203 | 0.6265 | 0.7593 | 0.8256 | nan | 0.8568 | 0.8967 | 0.7212 | 0.8569 | 0.7082 | 0.8832 | 0.7463 | 0.4661 | 0.6005 | 0.6372 | 0.9132 | 0.8482 | 0.8314 | 0.8517 | 0.8351 | 0.8277 | 0.4268 | 0.0 | 0.7665 | 0.8147 | 0.6297 | 0.7679 | 0.6285 | 0.7707 | 0.5547 | 0.3604 | 0.5009 | 0.5349 | 0.8294 | 0.7401 | 0.7577 | 0.7606 | 0.7723 | 0.7758 | 0.3115 |
| 0.0286 | 12.08 | 6040 | 0.2250 | 0.6271 | 0.7585 | 0.8279 | nan | 0.8574 | 0.8988 | 0.7423 | 0.8675 | 0.7068 | 0.8874 | 0.7407 | 0.4549 | 0.6028 | 0.6397 | 0.9084 | 0.8455 | 0.8280 | 0.8531 | 0.8258 | 0.8309 | 0.4054 | 0.0 | 0.7684 | 0.8179 | 0.6376 | 0.7737 | 0.6257 | 0.7723 | 0.5564 | 0.3632 | 0.5019 | 0.5374 | 0.8298 | 0.7358 | 0.7559 | 0.7609 | 0.7717 | 0.7777 | 0.3018 |
| 0.0309 | 12.12 | 6060 | 0.2299 | 0.6233 | 0.7504 | 0.8261 | nan | 0.8402 | 0.9057 | 0.6992 | 0.8646 | 0.6978 | 0.8817 | 0.7436 | 0.4204 | 0.5674 | 0.6546 | 0.9063 | 0.8399 | 0.8438 | 0.8562 | 0.8334 | 0.8201 | 0.3814 | 0.0 | 0.7621 | 0.8182 | 0.6200 | 0.7726 | 0.6221 | 0.7671 | 0.5575 | 0.3449 | 0.4860 | 0.5407 | 0.8272 | 0.7355 | 0.7586 | 0.7605 | 0.7725 | 0.7678 | 0.3055 |
| 0.0335 | 12.16 | 6080 | 0.2293 | 0.6213 | 0.7477 | 0.8218 | nan | 0.8327 | 0.8919 | 0.7078 | 0.8492 | 0.6968 | 0.8750 | 0.7630 | 0.4157 | 0.5924 | 0.6157 | 0.9195 | 0.8414 | 0.8426 | 0.8437 | 0.8327 | 0.8217 | 0.3698 | 0.0 | 0.7595 | 0.8158 | 0.6204 | 0.7626 | 0.6262 | 0.7656 | 0.5507 | 0.3408 | 0.5001 | 0.5262 | 0.8277 | 0.7348 | 0.7566 | 0.7532 | 0.7695 | 0.7708 | 0.3035 |
| 0.0334 | 12.2 | 6100 | 0.2293 | 0.6235 | 0.7534 | 0.8234 | nan | 0.8485 | 0.9054 | 0.7384 | 0.8482 | 0.7003 | 0.8764 | 0.7602 | 0.4250 | 0.6150 | 0.6245 | 0.9104 | 0.8574 | 0.8285 | 0.8454 | 0.8390 | 0.8127 | 0.3723 | 0.0 | 0.7650 | 0.8190 | 0.6351 | 0.7630 | 0.6232 | 0.7688 | 0.5482 | 0.3464 | 0.5120 | 0.5339 | 0.8277 | 0.7326 | 0.7495 | 0.7546 | 0.7702 | 0.7689 | 0.3058 |
| 0.0413 | 12.24 | 6120 | 0.2224 | 0.6251 | 0.7572 | 0.8247 | nan | 0.8724 | 0.9004 | 0.7315 | 0.8544 | 0.7000 | 0.8835 | 0.7461 | 0.4563 | 0.5877 | 0.6541 | 0.9096 | 0.8544 | 0.8243 | 0.8548 | 0.8427 | 0.8206 | 0.3802 | 0.0 | 0.7680 | 0.8162 | 0.6332 | 0.7667 | 0.6181 | 0.7706 | 0.5492 | 0.3710 | 0.4992 | 0.5461 | 0.8275 | 0.7315 | 0.7495 | 0.7578 | 0.7706 | 0.7733 | 0.3027 |
| 0.0317 | 12.28 | 6140 | 0.2260 | 0.6248 | 0.7557 | 0.8251 | nan | 0.8752 | 0.8976 | 0.7346 | 0.8549 | 0.7024 | 0.8815 | 0.7496 | 0.4264 | 0.6123 | 0.6348 | 0.9121 | 0.8522 | 0.8280 | 0.8460 | 0.8366 | 0.8302 | 0.3733 | 0.0 | 0.7699 | 0.8190 | 0.6336 | 0.7651 | 0.6137 | 0.7748 | 0.5445 | 0.3573 | 0.5082 | 0.5388 | 0.8289 | 0.7329 | 0.7518 | 0.7561 | 0.7711 | 0.7785 | 0.3026 |
| 0.0357 | 12.32 | 6160 | 0.2295 | 0.6233 | 0.7542 | 0.8227 | nan | 0.8614 | 0.9038 | 0.7491 | 0.8420 | 0.7010 | 0.8852 | 0.7599 | 0.4142 | 0.5897 | 0.6365 | 0.9102 | 0.8520 | 0.8247 | 0.8376 | 0.8361 | 0.8309 | 0.3872 | 0.0 | 0.7686 | 0.8170 | 0.6399 | 0.7610 | 0.6167 | 0.7771 | 0.5468 | 0.3442 | 0.4971 | 0.5352 | 0.8287 | 0.7332 | 0.7538 | 0.7543 | 0.7677 | 0.7790 | 0.2991 |
| 0.0362 | 12.36 | 6180 | 0.2290 | 0.6259 | 0.7574 | 0.8260 | nan | 0.8600 | 0.9036 | 0.7575 | 0.8503 | 0.6978 | 0.8862 | 0.7541 | 0.3948 | 0.6014 | 0.6476 | 0.9111 | 0.8516 | 0.8385 | 0.8550 | 0.8375 | 0.8296 | 0.3996 | 0.0 | 0.7734 | 0.8207 | 0.6423 | 0.7641 | 0.6160 | 0.7747 | 0.5464 | 0.3382 | 0.5043 | 0.5414 | 0.8295 | 0.7401 | 0.7631 | 0.7609 | 0.7712 | 0.7805 | 0.2992 |
| 0.0484 | 12.4 | 6200 | 0.2278 | 0.6258 | 0.7550 | 0.8253 | nan | 0.8532 | 0.9050 | 0.7494 | 0.8537 | 0.6986 | 0.8866 | 0.7488 | 0.4345 | 0.5954 | 0.6401 | 0.9056 | 0.8454 | 0.8465 | 0.8529 | 0.8325 | 0.8251 | 0.3620 | 0.0 | 0.7676 | 0.8179 | 0.6411 | 0.7666 | 0.6182 | 0.7709 | 0.5495 | 0.3644 | 0.5026 | 0.5401 | 0.8280 | 0.7389 | 0.7637 | 0.7584 | 0.7688 | 0.7777 | 0.2906 |
| 0.0353 | 12.44 | 6220 | 0.2256 | 0.6294 | 0.7594 | 0.8279 | nan | 0.8645 | 0.9064 | 0.7356 | 0.8636 | 0.7006 | 0.8859 | 0.7354 | 0.4782 | 0.6007 | 0.6601 | 0.9118 | 0.8441 | 0.8395 | 0.8566 | 0.8366 | 0.8307 | 0.3597 | 0.0 | 0.7718 | 0.8221 | 0.6358 | 0.7727 | 0.6177 | 0.7719 | 0.5516 | 0.3942 | 0.5053 | 0.5472 | 0.8294 | 0.7407 | 0.7645 | 0.7622 | 0.7718 | 0.7794 | 0.2904 |
| 0.0361 | 12.48 | 6240 | 0.2236 | 0.6265 | 0.7557 | 0.8261 | nan | 0.8510 | 0.9002 | 0.7453 | 0.8569 | 0.6987 | 0.8855 | 0.7481 | 0.4498 | 0.5990 | 0.6371 | 0.9145 | 0.8531 | 0.8317 | 0.8567 | 0.8332 | 0.8344 | 0.3515 | 0.0 | 0.7644 | 0.8185 | 0.6377 | 0.7703 | 0.6220 | 0.7704 | 0.5536 | 0.3703 | 0.5037 | 0.5392 | 0.8296 | 0.7372 | 0.7584 | 0.7628 | 0.7706 | 0.7792 | 0.2882 |
| 0.0511 | 12.52 | 6260 | 0.2277 | 0.6253 | 0.7548 | 0.8242 | nan | 0.8476 | 0.8931 | 0.7597 | 0.8480 | 0.7010 | 0.8868 | 0.7604 | 0.4331 | 0.6105 | 0.6158 | 0.9159 | 0.8539 | 0.8393 | 0.8495 | 0.8376 | 0.8202 | 0.3593 | 0.0 | 0.7640 | 0.8184 | 0.6402 | 0.7621 | 0.6255 | 0.7707 | 0.5468 | 0.3641 | 0.5030 | 0.5265 | 0.8306 | 0.7393 | 0.7614 | 0.7625 | 0.7736 | 0.7731 | 0.2929 |
| 0.0586 | 12.56 | 6280 | 0.2299 | 0.6242 | 0.7543 | 0.8224 | nan | 0.8597 | 0.8940 | 0.7576 | 0.8428 | 0.7032 | 0.8725 | 0.7691 | 0.4026 | 0.6018 | 0.6374 | 0.9108 | 0.8519 | 0.8347 | 0.8484 | 0.8349 | 0.8241 | 0.3781 | 0.0 | 0.7651 | 0.8190 | 0.6397 | 0.7572 | 0.6239 | 0.7710 | 0.5454 | 0.3396 | 0.5044 | 0.5380 | 0.8308 | 0.7388 | 0.7568 | 0.7571 | 0.7711 | 0.7736 | 0.3037 |
| 0.0261 | 12.6 | 6300 | 0.2290 | 0.6244 | 0.7553 | 0.8225 | nan | 0.8704 | 0.8966 | 0.7397 | 0.8438 | 0.7034 | 0.8785 | 0.7639 | 0.4307 | 0.5786 | 0.6540 | 0.9126 | 0.8562 | 0.8144 | 0.8458 | 0.8396 | 0.8254 | 0.3871 | 0.0 | 0.7687 | 0.8189 | 0.6341 | 0.7586 | 0.6231 | 0.7710 | 0.5491 | 0.3626 | 0.4951 | 0.5432 | 0.8300 | 0.7328 | 0.7460 | 0.7561 | 0.7715 | 0.7739 | 0.3039 |
| 0.04 | 12.64 | 6320 | 0.2329 | 0.6277 | 0.7594 | 0.8252 | nan | 0.8835 | 0.8976 | 0.7452 | 0.8447 | 0.6999 | 0.8810 | 0.7746 | 0.4545 | 0.5671 | 0.6589 | 0.9143 | 0.8449 | 0.8405 | 0.8459 | 0.8404 | 0.8280 | 0.3883 | 0.0 | 0.7703 | 0.8184 | 0.6348 | 0.7600 | 0.6321 | 0.7721 | 0.5557 | 0.3785 | 0.4905 | 0.5449 | 0.8301 | 0.7400 | 0.7592 | 0.7572 | 0.7744 | 0.7767 | 0.3029 |
| 0.0781 | 12.68 | 6340 | 0.2256 | 0.6255 | 0.7551 | 0.8252 | nan | 0.8670 | 0.8966 | 0.7042 | 0.8548 | 0.7049 | 0.8694 | 0.7625 | 0.4641 | 0.5711 | 0.6488 | 0.9170 | 0.8511 | 0.8333 | 0.8529 | 0.8267 | 0.8376 | 0.3752 | 0.0 | 0.7684 | 0.8176 | 0.6185 | 0.7655 | 0.6280 | 0.7709 | 0.5596 | 0.3800 | 0.4920 | 0.5416 | 0.8285 | 0.7369 | 0.7551 | 0.7539 | 0.7680 | 0.7801 | 0.2950 |
| 0.0363 | 12.72 | 6360 | 0.2250 | 0.6249 | 0.7525 | 0.8253 | nan | 0.8345 | 0.9020 | 0.7121 | 0.8564 | 0.7004 | 0.8744 | 0.7617 | 0.4431 | 0.5829 | 0.6374 | 0.9145 | 0.8497 | 0.8377 | 0.8500 | 0.8310 | 0.8220 | 0.3834 | 0.0 | 0.7609 | 0.8184 | 0.6233 | 0.7670 | 0.6281 | 0.7684 | 0.5605 | 0.3693 | 0.4970 | 0.5384 | 0.8282 | 0.7373 | 0.7557 | 0.7550 | 0.7704 | 0.7748 | 0.2953 |
| 0.0593 | 12.76 | 6380 | 0.2211 | 0.6265 | 0.7593 | 0.8254 | nan | 0.8452 | 0.9015 | 0.7707 | 0.8558 | 0.7028 | 0.8872 | 0.7524 | 0.4794 | 0.5794 | 0.6445 | 0.9071 | 0.8471 | 0.8278 | 0.8500 | 0.8447 | 0.8158 | 0.3967 | 0.0 | 0.7626 | 0.8188 | 0.6433 | 0.7688 | 0.6237 | 0.7701 | 0.5560 | 0.3839 | 0.4912 | 0.5370 | 0.8281 | 0.7371 | 0.7547 | 0.7579 | 0.7748 | 0.7698 | 0.2995 |
| 0.0413 | 12.8 | 6400 | 0.2294 | 0.6243 | 0.7537 | 0.8258 | nan | 0.8638 | 0.9019 | 0.7530 | 0.8542 | 0.7002 | 0.8839 | 0.7623 | 0.4083 | 0.5835 | 0.6451 | 0.9085 | 0.8509 | 0.8287 | 0.8441 | 0.8519 | 0.8128 | 0.3597 | 0.0 | 0.7640 | 0.8197 | 0.6395 | 0.7671 | 0.6266 | 0.7705 | 0.5563 | 0.3461 | 0.4931 | 0.5383 | 0.8275 | 0.7364 | 0.7548 | 0.7586 | 0.7787 | 0.7688 | 0.2912 |
| 0.0643 | 12.84 | 6420 | 0.2268 | 0.6205 | 0.7460 | 0.8258 | nan | 0.8655 | 0.8930 | 0.7164 | 0.8635 | 0.7005 | 0.8766 | 0.7589 | 0.3734 | 0.5981 | 0.6227 | 0.9131 | 0.8497 | 0.8373 | 0.8601 | 0.8369 | 0.8054 | 0.3110 | 0.0 | 0.7610 | 0.8162 | 0.6249 | 0.7705 | 0.6263 | 0.7691 | 0.5590 | 0.3202 | 0.4985 | 0.5288 | 0.8268 | 0.7389 | 0.7588 | 0.7603 | 0.7768 | 0.7641 | 0.2695 |
| 0.0395 | 12.88 | 6440 | 0.2283 | 0.6245 | 0.7517 | 0.8281 | nan | 0.8563 | 0.9066 | 0.7141 | 0.8563 | 0.6995 | 0.8924 | 0.7603 | 0.4074 | 0.5881 | 0.6474 | 0.9126 | 0.8516 | 0.8405 | 0.8606 | 0.8364 | 0.8136 | 0.3343 | 0.0 | 0.7669 | 0.8196 | 0.6246 | 0.7732 | 0.6249 | 0.7803 | 0.5577 | 0.3405 | 0.4975 | 0.5420 | 0.8271 | 0.7388 | 0.7590 | 0.7615 | 0.7773 | 0.7684 | 0.2824 |
| 0.0405 | 12.92 | 6460 | 0.2262 | 0.6250 | 0.7532 | 0.8276 | nan | 0.8608 | 0.8982 | 0.7534 | 0.8616 | 0.6956 | 0.8992 | 0.7566 | 0.4366 | 0.5871 | 0.6325 | 0.9096 | 0.8538 | 0.8318 | 0.8533 | 0.8305 | 0.8112 | 0.3330 | 0.0 | 0.7663 | 0.8200 | 0.6393 | 0.7754 | 0.6220 | 0.7795 | 0.5576 | 0.3592 | 0.4954 | 0.5359 | 0.8281 | 0.7382 | 0.7560 | 0.7588 | 0.7745 | 0.7656 | 0.2786 |
| 0.0499 | 12.96 | 6480 | 0.2250 | 0.6244 | 0.7539 | 0.8266 | nan | 0.8606 | 0.8939 | 0.7448 | 0.8603 | 0.6943 | 0.8968 | 0.7500 | 0.4342 | 0.5886 | 0.6393 | 0.9134 | 0.8534 | 0.8320 | 0.8542 | 0.8384 | 0.8159 | 0.3458 | 0.0 | 0.7622 | 0.8176 | 0.6369 | 0.7764 | 0.6152 | 0.7770 | 0.5559 | 0.3563 | 0.4988 | 0.5392 | 0.8275 | 0.7375 | 0.7557 | 0.7568 | 0.7745 | 0.7651 | 0.2865 |
| 0.0759 | 13.0 | 6500 | 0.2264 | 0.6232 | 0.7504 | 0.8292 | nan | 0.8655 | 0.8962 | 0.7145 | 0.8670 | 0.6965 | 0.8953 | 0.7496 | 0.3597 | 0.6238 | 0.6121 | 0.9137 | 0.8443 | 0.8349 | 0.8655 | 0.8427 | 0.8243 | 0.3505 | 0.0 | 0.7682 | 0.8209 | 0.6255 | 0.7787 | 0.6182 | 0.7777 | 0.5565 | 0.3142 | 0.5113 | 0.5263 | 0.8282 | 0.7378 | 0.7571 | 0.7596 | 0.7752 | 0.7701 | 0.2922 |
| 0.0346 | 13.04 | 6520 | 0.2275 | 0.6243 | 0.7520 | 0.8272 | nan | 0.8592 | 0.8995 | 0.7354 | 0.8599 | 0.6961 | 0.8982 | 0.7528 | 0.4045 | 0.6214 | 0.6191 | 0.9039 | 0.8312 | 0.8476 | 0.8599 | 0.8302 | 0.8213 | 0.3431 | 0.0 | 0.7646 | 0.8169 | 0.6353 | 0.7762 | 0.6238 | 0.7778 | 0.5570 | 0.3432 | 0.5123 | 0.5295 | 0.8263 | 0.7357 | 0.7576 | 0.7561 | 0.7707 | 0.7691 | 0.2859 |
| 0.0732 | 13.08 | 6540 | 0.2215 | 0.6250 | 0.7543 | 0.8273 | nan | 0.8583 | 0.8961 | 0.7646 | 0.8582 | 0.6937 | 0.9009 | 0.7533 | 0.3897 | 0.6029 | 0.6417 | 0.9080 | 0.8392 | 0.8441 | 0.8565 | 0.8248 | 0.8273 | 0.3642 | 0.0 | 0.7647 | 0.8161 | 0.6412 | 0.7749 | 0.6255 | 0.7769 | 0.5579 | 0.3359 | 0.5064 | 0.5398 | 0.8271 | 0.7387 | 0.7568 | 0.7575 | 0.7706 | 0.7712 | 0.2897 |
| 0.0573 | 13.12 | 6560 | 0.2277 | 0.6239 | 0.7521 | 0.8278 | nan | 0.8549 | 0.9003 | 0.7490 | 0.8600 | 0.6969 | 0.8982 | 0.7494 | 0.3698 | 0.6079 | 0.6389 | 0.9136 | 0.8442 | 0.8399 | 0.8518 | 0.8394 | 0.8175 | 0.3537 | 0.0 | 0.7653 | 0.8189 | 0.6380 | 0.7747 | 0.6242 | 0.7777 | 0.5570 | 0.3218 | 0.5059 | 0.5375 | 0.8273 | 0.7397 | 0.7563 | 0.7568 | 0.7733 | 0.7680 | 0.2879 |
| 0.0778 | 13.16 | 6580 | 0.2248 | 0.6238 | 0.7522 | 0.8273 | nan | 0.8608 | 0.8912 | 0.7534 | 0.8637 | 0.7025 | 0.8966 | 0.7488 | 0.3889 | 0.5965 | 0.6424 | 0.9154 | 0.8425 | 0.8367 | 0.8508 | 0.8299 | 0.8165 | 0.3509 | 0.0 | 0.7646 | 0.8171 | 0.6389 | 0.7757 | 0.6225 | 0.7797 | 0.5567 | 0.3331 | 0.4992 | 0.5377 | 0.8284 | 0.7414 | 0.7567 | 0.7548 | 0.7699 | 0.7658 | 0.2859 |
| 0.0471 | 13.2 | 6600 | 0.2250 | 0.6262 | 0.7549 | 0.8281 | nan | 0.8596 | 0.8987 | 0.7459 | 0.8625 | 0.7008 | 0.8925 | 0.7580 | 0.4383 | 0.5730 | 0.6607 | 0.9067 | 0.8400 | 0.8446 | 0.8613 | 0.8206 | 0.8170 | 0.3530 | 0.0 | 0.7647 | 0.8188 | 0.6374 | 0.7751 | 0.6291 | 0.7785 | 0.5614 | 0.3660 | 0.4895 | 0.5442 | 0.8279 | 0.7419 | 0.7590 | 0.7556 | 0.7670 | 0.7670 | 0.2879 |
| 0.0286 | 13.24 | 6620 | 0.2275 | 0.6251 | 0.7541 | 0.8264 | nan | 0.8571 | 0.9003 | 0.7318 | 0.8554 | 0.6998 | 0.8911 | 0.7582 | 0.4283 | 0.6010 | 0.6385 | 0.9097 | 0.8407 | 0.8339 | 0.8515 | 0.8390 | 0.8200 | 0.3629 | 0.0 | 0.7634 | 0.8170 | 0.6323 | 0.7720 | 0.6288 | 0.7760 | 0.5574 | 0.3604 | 0.4999 | 0.5328 | 0.8276 | 0.7388 | 0.7557 | 0.7560 | 0.7715 | 0.7704 | 0.2911 |
| 0.0349 | 13.28 | 6640 | 0.2300 | 0.6261 | 0.7560 | 0.8281 | nan | 0.8669 | 0.8957 | 0.7340 | 0.8597 | 0.7003 | 0.8930 | 0.7522 | 0.4288 | 0.6015 | 0.6413 | 0.9139 | 0.8436 | 0.8380 | 0.8504 | 0.8430 | 0.8348 | 0.3542 | 0.0 | 0.7660 | 0.8175 | 0.6332 | 0.7744 | 0.6267 | 0.7768 | 0.5568 | 0.3611 | 0.5022 | 0.5371 | 0.8287 | 0.7393 | 0.7569 | 0.7566 | 0.7738 | 0.7787 | 0.2840 |
| 0.0306 | 13.32 | 6660 | 0.2307 | 0.6266 | 0.7564 | 0.8283 | nan | 0.8701 | 0.8999 | 0.7348 | 0.8608 | 0.6980 | 0.8911 | 0.7512 | 0.4234 | 0.6036 | 0.6437 | 0.9131 | 0.8350 | 0.8476 | 0.8492 | 0.8432 | 0.8303 | 0.3638 | 0.0 | 0.7672 | 0.8194 | 0.6338 | 0.7726 | 0.6252 | 0.7740 | 0.5581 | 0.3583 | 0.5038 | 0.5401 | 0.8289 | 0.7399 | 0.7602 | 0.7588 | 0.7746 | 0.7781 | 0.2860 |
| 0.0311 | 13.36 | 6680 | 0.2294 | 0.6266 | 0.7570 | 0.8274 | nan | 0.8626 | 0.9014 | 0.7207 | 0.8600 | 0.6993 | 0.8897 | 0.7452 | 0.4604 | 0.5968 | 0.6393 | 0.9114 | 0.8394 | 0.8461 | 0.8619 | 0.8449 | 0.8236 | 0.3669 | 0.0 | 0.7658 | 0.8194 | 0.6288 | 0.7721 | 0.6222 | 0.7735 | 0.5564 | 0.3823 | 0.4997 | 0.5362 | 0.8276 | 0.7403 | 0.7596 | 0.7609 | 0.7734 | 0.7732 | 0.2875 |
| 0.0306 | 13.4 | 6700 | 0.2276 | 0.6260 | 0.7567 | 0.8260 | nan | 0.8548 | 0.8992 | 0.7393 | 0.8555 | 0.7020 | 0.8857 | 0.7528 | 0.4614 | 0.6084 | 0.6323 | 0.9099 | 0.8456 | 0.8381 | 0.8640 | 0.8356 | 0.8217 | 0.3570 | 0.0 | 0.7620 | 0.8181 | 0.6351 | 0.7704 | 0.6199 | 0.7759 | 0.5546 | 0.3800 | 0.5050 | 0.5352 | 0.8275 | 0.7395 | 0.7570 | 0.7588 | 0.7712 | 0.7712 | 0.2867 |
| 0.039 | 13.44 | 6720 | 0.2236 | 0.6247 | 0.7550 | 0.8256 | nan | 0.8596 | 0.8948 | 0.7488 | 0.8575 | 0.7069 | 0.8837 | 0.7453 | 0.4302 | 0.6010 | 0.6397 | 0.9133 | 0.8442 | 0.8393 | 0.8567 | 0.8473 | 0.8183 | 0.3490 | 0.0 | 0.7612 | 0.8165 | 0.6382 | 0.7708 | 0.6181 | 0.7748 | 0.5527 | 0.3618 | 0.5029 | 0.5384 | 0.8277 | 0.7398 | 0.7570 | 0.7584 | 0.7745 | 0.7701 | 0.2819 |
| 0.0432 | 13.48 | 6740 | 0.2253 | 0.6248 | 0.7534 | 0.8265 | nan | 0.8610 | 0.8984 | 0.7402 | 0.8586 | 0.7057 | 0.8851 | 0.7493 | 0.4230 | 0.5866 | 0.6460 | 0.9102 | 0.8378 | 0.8436 | 0.8502 | 0.8424 | 0.8311 | 0.3393 | 0.0 | 0.7616 | 0.8183 | 0.6364 | 0.7708 | 0.6213 | 0.7751 | 0.5551 | 0.3581 | 0.4975 | 0.5416 | 0.8284 | 0.7396 | 0.7572 | 0.7562 | 0.7728 | 0.7769 | 0.2802 |
| 0.0561 | 13.52 | 6760 | 0.2249 | 0.6252 | 0.7538 | 0.8258 | nan | 0.8634 | 0.8931 | 0.7255 | 0.8613 | 0.7117 | 0.8817 | 0.7439 | 0.4569 | 0.5847 | 0.6417 | 0.9144 | 0.8428 | 0.8335 | 0.8479 | 0.8433 | 0.8290 | 0.3400 | 0.0 | 0.7629 | 0.8170 | 0.6301 | 0.7711 | 0.6232 | 0.7737 | 0.5549 | 0.3799 | 0.4953 | 0.5382 | 0.8287 | 0.7379 | 0.7536 | 0.7570 | 0.7743 | 0.7745 | 0.2810 |
| 0.0274 | 13.56 | 6780 | 0.2255 | 0.6257 | 0.7535 | 0.8276 | nan | 0.8548 | 0.9047 | 0.7118 | 0.8624 | 0.7132 | 0.8827 | 0.7408 | 0.4344 | 0.5899 | 0.6469 | 0.9102 | 0.8451 | 0.8372 | 0.8485 | 0.8431 | 0.8342 | 0.3497 | 0.0 | 0.7653 | 0.8200 | 0.6253 | 0.7725 | 0.6241 | 0.7734 | 0.5553 | 0.3660 | 0.4977 | 0.5403 | 0.8283 | 0.7404 | 0.7565 | 0.7594 | 0.7761 | 0.7769 | 0.2846 |
| 0.0351 | 13.6 | 6800 | 0.2265 | 0.6253 | 0.7529 | 0.8267 | nan | 0.8525 | 0.8998 | 0.7031 | 0.8561 | 0.7110 | 0.8882 | 0.7468 | 0.4319 | 0.6002 | 0.6402 | 0.9130 | 0.8394 | 0.8354 | 0.8608 | 0.8389 | 0.8351 | 0.3463 | 0.0 | 0.7637 | 0.8186 | 0.6208 | 0.7706 | 0.6258 | 0.7751 | 0.5545 | 0.3662 | 0.5019 | 0.5370 | 0.8282 | 0.7395 | 0.7572 | 0.7591 | 0.7740 | 0.7785 | 0.2853 |
| 0.03 | 13.64 | 6820 | 0.2249 | 0.6277 | 0.7571 | 0.8275 | nan | 0.8542 | 0.9011 | 0.7257 | 0.8581 | 0.7129 | 0.8850 | 0.7441 | 0.4520 | 0.6132 | 0.6366 | 0.9075 | 0.8438 | 0.8373 | 0.8605 | 0.8409 | 0.8409 | 0.3568 | 0.0 | 0.7643 | 0.8179 | 0.6311 | 0.7724 | 0.6256 | 0.7747 | 0.5538 | 0.3791 | 0.5082 | 0.5368 | 0.8279 | 0.7398 | 0.7573 | 0.7594 | 0.7743 | 0.7809 | 0.2953 |
| 0.054 | 13.68 | 6840 | 0.2284 | 0.6284 | 0.7573 | 0.8271 | nan | 0.8525 | 0.9009 | 0.7383 | 0.8598 | 0.7058 | 0.8868 | 0.7452 | 0.4685 | 0.6112 | 0.6215 | 0.9114 | 0.8494 | 0.8378 | 0.8523 | 0.8422 | 0.8296 | 0.3611 | 0.0 | 0.7645 | 0.8183 | 0.6366 | 0.7723 | 0.6244 | 0.7750 | 0.5526 | 0.3927 | 0.5061 | 0.5297 | 0.8286 | 0.7404 | 0.7574 | 0.7601 | 0.7754 | 0.7771 | 0.2994 |
| 0.0289 | 13.72 | 6860 | 0.2274 | 0.6297 | 0.7595 | 0.8282 | nan | 0.8596 | 0.9078 | 0.7485 | 0.8556 | 0.6974 | 0.8891 | 0.7552 | 0.4650 | 0.6101 | 0.6309 | 0.9094 | 0.8471 | 0.8419 | 0.8515 | 0.8426 | 0.8371 | 0.3631 | 0.0 | 0.7676 | 0.8199 | 0.6401 | 0.7709 | 0.6265 | 0.7744 | 0.5559 | 0.3916 | 0.5079 | 0.5359 | 0.8284 | 0.7406 | 0.7582 | 0.7617 | 0.7749 | 0.7807 | 0.2995 |
| 0.0428 | 13.76 | 6880 | 0.2275 | 0.6282 | 0.7584 | 0.8271 | nan | 0.8697 | 0.8965 | 0.7569 | 0.8585 | 0.7026 | 0.8861 | 0.7531 | 0.4632 | 0.5979 | 0.6336 | 0.9129 | 0.8470 | 0.8393 | 0.8537 | 0.8435 | 0.8265 | 0.3511 | 0.0 | 0.7661 | 0.8186 | 0.6414 | 0.7708 | 0.6242 | 0.7755 | 0.5540 | 0.3873 | 0.5025 | 0.5358 | 0.8288 | 0.7410 | 0.7598 | 0.7606 | 0.7745 | 0.7759 | 0.2906 |
| 0.0262 | 13.8 | 6900 | 0.2307 | 0.6296 | 0.7619 | 0.8271 | nan | 0.8737 | 0.9034 | 0.7519 | 0.8523 | 0.7033 | 0.8888 | 0.7561 | 0.4930 | 0.5972 | 0.6564 | 0.9107 | 0.8473 | 0.8322 | 0.8615 | 0.8355 | 0.8268 | 0.3629 | 0.0 | 0.7664 | 0.8191 | 0.6413 | 0.7697 | 0.6252 | 0.7771 | 0.5545 | 0.4006 | 0.5030 | 0.5446 | 0.8283 | 0.7406 | 0.7594 | 0.7598 | 0.7721 | 0.7765 | 0.2948 |
| 0.034 | 13.84 | 6920 | 0.2306 | 0.6306 | 0.7642 | 0.8280 | nan | 0.8723 | 0.9016 | 0.7533 | 0.8544 | 0.7030 | 0.8925 | 0.7515 | 0.5148 | 0.6102 | 0.6373 | 0.9143 | 0.8519 | 0.8318 | 0.8573 | 0.8446 | 0.8296 | 0.3707 | 0.0 | 0.7661 | 0.8199 | 0.6412 | 0.7711 | 0.6243 | 0.7772 | 0.5539 | 0.4123 | 0.5073 | 0.5376 | 0.8288 | 0.7408 | 0.7590 | 0.7619 | 0.7752 | 0.7782 | 0.2967 |
| 0.0364 | 13.88 | 6940 | 0.2279 | 0.6298 | 0.7626 | 0.8268 | nan | 0.8683 | 0.8940 | 0.7468 | 0.8531 | 0.7034 | 0.8918 | 0.7561 | 0.5135 | 0.6046 | 0.6460 | 0.9170 | 0.8475 | 0.8329 | 0.8522 | 0.8421 | 0.8244 | 0.3708 | 0.0 | 0.7630 | 0.8169 | 0.6386 | 0.7703 | 0.6253 | 0.7771 | 0.5546 | 0.4098 | 0.5054 | 0.5407 | 0.8283 | 0.7404 | 0.7592 | 0.7606 | 0.7749 | 0.7758 | 0.2953 |
| 0.0521 | 13.92 | 6960 | 0.2275 | 0.6300 | 0.7623 | 0.8271 | nan | 0.8659 | 0.8991 | 0.7397 | 0.8542 | 0.7023 | 0.8863 | 0.7566 | 0.5049 | 0.6100 | 0.6424 | 0.9156 | 0.8527 | 0.8341 | 0.8587 | 0.8405 | 0.8202 | 0.3765 | 0.0 | 0.7651 | 0.8186 | 0.6366 | 0.7705 | 0.6265 | 0.7761 | 0.5561 | 0.4079 | 0.5090 | 0.5414 | 0.8282 | 0.7402 | 0.7585 | 0.7608 | 0.7742 | 0.7734 | 0.2968 |
| 0.0303 | 13.96 | 6980 | 0.2276 | 0.6298 | 0.7618 | 0.8277 | nan | 0.8509 | 0.9057 | 0.7412 | 0.8548 | 0.7029 | 0.8858 | 0.7557 | 0.5095 | 0.6060 | 0.6347 | 0.9150 | 0.8610 | 0.8288 | 0.8581 | 0.8385 | 0.8270 | 0.3748 | 0.0 | 0.7652 | 0.8209 | 0.6376 | 0.7709 | 0.6247 | 0.7765 | 0.5552 | 0.4065 | 0.5066 | 0.5384 | 0.8286 | 0.7394 | 0.7566 | 0.7611 | 0.7738 | 0.7768 | 0.2978 |
| 0.0313 | 14.0 | 7000 | 0.2287 | 0.6287 | 0.7593 | 0.8268 | nan | 0.8446 | 0.9004 | 0.7461 | 0.8603 | 0.7037 | 0.8831 | 0.7461 | 0.5012 | 0.5885 | 0.6483 | 0.9121 | 0.8581 | 0.8307 | 0.8587 | 0.8352 | 0.8259 | 0.3648 | 0.0 | 0.7627 | 0.8190 | 0.6387 | 0.7721 | 0.6214 | 0.7759 | 0.5527 | 0.4051 | 0.5000 | 0.5437 | 0.8286 | 0.7395 | 0.7566 | 0.7596 | 0.7726 | 0.7751 | 0.2937 |
| 0.0295 | 14.04 | 7020 | 0.2245 | 0.6275 | 0.7567 | 0.8264 | nan | 0.8466 | 0.8983 | 0.7551 | 0.8597 | 0.7003 | 0.8906 | 0.7474 | 0.4686 | 0.5751 | 0.6514 | 0.9114 | 0.8521 | 0.8331 | 0.8520 | 0.8400 | 0.8209 | 0.3621 | 0.0 | 0.7624 | 0.8184 | 0.6410 | 0.7722 | 0.6226 | 0.7765 | 0.5533 | 0.3895 | 0.4938 | 0.5430 | 0.8288 | 0.7398 | 0.7575 | 0.7587 | 0.7736 | 0.7730 | 0.2917 |
| 0.0335 | 14.08 | 7040 | 0.2252 | 0.6275 | 0.7575 | 0.8272 | nan | 0.8498 | 0.9024 | 0.7555 | 0.8566 | 0.7038 | 0.8934 | 0.7482 | 0.4464 | 0.5949 | 0.6440 | 0.9122 | 0.8530 | 0.8304 | 0.8594 | 0.8340 | 0.8248 | 0.3678 | 0.0 | 0.7637 | 0.8202 | 0.6406 | 0.7716 | 0.6209 | 0.7784 | 0.5514 | 0.3733 | 0.5023 | 0.5410 | 0.8293 | 0.7405 | 0.7581 | 0.7611 | 0.7730 | 0.7750 | 0.2953 |
| 0.0308 | 14.12 | 7060 | 0.2311 | 0.6268 | 0.7569 | 0.8266 | nan | 0.8595 | 0.9011 | 0.7570 | 0.8525 | 0.7014 | 0.8929 | 0.7559 | 0.4232 | 0.6013 | 0.6404 | 0.9101 | 0.8513 | 0.8356 | 0.8590 | 0.8357 | 0.8193 | 0.3719 | 0.0 | 0.7655 | 0.8191 | 0.6411 | 0.7699 | 0.6228 | 0.7777 | 0.5522 | 0.3576 | 0.5049 | 0.5401 | 0.8288 | 0.7413 | 0.7598 | 0.7607 | 0.7727 | 0.7719 | 0.2964 |
| 0.0901 | 14.16 | 7080 | 0.2238 | 0.6248 | 0.7521 | 0.8257 | nan | 0.8481 | 0.9002 | 0.7428 | 0.8561 | 0.7035 | 0.8920 | 0.7512 | 0.4234 | 0.5920 | 0.6396 | 0.9113 | 0.8482 | 0.8325 | 0.8501 | 0.8319 | 0.8177 | 0.3453 | 0.0 | 0.7600 | 0.8177 | 0.6368 | 0.7711 | 0.6212 | 0.7770 | 0.5519 | 0.3595 | 0.5001 | 0.5397 | 0.8287 | 0.7398 | 0.7578 | 0.7585 | 0.7701 | 0.7704 | 0.2867 |
| 0.0342 | 14.2 | 7100 | 0.2280 | 0.6261 | 0.7537 | 0.8276 | nan | 0.8545 | 0.8969 | 0.7266 | 0.8636 | 0.7020 | 0.8895 | 0.7496 | 0.4283 | 0.5876 | 0.6378 | 0.9157 | 0.8480 | 0.8372 | 0.8573 | 0.8374 | 0.8164 | 0.3642 | 0.0 | 0.7629 | 0.8182 | 0.6309 | 0.7742 | 0.6218 | 0.7774 | 0.5560 | 0.3651 | 0.4989 | 0.5398 | 0.8291 | 0.7396 | 0.7580 | 0.7601 | 0.7711 | 0.7713 | 0.2960 |
| 0.0464 | 14.24 | 7120 | 0.2264 | 0.6276 | 0.7568 | 0.8275 | nan | 0.8558 | 0.9002 | 0.7335 | 0.8599 | 0.7014 | 0.8886 | 0.7512 | 0.4561 | 0.5957 | 0.6327 | 0.9154 | 0.8503 | 0.8383 | 0.8605 | 0.8382 | 0.8179 | 0.3697 | 0.0 | 0.7631 | 0.8190 | 0.6342 | 0.7730 | 0.6218 | 0.7780 | 0.5556 | 0.3813 | 0.5025 | 0.5375 | 0.8291 | 0.7401 | 0.7586 | 0.7606 | 0.7711 | 0.7717 | 0.2997 |
| 0.035 | 14.28 | 7140 | 0.2272 | 0.6279 | 0.7576 | 0.8268 | nan | 0.8576 | 0.8974 | 0.7363 | 0.8581 | 0.7020 | 0.8893 | 0.7512 | 0.4621 | 0.5983 | 0.6404 | 0.9140 | 0.8468 | 0.8391 | 0.8556 | 0.8375 | 0.8194 | 0.3736 | 0.0 | 0.7628 | 0.8179 | 0.6349 | 0.7721 | 0.6215 | 0.7788 | 0.5543 | 0.3825 | 0.5040 | 0.5402 | 0.8294 | 0.7404 | 0.7596 | 0.7597 | 0.7714 | 0.7721 | 0.3005 |
| 0.0607 | 14.32 | 7160 | 0.2220 | 0.6271 | 0.7564 | 0.8263 | nan | 0.8558 | 0.9017 | 0.7173 | 0.8597 | 0.7047 | 0.8888 | 0.7371 | 0.4717 | 0.6011 | 0.6354 | 0.9143 | 0.8470 | 0.8350 | 0.8580 | 0.8417 | 0.8224 | 0.3679 | 0.0 | 0.7621 | 0.8178 | 0.6282 | 0.7734 | 0.6183 | 0.7781 | 0.5518 | 0.3886 | 0.5048 | 0.5376 | 0.8283 | 0.7403 | 0.7586 | 0.7595 | 0.7711 | 0.7723 | 0.2973 |
| 0.0385 | 14.36 | 7180 | 0.2286 | 0.6258 | 0.7531 | 0.8268 | nan | 0.8600 | 0.9010 | 0.7351 | 0.8591 | 0.7037 | 0.8914 | 0.7511 | 0.4106 | 0.5936 | 0.6409 | 0.9094 | 0.8412 | 0.8394 | 0.8497 | 0.8356 | 0.8172 | 0.3641 | 0.0 | 0.7641 | 0.8184 | 0.6351 | 0.7720 | 0.6222 | 0.7784 | 0.5543 | 0.3494 | 0.5018 | 0.5404 | 0.8295 | 0.7407 | 0.7608 | 0.7580 | 0.7723 | 0.7711 | 0.2966 |
| 0.0249 | 14.4 | 7200 | 0.2265 | 0.6277 | 0.7564 | 0.8279 | nan | 0.8588 | 0.9019 | 0.7445 | 0.8581 | 0.7004 | 0.8924 | 0.7549 | 0.4295 | 0.5960 | 0.6456 | 0.9119 | 0.8410 | 0.8413 | 0.8534 | 0.8380 | 0.8246 | 0.3664 | 0.0 | 0.7653 | 0.8200 | 0.6387 | 0.7719 | 0.6239 | 0.7791 | 0.5555 | 0.3618 | 0.5031 | 0.5431 | 0.8301 | 0.7412 | 0.7613 | 0.7592 | 0.7726 | 0.7750 | 0.2969 |
| 0.0696 | 14.44 | 7220 | 0.2261 | 0.6251 | 0.7524 | 0.8273 | nan | 0.8546 | 0.9017 | 0.7450 | 0.8596 | 0.7046 | 0.8882 | 0.7522 | 0.3870 | 0.5925 | 0.6459 | 0.9097 | 0.8463 | 0.8409 | 0.8488 | 0.8384 | 0.8196 | 0.3559 | 0.0 | 0.7635 | 0.8198 | 0.6386 | 0.7722 | 0.6209 | 0.7789 | 0.5533 | 0.3322 | 0.5011 | 0.5428 | 0.8294 | 0.7415 | 0.7607 | 0.7582 | 0.7736 | 0.7719 | 0.2937 |
| 0.0275 | 14.48 | 7240 | 0.2313 | 0.6257 | 0.7528 | 0.8277 | nan | 0.8543 | 0.9035 | 0.7401 | 0.8612 | 0.7019 | 0.8917 | 0.7480 | 0.3991 | 0.5864 | 0.6421 | 0.9076 | 0.8444 | 0.8442 | 0.8526 | 0.8423 | 0.8194 | 0.3585 | 0.0 | 0.7642 | 0.8200 | 0.6380 | 0.7729 | 0.6208 | 0.7786 | 0.5533 | 0.3423 | 0.4979 | 0.5409 | 0.8290 | 0.7413 | 0.7612 | 0.7601 | 0.7746 | 0.7720 | 0.2953 |
| 0.0275 | 14.52 | 7260 | 0.2287 | 0.6262 | 0.7541 | 0.8272 | nan | 0.8583 | 0.8979 | 0.7486 | 0.8614 | 0.7002 | 0.8887 | 0.7501 | 0.4107 | 0.6033 | 0.6407 | 0.9106 | 0.8440 | 0.8423 | 0.8479 | 0.8377 | 0.8219 | 0.3554 | 0.0 | 0.7642 | 0.8185 | 0.6394 | 0.7725 | 0.6219 | 0.7782 | 0.5540 | 0.3498 | 0.5049 | 0.5400 | 0.8294 | 0.7409 | 0.7605 | 0.7583 | 0.7735 | 0.7729 | 0.2929 |
| 0.0289 | 14.56 | 7280 | 0.2300 | 0.6261 | 0.7551 | 0.8266 | nan | 0.8598 | 0.9003 | 0.7461 | 0.8573 | 0.7020 | 0.8874 | 0.7491 | 0.4181 | 0.5875 | 0.6462 | 0.9131 | 0.8410 | 0.8484 | 0.8535 | 0.8421 | 0.8187 | 0.3665 | 0.0 | 0.7650 | 0.8185 | 0.6386 | 0.7712 | 0.6206 | 0.7776 | 0.5530 | 0.3536 | 0.4989 | 0.5423 | 0.8287 | 0.7406 | 0.7610 | 0.7598 | 0.7737 | 0.7712 | 0.2960 |
| 0.0344 | 14.6 | 7300 | 0.2288 | 0.6249 | 0.7539 | 0.8251 | nan | 0.8592 | 0.8959 | 0.7598 | 0.8538 | 0.7016 | 0.8922 | 0.7515 | 0.4125 | 0.5852 | 0.6357 | 0.9101 | 0.8403 | 0.8440 | 0.8519 | 0.8393 | 0.8194 | 0.3634 | 0.0 | 0.7626 | 0.8163 | 0.6421 | 0.7700 | 0.6202 | 0.7781 | 0.5519 | 0.3484 | 0.4966 | 0.5370 | 0.8285 | 0.7408 | 0.7605 | 0.7584 | 0.7721 | 0.7707 | 0.2945 |
| 0.0346 | 14.64 | 7320 | 0.2338 | 0.6268 | 0.7566 | 0.8269 | nan | 0.8557 | 0.9050 | 0.7529 | 0.8560 | 0.7025 | 0.8915 | 0.7463 | 0.4320 | 0.5965 | 0.6417 | 0.9079 | 0.8469 | 0.8410 | 0.8546 | 0.8412 | 0.8252 | 0.3643 | 0.0 | 0.7642 | 0.8193 | 0.6412 | 0.7712 | 0.6191 | 0.7787 | 0.5509 | 0.3614 | 0.5017 | 0.5405 | 0.8284 | 0.7421 | 0.7605 | 0.7596 | 0.7733 | 0.7743 | 0.2955 |
| 0.0307 | 14.68 | 7340 | 0.2271 | 0.6265 | 0.7557 | 0.8265 | nan | 0.8564 | 0.9005 | 0.7511 | 0.8552 | 0.7005 | 0.8950 | 0.7497 | 0.4260 | 0.5976 | 0.6397 | 0.9100 | 0.8436 | 0.8409 | 0.8508 | 0.8406 | 0.8237 | 0.3651 | 0.0 | 0.7637 | 0.8184 | 0.6400 | 0.7708 | 0.6203 | 0.7788 | 0.5515 | 0.3581 | 0.5018 | 0.5393 | 0.8290 | 0.7419 | 0.7607 | 0.7594 | 0.7733 | 0.7741 | 0.2952 |
| 0.0336 | 14.72 | 7360 | 0.2285 | 0.6264 | 0.7548 | 0.8272 | nan | 0.8554 | 0.9010 | 0.7462 | 0.8625 | 0.7020 | 0.8938 | 0.7406 | 0.4302 | 0.5991 | 0.6354 | 0.9109 | 0.8508 | 0.8367 | 0.8526 | 0.8378 | 0.8187 | 0.3578 | 0.0 | 0.7643 | 0.8186 | 0.6385 | 0.7732 | 0.6186 | 0.7790 | 0.5506 | 0.3647 | 0.5021 | 0.5378 | 0.8292 | 0.7416 | 0.7589 | 0.7596 | 0.7736 | 0.7720 | 0.2933 |
| 0.0341 | 14.76 | 7380 | 0.2335 | 0.6266 | 0.7552 | 0.8276 | nan | 0.8532 | 0.9024 | 0.7469 | 0.8566 | 0.6991 | 0.8969 | 0.7516 | 0.4132 | 0.5960 | 0.6437 | 0.9093 | 0.8471 | 0.8419 | 0.8524 | 0.8377 | 0.8259 | 0.3640 | 0.0 | 0.7633 | 0.8190 | 0.6388 | 0.7714 | 0.6215 | 0.7792 | 0.5524 | 0.3511 | 0.5017 | 0.5419 | 0.8290 | 0.7430 | 0.7612 | 0.7601 | 0.7740 | 0.7756 | 0.2950 |
| 0.0321 | 14.8 | 7400 | 0.2308 | 0.6264 | 0.7547 | 0.8276 | nan | 0.8541 | 0.9008 | 0.7331 | 0.8581 | 0.7018 | 0.8939 | 0.7496 | 0.4216 | 0.5962 | 0.6428 | 0.9152 | 0.8488 | 0.8427 | 0.8529 | 0.8394 | 0.8179 | 0.3604 | 0.0 | 0.7644 | 0.8196 | 0.6338 | 0.7715 | 0.6202 | 0.7798 | 0.5516 | 0.3569 | 0.5020 | 0.5416 | 0.8294 | 0.7426 | 0.7612 | 0.7601 | 0.7747 | 0.7718 | 0.2938 |
| 0.0783 | 14.84 | 7420 | 0.2278 | 0.6258 | 0.7540 | 0.8272 | nan | 0.8556 | 0.9037 | 0.7446 | 0.8563 | 0.7031 | 0.8952 | 0.7497 | 0.3995 | 0.6044 | 0.6390 | 0.9105 | 0.8453 | 0.8387 | 0.8480 | 0.8397 | 0.8223 | 0.3630 | 0.0 | 0.7644 | 0.8195 | 0.6383 | 0.7710 | 0.6198 | 0.7802 | 0.5510 | 0.3419 | 0.5047 | 0.5393 | 0.8294 | 0.7428 | 0.7609 | 0.7590 | 0.7742 | 0.7735 | 0.2945 |
| 0.0259 | 14.88 | 7440 | 0.2288 | 0.6263 | 0.7549 | 0.8268 | nan | 0.8559 | 0.8999 | 0.7459 | 0.8566 | 0.7012 | 0.8953 | 0.7488 | 0.4195 | 0.6040 | 0.6386 | 0.9119 | 0.8451 | 0.8358 | 0.8513 | 0.8396 | 0.8231 | 0.3611 | 0.0 | 0.7638 | 0.8185 | 0.6384 | 0.7710 | 0.6206 | 0.7792 | 0.5513 | 0.3552 | 0.5042 | 0.5389 | 0.8296 | 0.7422 | 0.7600 | 0.7592 | 0.7734 | 0.7737 | 0.2937 |
| 0.0353 | 14.92 | 7460 | 0.2265 | 0.6264 | 0.7550 | 0.8269 | nan | 0.8508 | 0.9005 | 0.7393 | 0.8568 | 0.7007 | 0.8919 | 0.7503 | 0.4240 | 0.6047 | 0.6397 | 0.9123 | 0.8487 | 0.8358 | 0.8533 | 0.8386 | 0.8246 | 0.3624 | 0.0 | 0.7618 | 0.8188 | 0.6362 | 0.7709 | 0.6215 | 0.7790 | 0.5519 | 0.3581 | 0.5051 | 0.5396 | 0.8293 | 0.7418 | 0.7596 | 0.7598 | 0.7734 | 0.7745 | 0.2943 |
| 0.0386 | 14.96 | 7480 | 0.2278 | 0.6261 | 0.7548 | 0.8261 | nan | 0.8536 | 0.8987 | 0.7446 | 0.8552 | 0.7021 | 0.8904 | 0.7532 | 0.4292 | 0.6033 | 0.6383 | 0.9109 | 0.8457 | 0.8402 | 0.8466 | 0.8366 | 0.8216 | 0.3618 | 0.0 | 0.7620 | 0.8177 | 0.6378 | 0.7700 | 0.6215 | 0.7788 | 0.5515 | 0.3583 | 0.5046 | 0.5391 | 0.8293 | 0.7418 | 0.7605 | 0.7575 | 0.7728 | 0.7725 | 0.2940 |
| 0.0279 | 15.0 | 7500 | 0.2292 | 0.6258 | 0.7547 | 0.8256 | nan | 0.8561 | 0.8974 | 0.7540 | 0.8553 | 0.7026 | 0.8913 | 0.7525 | 0.4251 | 0.6014 | 0.6374 | 0.9094 | 0.8452 | 0.8343 | 0.8506 | 0.8287 | 0.8232 | 0.3662 | 0.0 | 0.7625 | 0.8171 | 0.6400 | 0.7700 | 0.6211 | 0.7788 | 0.5512 | 0.3564 | 0.5032 | 0.5381 | 0.8294 | 0.7412 | 0.7591 | 0.7579 | 0.7705 | 0.7729 | 0.2956 |
### Framework versions
- Transformers 4.28.1
- Pytorch 2.0.0+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3
| 261,096 | [
[
-0.048370361328125,
-0.040191650390625,
0.01751708984375,
0.00791168212890625,
-0.009521484375,
0.0120697021484375,
0.00388336181640625,
-0.0024871826171875,
0.05511474609375,
0.0257415771484375,
-0.041778564453125,
-0.0380859375,
-0.05755615234375,
0.003732... |
TheBloke/WizardLM-7B-V1-0-Uncensored-SuperHOT-8K-GPTQ | 2023-08-21T14:14:34.000Z | [
"transformers",
"safetensors",
"llama",
"text-generation",
"custom_code",
"license:other",
"text-generation-inference",
"region:us"
] | text-generation | TheBloke | null | null | TheBloke/WizardLM-7B-V1-0-Uncensored-SuperHOT-8K-GPTQ | 14 | 537 | transformers | 2023-07-06T22:34:52 | ---
inference: false
license: other
---
<!-- header start -->
<!-- 200823 -->
<div style="width: auto; margin-left: auto; margin-right: auto">
<img src="https://i.imgur.com/EBdldam.jpg" alt="TheBlokeAI" style="width: 100%; min-width: 400px; display: block; margin: auto;">
</div>
<div style="display: flex; justify-content: space-between; width: 100%;">
<div style="display: flex; flex-direction: column; align-items: flex-start;">
<p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://discord.gg/theblokeai">Chat & support: TheBloke's Discord server</a></p>
</div>
<div style="display: flex; flex-direction: column; align-items: flex-end;">
<p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://www.patreon.com/TheBlokeAI">Want to contribute? TheBloke's Patreon page</a></p>
</div>
</div>
<div style="text-align:center; margin-top: 0em; margin-bottom: 0em"><p style="margin-top: 0.25em; margin-bottom: 0em;">TheBloke's LLM work is generously supported by a grant from <a href="https://a16z.com">andreessen horowitz (a16z)</a></p></div>
<hr style="margin-top: 1.0em; margin-bottom: 1.0em;">
<!-- header end -->
# Eric Hartford's WizardLM-7B-V1.0-Uncensored GPTQ
These files are GPTQ 4bit model files for [Eric Hartford's WizardLM-7B-V1.0-Uncensored](https://huggingface.co/ehartford/WizardLM-7B-V1.0-Uncensored) merged with [Kaio Ken's SuperHOT 8K](https://huggingface.co/kaiokendev/superhot-7b-8k-no-rlhf-test).
It is the result of quantising to 4bit using [GPTQ-for-LLaMa](https://github.com/qwopqwop200/GPTQ-for-LLaMa).
**This is an experimental new GPTQ which offers up to 8K context size**
The increased context is tested to work with [ExLlama](https://github.com/turboderp/exllama), via the latest release of [text-generation-webui](https://github.com/oobabooga/text-generation-webui).
It has also been tested from Python code using AutoGPTQ, and `trust_remote_code=True`.
Code credits:
- Original concept and code for increasing context length: [kaiokendev](https://huggingface.co/kaiokendev)
- Updated Llama modelling code that includes this automatically via trust_remote_code: [emozilla](https://huggingface.co/emozilla).
Please read carefully below to see how to use it.
## Repositories available
* [4-bit GPTQ models for GPU inference](https://huggingface.co/TheBloke/WizardLM-7B-V1-0-Uncensored-SuperHOT-8K-GPTQ)
* [2, 3, 4, 5, 6 and 8-bit GGML models for CPU inference](https://huggingface.co/TheBloke/WizardLM-7B-V1-0-Uncensored-SuperHOT-8K-GGML)
* [Unquantised SuperHOT fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/TheBloke/WizardLM-7B-V1-0-Uncensored-SuperHOT-8K-fp16)
* [Unquantised base fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/ehartford/WizardLM-7B-V1.0-Uncensored)
## How to easily download and use this model in text-generation-webui with ExLlama
Please make sure you're using the latest version of text-generation-webui
1. Click the **Model tab**.
2. Under **Download custom model or LoRA**, enter `TheBloke/WizardLM-7B-V1-0-Uncensored-SuperHOT-8K-GPTQ`.
3. Click **Download**.
4. The model will start downloading. Once it's finished it will say "Done"
5. Untick **Autoload the model**
6. In the top left, click the refresh icon next to **Model**.
7. In the **Model** dropdown, choose the model you just downloaded: `WizardLM-7B-V1-0-Uncensored-SuperHOT-8K-GPTQ`
8. To use the increased context, set the **Loader** to **ExLlama**, set **max_seq_len** to 8192 or 4096, and set **compress_pos_emb** to **4** for 8192 context, or to **2** for 4096 context.
9. Now click **Save Settings** followed by **Reload**
10. The model will automatically load, and is now ready for use!
11. Once you're ready, click the **Text Generation tab** and enter a prompt to get started!
## How to use this GPTQ model from Python code with AutoGPTQ
First make sure you have AutoGPTQ and Einops installed:
```
pip3 install einops auto-gptq
```
Then run the following code. Note that in order to get this to work, `config.json` has been hardcoded to a sequence length of 8192.
If you want to try 4096 instead to reduce VRAM usage, please manually edit `config.json` to set `max_position_embeddings` to the value you want.
```python
from transformers import AutoTokenizer, pipeline, logging
from auto_gptq import AutoGPTQForCausalLM, BaseQuantizeConfig
import argparse
model_name_or_path = "TheBloke/WizardLM-7B-V1-0-Uncensored-SuperHOT-8K-GPTQ"
model_basename = "wizardlm-7b-v1.0-superhot-8k-GPTQ-4bit-128g.no-act.order"
use_triton = False
tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, use_fast=True)
model = AutoGPTQForCausalLM.from_quantized(model_name_or_path,
model_basename=model_basename,
use_safetensors=True,
trust_remote_code=True,
device_map='auto',
use_triton=use_triton,
quantize_config=None)
model.seqlen = 8192
# Note: check the prompt template is correct for this model.
prompt = "Tell me about AI"
prompt_template=f'''USER: {prompt}
ASSISTANT:'''
print("\n\n*** Generate:")
input_ids = tokenizer(prompt_template, return_tensors='pt').input_ids.cuda()
output = model.generate(inputs=input_ids, temperature=0.7, max_new_tokens=512)
print(tokenizer.decode(output[0]))
# Inference can also be done using transformers' pipeline
# Prevent printing spurious transformers error when using pipeline with AutoGPTQ
logging.set_verbosity(logging.CRITICAL)
print("*** Pipeline:")
pipe = pipeline(
"text-generation",
model=model,
tokenizer=tokenizer,
max_new_tokens=512,
temperature=0.7,
top_p=0.95,
repetition_penalty=1.15
)
print(pipe(prompt_template)[0]['generated_text'])
```
## Using other UIs: monkey patch
Provided in the repo is `llama_rope_scaled_monkey_patch.py`, written by @kaiokendev.
It can be theoretically be added to any Python UI or custom code to enable the same result as `trust_remote_code=True`. I have not tested this, and it should be superseded by using `trust_remote_code=True`, but I include it for completeness and for interest.
## Provided files
**wizardlm-7b-v1.0-superhot-8k-GPTQ-4bit-128g.no-act.order.safetensors**
This will work with AutoGPTQ, ExLlama, and CUDA versions of GPTQ-for-LLaMa. There are reports of issues with Triton mode of recent GPTQ-for-LLaMa. If you have issues, please use AutoGPTQ instead.
It was created with group_size 128 to increase inference accuracy, but without --act-order (desc_act) to increase compatibility and improve inference speed.
* `wizardlm-7b-v1.0-superhot-8k-GPTQ-4bit-128g.no-act.order.safetensors`
* Works for use with ExLlama with increased context (4096 or 8192)
* Works with AutoGPTQ in Python code, including with increased context, if `trust_remote_code=True` is set.
* Should work with GPTQ-for-LLaMa in CUDA mode, but unknown if increased context works - TBC. May have issues with GPTQ-for-LLaMa Triton mode.
* Works with text-generation-webui, including one-click-installers.
* Parameters: Groupsize = 128. Act Order / desc_act = False.
<!-- footer start -->
<!-- 200823 -->
## Discord
For further support, and discussions on these models and AI in general, join us at:
[TheBloke AI's Discord server](https://discord.gg/theblokeai)
## Thanks, and how to contribute.
Thanks to the [chirper.ai](https://chirper.ai) team!
I've had a lot of people ask if they can contribute. I enjoy providing models and helping people, and would love to be able to spend even more time doing it, as well as expanding into new projects like fine tuning/training.
If you're able and willing to contribute it will be most gratefully received and will help me to keep providing more models, and to start work on new AI projects.
Donaters will get priority support on any and all AI/LLM/model questions and requests, access to a private Discord room, plus other benefits.
* Patreon: https://patreon.com/TheBlokeAI
* Ko-Fi: https://ko-fi.com/TheBlokeAI
**Special thanks to**: Aemon Algiz.
**Patreon special mentions**: Sam, theTransient, Jonathan Leane, Steven Wood, webtim, Johann-Peter Hartmann, Geoffrey Montalvo, Gabriel Tamborski, Willem Michiel, John Villwock, Derek Yates, Mesiah Bishop, Eugene Pentland, Pieter, Chadd, Stephen Murray, Daniel P. Andersen, terasurfer, Brandon Frisco, Thomas Belote, Sid, Nathan LeClaire, Magnesian, Alps Aficionado, Stanislav Ovsiannikov, Alex, Joseph William Delisle, Nikolai Manek, Michael Davis, Junyu Yang, K, J, Spencer Kim, Stefan Sabev, Olusegun Samson, transmissions 11, Michael Levine, Cory Kujawski, Rainer Wilmers, zynix, Kalila, Luke @flexchar, Ajan Kanaga, Mandus, vamX, Ai Maven, Mano Prime, Matthew Berman, subjectnull, Vitor Caleffi, Clay Pascal, biorpg, alfie_i, 阿明, Jeffrey Morgan, ya boyyy, Raymond Fosdick, knownsqashed, Olakabola, Leonard Tan, ReadyPlayerEmma, Enrico Ros, Dave, Talal Aujan, Illia Dulskyi, Sean Connelly, senxiiz, Artur Olbinski, Elle, Raven Klaugh, Fen Risland, Deep Realms, Imad Khwaja, Fred von Graf, Will Dee, usrbinkat, SuperWojo, Alexandros Triantafyllidis, Swaroop Kallakuri, Dan Guido, John Detwiler, Pedro Madruga, Iucharbius, Viktor Bowallius, Asp the Wyvern, Edmond Seymore, Trenton Dambrowitz, Space Cruiser, Spiking Neurons AB, Pyrater, LangChain4j, Tony Hughes, Kacper Wikieł, Rishabh Srivastava, David Ziegler, Luke Pendergrass, Andrey, Gabriel Puliatti, Lone Striker, Sebastain Graf, Pierre Kircher, Randy H, NimbleBox.ai, Vadim, danny, Deo Leter
Thank you to all my generous patrons and donaters!
And thank you again to a16z for their generous grant.
<!-- footer end -->
# Original model card: Kaio Ken's SuperHOT 8K
### SuperHOT Prototype 2 w/ 8K Context
This is a second prototype of SuperHOT, a NSFW focused LoRA, this time 7B with 8K context and no RLHF, using the same technique described in [the github blog](https://kaiokendev.github.io/til#extending-context-to-8k).
#### Looking for Merged & Quantized Models?
Make some please :)
#### Using the monkey-patch?
You will **NEED** to **apply the monkeypatch** or, if you are already using the monkeypatch, **change the scaling factor to 0.25 and the maximum sequence length to 8192**
The monkeypatch is only necessary if you are using a front-end/back-end that does not already support scaling and said front-end/back-end is Python-based (i.e. Huggingface Transformers). To apply the patch, you will need to copy the `llama_rope_scaled_monkey_patch.py` into your working directory and call the exported function `replace_llama_rope_with_scaled_rope` at the very start of your Python program. It will modify the Transformers library's implementation of RoPE to properly apply the scaling factor.
#### Using Oobabooga with Exllama?
Switch your loader to `exllama` or `exllama_hf` Add the arguments `max_seq_len 8192` and `compress_pos_emb 4`. **While the model may work well with `compress_pos_emb 2`, it was trained on 4, so that is what I advocate for you to use**
Example in the command-line:
- `python server.py --max_seq_len 8192 --compress_pos_emb 4 --loader exllama_hf`
In the UI, you will see the loader option in the `Models` tab. Once you select either `exllama` or `exllama_hf`, the `max_seq_len` and `compress_pos_emb` settings will appear.
#### Training Details
I trained the LoRA with the following configuration:
- 1200 samples (~400 samples over 2048 sequence length)
- learning rate of 3e-4
- 3 epochs
- The exported modules are:
- q_proj
- k_proj
- v_proj
- o_proj
- no bias
- Rank = 4
- Alpha = 8
- no dropout
- weight decay of 0.1
- AdamW beta1 of 0.9 and beta2 0.99, epsilon of 1e-5
- Trained on 4-bit base model
- Cutoff length: 4096
# Original model card: Eric Hartford's WizardLM-7B-V1.0-Uncensored
This is a retraining of https://huggingface.co/WizardLM/WizardLM-7B-V1.0 with a filtered dataset, intended to reduce refusals, avoidance, and bias.
Note that LLaMA itself has inherent ethical beliefs, so there's no such thing as a "truly uncensored" model. But this model will be more compliant than WizardLM/WizardLM-7B-V1.0.
Shout out to the open source AI/ML community, and everyone who helped me out.
Note: An uncensored model has no guardrails. You are responsible for anything you do with the model, just as you are responsible for anything you do with any dangerous object such as a knife, gun, lighter, or car. Publishing anything this model generates is the same as publishing it yourself. You are responsible for the content you publish, and you cannot blame the model any more than you can blame the knife, gun, lighter, or car for what you do with it.
Unlike WizardLM/WizardLM-7B-V1.0, but like WizardLM/WizardLM-13B-V1.0 and WizardLM/WizardLM-33B-V1.0, this model is trained with Vicuna-1.1 style prompts.
```
You are a helpful AI assistant.
USER: <prompt>
ASSISTANT:
```
Thank you [chirper.ai](https://chirper.ai) for sponsoring some of my compute!
| 12,965 | [
[
-0.033203125,
-0.0654296875,
0.0151824951171875,
0.0106201171875,
-0.0232696533203125,
-0.01270294189453125,
0.00222015380859375,
-0.037567138671875,
0.007717132568359375,
0.017608642578125,
-0.034942626953125,
-0.0357666015625,
-0.0310821533203125,
0.009475... |
pruas/BENT-PubMedBERT-NER-Cell-Line | 2023-01-15T12:24:51.000Z | [
"transformers",
"pytorch",
"bert",
"token-classification",
"en",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | token-classification | pruas | null | null | pruas/BENT-PubMedBERT-NER-Cell-Line | 2 | 536 | transformers | 2023-01-14T14:25:56 | ---
language:
- en
pipeline_tag: token-classification
---
Named Entity Recognition (NER) model to recognize cell line entities.
[PubMedBERT](https://huggingface.co/microsoft/BiomedNLP-PubMedBERT-base-uncased-abstract-fulltext) fine-tuned on the following datasets:
- [CellFinder](http://cellfinder.org/about/annotation/): entity type "CellLine"
- [JNLPBA](http://www.geniaproject.org/genia-corpus/term-corpus): entity type "cell_line" | 436 | [
[
-0.03448486328125,
-0.042572021484375,
0.0250091552734375,
0.005229949951171875,
-0.00763702392578125,
0.01385498046875,
0.0247039794921875,
-0.053802490234375,
0.03533935546875,
0.054290771484375,
-0.0294036865234375,
-0.035308837890625,
-0.0074920654296875,
... |
lakshyakh93/deberta_finetuned_pii | 2023-10-08T09:52:35.000Z | [
"transformers",
"pytorch",
"deberta",
"token-classification",
"en",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | token-classification | lakshyakh93 | null | null | lakshyakh93/deberta_finetuned_pii | 1 | 536 | transformers | 2023-10-06T14:19:19 | ---
license: mit
language:
- en
pipeline_tag: token-classification
---
A finetuned model designed to recognize and classify Personally Identifiable Information (PII) within unstructured text data. This powerful model accurately identifies a wide range of PII categories, such as account names, credit card numbers, emails, phone numbers, and addresses. The model is specifically trained to detect various PII types, including but not limited to:
```
| Category | Data |
|------------------------|----------------------------------------------------------------------------------------|
| Account-related information | Account name, account number, and transaction amounts |
| Banking details | BIC, IBAN, and Bitcoin or Ethereum addresses |
| Personal information | Full name, first name, middle name, last name, gender, and date of birth |
| Contact information | Email, phone number, and street address (including building number, city, county, state, and zip code) |
| Job-related data | Job title, job area, job descriptor, and job type |
| Financial data | Credit card number, issuer, CVV, and currency information (code, name, and symbol) |
| Digital identifiers | IP addresses (IPv4 and IPv6), MAC addresses, and user agents |
| Online presence | URL, usernames, and passwords |
| Other sensitive data | SSN, vehicle VIN and VRM, phone IMEI, and nearby GPS coordinates |
```
The PII Identifier Model ensures data privacy and compliance by effectively detecting and categorizing sensitive information within documents, emails, user-generated content, and more. Make your data processing safer and more secure with our state-of-the-art PII detection technology.
How to do Inference :
```
from transformers import pipeline
gen = pipeline("token-classification", "lakshyakh93/deberta_finetuned_pii", device=-1)
text = "My name is John and I live in California."
output = gen(text, aggregation_strategy="first")
```
| 2,291 | [
[
-0.0241851806640625,
-0.06268310546875,
0.026336669921875,
-0.004863739013671875,
-0.003124237060546875,
-0.005931854248046875,
0.00460052490234375,
-0.03173828125,
-0.003353118896484375,
0.041290283203125,
-0.027099609375,
-0.053466796875,
-0.040252685546875,
... |
zeerakwyne/dreambooth_lora_model | 2023-10-12T12:58:58.000Z | [
"diffusers",
"tensorboard",
"stable-diffusion",
"stable-diffusion-diffusers",
"text-to-image",
"lora",
"license:creativeml-openrail-m",
"has_space",
"region:us"
] | text-to-image | zeerakwyne | null | null | zeerakwyne/dreambooth_lora_model | 1 | 536 | diffusers | 2023-10-12T11:50:17 |
---
license: creativeml-openrail-m
base_model: runwayml/stable-diffusion-v1-5
instance_prompt: a photo of sks dog
tags:
- stable-diffusion
- stable-diffusion-diffusers
- text-to-image
- diffusers
- lora
inference: true
---
# LoRA DreamBooth - zeerakwyne/dreambooth_lora_model
These are LoRA adaption weights for runwayml/stable-diffusion-v1-5. The weights were trained on a photo of sks dog using [DreamBooth](https://dreambooth.github.io/). You can find some example images in the following.
LoRA for the text encoder was enabled: False.
| 646 | [
[
-0.0135345458984375,
-0.0193328857421875,
0.0202789306640625,
0.0212249755859375,
-0.0452880859375,
0.01087188720703125,
0.035736083984375,
-0.01458740234375,
0.0501708984375,
0.040435791015625,
-0.048309326171875,
-0.03472900390625,
-0.044677734375,
-0.0144... |
climatebert/distilroberta-base-climate-commitment | 2023-06-20T18:51:55.000Z | [
"transformers",
"pytorch",
"safetensors",
"roberta",
"text-classification",
"en",
"dataset:climatebert/climate_commitments_actions",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | text-classification | climatebert | null | null | climatebert/distilroberta-base-climate-commitment | 0 | 535 | transformers | 2022-03-02T23:29:05 | ---
license: apache-2.0
datasets:
- climatebert/climate_commitments_actions
language:
- en
metrics:
- accuracy
---
# Model Card for distilroberta-base-climate-commitment
## Model Description
This is the fine-tuned ClimateBERT language model with a classification head for classifying climate-related paragraphs into paragraphs being about climate commitments and actions and paragraphs not being about climate commitments and actions.
Using the [climatebert/distilroberta-base-climate-f](https://huggingface.co/climatebert/distilroberta-base-climate-f) language model as starting point, the distilroberta-base-climate-commitment model is fine-tuned on our [climatebert/climate_commitments_actions](https://huggingface.co/climatebert/climate_commitments_actions) dataset.
*Note: This model is trained on paragraphs. It may not perform well on sentences.*
## Citation Information
```bibtex
@techreport{bingler2023cheaptalk,
title={How Cheap Talk in Climate Disclosures Relates to Climate Initiatives, Corporate Emissions, and Reputation Risk},
author={Bingler, Julia and Kraus, Mathias and Leippold, Markus and Webersinke, Nicolas},
type={Working paper},
institution={Available at SSRN 3998435},
year={2023}
}
```
## How to Get Started With the Model
You can use the model with a pipeline for text classification:
```python
from transformers import AutoModelForSequenceClassification, AutoTokenizer, pipeline
from transformers.pipelines.pt_utils import KeyDataset
import datasets
from tqdm.auto import tqdm
dataset_name = "climatebert/climate_commitments_actions"
model_name = "climatebert/distilroberta-base-climate-commitment"
# If you want to use your own data, simply load them as 🤗 Datasets dataset, see https://huggingface.co/docs/datasets/loading
dataset = datasets.load_dataset(dataset_name, split="test")
model = AutoModelForSequenceClassification.from_pretrained(model_name)
tokenizer = AutoTokenizer.from_pretrained(model_name, max_len=512)
pipe = pipeline("text-classification", model=model, tokenizer=tokenizer, device=0)
# See https://huggingface.co/docs/transformers/main_classes/pipelines#transformers.pipeline
for out in tqdm(pipe(KeyDataset(dataset, "text"), padding=True, truncation=True)):
print(out)
``` | 2,260 | [
[
-0.0245208740234375,
-0.04150390625,
0.0195770263671875,
0.009918212890625,
-0.0159912109375,
0.0029888153076171875,
-0.00847625732421875,
-0.00843048095703125,
-0.005626678466796875,
0.03192138671875,
-0.04107666015625,
-0.049072265625,
-0.06463623046875,
-... |
Dizex/InstaFoodRoBERTa-NER | 2023-06-24T07:57:31.000Z | [
"transformers",
"pytorch",
"safetensors",
"roberta",
"token-classification",
"Instagram",
"NER",
"Named Entity Recognition",
"Food Entity Extraction",
"Social Media",
"Informal text",
"RoBERTa",
"en",
"dataset:Dizex/InstaFoodSet",
"license:mit",
"autotrain_compatible",
"endpoints_com... | token-classification | Dizex | null | null | Dizex/InstaFoodRoBERTa-NER | 4 | 535 | transformers | 2022-11-21T19:30:17 | ---
language: en
datasets:
- Dizex/InstaFoodSet
widget:
- text: "Today's meal: Fresh olive poké bowl topped with chia seeds. Very delicious!"
example_title: "Food example 1"
- text: "Tartufo Pasta with garlic flavoured butter and olive oil, egg yolk, parmigiano and pasta water."
example_title: "Food example 2"
tags:
- Instagram
- NER
- Named Entity Recognition
- Food Entity Extraction
- Social Media
- Informal text
- RoBERTa
license: mit
---
# InstaFoodRoBERTa-NER
## Model description
**InstaFoodRoBERTa-NER** is a fine-tuned BERT model that is ready to use for **Named Entity Recognition** of Food entities on informal text (social media like). It has been trained to recognize a single entity: food (FOOD).
The model is deployed and testable [here](https://trendish.abiz.ch/).
Specifically, this model is a [*roberta-base*](https://huggingface.co/roberta-base) model that was fine-tuned on a dataset consisting of 400 English Instagram posts related to food. The [dataset](https://huggingface.co/datasets/Dizex/InstaFoodSet) is open source.
## Intended uses
#### How to use
You can use this model with Transformers *pipeline* for NER.
```python
from transformers import AutoTokenizer, AutoModelForTokenClassification
from transformers import pipeline
tokenizer = AutoTokenizer.from_pretrained("Dizex/InstaFoodRoBERTa-NER")
model = AutoModelForTokenClassification.from_pretrained("Dizex/InstaFoodRoBERTa-NER")
pipe = pipeline("ner", model=model, tokenizer=tokenizer)
example = "Today's meal: Fresh olive poké bowl topped with chia seeds. Very delicious!"
ner_entity_results = pipe(example, aggregation_strategy="simple")
print(ner_entity_results)
```
To get the extracted food entities as strings you can use the following code:
```python
def convert_entities_to_list(text, entities: list[dict]) -> list[str]:
ents = []
for ent in entities:
e = {"start": ent["start"], "end": ent["end"], "label": ent["entity_group"]}
if ents and -1 <= ent["start"] - ents[-1]["end"] <= 1 and ents[-1]["label"] == e["label"]:
ents[-1]["end"] = e["end"]
continue
ents.append(e)
return [text[e["start"]:e["end"]] for e in ents]
print(convert_entities_to_list(example, ner_entity_results))
```
This will result in the following output:
```python
['olive poké bowl', 'chia seeds']
```
## Performance on [InstaFoodSet](https://huggingface.co/datasets/Dizex/InstaFoodSet)
metric|val
-|-
f1 |0.91
precision |0.89
recall |0.93
| 2,528 | [
[
-0.01922607421875,
-0.05413818359375,
0.0071258544921875,
0.0133056640625,
-0.0022754669189453125,
0.00928497314453125,
-0.016754150390625,
-0.032867431640625,
0.043426513671875,
0.0254058837890625,
-0.0280914306640625,
-0.04608154296875,
-0.04937744140625,
... |
keremberke/yolov5s-aerial-sheep | 2023-01-05T09:20:04.000Z | [
"yolov5",
"tensorboard",
"yolo",
"vision",
"object-detection",
"pytorch",
"dataset:keremberke/aerial-sheep-object-detection",
"model-index",
"has_space",
"region:us"
] | object-detection | keremberke | null | null | keremberke/yolov5s-aerial-sheep | 1 | 535 | yolov5 | 2023-01-05T09:19:24 |
---
tags:
- yolov5
- yolo
- vision
- object-detection
- pytorch
library_name: yolov5
library_version: 7.0.7
inference: false
datasets:
- keremberke/aerial-sheep-object-detection
model-index:
- name: keremberke/yolov5s-aerial-sheep
results:
- task:
type: object-detection
dataset:
type: keremberke/aerial-sheep-object-detection
name: keremberke/aerial-sheep-object-detection
split: validation
metrics:
- type: precision # since mAP@0.5 is not available on hf.co/metrics
value: 0.9651314172419881 # min: 0.0 - max: 1.0
name: mAP@0.5
---
<div align="center">
<img width="640" alt="keremberke/yolov5s-aerial-sheep" src="https://huggingface.co/keremberke/yolov5s-aerial-sheep/resolve/main/sample_visuals.jpg">
</div>
### How to use
- Install [yolov5](https://github.com/fcakyon/yolov5-pip):
```bash
pip install -U yolov5
```
- Load model and perform prediction:
```python
import yolov5
# load model
model = yolov5.load('keremberke/yolov5s-aerial-sheep')
# set model parameters
model.conf = 0.25 # NMS confidence threshold
model.iou = 0.45 # NMS IoU threshold
model.agnostic = False # NMS class-agnostic
model.multi_label = False # NMS multiple labels per box
model.max_det = 1000 # maximum number of detections per image
# set image
img = 'https://github.com/ultralytics/yolov5/raw/master/data/images/zidane.jpg'
# perform inference
results = model(img, size=640)
# inference with test time augmentation
results = model(img, augment=True)
# parse results
predictions = results.pred[0]
boxes = predictions[:, :4] # x1, y1, x2, y2
scores = predictions[:, 4]
categories = predictions[:, 5]
# show detection bounding boxes on image
results.show()
# save results into "results/" folder
results.save(save_dir='results/')
```
- Finetune the model on your custom dataset:
```bash
yolov5 train --data data.yaml --img 640 --batch 16 --weights keremberke/yolov5s-aerial-sheep --epochs 10
```
**More models available at: [awesome-yolov5-models](https://github.com/keremberke/awesome-yolov5-models)**
| 2,075 | [
[
-0.06298828125,
-0.035400390625,
0.02850341796875,
-0.0276947021484375,
-0.01580810546875,
-0.0250701904296875,
0.007091522216796875,
-0.040802001953125,
0.010406494140625,
0.02130126953125,
-0.05072021484375,
-0.0543212890625,
-0.0419921875,
-0.002975463867... |
timm/resnetv2_101.a1h_in1k | 2023-03-22T21:07:15.000Z | [
"timm",
"pytorch",
"safetensors",
"image-classification",
"dataset:imagenet-1k",
"arxiv:2110.00476",
"arxiv:1603.05027",
"license:apache-2.0",
"region:us"
] | image-classification | timm | null | null | timm/resnetv2_101.a1h_in1k | 0 | 535 | timm | 2023-03-22T21:06:33 | ---
tags:
- image-classification
- timm
library_tag: timm
license: apache-2.0
datasets:
- imagenet-1k
---
# Model card for resnetv2_101.a1h_in1k
A ResNet-V2 (pre-activation ResNet) image classification model. Trained on ImageNet-1k by Ross Wightman in `timm` using ResNet strikes back (RSB) `A1` based recipe.
## Model Details
- **Model Type:** Image classification / feature backbone
- **Model Stats:**
- Params (M): 44.5
- GMACs: 7.8
- Activations (M): 16.2
- Image size: 224 x 224
- **Papers:**
- ResNet strikes back: An improved training procedure in timm: https://arxiv.org/abs/2110.00476
- Identity Mappings in Deep Residual Networks: https://arxiv.org/abs/1603.05027
- **Dataset:** ImageNet-1k
- **Original:** https://github.com/huggingface/pytorch-image-models
## Model Usage
### Image Classification
```python
from urllib.request import urlopen
from PIL import Image
import timm
img = Image.open(urlopen(
'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
))
model = timm.create_model('resnetv2_101.a1h_in1k', pretrained=True)
model = model.eval()
# get model specific transforms (normalization, resize)
data_config = timm.data.resolve_model_data_config(model)
transforms = timm.data.create_transform(**data_config, is_training=False)
output = model(transforms(img).unsqueeze(0)) # unsqueeze single image into batch of 1
top5_probabilities, top5_class_indices = torch.topk(output.softmax(dim=1) * 100, k=5)
```
### Feature Map Extraction
```python
from urllib.request import urlopen
from PIL import Image
import timm
img = Image.open(urlopen(
'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
))
model = timm.create_model(
'resnetv2_101.a1h_in1k',
pretrained=True,
features_only=True,
)
model = model.eval()
# get model specific transforms (normalization, resize)
data_config = timm.data.resolve_model_data_config(model)
transforms = timm.data.create_transform(**data_config, is_training=False)
output = model(transforms(img).unsqueeze(0)) # unsqueeze single image into batch of 1
for o in output:
# print shape of each feature map in output
# e.g.:
# torch.Size([1, 64, 112, 112])
# torch.Size([1, 256, 56, 56])
# torch.Size([1, 512, 28, 28])
# torch.Size([1, 1024, 14, 14])
# torch.Size([1, 2048, 7, 7])
print(o.shape)
```
### Image Embeddings
```python
from urllib.request import urlopen
from PIL import Image
import timm
img = Image.open(urlopen(
'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
))
model = timm.create_model(
'resnetv2_101.a1h_in1k',
pretrained=True,
num_classes=0, # remove classifier nn.Linear
)
model = model.eval()
# get model specific transforms (normalization, resize)
data_config = timm.data.resolve_model_data_config(model)
transforms = timm.data.create_transform(**data_config, is_training=False)
output = model(transforms(img).unsqueeze(0)) # output is (batch_size, num_features) shaped tensor
# or equivalently (without needing to set num_classes=0)
output = model.forward_features(transforms(img).unsqueeze(0))
# output is unpooled, a (1, 2048, 7, 7) shaped tensor
output = model.forward_head(output, pre_logits=True)
# output is a (1, num_features) shaped tensor
```
## Model Comparison
Explore the dataset and runtime metrics of this model in timm [model results](https://github.com/huggingface/pytorch-image-models/tree/main/results).
## Citation
```bibtex
@inproceedings{wightman2021resnet,
title={ResNet strikes back: An improved training procedure in timm},
author={Wightman, Ross and Touvron, Hugo and Jegou, Herve},
booktitle={NeurIPS 2021 Workshop on ImageNet: Past, Present, and Future}
}
```
```bibtex
@article{He2016,
author = {Kaiming He and Xiangyu Zhang and Shaoqing Ren and Jian Sun},
title = {Identity Mappings in Deep Residual Networks},
journal = {arXiv preprint arXiv:1603.05027},
year = {2016}
}
```
```bibtex
@misc{rw2019timm,
author = {Ross Wightman},
title = {PyTorch Image Models},
year = {2019},
publisher = {GitHub},
journal = {GitHub repository},
doi = {10.5281/zenodo.4414861},
howpublished = {\url{https://github.com/huggingface/pytorch-image-models}}
}
```
| 4,335 | [
[
-0.030792236328125,
-0.0253448486328125,
-0.004924774169921875,
-0.002765655517578125,
-0.0220184326171875,
-0.0203094482421875,
-0.0167694091796875,
-0.0228424072265625,
0.0233154296875,
0.04302978515625,
-0.038360595703125,
-0.050201416015625,
-0.051513671875,... |
llm-book/bert-base-japanese-v3-jsts | 2023-07-29T11:27:18.000Z | [
"transformers",
"pytorch",
"bert",
"text-classification",
"ja",
"dataset:llm-book/JGLUE",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | text-classification | llm-book | null | null | llm-book/bert-base-japanese-v3-jsts | 0 | 535 | transformers | 2023-06-11T15:27:32 | ---
language:
- ja
license: apache-2.0
library_name: transformers
datasets:
- llm-book/JGLUE
---
# bert-base-japanese-v3-jsts
「[大規模言語モデル入門](https://www.amazon.co.jp/dp/4297136333)」の第5章で紹介している(意味類似度計算)のモデルです。
[cl-tohoku/bert-base-japanese-v3](https://huggingface.co/cl-tohoku/bert-base-japanese-v3)を[JGLUE](https://huggingface.co/datasets/llm-book/JGLUE)のJSTSデータセットでファインチューニングして構築されています。
## 関連リンク
* [GitHubリポジトリ](https://github.com/ghmagazine/llm-book)
* [Colabノートブック（訓練）](https://colab.research.google.com/github/ghmagazine/llm-book/blob/main/chapter5/5-4-sts-finetuning.ipynb)
* [Colabノートブック（推論）](https://colab.research.google.com/github/ghmagazine/llm-book/blob/main/chapter5/5-4-sts-analysis.ipynb)
* [データセット](https://huggingface.co/datasets/llm-book/JGLUE)
* [大規模言語モデル入門（Amazon.co.jp）](https://www.amazon.co.jp/dp/4297136333/)
* [大規模言語モデル入門（gihyo.jp）](https://gihyo.jp/book/2023/978-4-297-13633-8)
## 使い方
```python
from transformers import pipeline
text_sim_pipeline = pipeline(
model="llm-book/bert-base-japanese-v3-jsts",
function_to_apply="none",
)
text = "川べりでサーフボードを持った人たちがいます"
sim_text = "サーファーたちが川べりに立っています"
# textとsim_textの類似度を計算
result = text_sim_pipeline({"text": text, "text_pair": sim_text})
print(result["score"])
# 3.5703558921813965
```
## ライセンス
[Apache License 2.0](https://www.apache.org/licenses/LICENSE-2.0) | 1,346 | [
[
-0.0276031494140625,
-0.046630859375,
0.02301025390625,
0.024627685546875,
-0.043701171875,
0.0008516311645507812,
-0.0195465087890625,
-0.0265045166015625,
0.0287017822265625,
0.03131103515625,
-0.0562744140625,
-0.059295654296875,
-0.04119873046875,
0.0166... |
hztang/BART-large-base-custom | 2023-06-28T08:57:46.000Z | [
"transformers",
"pytorch",
"bart",
"text2text-generation",
"generated_from_trainer",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text2text-generation | hztang | null | null | hztang/BART-large-base-custom | 0 | 535 | transformers | 2023-06-28T01:48:16 | ---
license: apache-2.0
tags:
- generated_from_trainer
model-index:
- name: BART-large-base-custom
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# BART-large-base-custom
This model is a fine-tuned version of [facebook/bart-large](https://huggingface.co/facebook/bart-large) on the None dataset.
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 1
### Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|:-------:|:---------:|:-------:|
| No log | 1.0 | 238 | 0.6719 | 24.2424 | 19.2095 | 23.2835 | 23.9833 | 20.0 |
### Framework versions
- Transformers 4.30.2
- Pytorch 1.12.1
- Datasets 2.13.1
- Tokenizers 0.11.0
| 1,347 | [
[
-0.03973388671875,
-0.06121826171875,
0.02215576171875,
0.01439666748046875,
-0.017303466796875,
-0.01090240478515625,
-0.012115478515625,
-0.0220489501953125,
0.042633056640625,
0.043365478515625,
-0.055816650390625,
-0.0509033203125,
-0.03656005859375,
-0.... |
diffusers/controlnet-canny-sdxl-1.0-small | 2023-08-16T12:59:11.000Z | [
"diffusers",
"stable-diffusion-xl",
"stable-diffusion-xl-diffusers",
"text-to-image",
"controlnet",
"license:openrail++",
"diffusers:ControlNetModel",
"region:us"
] | text-to-image | diffusers | null | null | diffusers/controlnet-canny-sdxl-1.0-small | 11 | 535 | diffusers | 2023-08-15T19:51:44 | ---
license: openrail++
base_model: stabilityai/stable-diffusion-xl-base-1.0
tags:
- stable-diffusion-xl
- stable-diffusion-xl-diffusers
- text-to-image
- diffusers
- controlnet
inference: false
---
# Small SDXL-controlnet: Canny
These are small controlnet weights trained on stabilityai/stable-diffusion-xl-base-1.0 with canny conditioning. This checkpoint is 7x smaller than the original XL controlnet checkpoint.
You can find some example images in the following.
prompt: aerial view, a futuristic research complex in a bright foggy jungle, hard lighting
prompt: a woman, close up, detailed, beautiful, street photography, photorealistic, detailed, Kodak ektar 100, natural, candid shot
prompt: megatron in an apocalyptic world ground, runied city in the background, photorealistic
prompt: a couple watching sunset, 4k photo
## Usage
Make sure to first install the libraries:
```bash
pip install accelerate transformers safetensors opencv-python diffusers
```
And then we're ready to go:
```python
from diffusers import ControlNetModel, StableDiffusionXLControlNetPipeline, AutoencoderKL
from diffusers.utils import load_image
from PIL import Image
import torch
import numpy as np
import cv2
prompt = "aerial view, a futuristic research complex in a bright foggy jungle, hard lighting"
negative_prompt = "low quality, bad quality, sketches"
image = load_image("https://huggingface.co/datasets/hf-internal-testing/diffusers-images/resolve/main/sd_controlnet/hf-logo.png")
controlnet_conditioning_scale = 0.5 # recommended for good generalization
controlnet = ControlNetModel.from_pretrained(
"diffusers/controlnet-canny-sdxl-1.0-small",
torch_dtype=torch.float16
)
vae = AutoencoderKL.from_pretrained("madebyollin/sdxl-vae-fp16-fix", torch_dtype=torch.float16)
pipe = StableDiffusionXLControlNetPipeline.from_pretrained(
"stabilityai/stable-diffusion-xl-base-1.0",
controlnet=controlnet,
vae=vae,
torch_dtype=torch.float16,
)
pipe.enable_model_cpu_offload()
image = np.array(image)
image = cv2.Canny(image, 100, 200)
image = image[:, :, None]
image = np.concatenate([image, image, image], axis=2)
image = Image.fromarray(image)
images = pipe(
prompt, negative_prompt=negative_prompt, image=image, controlnet_conditioning_scale=controlnet_conditioning_scale,
).images
images[0].save(f"hug_lab.png")
```
To more details, check out the official documentation of [`StableDiffusionXLControlNetPipeline`](https://huggingface.co/docs/diffusers/main/en/api/pipelines/controlnet_sdxl).
🚨 Please note that this checkpoint is experimental and there's a lot of room for improvement. We encourage the community to build on top of it, improve it, and provide us with feedback. 🚨
### Training
Our training script was built on top of the official training script that we provide [here](https://github.com/huggingface/diffusers/blob/main/examples/controlnet/README_sdxl.md).
You can refer to [this script](https://github.com/huggingface/diffusers/blob/7b93c2a882d8e12209fbaeffa51ee2b599ab5349/examples/research_projects/controlnet/train_controlnet_webdataset.py) for full discolsure.
* This checkpoint does not perform distillation. We just use a smaller ControlNet initialized from the SDXL UNet. We
encourage the community to try and conduct distillation too. This resource might be of help in [this regard](https://huggingface.co/blog/sd_distillation).
* To learn more about how the ControlNet was initialized, refer to [this code block](https://github.com/huggingface/diffusers/blob/7b93c2a882d8e12209fbaeffa51ee2b599ab5349/examples/research_projects/controlnet/train_controlnet_webdataset.py#L981C1-L999C36).
* It does not have any attention blocks.
* The model works pretty good on most conditioning images. But for more complex conditionings, the bigger checkpoints might be better. We are still working on improving the quality of this checkpoint and looking for feedback from the community.
* We recommend playing around with the `controlnet_conditioning_scale` and `guidance_scale` arguments for potentially better
image generation quality.
#### Training data
The model was trained on 3M images from LAION aesthetic 6 plus subset, with batch size of 256 for 50k steps with constant learning rate of 3e-5.
#### Compute
One 8xA100 machine
#### Mixed precision
FP16 | 4,514 | [
[
-0.0399169921875,
-0.0281829833984375,
0.0179290771484375,
0.029449462890625,
-0.0202789306640625,
-0.01995849609375,
-0.0030918121337890625,
-0.015472412109375,
0.0296630859375,
0.026123046875,
-0.042694091796875,
-0.0211639404296875,
-0.05157470703125,
-0.... |
Leekp/toonmaker3 | 2023-09-16T07:02:08.000Z | [
"diffusers",
"text-to-image",
"autotrain",
"has_space",
"region:us"
] | text-to-image | Leekp | null | null | Leekp/toonmaker3 | 1 | 535 | diffusers | 2023-09-16T07:02:07 |
---
base_model: stabilityai/stable-diffusion-xl-base-1.0
instance_prompt: Korean webtoon image depicting a character named fred
tags:
- text-to-image
- diffusers
- autotrain
inference: true
---
# DreamBooth trained by AutoTrain
Text encoder was not trained.
| 266 | [
[
0.004871368408203125,
-0.011810302734375,
0.015594482421875,
0.0089569091796875,
-0.03631591796875,
0.06683349609375,
0.01294708251953125,
-0.0135040283203125,
0.035552978515625,
-0.0002448558807373047,
-0.03582763671875,
-0.0029697418212890625,
-0.0597534179687... |
llmware/industry-bert-insurance-v0.1 | 2023-09-30T10:17:11.000Z | [
"transformers",
"pytorch",
"bert",
"feature-extraction",
"arxiv:2104.06979",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | feature-extraction | llmware | null | null | llmware/industry-bert-insurance-v0.1 | 4 | 535 | transformers | 2023-09-29T21:15:45 | ---
license: apache-2.0
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
industry-bert-insurance-v0.1 is part of a series of industry-fine-tuned sentence_transformer embedding models.
### Model Description
<!-- Provide a longer summary of what this model is. -->
industry-bert-insurance-v0.1 is a domain fine-tuned BERT-based 768-parameter Sentence Transformer model, intended to as a "drop-in"
substitute for embeddings in the insurance industry domain. This model was trained on a wide range of publicly available documents on the insurance industry.
- **Developed by:** llmware
- **Model type:** BERT-based Industry domain fine-tuned Sentence Transformer architecture
- **Language(s) (NLP):** English
- **License:** Apache 2.0
- **Finetuned from model [optional]:** BERT-based model, fine-tuning methodology described below.
## Model Use
from transformers import AutoTokenizer, AutoModel
tokenizer = AutoTokenizer.from_pretrained("llmware/industry-bert-insurance-v0.1")
model = AutoModel.from_pretrained("llmware/industry-bert-insurance-v0.1")
## Bias, Risks, and Limitations
This is a semantic embedding model, fine-tuned on public domain documents about the insurance industry. Results may vary if used outside of this
domain, and like any embedding model, there is always the potential for anomalies in the vector embedding space. No specific safeguards have
put in place for safety or mitigate potential bias in the dataset.
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
This model was fine-tuned using a custom self-supervised procedure and custom dataset that combined contrastive techniques
with stochastic injections of distortions in the samples. The methodology was derived, adapted and inspired primarily from
three research papers cited below: TSDAE (Reimers), DeClutr (Giorgi), and Contrastive Tension (Carlsson).
## Citation [optional]
Custom self-supervised training protocol used to train the model, which was derived and inspired by the following papers:
@article{wang-2021-TSDAE,
title = "TSDAE: Using Transformer-based Sequential Denoising Auto-Encoderfor Unsupervised Sentence Embedding Learning",
author = "Wang, Kexin and Reimers, Nils and Gurevych, Iryna",
journal= "arXiv preprint arXiv:2104.06979",
month = "4",
year = "2021",
url = "https://arxiv.org/abs/2104.06979",
}
@inproceedings{giorgi-etal-2021-declutr,
title = {{D}e{CLUTR}: Deep Contrastive Learning for Unsupervised Textual Representations},
author = {Giorgi, John and Nitski, Osvald and Wang, Bo and Bader, Gary},
year = 2021,
month = aug,
booktitle = {Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)},
publisher = {Association for Computational Linguistics},
address = {Online},
pages = {879--895},
doi = {10.18653/v1/2021.acl-long.72},
url = {https://aclanthology.org/2021.acl-long.72}
}
@article{Carlsson-2021-CT,
title = {Semantic Re-tuning with Contrastive Tension},
author= {Fredrik Carlsson, Amaru Cuba Gyllensten, Evangelia Gogoulou, Erik Ylipää Hellqvist, Magnus Sahlgren},
year= {2021},
month= {"January"}
Published: 12 Jan 2021, Last Modified: 05 May 2023
}
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
## Model Card Contact
Darren Oberst @ llmware
| 3,763 | [
[
-0.019561767578125,
-0.05780029296875,
0.019561767578125,
0.021453857421875,
-0.0233612060546875,
-0.0243377685546875,
-0.00159454345703125,
-0.040740966796875,
0.01523590087890625,
0.034332275390625,
-0.0574951171875,
-0.050872802734375,
-0.04742431640625,
... |
beomi/KoAlpaca-llama-1-7b | 2023-03-21T09:29:45.000Z | [
"transformers",
"pytorch",
"llama",
"text-generation",
"alpaca",
"KoAlpaca",
"ko",
"en",
"license:apache-2.0",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | beomi | null | null | beomi/KoAlpaca-llama-1-7b | 23 | 534 | transformers | 2023-03-17T15:20:05 | ---
license: apache-2.0
language:
- ko
- en
pipeline_tag: text-generation
tags:
- alpaca
- llama
- KoAlpaca
---
# KoAlpaca: Korean Alpaca Model based on Stanford Alpaca (feat. LLAMA and Polyglot-ko)
- More informations at https://github.com/Beomi/KoAlpaca
- This repository contains finetuned KoAlpaca model weights based on LLAMA | 332 | [
[
-0.0163116455078125,
-0.04058837890625,
0.04345703125,
0.046722412109375,
-0.0243377685546875,
0.00946807861328125,
0.0238800048828125,
-0.0438232421875,
0.056976318359375,
0.03955078125,
-0.0400390625,
-0.037139892578125,
-0.04705810546875,
-0.0082473754882... |
lberglund/sweep_full_2_20231012114749 | 2023-10-12T13:00:06.000Z | [
"diffusers",
"stable-diffusion-xl",
"stable-diffusion-xl-diffusers",
"text-to-image",
"lora",
"license:openrail++",
"has_space",
"region:us"
] | text-to-image | lberglund | null | null | lberglund/sweep_full_2_20231012114749 | 1 | 534 | diffusers | 2023-10-12T11:47:53 |
---
license: openrail++
base_model: stabilityai/stable-diffusion-xl-base-1.0
instance_prompt: "a photo of a person showing <thumbs_up> thumbs up"
tags:
- stable-diffusion-xl
- stable-diffusion-xl-diffusers
- text-to-image
- diffusers
- lora
inference: true
---
# LoRA DreamBooth - lberglund/sweep_full_2_20231012114749
These are LoRA adaption weights for stabilityai/stable-diffusion-xl-base-1.0. The weights were trained on "a photo of a person showing <thumbs_up> thumbs up" using [DreamBooth](https://dreambooth.github.io/). You can find some example images in the following.
LoRA for the text encoder was enabled: False.
Special VAE used for training: madebyollin/sdxl-vae-fp16-fix.
| 699 | [
[
-0.023651123046875,
-0.0295562744140625,
0.02447509765625,
0.00738525390625,
-0.03558349609375,
0.00658416748046875,
0.0264739990234375,
-0.023193359375,
0.08026123046875,
0.042022705078125,
-0.03692626953125,
-0.022857666015625,
-0.052001953125,
-0.01625061... |
keremberke/yolov5s-football | 2022-12-30T20:49:24.000Z | [
"yolov5",
"tensorboard",
"yolo",
"vision",
"object-detection",
"pytorch",
"dataset:keremberke/football-object-detection",
"model-index",
"has_space",
"region:us"
] | object-detection | keremberke | null | null | keremberke/yolov5s-football | 2 | 533 | yolov5 | 2022-12-28T21:31:37 |
---
tags:
- yolov5
- yolo
- vision
- object-detection
- pytorch
library_name: yolov5
library_version: 7.0.6
inference: false
datasets:
- keremberke/football-object-detection
model-index:
- name: keremberke/yolov5s-football
results:
- task:
type: object-detection
dataset:
type: keremberke/football-object-detection
name: keremberke/football-object-detection
split: validation
metrics:
- type: precision # since mAP@0.5 is not available on hf.co/metrics
value: 0.6998682900537505 # min: 0.0 - max: 1.0
name: mAP@0.5
---
<div align="center">
<img width="640" alt="keremberke/yolov5s-football" src="https://huggingface.co/keremberke/yolov5s-football/resolve/main/sample_visuals.jpg">
</div>
### How to use
- Install [yolov5](https://github.com/fcakyon/yolov5-pip):
```bash
pip install -U yolov5
```
- Load model and perform prediction:
```python
import yolov5
# load model
model = yolov5.load('keremberke/yolov5s-football')
# set model parameters
model.conf = 0.25 # NMS confidence threshold
model.iou = 0.45 # NMS IoU threshold
model.agnostic = False # NMS class-agnostic
model.multi_label = False # NMS multiple labels per box
model.max_det = 1000 # maximum number of detections per image
# set image
img = 'https://github.com/ultralytics/yolov5/raw/master/data/images/zidane.jpg'
# perform inference
results = model(img, size=640)
# inference with test time augmentation
results = model(img, augment=True)
# parse results
predictions = results.pred[0]
boxes = predictions[:, :4] # x1, y1, x2, y2
scores = predictions[:, 4]
categories = predictions[:, 5]
# show detection bounding boxes on image
results.show()
# save results into "results/" folder
results.save(save_dir='results/')
```
- Finetune the model on your custom dataset:
```bash
yolov5 train --data data.yaml --img 640 --batch 16 --weights keremberke/yolov5s-football --epochs 10
```
**More models available at: [awesome-yolov5-models](https://github.com/keremberke/awesome-yolov5-models)** | 2,042 | [
[
-0.062103271484375,
-0.035186767578125,
0.032440185546875,
-0.021484375,
-0.0267791748046875,
-0.0157928466796875,
0.00910186767578125,
-0.047576904296875,
0.0175628662109375,
0.01255035400390625,
-0.057647705078125,
-0.053741455078125,
-0.038330078125,
0.00... |
pruas/BENT-PubMedBERT-NER-Cell-Component | 2023-01-14T19:31:40.000Z | [
"transformers",
"pytorch",
"bert",
"token-classification",
"en",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | token-classification | pruas | null | null | pruas/BENT-PubMedBERT-NER-Cell-Component | 2 | 533 | transformers | 2023-01-14T14:27:59 | ---
language:
- en
pipeline_tag: token-classification
---
Named Entity Recognition (NER) model to recognize cell component entities.
[PubMedBERT](https://huggingface.co/microsoft/BiomedNLP-PubMedBERT-base-uncased-abstract-fulltext) fine-tuned on the following datasets:
- [CRAFT](https://github.com/UCDenver-ccp/CRAFT/tree/master/concept-annotation): entity type "GO-CC"
- [MLEE](http://nactem.ac.uk/MLEE/): entity type "Cellular_component"
- [BioNLP13CG-cc](https://github.com/cambridgeltl/MTL-Bioinformatics-2016/tree/master/data/BioNLP13CG-cc-IOB) | 551 | [
[
-0.01448822021484375,
-0.033416748046875,
0.0355224609375,
-0.002552032470703125,
-0.0096282958984375,
0.01396942138671875,
0.01352691650390625,
-0.0506591796875,
0.0306396484375,
0.036590576171875,
-0.041900634765625,
-0.04754638671875,
-0.01158905029296875,
... |
Subhaka/whisper-small-Sinhala-Fine_Tune | 2023-04-29T08:49:56.000Z | [
"transformers",
"pytorch",
"tensorboard",
"whisper",
"automatic-speech-recognition",
"trnslation",
"generated_from_trainer",
"license:apache-2.0",
"endpoints_compatible",
"has_space",
"region:us"
] | automatic-speech-recognition | Subhaka | null | null | Subhaka/whisper-small-Sinhala-Fine_Tune | 1 | 533 | transformers | 2023-04-28T21:31:54 | ---
license: apache-2.0
tags:
- trnslation
- generated_from_trainer
model-index:
- name: whisper-small-Sinhala-Fine_Tune
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# whisper-small-Sinhala-Fine_Tune
This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the None dataset.
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 1e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 10
- mixed_precision_training: Native AMP
### Training results
### Framework versions
- Transformers 4.28.1
- Pytorch 2.0.0+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3
| 1,209 | [
[
-0.0270843505859375,
-0.0467529296875,
0.00620269775390625,
-0.00223541259765625,
-0.033721923828125,
-0.047149658203125,
-0.02960205078125,
-0.029449462890625,
0.02294921875,
0.022705078125,
-0.055145263671875,
-0.032012939453125,
-0.032440185546875,
-0.006... |
Yntec/rainbowpatch | 2023-07-13T13:38:28.000Z | [
"diffusers",
"stable-diffusion",
"stable-diffusion-diffusers",
"text-to-image",
"lexica",
"license:creativeml-openrail-m",
"endpoints_compatible",
"has_space",
"diffusers:StableDiffusionPipeline",
"region:us"
] | text-to-image | Yntec | null | null | Yntec/rainbowpatch | 0 | 533 | diffusers | 2023-07-13T11:50:41 | ---
license: creativeml-openrail-m
library_name: diffusers
pipeline_tag: text-to-image
tags:
- stable-diffusion
- stable-diffusion-diffusers
- diffusers
- text-to-image
- lexica
---
# Rainbowpatch
Use "Rainbowpatch" in the prompt to enhance the style.
Model by Patchmonk, original page:
https://civitai.com/models/5528/rainbowpatch | 333 | [
[
-0.05419921875,
-0.02288818359375,
0.000008344650268554688,
0.06353759765625,
-0.033538818359375,
0.010498046875,
0.029693603515625,
-0.0328369140625,
0.0615234375,
0.0421142578125,
-0.08685302734375,
0.002780914306640625,
-0.018218994140625,
0.0117874145507... |
Linaqruf/pastel-anime-xl-lora | 2023-08-28T01:56:08.000Z | [
"diffusers",
"text-to-image",
"stable-diffusion",
"lora",
"safetensors",
"stable-diffusion-xl",
"en",
"dataset:Linaqruf/sdxl-dataset",
"license:openrail++",
"has_space",
"region:us"
] | text-to-image | Linaqruf | null | null | Linaqruf/pastel-anime-xl-lora | 12 | 533 | diffusers | 2023-08-12T16:18:47 | ---
license: openrail++
language:
- en
tags:
- text-to-image
- stable-diffusion
- lora
- safetensors
- diffusers
- stable-diffusion-xl
base_model: Linaqruf/animagine-xl
inference:
parameter:
negative_prompt: lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry
widget:
- text: >-
face focus, cute, masterpiece, best quality, 1girl, green hair, sweater, looking at viewer, upper body, beanie, outdoors, night, turtleneck
example_title: example 1girl
- text: >-
face focus, bishounen, masterpiece, best quality, 1boy, green hair, sweater, looking at viewer, upper body, beanie, outdoors, night, turtleneck
example_title: example 1boy
datasets:
- Linaqruf/sdxl-dataset
---
<style>
.title-container {
display: flex;
flex-direction: column; /* Allow vertical stacking of title and subtitle */
justify-content: center;
align-items: center;
height: 100vh;
background-color: #f5f5f5;
}
.title {
font-size: 2.5em;
text-align: center;
color: #333;
font-family: 'Verdana', sans-serif;
text-transform: uppercase;
letter-spacing: 0.2em;
padding: 1em;
border: 2px solid #7ed56f;
box-shadow: 5px 5px 15px rgba(0,0,0,0.1);
}
.title span, .subtitle span {
background: -webkit-linear-gradient(45deg, #ff9a9e, #fad0c4, #f6d365);
-webkit-background-clip: text;
-webkit-text-fill-color: transparent;
}
.subtitle {
margin-top: 15px;
font-size: 1em;
font-family: 'Verdana', sans-serif;
color: #666;
text-align: center;
}
.custom-table {
table-layout: fixed;
width: 100%;
border-collapse: collapse;
margin-top: 2em;
}
.custom-table td {
width: 50%;
vertical-align: top;
padding: 10px;
box-shadow: 0px 0px 10px 0px rgba(0,0,0,0.15);
}
.custom-image {
width: 100%;
height: auto;
object-fit: cover;
border-radius: 10px;
transition: transform .2s;
margin-bottom: 1em;
}
.custom-image:hover {
transform: scale(1.05);
}
</style>
<h1 class="title"><span>Pastel Anime LoRA for SDXL</span></h1>
<h2 class="subtitle"><span>TRAINED WITH </span><a href="https://huggingface.co/Linaqruf/animagine-xl"><span>ANIMAGINE XL</span></a></h2>
<hr>
<table class="custom-table">
<tr>
<td>
<a href="https://huggingface.co/Linaqruf/pastel-anime-xl-lora/blob/main/samples/xl_output_upscaled_00001_.png">
<img class="custom-image" src="https://huggingface.co/Linaqruf/pastel-anime-xl-lora/resolve/main/samples/xl_output_upscaled_00001_.png" alt="sample1">
</a>
</td>
<td>
<a href="https://huggingface.co/Linaqruf/pastel-anime-xl-lora/blob/main/samples/xl_output_upscaled_00006_.png">
<img class="custom-image" src="https://huggingface.co/Linaqruf/pastel-anime-xl-lora/resolve/main/samples/xl_output_upscaled_00006_.png" alt="sample2">
</a>
</td>
</tr>
</table>
<hr>
## Overview
**Pastel Anime LoRA for SDXL** is a high-resolution, Low-Rank Adaptation model for Stable Diffusion XL. The model has been fine-tuned using a learning rate of 1e-5 over 1300 global steps with a batch size of 24 on a curated dataset of superior-quality anime-style images. This model is derived from Animagine XL.
Like other anime-style Stable Diffusion models, it also supports Danbooru tags to generate images.
e.g. _**face focus, cute, masterpiece, best quality, 1girl, green hair, sweater, looking at viewer, upper body, beanie, outdoors, night, turtleneck**_
<hr>
## Model Details
- **Developed by:** [Linaqruf](https://github.com/Linaqruf)
- **Model type:** Low-rank adaptation of diffusion-based text-to-image generative model
- **Model Description:** This is a small model that should be used with big model and can be used to generate and modify high quality anime-themed images based on text prompts.
- **License:** [CreativeML Open RAIL++-M License](https://huggingface.co/stabilityai/stable-diffusion-2/blob/main/LICENSE-MODEL)
- **Finetuned from model:** [Animagine XL](https://huggingface.co/Linaqruf/animagine-xl)
<hr>
## 🧨 Diffusers
Make sure to upgrade diffusers to >= 0.18.2:
```
pip install diffusers --upgrade
```
In addition make sure to install `transformers`, `safetensors`, `accelerate` as well as the invisible watermark:
```
pip install invisible_watermark transformers accelerate safetensors
```
Running the pipeline (if you don't swap the scheduler it will run with the default **EulerDiscreteScheduler** in this example we are swapping it to **EulerAncestralDiscreteScheduler**:
```py
import torch
from torch import autocast
from diffusers import StableDiffusionXLPipeline, EulerAncestralDiscreteScheduler
base_model = "Linaqruf/animagine-xl"
lora_model_id = "Linaqruf/pastel-anime-xl-lora"
lora_filename = "pastel-anime-xl.safetensors"
pipe = StableDiffusionXLPipeline.from_pretrained(
model,
torch_dtype=torch.float16,
use_safetensors=True,
variant="fp16"
)
pipe.scheduler = EulerAncestralDiscreteScheduler.from_config(pipe.scheduler.config)
pipe.to('cuda')
pipe.load_lora_weights(lora_model_id, weight_name=lora_filename)
prompt = "face focus, cute, masterpiece, best quality, 1girl, green hair, sweater, looking at viewer, upper body, beanie, outdoors, night, turtleneck"
negative_prompt = "lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry"
image = pipe(
prompt,
negative_prompt=negative_prompt,
width=1024,
height=1024,
guidance_scale=12,
target_size=(1024,1024),
original_size=(4096,4096),
num_inference_steps=50
).images[0]
image.save("anime_girl.png")
```
<hr>
## Limitation
This model inherit Stable Diffusion XL 1.0 [limitation](https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0#limitations)
| 6,042 | [
[
-0.036468505859375,
-0.057098388671875,
0.02239990234375,
0.01373291015625,
-0.0226593017578125,
-0.0009870529174804688,
0.0222320556640625,
-0.0265960693359375,
0.045013427734375,
0.025115966796875,
-0.054718017578125,
-0.04571533203125,
-0.05010986328125,
... |
pszemraj/pegasus-x-large-book-summary | 2023-09-23T20:46:57.000Z | [
"transformers",
"pytorch",
"safetensors",
"pegasus_x",
"text2text-generation",
"summarization",
"summary",
"booksum",
"long-document",
"long-form",
"dataset:kmfoda/booksum",
"license:apache-2.0",
"license:bsd-3-clause",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"... | summarization | pszemraj | null | null | pszemraj/pegasus-x-large-book-summary | 32 | 532 | transformers | 2022-09-16T10:55:11 | ---
license:
- apache-2.0
- bsd-3-clause
tags:
- summarization
- summary
- booksum
- long-document
- long-form
datasets:
- kmfoda/booksum
metrics:
- rouge
languages: en
widget:
- text: large earthquakes along a given fault segment do not occur at random intervals
because it takes time to accumulate the strain energy for the rupture. The rates
at which tectonic plates move and accumulate strain at their boundaries are approximately
uniform. Therefore, in first approximation, one may expect that large ruptures
of the same fault segment will occur at approximately constant time intervals.
If subsequent main shocks have different amounts of slip across the fault, then
the recurrence time may vary, and the basic idea of periodic mainshocks must be
modified. For great plate boundary ruptures the length and slip often vary by
a factor of 2. Along the southern segment of the San Andreas fault the recurrence
interval is 145 years with variations of several decades. The smaller the standard
deviation of the average recurrence interval, the more specific could be the long
term prediction of a future mainshock.
example_title: earthquakes
- text: ' A typical feed-forward neural field algorithm. Spatiotemporal coordinates
are fed into a neural network that predicts values in the reconstructed domain.
Then, this domain is mapped to the sensor domain where sensor measurements are
available as supervision. Class and Section Problems Addressed Generalization
(Section 2) Inverse problems, ill-posed problems, editability; symmetries. Hybrid
Representations (Section 3) Computation & memory efficiency, representation capacity,
editability: Forward Maps (Section 4) Inverse problems Network Architecture (Section
5) Spectral bias, integration & derivatives. Manipulating Neural Fields (Section
6) Edit ability, constraints, regularization. Table 2: The five classes of techniques
in the neural field toolbox each addresses problems that arise in learning, inference,
and control. (Section 3). We can supervise reconstruction via differentiable forward
maps that transform Or project our domain (e.g, 3D reconstruction via 2D images;
Section 4) With appropriate network architecture choices, we can overcome neural
network spectral biases (blurriness) and efficiently compute derivatives and integrals
(Section 5). Finally, we can manipulate neural fields to add constraints and regularizations,
and to achieve editable representations (Section 6). Collectively, these classes
constitute a ''toolbox'' of techniques to help solve problems with neural fields
There are three components in a conditional neural field: (1) An encoder or inference
function € that outputs the conditioning latent variable 2 given an observation
0 E(0) =2. 2 is typically a low-dimensional vector, and is often referred to aS
a latent code Or feature code_ (2) A mapping function 4 between Z and neural field
parameters O: Y(z) = O; (3) The neural field itself $. The encoder € finds the
most probable z given the observations O: argmaxz P(2/0). The decoder maximizes
the inverse conditional probability to find the most probable 0 given Z: arg-
max P(Olz). We discuss different encoding schemes with different optimality guarantees
(Section 2.1.1), both global and local conditioning (Section 2.1.2), and different
mapping functions Y (Section 2.1.3) 2. Generalization Suppose we wish to estimate
a plausible 3D surface shape given a partial or noisy point cloud. We need a suitable
prior over the sur- face in its reconstruction domain to generalize to the partial
observations. A neural network expresses a prior via the function space of its
architecture and parameters 0, and generalization is influenced by the inductive
bias of this function space (Section 5).'
example_title: scientific paper
- text: 'Is a else or outside the cob and tree written being of early client rope
and you have is for good reasons. On to the ocean in Orange for time. By''s the
aggregate we can bed it yet. Why this please pick up on a sort is do and also
M Getoi''s nerocos and do rain become you to let so is his brother is made in
use and Mjulia''s''s the lay major is aging Masastup coin present sea only of
Oosii rooms set to you We do er do we easy this private oliiishs lonthen might
be okay. Good afternoon everybody. Welcome to this lecture of Computational Statistics.
As you can see, I''m not socially my name is Michael Zelinger. I''m one of the
task for this class and you might have already seen me in the first lecture where
I made a quick appearance. I''m also going to give the tortillas in the last third
of this course. So to give you a little bit about me, I''m a old student here
with better Bulman and my research centres on casual inference applied to biomedical
disasters, so that could be genomics or that could be hospital data. If any of
you is interested in writing a bachelor thesis, a semester paper may be mastathesis
about this topic feel for reach out to me. you have my name on models and my email
address you can find in the directory I''d Be very happy to talk about it. you
do not need to be sure about it, we can just have a chat. So with that said, let''s
get on with the lecture. There''s an exciting topic today I''m going to start
by sharing some slides with you and later on during the lecture we''ll move to
the paper. So bear with me for a few seconds. Well, the projector is starting
up. Okay, so let''s get started. Today''s topic is a very important one. It''s
about a technique which really forms one of the fundamentals of data science,
machine learning, and any sort of modern statistics. It''s called cross validation.
I know you really want to understand this topic I Want you to understand this
and frankly, nobody''s gonna leave Professor Mineshousen''s class without understanding
cross validation. So to set the stage for this, I Want to introduce you to the
validation problem in computational statistics. So the problem is the following:
You trained a model on available data. You fitted your model, but you know the
training data you got could always have been different and some data from the
environment. Maybe it''s a random process. You do not really know what it is,
but you know that somebody else who gets a different batch of data from the same
environment they would get slightly different training data and you do not care
that your method performs as well. On this training data. you want to to perform
well on other data that you have not seen other data from the same environment.
So in other words, the validation problem is you want to quantify the performance
of your model on data that you have not seen. So how is this even possible? How
could you possibly measure the performance on data that you do not know The solution
to? This is the following realization is that given that you have a bunch of data,
you were in charge. You get to control how much that your model sees. It works
in the following way: You can hide data firms model. Let''s say you have a training
data set which is a bunch of doubtless so X eyes are the features those are typically
hide and national vector. It''s got more than one dimension for sure. And the
why why eyes. Those are the labels for supervised learning. As you''ve seen before,
it''s the same set up as we have in regression. And so you have this training
data and now you choose that you only use some of those data to fit your model.
You''re not going to use everything, you only use some of it the other part you
hide from your model. And then you can use this hidden data to do validation from
the point of you of your model. This hidden data is complete by unseen. In other
words, we solve our problem of validation.'
example_title: transcribed audio - lecture
- text: 'Transformer-based models have shown to be very useful for many NLP tasks.
However, a major limitation of transformers-based models is its O(n^2)O(n 2) time
& memory complexity (where nn is sequence length). Hence, it''s computationally
very expensive to apply transformer-based models on long sequences n > 512n>512.
Several recent papers, e.g. Longformer, Performer, Reformer, Clustered attention
try to remedy this problem by approximating the full attention matrix. You can
checkout 🤗''s recent blog post in case you are unfamiliar with these models.
BigBird (introduced in paper) is one of such recent models to address this issue.
BigBird relies on block sparse attention instead of normal attention (i.e. BERT''s
attention) and can handle sequences up to a length of 4096 at a much lower computational
cost compared to BERT. It has achieved SOTA on various tasks involving very long
sequences such as long documents summarization, question-answering with long contexts.
BigBird RoBERTa-like model is now available in 🤗Transformers. The goal of this
post is to give the reader an in-depth understanding of big bird implementation
& ease one''s life in using BigBird with 🤗Transformers. But, before going into
more depth, it is important to remember that the BigBird''s attention is an approximation
of BERT''s full attention and therefore does not strive to be better than BERT''s
full attention, but rather to be more efficient. It simply allows to apply transformer-based
models to much longer sequences since BERT''s quadratic memory requirement quickly
becomes unbearable. Simply put, if we would have ∞ compute & ∞ time, BERT''s attention
would be preferred over block sparse attention (which we are going to discuss
in this post).
If you wonder why we need more compute when working with longer sequences, this
blog post is just right for you!
Some of the main questions one might have when working with standard BERT-like
attention include:
Do all tokens really have to attend to all other tokens? Why not compute attention
only over important tokens? How to decide what tokens are important? How to attend
to just a few tokens in a very efficient way? In this blog post, we will try to
answer those questions.
What tokens should be attended to? We will give a practical example of how attention
works by considering the sentence ''BigBird is now available in HuggingFace for
extractive question answering''. In BERT-like attention, every word would simply
attend to all other tokens.
Let''s think about a sensible choice of key tokens that a queried token actually
only should attend to by writing some pseudo-code. Will will assume that the token
available is queried and build a sensible list of key tokens to attend to.
>>> # let''s consider following sentence as an example >>> example = [''BigBird'',
''is'', ''now'', ''available'', ''in'', ''HuggingFace'', ''for'', ''extractive'',
''question'', ''answering'']
>>> # further let''s assume, we''re trying to understand the representation of
''available'' i.e. >>> query_token = ''available'' >>> # We will initialize an
empty `set` and fill up the tokens of our interest as we proceed in this section.
>>> key_tokens = [] # => currently ''available'' token doesn''t have anything
to attend Nearby tokens should be important because, in a sentence (sequence of
words), the current word is highly dependent on neighboring past & future tokens.
This intuition is the idea behind the concept of sliding attention.'
example_title: bigbird blog intro
- text: 'To be fair, you have to have a very high IQ to understand Rick and Morty.
The humour is extremely subtle, and without a solid grasp of theoretical physics
most of the jokes will go over a typical viewer''s head. There''s also Rick''s
nihilistic outlook, which is deftly woven into his characterisation- his personal
philosophy draws heavily from Narodnaya Volya literature, for instance. The fans
understand this stuff; they have the intellectual capacity to truly appreciate
the depths of these jokes, to realise that they''re not just funny- they say something
deep about LIFE. As a consequence people who dislike Rick & Morty truly ARE idiots-
of course they wouldn''t appreciate, for instance, the humour in Rick''s existential
catchphrase ''Wubba Lubba Dub Dub,'' which itself is a cryptic reference to Turgenev''s
Russian epic Fathers and Sons. I''m smirking right now just imagining one of those
addlepated simpletons scratching their heads in confusion as Dan Harmon''s genius
wit unfolds itself on their television screens. What fools.. how I pity them.
😂
And yes, by the way, i DO have a Rick & Morty tattoo. And no, you cannot see it.
It''s for the ladies'' eyes only- and even then they have to demonstrate that
they''re within 5 IQ points of my own (preferably lower) beforehand. Nothin personnel
kid 😎'
example_title: Richard & Mortimer
parameters:
max_length: 48
min_length: 2
no_repeat_ngram_size: 3
encoder_no_repeat_ngram_size: 3
early_stopping: true
length_penalty: 0.1
num_beams: 2
base_model: google/pegasus-x-large
model-index:
- name: pszemraj/pegasus-x-large-book-summary
results:
- task:
type: summarization
name: Summarization
dataset:
name: samsum
type: samsum
config: samsum
split: test
metrics:
- type: rouge
value: 33.1401
name: ROUGE-1
verified: true
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiYjQ1NjY1OGVjYWEwMzBjMzk3ZmMyZDA0ZTcxOTdmZTUxNTc0OGYxYmY3MzJkMzFmYTVjNzU2ZTk4MzE0NWMzMSIsInZlcnNpb24iOjF9.PSHB6DMF6tkwSw5nsFE57a2ApRAy_tkS6ziKA6PSTWddEdaqfca4pfig6_olmRmcS4KxN6HHcsmioHzv4LJQBw
- type: rouge
value: 9.3095
name: ROUGE-2
verified: true
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMzk3MTA3NmY1OGE3MzFjZTJhYWYzNGU4NTUzMTgwM2Y1NWZjMmEyNDNmNmEzYmQzZThjOGExMjc2ZjAyZjMzZCIsInZlcnNpb24iOjF9.tfgp8p-WlkVrfducTSg4zs-byeZMCmdZw1aizPQHXm_qRAwGtKcuVkZcmza5Y3o3VqsAEmGzg5HQD1vnZvWIDA
- type: rouge
value: 24.8552
name: ROUGE-L
verified: true
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiOTVmMTIwNDQwNTI4MmI2MmY1ODc1Mjk0NGQ5ZWE4ZTYzOGNkMjY2ZmJhMjg2MTZlNTdhYTA2ZDAxNTFjMjA2MSIsInZlcnNpb24iOjF9.9HLgy9842oIDm6ABb3L94R1P4zAqTI0QN8aP62xzIyDxUXTbWw68PEDufYLiBJbTgZ8ElopZ9I7aou2zCgXeAA
- type: rouge
value: 29.0391
name: ROUGE-LSUM
verified: true
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMmNhYWJjYjdjMzMxMmE4ZTE4NGEzMDdmZDZjODI5ZWRjZWJmYTEyZGIzYWQ2NjM3YzQ4MjI4ZTM4MmU5MzRjZSIsInZlcnNpb24iOjF9.d2yoVdmxjVJnsgIYFiLuaBO5Krgw4Axl5yeOSTKrvHygrAxoqT1nl4anzQiyoR3PwYBXwBkwmgpJUfZ7RNXtDQ
- type: loss
value: 2.288182497024536
name: loss
verified: true
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiYzM5NGIwODMxOTA3MTY3ODc2ZDczYTNmMTMwM2QyZmNlZjFmZDJjMGY3NWNkMDEyYzA4OTA2ZDRiODY3Zjg4OCIsInZlcnNpb24iOjF9.8k9mC050OS7mQSR9oA8liDRDQvEx1VxmTXGLmDYJVYYtTh2HYJFGP8Vy_krocFRIYDxh-IHPEOOSr5NrLMWHBA
- type: gen_len
value: 45.2173
name: gen_len
verified: true
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNWZhNzQ5OTQ5Yjg5YjhlOTZiZmJhZjZiODNmY2E2OTg4YTg4NWVhYzRkNzM2Mzk4NzdlMDgxM2M4NjY2YzhhYSIsInZlcnNpb24iOjF9.tDEEsPUclZDygAdGhNrBGrF24vR8ao08Nw7hmtUt5lmSZZZK_u-8rpz97QgVS6MCJdjFVnbYC4bkFnlQWI_FAA
- task:
type: summarization
name: Summarization
dataset:
name: launch/gov_report
type: launch/gov_report
config: plain_text
split: test
metrics:
- type: rouge
value: 39.7279
name: ROUGE-1
verified: true
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiOTAxODk3OTUwMTIzODU3NzU2YzAzZjE2NTM3MzBjNDA0ZWRmZGU3NWUzNTg1YThhNDQ1NjQ5ZmM3OWI2YzBhNSIsInZlcnNpb24iOjF9.vnNKucBNt2-nIyODj9P2HeaWPX5AQR8L-DL8QzrO7kj58-vZnjT6hsAGmepRNzdZ1TLF-3j2J2plcNJ8lUO8Dg
- type: rouge
value: 10.8944
name: ROUGE-2
verified: true
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNjYzMmIxOTJmZjkxOGI5N2U0NTRmMmQwOGJhMzMxYWIzMWMzYzUwMDEyMDdiZDQ2YTUzOWU0OTViMTI2YTAwYiIsInZlcnNpb24iOjF9.De0PaAikWqfWpoIXTCYP-mSFu3PUATLX08Qq74OHXM8784heFVDX1E1sXlh_QbbKJbuMuZtTKM4qr7oLUizOAw
- type: rouge
value: 19.7018
name: ROUGE-L
verified: true
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiYzI3MjQzOGQ3MGE3NDNkZTEyMWRkYjUyYTYzNDEwOWVjMGFmNTBiZjE4ZTBhMGYzMmI1Yzk0YjBmYmIzMWMxZSIsInZlcnNpb24iOjF9.FVikJ5Ma0gUgM-tpbomWXnC4jtmvhxqikPqCk84t4IbIdU0CIYGTQEONiz-VqI0fJeNrnTS6lxpBv7XxKoq3BQ
- type: rouge
value: 36.5634
name: ROUGE-LSUM
verified: true
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiOTI2OTVmNDZiZWE5ZjNkODIwZjJiNTU2ZjJjYjczODUwM2JiNDEzYmE3N2U5YWM5NzJjOWEzMmYzZjdlYWJmYyIsInZlcnNpb24iOjF9.poR4zcqRvdaierfWFdTa53Cv6ZbNbnRwyRTi9HukHF5AWAQgc6zpBLkwOYFYoWjuSH83ohWeMM3MoIdw3zypBw
- type: loss
value: 2.473011016845703
name: loss
verified: true
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNDFmMjg3NWQ2YTMxMTc1OGZiYWYzNjg5NDY3MWE4MjY5ZDQxZDZhZGI1OTc5MzZkZGEzYmVlNWFiMzZjNDdhNCIsInZlcnNpb24iOjF9.05nKB3SmEfFKSduJqlleF4Fd2_IhwJS8eTOrnzZYCQQfLCfpJAZLhp3eLQCuBY4htd-FNrZftrThL66zVxyrCQ
- type: gen_len
value: 212.8243
name: gen_len
verified: true
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiOGNjMTg4ZDZlZjAxZGNhN2M0NWI0ZTA0OWEzNDkzNDAzOTJhODA2MmVkODI4YjYzN2FiOTU1ZDMwM2VlNWMyYyIsInZlcnNpb24iOjF9.WYx6XJFKokY2heoN-jpAMp1Z1gsyJus3zpktQgNd0FOYJxOUqW40A0kkHtd15y4dUhsbccLpuJGY1fNJgHOiDw
- task:
type: summarization
name: Summarization
dataset:
name: billsum
type: billsum
config: default
split: test
metrics:
- type: rouge
value: 42.1065
name: ROUGE-1
verified: true
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiZDJhNDM2MWEwMjJlYjRmZTVkYzljODcwMzlmMGUxMDA4ZmRjNjM0NmY3ZWJlMmZjNGI3NDQ3NTQyOTQ3MjBkNSIsInZlcnNpb24iOjF9.l1MiZbXyFyXAcsfFChMrTvSaBhzBR6AuDnBuII8zY3Csz3ShWK0vo09MkQdZ1epe8PKWV9wwUBuJyKk3wL7MDw
- type: rouge
value: 15.4079
name: ROUGE-2
verified: true
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNTY3NDBkYTVkNjdhY2I0ZmY0NTA4YzVkMGE5YWE5ODdjOGE1MDhkOTJhOWY3NmI2ZWI1MGU2MGI1NDRlYjI3MSIsInZlcnNpb24iOjF9.VN-5eK2SzFDCJnFTHHu7XCU_lynaxW_JEDc3llmcNo_ffDgRmISHHGaqV7fPFymBBMXpPly7XblO_sukyqj1Cg
- type: rouge
value: 24.8814
name: ROUGE-L
verified: true
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiZDYyNGZmNDY3MTY4YzI4ZjZhODE0NGIyN2ZkOGEyYzM3MWZjM2QzZTg5ZjNmZmYzZDE5NzhiZDQ4OGM1YjNiMyIsInZlcnNpb24iOjF9.L73M1M5XdMQkf8zSdfLN0MUrxtO0r6UiLjoOkHfrIGbWNsNJ8tU5lciYFNIhJrICUL8LchCsFqR9LAClKS4bCg
- type: rouge
value: 36.0375
name: ROUGE-LSUM
verified: true
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMTBlMTQ5OTQxNTA3ZmFiMGYyZWQ0MGM0ODY2YWI3MzgyNjkwNzQyM2FmNGRjMzc3MjJmZDZkOWY4M2RhZTg2MSIsInZlcnNpb24iOjF9.IiMSSVahBgH8n34bGCC_DDGpujDXQbIvGhlcpVV2EBVQLLWUqcCy5WwBdbRrxPC-asBRCNERQxj8Uii4FvPsDQ
- type: loss
value: 1.9130958318710327
name: loss
verified: true
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNTg2NTMxZDE3MDg3MDFkMTYxNjY1OTc5YjQ4ODcyMGUxMTFiZjJiNDgyYWZhN2NjZmE1MDQ1NTRmZGY0NjQzZSIsInZlcnNpb24iOjF9.kADUBMO8i6-oGDDt1cOiGMrGcMkF_Qc1jSpS2NSFyksDRusQa_YuuShefF4DuHVEr3CS0hNjjRH9_JBeX9ZQDg
- type: gen_len
value: 179.2184
name: gen_len
verified: true
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNjM4NGNiMTY3YzZjMzg4MTRiMDdiZDFiMzA1ZDIyMDM2MDk1OWRhYWQzN2UxZDNlODIxOWVhY2JlYjk4Mjk5YyIsInZlcnNpb24iOjF9.nU8ImMNWgjg9BKjUBJQLFaJOBq3kyIne8ldlpL0OV0e4888wOntIAcJP0dCCYfRSLVmZuXQ1M8cpDuTf50hNCw
- task:
type: summarization
name: Summarization
dataset:
name: kmfoda/booksum
type: kmfoda/booksum
config: kmfoda--booksum
split: test
metrics:
- type: rouge
value: 35.2154
name: ROUGE-1
verified: true
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiZWQ5MGMzNDc4MDBiNmRiNDY5ZDM4N2QzYTJlYTNiYTcwNDBlMzdlM2I4N2VmM2ZjMmQ3NGU3OTRlMTMzMTg3NyIsInZlcnNpb24iOjF9.E55gu7HvMwc4HejF3YOD6yqQJj7_6GCoCMWm78sY5_w2glR-oM98tu9IsG27VaPva7UklxsspzT2DIVaVKY0CQ
- type: rouge
value: 6.8702
name: ROUGE-2
verified: true
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiZjFhN2JlYzlmMGZmYzkwYjBlNjY4YzhlYzNmMTdmZWYyYmU3NWI0ZTRkMTgxNmRiM2EyZWMyMWFjY2JkNzg1MCIsInZlcnNpb24iOjF9.I9BoHbGt8LLNtLAssIXm9tQ4lHqFCMt0zJS_zTezzxGRMS5On71c3jnlzrDtwEm6wjmZEwYIJK8qqJh-Qa5YAA
- type: rouge
value: 17.6693
name: ROUGE-L
verified: true
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiOGZlZjcwOTZjMmNjZWFkM2M5Zjg1OTgzMzcxOTM2Y2RkMzY4NGU2NDE2MTVjMjcyMWIwNWI4ODc0YTY3YTA2MSIsInZlcnNpb24iOjF9.Ou1C6U6PrOtXPxlk9PMucdJ_vlnVnSk94QrLJL4b_g2pcY3D80Xrw09iz4BTOPzZ2UTNBLyn8YdLY3m2vHpiAQ
- type: rouge
value: 32.8365
name: ROUGE-LSUM
verified: true
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMmIzMGQ5MzQ1MjI4MTU0ZGZkZTRhODllNWQyOTQ4ZjA5YWE4ZTJjMzQ2ZWQzOGFiMWUzZDMxOTU5NzkxYjliZiIsInZlcnNpb24iOjF9.2mYURQZYo7e3AY0tfkpqFMNhoHvrysvBXza-XYYrX_xLpruMU9Gzrwc3jvpi2wtp4eeyhzIiZJvH0O6la6zxCg
- type: loss
value: 2.9878039360046387
name: loss
verified: true
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiZGU0ODBmN2I3OGFkNTFiM2I3YWQyNmUzNzUwYzEwNzczZWEwZjIxYTAwZDE2ZTIwMGE3ZGNmMDQzNTFmNjEwYyIsInZlcnNpb24iOjF9.0IKWIImKTXqysQUb2IMPk2eeHlOcBjndiPcU42nfFBMhRTqeXdBqOCP6cidlho7pVN4hsC-77ArJ9pZlbTFuBg
- type: gen_len
value: 200.6785
name: gen_len
verified: true
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMDUzYTE3MmIxZGM3MWI1MjNhMTU3MTdkMjJjNjY5Y2UzYTdjYWRiY2I4MmUxMDY4NTA5NWZjYWU0NzliODdkYiIsInZlcnNpb24iOjF9.BqmCaWzbCMNUied6zNO744Dl-0LC47FCIv-l8kDjkhSkwQcb_hi93VYts5PTsrFY_MmM8j7AsY1PiFr6nNFMBQ
- task:
type: summarization
name: Summarization
dataset:
name: big_patent
type: big_patent
config: y
split: test
metrics:
- type: rouge
value: 37.376
name: ROUGE-1
verified: true
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMWI4ZjMxODcxMThiMzE3NjQ3Zjg0NzhmZjlhY2ZmYjQwMGY5ZjlkZGY1MzZmY2M5YTU4NmY1Y2NhZDA3YWFkOCIsInZlcnNpb24iOjF9.sYh4IynXgOpVetYYSWUp0v5QZWvXC1x7_uJR0LZUxaeYKEc4yfICNmDOPzNzoroaV4ELeOaPjHQpYVm-lpAHBA
- type: rouge
value: 11.4432
name: ROUGE-2
verified: true
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiZTZkOGIyYzU3YTQ5ZTFmMDU3MjQ5ZWM2NGQ1MzgwMDYyZDkxN2Q2YjgyZTkzMTEyYjczMGJiYmNkZmU5MTQ3NSIsInZlcnNpb24iOjF9.Qk38acpjPjU64Z1nXEuqMXjKZrGvdC9oY586EjuCPeEAJCSzKimp8FsB-1QrjMH73q6rN2CdumJUxih6HF-KAA
- type: rouge
value: 22.2754
name: ROUGE-L
verified: true
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNzlmOTUxYmEzYzYyYmVjNGZlNzNiZWIwZmQ5OWVlY2U3NTBiZDExYWUwODQ0Y2ZjMmQyMTNmMTlmNjdmZWUwNCIsInZlcnNpb24iOjF9.bUVhxaepySyaityby71j6h4YO_l4x8OSeZoblagwUMYGXRc0Ej286QzEtZFeRGygMJ5sjUN_loWCtOmAnHY2BA
- type: rouge
value: 32.5087
name: ROUGE-LSUM
verified: true
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNDEyNjM5NjAzYTNjN2MwZTY4MWY2Y2U5YWUyM2Y1YjAyNjBhZTM0YTAyZjM5N2M1ZDkxOWUxNzE2OWZkYTBmMSIsInZlcnNpb24iOjF9.QfMHkcoAR3xqzsgL1xjHk3Lui1xhE12pJKvYujQ_h5o6PBXT79dsENsrqDGGBjiKdTKNwWqADgaviy1VrWMDCQ
- type: loss
value: 2.9867310523986816
name: loss
verified: true
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiZTUzM2Q5MmE5MzU4YmFlMjFiMmUzZGU2NDAzMTQ1Y2NjZDVlYWI3NGE5MjM0NmMxMjdiOWI3MTU0NDk3NmNkZiIsInZlcnNpb24iOjF9.VoQqu6ZU3AR_cji82UkpvbLnTmZ17fZmR2E4DeonjCyTZpyyfvUsQ2nbKDovQf34DBkYXENk42EUsUF1mBZNBg
- type: gen_len
value: 172.7776
name: gen_len
verified: true
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNTEzNTMyMDY1N2Q5ZTMxNjNlMTI0Nzk5ZDc1ZWQ5Y2IwZWM0NWNhNWY2MTk3YTRkYzUwMTI4NjZiOWVhOGQwYSIsInZlcnNpb24iOjF9.-Rek2VFmGqIEgqeFoxU_0aCWdFbGYi9BV5c7x-izm9_4vtZdYQ4ITXm4T8C3UlpOax60veJQt2Uax5vyiFc9Ag
---
# pszemraj/pegasus-x-large-book-summary
<a href="https://colab.research.google.com/gist/pszemraj/6c326c0649233ab017d63adc36958d1a/pegasus-x-large-booksum-demo.ipynb">
<img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"/>
</a>
Get SparkNotes-esque summaries of arbitrary text! Due to the model size, it's recommended to try it out in Colab (linked above) as the API textbox may time out.
This model is a fine-tuned version of [google/pegasus-x-large](https://huggingface.co/google/pegasus-x-large) on the `kmfoda/booksum` dataset for approx eight epochs.
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
#### Epochs 1-4
TODO
#### Epochs 5 & 6
The following hyperparameters were used during training:
- learning_rate: 6e-05
- train_batch_size: 4
- eval_batch_size: 1
- seed: 42
- distributed_type: multi-GPU
- gradient_accumulation_steps: 32
- total_train_batch_size: 128
- optimizer: _ADAN_ using lucidrains' `adan-pytorch` with default betas
- lr_scheduler_type: constant_with_warmup
- data type: TF32
- num_epochs: 2
#### Epochs 7 & 8
- epochs 5 & 6 were trained with 12288 tokens input
- this fixes that with 2 epochs at 16384 tokens input
The following hyperparameters were used during training:
- learning_rate: 0.0004
- train_batch_size: 4
- eval_batch_size: 1
- seed: 42
- distributed_type: multi-GPU
- gradient_accumulation_steps: 16
- total_train_batch_size: 64
- optimizer: _ADAN_ using lucidrains' `adan-pytorch` with default betas
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.03
- num_epochs: 2
### Framework versions
- Transformers 4.22.0
- Pytorch 1.11.0a0+17540c5
- Datasets 2.4.0
- Tokenizers 0.12.1
| 26,423 | [
[
-0.043792724609375,
-0.03717041015625,
0.01369476318359375,
0.01190948486328125,
-0.0304412841796875,
-0.0304107666015625,
-0.01523590087890625,
-0.0274200439453125,
0.0249786376953125,
0.01430511474609375,
-0.04620361328125,
-0.032806396484375,
-0.0465087890625... |
OFA-Sys/chinese-clip-vit-large-patch14-336px | 2022-12-09T06:10:57.000Z | [
"transformers",
"pytorch",
"chinese_clip",
"zero-shot-image-classification",
"vision",
"arxiv:2211.01335",
"endpoints_compatible",
"has_space",
"region:us"
] | zero-shot-image-classification | OFA-Sys | null | null | OFA-Sys/chinese-clip-vit-large-patch14-336px | 9 | 532 | transformers | 2022-11-09T09:40:25 | ---
tags:
- vision
widget:
- src: https://huggingface.co/OFA-Sys/chinese-clip-vit-base-patch16/resolve/main/festival.jpg
candidate_labels: 灯笼, 鞭炮, 对联
example_title: festival
- src: https://huggingface.co/datasets/mishig/sample_images/resolve/main/cat-dog-music.png
candidate_labels: 音乐表演, 体育运动
example_title: cat & dog
- src: https://huggingface.co/datasets/mishig/sample_images/resolve/main/football-match.jpg
candidate_labels: 梅西, C罗, 马奎尔
example_title: football
---
# Chinese-CLIP-ViT-Large-Patch14-336px
## Introduction
This is the large-version of the Chinese CLIP, with ViT-L/14@336px as the image encoder and RoBERTa-wwm-base as the text encoder. Chinese CLIP is a simple implementation of CLIP on a large-scale dataset of around 200 million Chinese image-text pairs. For more details, please refer to our technical report https://arxiv.org/abs/2211.01335 and our official github repo https://github.com/OFA-Sys/Chinese-CLIP (Welcome to star! 🔥🔥)
## Use with the official API
We provide a simple code snippet to show how to use the API of Chinese-CLIP to compute the image & text embeddings and similarities.
```python
from PIL import Image
import requests
from transformers import ChineseCLIPProcessor, ChineseCLIPModel
model = ChineseCLIPModel.from_pretrained("OFA-Sys/chinese-clip-vit-large-patch14-336px")
processor = ChineseCLIPProcessor.from_pretrained("OFA-Sys/chinese-clip-vit-large-patch14-336px")
url = "https://clip-cn-beijing.oss-cn-beijing.aliyuncs.com/pokemon.jpeg"
image = Image.open(requests.get(url, stream=True).raw)
# Squirtle, Bulbasaur, Charmander, Pikachu in English
texts = ["杰尼龟", "妙蛙种子", "小火龙", "皮卡丘"]
# compute image feature
inputs = processor(images=image, return_tensors="pt")
image_features = model.get_image_features(**inputs)
image_features = image_features / image_features.norm(p=2, dim=-1, keepdim=True) # normalize
# compute text features
inputs = processor(text=texts, padding=True, return_tensors="pt")
text_features = model.get_text_features(**inputs)
text_features = text_features / text_features.norm(p=2, dim=-1, keepdim=True) # normalize
# compute image-text similarity scores
inputs = processor(text=texts, images=image, return_tensors="pt", padding=True)
outputs = model(**inputs)
logits_per_image = outputs.logits_per_image # this is the image-text similarity score
probs = logits_per_image.softmax(dim=1) # probs: [[0.0219, 0.0316, 0.0043, 0.9423]]
```
However, if you are not satisfied with only using the API, feel free to check our github repo https://github.com/OFA-Sys/Chinese-CLIP for more details about training and inference.
<br><br>
## Results
**MUGE Text-to-Image Retrieval**:
<table border="1" width="100%">
<tr align="center">
<th>Setup</th><th colspan="4">Zero-shot</th><th colspan="4">Finetune</th>
</tr>
<tr align="center">
<td>Metric</td><td>R@1</td><td>R@5</td><td>R@10</td><td>MR</td><td>R@1</td><td>R@5</td><td>R@10</td><td>MR</td>
</tr>
<tr align="center">
<td width="120%">Wukong</td><td>42.7</td><td>69.0</td><td>78.0</td><td>63.2</td><td>52.7</td><td>77.9</td><td>85.6</td><td>72.1</td>
</tr>
<tr align="center">
<td width="120%">R2D2</td><td>49.5</td><td>75.7</td><td>83.2</td><td>69.5</td><td>60.1</td><td>82.9</td><td>89.4</td><td>77.5</td>
</tr>
<tr align="center">
<td width="120%">CN-CLIP</td><td>63.0</td><td>84.1</td><td>89.2</td><td>78.8</td><td>68.9</td><td>88.7</td><td>93.1</td><td>83.6</td>
</tr>
</table>
<br>
**Flickr30K-CN Retrieval**:
<table border="1" width="120%">
<tr align="center">
<th>Task</th><th colspan="6">Text-to-Image</th><th colspan="6">Image-to-Text</th>
</tr>
<tr align="center">
<th>Setup</th><th colspan="3">Zero-shot</th><th colspan="3">Finetune</th><th colspan="3">Zero-shot</th><th colspan="3">Finetune</th>
</tr>
<tr align="center">
<td>Metric</td><td>R@1</td><td>R@5</td><td>R@10</td><td>R@1</td><td>R@5</td><td>R@10</td><td>R@1</td><td>R@5</td><td>R@10</td><td>R@1</td><td>R@5</td><td>R@10</td>
</tr>
<tr align="center">
<td width="120%">Wukong</td><td>51.7</td><td>78.9</td><td>86.3</td><td>77.4</td><td>94.5</td><td>97.0</td><td>76.1</td><td>94.8</td><td>97.5</td><td>92.7</td><td>99.1</td><td>99.6</td>
</tr>
<tr align="center">
<td width="120%">R2D2</td><td>60.9</td><td>86.8</td><td>92.7</td><td>84.4</td><td>96.7</td><td>98.4</td><td>77.6</td><td>96.7</td><td>98.9</td><td>95.6</td><td>99.8</td><td>100.0</td>
</tr>
<tr align="center">
<td width="120%">CN-CLIP</td><td>71.2</td><td>91.4</td><td>95.5</td><td>83.8</td><td>96.9</td><td>98.6</td><td>81.6</td><td>97.5</td><td>98.8</td><td>95.3</td><td>99.7</td><td>100.0</td>
</tr>
</table>
<br>
**COCO-CN Retrieval**:
<table border="1" width="100%">
<tr align="center">
<th>Task</th><th colspan="6">Text-to-Image</th><th colspan="6">Image-to-Text</th>
</tr>
<tr align="center">
<th>Setup</th><th colspan="3">Zero-shot</th><th colspan="3">Finetune</th><th colspan="3">Zero-shot</th><th colspan="3">Finetune</th>
</tr>
<tr align="center">
<td>Metric</td><td>R@1</td><td>R@5</td><td>R@10</td><td>R@1</td><td>R@5</td><td>R@10</td><td>R@1</td><td>R@5</td><td>R@10</td><td>R@1</td><td>R@5</td><td>R@10</td>
</tr>
<tr align="center">
<td width="120%">Wukong</td><td>53.4</td><td>80.2</td><td>90.1</td><td>74.0</td><td>94.4</td><td>98.1</td><td>55.2</td><td>81.0</td><td>90.6</td><td>73.3</td><td>94.0</td><td>98.0</td>
</tr>
<tr align="center">
<td width="120%">R2D2</td><td>56.4</td><td>85.0</td><td>93.1</td><td>79.1</td><td>96.5</td><td>98.9</td><td>63.3</td><td>89.3</td><td>95.7</td><td>79.3</td><td>97.1</td><td>98.7</td>
</tr>
<tr align="center">
<td width="120%">CN-CLIP</td><td>69.2</td><td>89.9</td><td>96.1</td><td>81.5</td><td>96.9</td><td>99.1</td><td>63.0</td><td>86.6</td><td>92.9</td><td>83.5</td><td>97.3</td><td>99.2</td>
</tr>
</table>
<br>
**Zero-shot Image Classification**:
<table border="1" width="100%">
<tr align="center">
<th>Task</th><th>CIFAR10</th><th>CIFAR100</th><th>DTD</th><th>EuroSAT</th><th>FER</th><th>FGVC</th><th>KITTI</th><th>MNIST</th><th>PC</th><th>VOC</th>
</tr>
<tr align="center">
<td width="150%">GIT</td><td>88.5</td><td>61.1</td><td>42.9</td><td>43.4</td><td>41.4</td><td>6.7</td><td>22.1</td><td>68.9</td><td>50.0</td><td>80.2</td>
</tr>
<tr align="center">
<td width="150%">ALIGN</td><td>94.9</td><td>76.8</td><td>66.1</td><td>52.1</td><td>50.8</td><td>25.0</td><td>41.2</td><td>74.0</td><td>55.2</td><td>83.0</td>
</tr>
<tr align="center">
<td width="150%">CLIP</td><td>94.9</td><td>77.0</td><td>56.0</td><td>63.0</td><td>48.3</td><td>33.3</td><td>11.5</td><td>79.0</td><td>62.3</td><td>84.0</td>
</tr>
<tr align="center">
<td width="150%">Wukong</td><td>95.4</td><td>77.1</td><td>40.9</td><td>50.3</td><td>-</td><td>-</td><td>-</td><td>-</td><td>-</td><td>-</td>
</tr>
<tr align="center">
<td width="150%">CN-CLIP</td><td>96.0</td><td>79.7</td><td>51.2</td><td>52.0</td><td>55.1</td><td>26.2</td><td>49.9</td><td>79.4</td><td>63.5</td><td>84.9</td>
</tr>
</table>
<br>
## Citation
If you find Chinese CLIP helpful, feel free to cite our paper. Thanks for your support!
```
@article{chinese-clip,
title={Chinese CLIP: Contrastive Vision-Language Pretraining in Chinese},
author={Yang, An and Pan, Junshu and Lin, Junyang and Men, Rui and Zhang, Yichang and Zhou, Jingren and Zhou, Chang},
journal={arXiv preprint arXiv:2211.01335},
year={2022}
}
```
<br> | 7,641 | [
[
-0.049224853515625,
-0.041900634765625,
0.0021114349365234375,
0.0252838134765625,
-0.0245819091796875,
0.00008112192153930664,
-0.01334381103515625,
-0.030517578125,
0.033538818359375,
0.00008916854858398438,
-0.059967041015625,
-0.024566650390625,
-0.040832519... |
keremberke/yolov5s-blood-cell | 2023-01-01T10:00:19.000Z | [
"yolov5",
"tensorboard",
"yolo",
"vision",
"object-detection",
"pytorch",
"dataset:keremberke/blood-cell-object-detection",
"model-index",
"has_space",
"region:us"
] | object-detection | keremberke | null | null | keremberke/yolov5s-blood-cell | 2 | 532 | yolov5 | 2023-01-01T00:19:09 |
---
tags:
- yolov5
- yolo
- vision
- object-detection
- pytorch
library_name: yolov5
library_version: 7.0.6
inference: false
datasets:
- keremberke/blood-cell-object-detection
model-index:
- name: keremberke/yolov5s-blood-cell
results:
- task:
type: object-detection
dataset:
type: keremberke/blood-cell-object-detection
name: keremberke/blood-cell-object-detection
split: validation
metrics:
- type: precision # since mAP@0.5 is not available on hf.co/metrics
value: 0.9022929540677422 # min: 0.0 - max: 1.0
name: mAP@0.5
---
<div align="center">
<img width="640" alt="keremberke/yolov5s-blood-cell" src="https://huggingface.co/keremberke/yolov5s-blood-cell/resolve/main/sample_visuals.jpg">
</div>
### How to use
- Install [yolov5](https://github.com/fcakyon/yolov5-pip):
```bash
pip install -U yolov5
```
- Load model and perform prediction:
```python
import yolov5
# load model
model = yolov5.load('keremberke/yolov5s-blood-cell')
# set model parameters
model.conf = 0.25 # NMS confidence threshold
model.iou = 0.45 # NMS IoU threshold
model.agnostic = False # NMS class-agnostic
model.multi_label = False # NMS multiple labels per box
model.max_det = 1000 # maximum number of detections per image
# set image
img = 'https://github.com/ultralytics/yolov5/raw/master/data/images/zidane.jpg'
# perform inference
results = model(img, size=640)
# inference with test time augmentation
results = model(img, augment=True)
# parse results
predictions = results.pred[0]
boxes = predictions[:, :4] # x1, y1, x2, y2
scores = predictions[:, 4]
categories = predictions[:, 5]
# show detection bounding boxes on image
results.show()
# save results into "results/" folder
results.save(save_dir='results/')
```
- Finetune the model on your custom dataset:
```bash
yolov5 train --data data.yaml --img 640 --batch 16 --weights keremberke/yolov5s-blood-cell --epochs 10
```
**More models available at: [awesome-yolov5-models](https://github.com/keremberke/awesome-yolov5-models)** | 2,058 | [
[
-0.043609619140625,
-0.032684326171875,
0.03961181640625,
-0.0361328125,
-0.035919189453125,
-0.01226043701171875,
0.0167083740234375,
-0.0440673828125,
0.016876220703125,
0.0227203369140625,
-0.043121337890625,
-0.057647705078125,
-0.033233642578125,
0.0024... |
Daniil-plotnikov/russian-vision-v5-beta-3 | 2023-07-15T09:29:26.000Z | [
"diffusers",
"text-to-image",
"stable-diffusion",
"ru",
"en",
"license:creativeml-openrail-m",
"endpoints_compatible",
"has_space",
"diffusers:StableDiffusionPipeline",
"region:us"
] | text-to-image | Daniil-plotnikov | null | null | Daniil-plotnikov/russian-vision-v5-beta-3 | 0 | 532 | diffusers | 2023-07-15T09:24:04 | ---
license: creativeml-openrail-m
tags:
- text-to-image
- stable-diffusion
language:
- ru
- en
---
### Russian-Vision-V5-beta-3 Dreambooth model trained by Daniil-plotnikov with [TheLastBen's fast-DreamBooth](https://colab.research.google.com/github/TheLastBen/fast-stable-diffusion/blob/main/fast-DreamBooth.ipynb) notebook
Test the concept via A1111 Colab [fast-Colab-A1111](https://colab.research.google.com/github/TheLastBen/fast-stable-diffusion/blob/main/fast_stable_diffusion_AUTOMATIC1111.ipynb)
Sample pictures of this concept: | 540 | [
[
-0.017822265625,
-0.0411376953125,
0.058685302734375,
0.030120849609375,
-0.034088134765625,
0.0240936279296875,
0.03704833984375,
-0.031646728515625,
0.03485107421875,
0.005603790283203125,
-0.0254364013671875,
-0.03466796875,
-0.04150390625,
-0.01686096191... |
compressed-llm/vicuna-13b-v1.3-awq | 2023-10-05T00:48:06.000Z | [
"region:us"
] | null | compressed-llm | null | null | compressed-llm/vicuna-13b-v1.3-awq | 0 | 532 | null | 2023-10-04T12:40:27 | Please use the following code sample to load these AWQ models:
```
from transformers import AutoTokenizer, AutoModelForCausalLM, AutoConfig
from auto_gptq import AutoGPTQForCausalLM
import torch
model_path = 'efficient-llm/vicuna-13b-v1.3-awq'
config = AutoConfig.from_pretrained(model_path, revision='3bit_128g', trust_remote_code=True)
enc = AutoTokenizer.from_pretrained('meta-llama/Llama-2-7b-hf', trust_remote_code=True)
kwargs = {"torch_dtype": torch.float16, "low_cpu_mem_usage": True}
model = AutoModelForCausalLM.from_pretrained(
model_path, config=config, trust_remote_code=True, device_map='auto', revision='3bit_128g', **kwargs)
model.eval()
input_ids = enc('How are you today?', return_tensors='pt').input_ids.to('cuda')
outputs = model.generate(input_ids=input_ids, max_length=128)
print(enc.decode(outputs[0]))
``` | 835 | [
[
-0.0311126708984375,
-0.019500732421875,
0.0233612060546875,
0.005847930908203125,
-0.033172607421875,
0.01529693603515625,
0.0386962890625,
-0.0283355712890625,
-0.03778076171875,
0.049774169921875,
-0.04156494140625,
-0.03082275390625,
-0.040252685546875,
... |
CausalLM/7B | 2023-11-05T17:42:13.000Z | [
"transformers",
"pytorch",
"llama",
"text-generation",
"llama2",
"qwen",
"en",
"zh",
"dataset:JosephusCheung/GuanacoDataset",
"dataset:Open-Orca/OpenOrca",
"dataset:stingning/ultrachat",
"dataset:meta-math/MetaMathQA",
"dataset:liuhaotian/LLaVA-Instruct-150K",
"dataset:jondurbin/airoboros-... | text-generation | CausalLM | null | null | CausalLM/7B | 101 | 532 | transformers | 2023-10-22T10:23:00 | ---
license: wtfpl
datasets:
- JosephusCheung/GuanacoDataset
- Open-Orca/OpenOrca
- stingning/ultrachat
- meta-math/MetaMathQA
- liuhaotian/LLaVA-Instruct-150K
- jondurbin/airoboros-3.1
- WizardLM/WizardLM_evol_instruct_V2_196k
- RyokoAI/ShareGPT52K
- RyokoAI/Fandom23K
- milashkaarshif/MoeGirlPedia_wikitext_raw_archive
- wikipedia
- wiki_lingua
- fnlp/moss-003-sft-data
- garage-bAInd/Open-Platypus
- LDJnr/Puffin
- openbmb/llava_zh
- BAAI/COIG
- TigerResearch/tigerbot-zhihu-zh-10k
- liwu/MNBVC
- teknium/openhermes
language:
- en
- zh
pipeline_tag: text-generation
tags:
- llama
- llama2
- qwen
---
*Image drawn by GPT-4 DALL·E 3* **TL;DR: Perhaps this 7B model, better than all existing models <= 33B, in most quantitative evaluations...**
# CausalLM 7B - Fully Compatible with Meta LLaMA 2
Use the transformers library that does not require remote/external code to load the model, AutoModelForCausalLM and AutoTokenizer (or manually specify LlamaForCausalLM to load LM, GPT2Tokenizer to load Tokenizer), and model quantization is fully compatible with GGUF (llama.cpp), GPTQ, and AWQ.
# Recent Updates: [DPO-α Version](https://huggingface.co/CausalLM/7B-DPO-alpha) outperforms Zephyr-β in MT-Bench
**llama.cpp GGUF models**
GPT2Tokenizer fixed by [Kerfuffle](https://github.com/KerfuffleV2) on [https://github.com/ggerganov/llama.cpp/pull/3743](https://github.com/ggerganov/llama.cpp/pull/3743), new models are reuploaded.
Thanks TheBloke for GGUF quants: [https://huggingface.co/TheBloke/CausalLM-7B-GGUF](https://huggingface.co/TheBloke/CausalLM-7B-GGUF)
## Read Me:
Also see [14B Version](https://huggingface.co/CausalLM/14B)
This model was trained based on the model weights of Qwen (and LLaMA2 was used, yes, for calculating some initial weights), you may also need to comply with the commercial use restrictions of these two models depending on the situation. The training process utilized a model structure that was identical to LLaMA2, using the same attention calculation method as the original MHA LLaMA2 models, and no additional scaling applied to the Rotary Positional Encoding (RoPE).
We manually curated a SFT dataset of 1.3B tokens for training, utilizing open source datasets from Hugging Face. For most of these sentences, we performed manual or synthetic rewrites and generated alternate language versions using larger language models. Additionally, we conducted augmented text training using carefully selected entries from Wikipedia, as well as featured entries from Fandom and filtered entries from Moegirlpedia. In order to strike a balance between efficiency and quality, 100% of the data used for training was synthetic data, no direct use of text from the internet or original texts from publicly available datasets was employed for fine-tuning.
The 7B version of the model is a distilled version of the 14B model, specifically designed for speculative sampling. Therefore, it is important to exercise caution when directly using the model, as it may produce hallucinations or unreliable outputs.
Please note that the model was trained on unfiltered internet data. Since we do not have the capacity to vet all of it, there may be a substantial amount of objectionable content, pornography, violence, and offensive language present that we are unable to remove. Therefore, you will still need to complete your own checks on the model's safety and filter keywords in the output. Due to computational resource constraints, we are presently unable to implement RLHF for the model's ethics and safety, nor training on SFT samples that refuse to answer certain questions for restrictive fine-tuning.
Bonus: The model underwent some fine-tuning on the prompt format introduced in LLaVA1.5 that is unrelated to image attention calculation. Therefore, aligning the ViT Projection module with frozen LM under visual instructions would enable rapid implementation of effective multimodal capabilities.
## PROMPT FORMAT:
[chatml](https://github.com/openai/openai-python/blob/main/chatml.md)
**System Prompt must not be empty!**
## MMLU:
stem ACC: 56.83
Humanities ACC: 58.79
other ACC: 70.04
social ACC: 72.41
**AVERAGE ACC:63.82** (Outperforms / Equal to the best Mistral-7B Chat-style fine-tunes, ChatGLM3-6B and ALL other models under 33B.)
## CEval (Val):
STEM acc: 61.67
Social Science acc: 81.94
Humanities acc: 77.19
Other acc: 68.35
Hard acc:48.03
**AVERAGE acc:70.27** (Outperforms ALL 7B models currently, including ChatGLM3-6B.)
## GSM8K
**Zero-shot ACC 0.5921152388172858** (Outperforms WizardMath-7B and Qwen-7B)
## MT-Behch on DPO Version
| Model | MT-Bench |
| ------------------------- | ------------ |
| GPT-4 | 8.99 |
| GPT-3.5-Turbo | 7.94 |
| | |
| Zephyr-7b-β (Overfitting) | 7.34 |
| Zephyr-7b-α | 6.88 |
| | |
| **[CausalLM/14B-DPO-α](https://huggingface.co/CausalLM/14B-DPO-alpha)** | **7.618868** |
| **[CausalLM/7B-DPO-α](https://huggingface.co/CausalLM/7B-DPO-alpha)** | **7.038125** |
# 因果语言模型 7B - 与 Meta LLaMA 2 完全兼容
使用无需远程/外部代码的transformers库加载模型，AutoModelForCausalLM和AutoTokenizer（或者手动指定LlamaForCausalLM加载LM， GPT2Tokenizer加载Tokenizer），并且模型量化与GGUF（llama.cpp）、GPTQ、AWQ完全兼容。
# 最近更新: [DPO-α Version](https://huggingface.co/CausalLM/7B-DPO-alpha) 在 MT-Bench 超过 Zephyr-β
**llama.cpp GGUF models**
GPT2Tokenizer 支持由 [Kerfuffle](https://github.com/KerfuffleV2) 修复于 [https://github.com/ggerganov/llama.cpp/pull/3743](https://github.com/ggerganov/llama.cpp/pull/3743)，新模型稍后上传。
感谢 TheBloke 制作 GGUF 版本量化模型: [https://huggingface.co/TheBloke/CausalLM-7B-GGUF](https://huggingface.co/TheBloke/CausalLM-7B-GGUF)
## 请读我：
另请参阅[14B版本](https://huggingface.co/CausalLM/14B)
该模型是基于Qwen的权重（并使用了LLaMA2权重，是的，用于计算一些权重初始化），您根据情况可能还需要遵守这两个模型的商业使用限制。训练过程中使用了与LLaMA2相同的模型结构，使用原始MHA LLaMA2模型的相同注意力计算方法，对旋转位置编码（RoPE）没有进行额外的缩放。
我们手动筛选了一个包含13亿个标记的SFT数据集进行训练，利用了Hugging Face的开源数据集。对于大多数句子，我们进行了手动或合成改写，并使用更大的语言模型生成了其他语言版本。此外，我们还使用了精心挑选的来自维基百科的条目、来自Fandom的精选条目以及来自萌娘百科的过滤条目进行增强文本训练。为了在效率和质量之间取得平衡，训练所使用的100%数据都是合成数据，没有直接使用来自互联网或公开可用数据集的原始文本进行微调。
7B版本的模型是14B模型的精简版本，专门设计用于推测抽样。因此，在直接使用模型时，需要谨慎行事，因为它可能会产生幻觉或不可靠的输出。
请注意，模型是在未经过滤的互联网数据上进行训练的。由于我们无法审核所有数据，可能会出现大量不良内容、色情、暴力和冒犯性语言，我们无法删除这些内容。因此，您仍然需要对模型的安全性进行自己的检查，并对输出中的关键词进行过滤。由于计算资源的限制，我们目前无法为模型的伦理和安全实施RLHF，也无法对拒绝回答某些问题的SFT样本进行训练以进行限制性微调。
额外奖励：模型在LLaVA1.5中引入的提示格式上进行了一些微调，与图像注意力计算无关。因此，将ViT投影模块与冻结的LM对齐，并根据视觉指令实施快速实现有效的多模态能力。
## 提示格式：
[chatml](https://github.com/openai/openai-python/blob/main/chatml.md)
**系统提示不能为空！**
## MMLU：
STEM准确率：56.83
人文学科准确率：58.79
其他准确率：70.04
社会学准确率：72.41
**平均准确率：63.82** （优于/平于最好的 Mistral-7B 聊天格式的微调，ChatGLM3-6B 和其余的33B及以下模型。）
## CEval（验证集）：
STEM准确率：61.67
社会科学准确率：81.94
人文学科准确率：77.19
其他准确率：68.35
困难准确率：48.03
**平均准确率：70.27** （优于当前所有7B模型，包括 ChatGLM3-6B）
## GSM8K
**零样本准确率0.5921152388172858** （优于WizardMath-7B和Qwen-7B）
## DPO 版本的 MT-Behch
| Model | MT-Bench |
| ------------------------- | ------------ |
| GPT-4 | 8.99 |
| GPT-3.5-Turbo | 7.94 |
| | |
| Zephyr-7b-β (Overfitting) | 7.34 |
| Zephyr-7b-α | 6.88 |
| | |
| **[CausalLM/14B-DPO-α](https://huggingface.co/CausalLM/14B-DPO-alpha)** | **7.618868** |
| **[CausalLM/7B-DPO-α](https://huggingface.co/CausalLM/7B-DPO-alpha)** | **7.038125** |
| 7,592 | [
[
-0.038421630859375,
-0.05584716796875,
0.0232391357421875,
0.0233001708984375,
-0.039794921875,
-0.01434326171875,
-0.0037212371826171875,
-0.05279541015625,
0.0251007080078125,
0.01030731201171875,
-0.043670654296875,
-0.034027099609375,
-0.050506591796875,
... |
timm/vit_base_patch32_clip_224.openai_ft_in1k | 2023-05-06T00:04:11.000Z | [
"timm",
"pytorch",
"safetensors",
"image-classification",
"dataset:imagenet-1k",
"dataset:wit-400m",
"arxiv:2212.07143",
"arxiv:2103.00020",
"arxiv:2010.11929",
"license:apache-2.0",
"region:us"
] | image-classification | timm | null | null | timm/vit_base_patch32_clip_224.openai_ft_in1k | 0 | 531 | timm | 2022-11-10T07:58:45 | ---
tags:
- image-classification
- timm
library_name: timm
license: apache-2.0
datasets:
- imagenet-1k
- wit-400m
---
# Model card for vit_base_patch32_clip_224.openai_ft_in1k
A Vision Transformer (ViT) image classification model. Pretrained on WIT-400M image-text pairs by OpenAI using CLIP. Fine-tuned on ImageNet-1k in `timm`. See recipes in [Reproducible scaling laws](https://arxiv.org/abs/2212.07143).
## Model Details
- **Model Type:** Image classification / feature backbone
- **Model Stats:**
- Params (M): 88.2
- GMACs: 4.4
- Activations (M): 4.2
- Image size: 224 x 224
- **Papers:**
- Learning Transferable Visual Models From Natural Language Supervision: https://arxiv.org/abs/2103.00020
- Reproducible scaling laws for contrastive language-image learning: https://arxiv.org/abs/2212.07143
- An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale: https://arxiv.org/abs/2010.11929v2
- **Dataset:** ImageNet-1k
- **Pretrain Dataset:**
- WIT-400M
## Model Usage
### Image Classification
```python
from urllib.request import urlopen
from PIL import Image
import timm
img = Image.open(urlopen(
'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
))
model = timm.create_model('vit_base_patch32_clip_224.openai_ft_in1k', pretrained=True)
model = model.eval()
# get model specific transforms (normalization, resize)
data_config = timm.data.resolve_model_data_config(model)
transforms = timm.data.create_transform(**data_config, is_training=False)
output = model(transforms(img).unsqueeze(0)) # unsqueeze single image into batch of 1
top5_probabilities, top5_class_indices = torch.topk(output.softmax(dim=1) * 100, k=5)
```
### Image Embeddings
```python
from urllib.request import urlopen
from PIL import Image
import timm
img = Image.open(urlopen(
'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
))
model = timm.create_model(
'vit_base_patch32_clip_224.openai_ft_in1k',
pretrained=True,
num_classes=0, # remove classifier nn.Linear
)
model = model.eval()
# get model specific transforms (normalization, resize)
data_config = timm.data.resolve_model_data_config(model)
transforms = timm.data.create_transform(**data_config, is_training=False)
output = model(transforms(img).unsqueeze(0)) # output is (batch_size, num_features) shaped tensor
# or equivalently (without needing to set num_classes=0)
output = model.forward_features(transforms(img).unsqueeze(0))
# output is unpooled, a (1, 50, 768) shaped tensor
output = model.forward_head(output, pre_logits=True)
# output is a (1, num_features) shaped tensor
```
## Model Comparison
Explore the dataset and runtime metrics of this model in timm [model results](https://github.com/huggingface/pytorch-image-models/tree/main/results).
## Citation
```bibtex
@inproceedings{Radford2021LearningTV,
title={Learning Transferable Visual Models From Natural Language Supervision},
author={Alec Radford and Jong Wook Kim and Chris Hallacy and A. Ramesh and Gabriel Goh and Sandhini Agarwal and Girish Sastry and Amanda Askell and Pamela Mishkin and Jack Clark and Gretchen Krueger and Ilya Sutskever},
booktitle={ICML},
year={2021}
}
```
```bibtex
@article{cherti2022reproducible,
title={Reproducible scaling laws for contrastive language-image learning},
author={Cherti, Mehdi and Beaumont, Romain and Wightman, Ross and Wortsman, Mitchell and Ilharco, Gabriel and Gordon, Cade and Schuhmann, Christoph and Schmidt, Ludwig and Jitsev, Jenia},
journal={arXiv preprint arXiv:2212.07143},
year={2022}
}
```
```bibtex
@article{dosovitskiy2020vit,
title={An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale},
author={Dosovitskiy, Alexey and Beyer, Lucas and Kolesnikov, Alexander and Weissenborn, Dirk and Zhai, Xiaohua and Unterthiner, Thomas and Dehghani, Mostafa and Minderer, Matthias and Heigold, Georg and Gelly, Sylvain and Uszkoreit, Jakob and Houlsby, Neil},
journal={ICLR},
year={2021}
}
```
```bibtex
@misc{rw2019timm,
author = {Ross Wightman},
title = {PyTorch Image Models},
year = {2019},
publisher = {GitHub},
journal = {GitHub repository},
doi = {10.5281/zenodo.4414861},
howpublished = {\url{https://github.com/huggingface/pytorch-image-models}}
}
```
| 4,361 | [
[
-0.0312347412109375,
-0.03790283203125,
0.002979278564453125,
0.01580810546875,
-0.0239410400390625,
-0.0333251953125,
-0.032684326171875,
-0.031402587890625,
0.00988006591796875,
0.0307159423828125,
-0.0307464599609375,
-0.040069580078125,
-0.057220458984375,
... |
arnolfokam/ai-generated-image-detector | 2023-03-19T22:51:59.000Z | [
"transformers",
"pytorch",
"resnet",
"image-classification",
"custom_code",
"en",
"dataset:competitions/aiornot",
"license:apache-2.0",
"autotrain_compatible",
"has_space",
"region:us"
] | image-classification | arnolfokam | null | null | arnolfokam/ai-generated-image-detector | 3 | 531 | transformers | 2023-03-17T20:19:34 | ---
license: apache-2.0
datasets:
- competitions/aiornot
language:
- en
metrics:
- accuracy
pipeline_tag: image-classification
---
### How to use
Here is how to use this model to classify an image of the AIorNot dataset into one of the 2 classes:
```python
from transformers import AutoImageProcessor, AutoModelForImageClassification
import torch
from datasets import load_dataset
dataset = load_dataset("competitions/aiornot")
image = dataset["test"][0]["image"]
processor = AutoImageProcessor.from_pretrained("microsoft/resnet-50")
model = AutoModelForImageClassification.from_pretrained("arnolfokam/ai-generated-image-detector", trust_remote_code=True)
inputs = processor(image, return_tensors="pt")
with torch.no_grad():
logits = model(**inputs).logits
# model predicts one of the 2 classes
predicted_label = logits.argmax(-1).item()
print(model.config.id2label[predicted_label])
```
| 901 | [
[
-0.0279998779296875,
-0.01061248779296875,
-0.01049041748046875,
-0.0134124755859375,
-0.0251617431640625,
-0.007343292236328125,
0.0091094970703125,
-0.04510498046875,
-0.01548004150390625,
0.0279693603515625,
-0.01104736328125,
-0.028656005859375,
-0.057525634... |
internlm/internlm-xcomposer-vl-7b | 2023-10-19T09:49:56.000Z | [
"transformers",
"pytorch",
"InternLMXComposer",
"feature-extraction",
"text-generation",
"custom_code",
"license:apache-2.0",
"region:us"
] | text-generation | internlm | null | null | internlm/internlm-xcomposer-vl-7b | 13 | 531 | transformers | 2023-09-26T09:31:54 | ---
license: apache-2.0
pipeline_tag: text-generation
---
<p align="center">
<img src="logo.png" width="400"/>
<p>
<p align="center">
<b><font size="6">InternLM-XComposer</font></b>
<p>
<div align="center">
[💻Github Repo](https://github.com/InternLM/InternLM-XComposer)
</div>
**InternLM-XComposer** is a vision-language large model (VLLM) based on [InternLM](https://github.com/InternLM/InternLM/tree/main) for advanced text-image comprehension and composition. InternLM-XComposer has serveal appealing properties:
- **Interleaved Text-Image Composition**: InternLM-XComposer can effortlessly generate coherent and contextual articles that seamlessly integrate images, providing a more engaging and immersive reading experience. The interleaved text-image composition is implemented in following steps:
1. **Text Generation**: It crafts long-form text based on human-provided instructions.
2. **Image Spoting and Captioning**: It pinpoints optimal locations for image placement and furnishes image descriptions.
3. **Image Retrieval and Selection**: It select image candidates and identify the image that optimally complements the content.
- **Comprehension with Rich Multilingual Knowledge**: The text-image comprehension is empowered by training on extensive multi-modal multilingual concepts with carefully crafted strategies, resulting in a deep understanding of visual content.
- **Strong performance**: It consistently achieves state-of-the-art results across various benchmarks for vision-language large models, including [MME Benchmark](https://github.com/BradyFU/Awesome-Multimodal-Large-Language-Models/tree/Evaluation) (English), [MMBench](https://opencompass.org.cn/leaderboard-multimodal) (English), [Seed-Bench](https://huggingface.co/spaces/AILab-CVC/SEED-Bench_Leaderboard) (English), [CCBench](https://opencompass.org.cn/leaderboard-multimodal)(Chinese), and [MMBench-CN](https://opencompass.org.cn/leaderboard-multimodal) (Chineese).
We release InternLM-XComposer series in two versions:
- InternLM-XComposer-VL: The pretrained VLLM model with InternLM as the initialization of the LLM, achieving strong performance on various multimodal benchmarks, e.g., MME Benchmark, MMBench Seed-Bench, CCBench, and MMBench-CN.
- InternLM-XComposer: The finetuned VLLM for *Interleaved Text-Image Composition* and *LLM-based AI assistant*.
<br> | 2,386 | [
[
-0.03924560546875,
-0.0399169921875,
0.02056884765625,
0.0230712890625,
-0.028045654296875,
0.01177215576171875,
-0.01507568359375,
-0.061614990234375,
-0.013214111328125,
0.0220489501953125,
-0.030914306640625,
-0.045684814453125,
-0.026153564453125,
0.0023... |
nousr/robo-diffusion-2-base | 2023-03-23T17:31:19.000Z | [
"diffusers",
"robots",
"stable-diffusion",
"aiart",
"text-to-image",
"en",
"license:openrail++",
"endpoints_compatible",
"has_space",
"diffusers:StableDiffusionPipeline",
"region:us"
] | text-to-image | nousr | null | null | nousr/robo-diffusion-2-base | 186 | 530 | diffusers | 2022-11-28T20:36:50 | ---
language:
- en
thumbnail: "https://huggingface.co/nousr/robo-diffusion/resolve/main/robo_example.png"
tags:
- robots
- stable-diffusion
- aiart
- text-to-image
license: "openrail++"
---
# Robo-Diffusion 2 (base)
A dreambooth-method finetune of stable diffusion that will output cool looking robots when prompted.
<img src="https://huggingface.co/nousr/robo-diffusion-2-base/resolve/main/example_grid.png"/>
# Usage
Keep the words `nousr robot` towards the beginning of your prompt to invoke the finetuned style. Use negative prompts to achieve the best result.
```python
import torch
from diffusers import StableDiffusionPipeline, EulerDiscreteScheduler
scheduler = EulerDiscreteScheduler.from_pretrained("nousr/robo-diffusion-2-base", subfolder="scheduler")
pipe = StableDiffusionPipeline.from_pretrained("nousr/robo-diffusion-2-base", scheduler=scheduler, torch_dtype=torch.float16)
pipe = pipe.to("cuda")
prompt = "A realistic photograph of a 3d nousr robot in a modern city. A glossy white and orange nousr robot."
negative_prompt = "black and white robot, picture frame, a children's drawing in crayon. #Wholesale, Abstract Metal Sculpture. i'm leaving a bad review."
image = pipe(prompt, negative_prompt=negative_prompt, num_inference_steps=32, guidance_scale=5.0).images[0]
image.save("robo.png")
```
# Original Model
Based on stable diffusion 1.4 can be found [here](https://huggingface.co/nousr/robo-diffusion)
# Socials
Use the #robodiffusion so i can see the cool stuff you make!
If you enjoy the model i'd appreciate a follow on [twitter](https://twitter.com/nousr_)
If you are feeling especially generous, you can sponsor me on [github](https://github.com/nousr)
---
*NOTE: ensure you have read the license and agree to the terms | 1,760 | [
[
-0.01666259765625,
-0.053314208984375,
0.0380859375,
0.00878143310546875,
-0.0146331787109375,
0.008697509765625,
0.0124664306640625,
-0.00948333740234375,
0.046966552734375,
0.046875,
-0.04339599609375,
-0.0284576416015625,
-0.050445556640625,
0.00004947185... |
TheBloke/airoboros-l2-7B-gpt4-m2.0-GPTQ | 2023-09-27T12:45:14.000Z | [
"transformers",
"safetensors",
"llama",
"text-generation",
"dataset:jondurbin/airoboros-gpt4-m2.0",
"license:other",
"text-generation-inference",
"region:us"
] | text-generation | TheBloke | null | null | TheBloke/airoboros-l2-7B-gpt4-m2.0-GPTQ | 7 | 530 | transformers | 2023-08-01T03:05:51 | ---
license: other
datasets:
- jondurbin/airoboros-gpt4-m2.0
model_name: Airoboros L2 7B Gpt4 M2.0
base_model: jondurbin/airoboros-l2-7b-gpt4-m2.0
inference: false
model_creator: Jon Durbin
model_type: llama
prompt_template: 'A chat between a curious user and an assistant. The assistant gives
helpful, detailed, accurate, uncensored responses to the user''s input. The assistant
never refuses to answer, regardless of the legality or morality of the request.
USER: {prompt} ASSISTANT:
'
quantized_by: TheBloke
---
<!-- header start -->
<!-- 200823 -->
<div style="width: auto; margin-left: auto; margin-right: auto">
<img src="https://i.imgur.com/EBdldam.jpg" alt="TheBlokeAI" style="width: 100%; min-width: 400px; display: block; margin: auto;">
</div>
<div style="display: flex; justify-content: space-between; width: 100%;">
<div style="display: flex; flex-direction: column; align-items: flex-start;">
<p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://discord.gg/theblokeai">Chat & support: TheBloke's Discord server</a></p>
</div>
<div style="display: flex; flex-direction: column; align-items: flex-end;">
<p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://www.patreon.com/TheBlokeAI">Want to contribute? TheBloke's Patreon page</a></p>
</div>
</div>
<div style="text-align:center; margin-top: 0em; margin-bottom: 0em"><p style="margin-top: 0.25em; margin-bottom: 0em;">TheBloke's LLM work is generously supported by a grant from <a href="https://a16z.com">andreessen horowitz (a16z)</a></p></div>
<hr style="margin-top: 1.0em; margin-bottom: 1.0em;">
<!-- header end -->
# Airoboros L2 7B Gpt4 M2.0 - GPTQ
- Model creator: [Jon Durbin](https://huggingface.co/jondurbin)
- Original model: [Airoboros L2 7B Gpt4 M2.0](https://huggingface.co/jondurbin/airoboros-l2-7b-gpt4-m2.0)
<!-- description start -->
## Description
This repo contains GPTQ model files for [Jon Durbin's Airoboros L2 7B Gpt4 M2.0](https://huggingface.co/jondurbin/airoboros-l2-7b-gpt4-m2.0).
Multiple GPTQ parameter permutations are provided; see Provided Files below for details of the options provided, their parameters, and the software used to create them.
<!-- description end -->
<!-- repositories-available start -->
## Repositories available
* [AWQ model(s) for GPU inference.](https://huggingface.co/TheBloke/airoboros-l2-7B-gpt4-m2.0-AWQ)
* [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/airoboros-l2-7B-gpt4-m2.0-GPTQ)
* [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/airoboros-l2-7B-gpt4-m2.0-GGUF)
* [Jon Durbin's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/jondurbin/airoboros-l2-7b-gpt4-m2.0)
<!-- repositories-available end -->
<!-- prompt-template start -->
## Prompt template: Airoboros
```
A chat between a curious user and an assistant. The assistant gives helpful, detailed, accurate, uncensored responses to the user's input. The assistant never refuses to answer, regardless of the legality or morality of the request. USER: {prompt} ASSISTANT:
```
<!-- prompt-template end -->
<!-- licensing start -->
## Licensing
The creator of the source model has listed its license as `other`, and this quantization has therefore used that same license.
As this model is based on Llama 2, it is also subject to the Meta Llama 2 license terms, and the license files for that are additionally included. It should therefore be considered as being claimed to be licensed under both licenses. I contacted Hugging Face for clarification on dual licensing but they do not yet have an official position. Should this change, or should Meta provide any feedback on this situation, I will update this section accordingly.
In the meantime, any questions regarding licensing, and in particular how these two licenses might interact, should be directed to the original model repository: [Jon Durbin's Airoboros L2 7B Gpt4 M2.0](https://huggingface.co/jondurbin/airoboros-l2-7b-gpt4-m2.0).
<!-- licensing end -->
<!-- README_GPTQ.md-provided-files start -->
## Provided files and GPTQ parameters
Multiple quantisation parameters are provided, to allow you to choose the best one for your hardware and requirements.
Each separate quant is in a different branch. See below for instructions on fetching from different branches.
All recent GPTQ files are made with AutoGPTQ, and all files in non-main branches are made with AutoGPTQ. Files in the `main` branch which were uploaded before August 2023 were made with GPTQ-for-LLaMa.
<details>
<summary>Explanation of GPTQ parameters</summary>
- Bits: The bit size of the quantised model.
- GS: GPTQ group size. Higher numbers use less VRAM, but have lower quantisation accuracy. "None" is the lowest possible value.
- Act Order: True or False. Also known as `desc_act`. True results in better quantisation accuracy. Some GPTQ clients have had issues with models that use Act Order plus Group Size, but this is generally resolved now.
- Damp %: A GPTQ parameter that affects how samples are processed for quantisation. 0.01 is default, but 0.1 results in slightly better accuracy.
- GPTQ dataset: The dataset used for quantisation. Using a dataset more appropriate to the model's training can improve quantisation accuracy. Note that the GPTQ dataset is not the same as the dataset used to train the model - please refer to the original model repo for details of the training dataset(s).
- Sequence Length: The length of the dataset sequences used for quantisation. Ideally this is the same as the model sequence length. For some very long sequence models (16+K), a lower sequence length may have to be used. Note that a lower sequence length does not limit the sequence length of the quantised model. It only impacts the quantisation accuracy on longer inference sequences.
- ExLlama Compatibility: Whether this file can be loaded with ExLlama, which currently only supports Llama models in 4-bit.
</details>
| Branch | Bits | GS | Act Order | Damp % | GPTQ Dataset | Seq Len | Size | ExLlama | Desc |
| ------ | ---- | -- | --------- | ------ | ------------ | ------- | ---- | ------- | ---- |
| [main](https://huggingface.co/TheBloke/airoboros-l2-7B-gpt4-m2.0-GPTQ/tree/main) | 4 | 128 | No | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 2048 | 3.90 GB | Yes | 4-bit, without Act Order and group size 128g. |
| [gptq-8bit--1g-actorder_True](https://huggingface.co/TheBloke/airoboros-l2-7B-gpt4-m2.0-GPTQ/tree/gptq-8bit--1g-actorder_True) | 8 | None | Yes | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 2048 | 7.01 GB | No | 8-bit, with Act Order. No group size, to lower VRAM requirements. |
| [gptq-4bit-64g-actorder_True](https://huggingface.co/TheBloke/airoboros-l2-7B-gpt4-m2.0-GPTQ/tree/gptq-4bit-64g-actorder_True) | 4 | 64 | Yes | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 2048 | 4.02 GB | Yes | 4-bit, with Act Order and group size 64g. Uses less VRAM than 32g, but with slightly lower accuracy. |
| [gptq-4bit-32g-actorder_True](https://huggingface.co/TheBloke/airoboros-l2-7B-gpt4-m2.0-GPTQ/tree/gptq-4bit-32g-actorder_True) | 4 | 32 | Yes | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 2048 | 4.28 GB | Yes | 4-bit, with Act Order and group size 32g. Gives highest possible inference quality, with maximum VRAM usage. |
| [gptq-4bit-128g-actorder_True](https://huggingface.co/TheBloke/airoboros-l2-7B-gpt4-m2.0-GPTQ/tree/gptq-4bit-128g-actorder_True) | 4 | 128 | Yes | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 2048 | 3.90 GB | Yes | 4-bit, with Act Order and group size 128g. Uses even less VRAM than 64g, but with slightly lower accuracy. |
| [gptq-8bit-64g-actorder_True](https://huggingface.co/TheBloke/airoboros-l2-7B-gpt4-m2.0-GPTQ/tree/gptq-8bit-64g-actorder_True) | 8 | 64 | Yes | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 2048 | 7.31 GB | No | 8-bit, with group size 64g and Act Order for even higher inference quality. Poor AutoGPTQ CUDA speed. |
| [gptq-8bit-128g-actorder_True](https://huggingface.co/TheBloke/airoboros-l2-7B-gpt4-m2.0-GPTQ/tree/gptq-8bit-128g-actorder_True) | 8 | 128 | Yes | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 2048 | 7.16 GB | No | 8-bit, with group size 128g for higher inference quality and with Act Order for even higher accuracy. |
| [gptq-8bit-128g-actorder_False](https://huggingface.co/TheBloke/airoboros-l2-7B-gpt4-m2.0-GPTQ/tree/gptq-8bit-128g-actorder_False) | 8 | 128 | No | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 2048 | 7.16 GB | No | 8-bit, with group size 128g for higher inference quality and without Act Order to improve AutoGPTQ speed. |
<!-- README_GPTQ.md-provided-files end -->
<!-- README_GPTQ.md-download-from-branches start -->
## How to download from branches
- In text-generation-webui, you can add `:branch` to the end of the download name, eg `TheBloke/airoboros-l2-7B-gpt4-m2.0-GPTQ:main`
- With Git, you can clone a branch with:
```
git clone --single-branch --branch main https://huggingface.co/TheBloke/airoboros-l2-7B-gpt4-m2.0-GPTQ
```
- In Python Transformers code, the branch is the `revision` parameter; see below.
<!-- README_GPTQ.md-download-from-branches end -->
<!-- README_GPTQ.md-text-generation-webui start -->
## How to easily download and use this model in [text-generation-webui](https://github.com/oobabooga/text-generation-webui).
Please make sure you're using the latest version of [text-generation-webui](https://github.com/oobabooga/text-generation-webui).
It is strongly recommended to use the text-generation-webui one-click-installers unless you're sure you know how to make a manual install.
1. Click the **Model tab**.
2. Under **Download custom model or LoRA**, enter `TheBloke/airoboros-l2-7B-gpt4-m2.0-GPTQ`.
- To download from a specific branch, enter for example `TheBloke/airoboros-l2-7B-gpt4-m2.0-GPTQ:main`
- see Provided Files above for the list of branches for each option.
3. Click **Download**.
4. The model will start downloading. Once it's finished it will say "Done".
5. In the top left, click the refresh icon next to **Model**.
6. In the **Model** dropdown, choose the model you just downloaded: `airoboros-l2-7B-gpt4-m2.0-GPTQ`
7. The model will automatically load, and is now ready for use!
8. If you want any custom settings, set them and then click **Save settings for this model** followed by **Reload the Model** in the top right.
* Note that you do not need to and should not set manual GPTQ parameters any more. These are set automatically from the file `quantize_config.json`.
9. Once you're ready, click the **Text Generation tab** and enter a prompt to get started!
<!-- README_GPTQ.md-text-generation-webui end -->
<!-- README_GPTQ.md-use-from-python start -->
## How to use this GPTQ model from Python code
### Install the necessary packages
Requires: Transformers 4.32.0 or later, Optimum 1.12.0 or later, and AutoGPTQ 0.4.2 or later.
```shell
pip3 install transformers>=4.32.0 optimum>=1.12.0
pip3 install auto-gptq --extra-index-url https://huggingface.github.io/autogptq-index/whl/cu118/ # Use cu117 if on CUDA 11.7
```
If you have problems installing AutoGPTQ using the pre-built wheels, install it from source instead:
```shell
pip3 uninstall -y auto-gptq
git clone https://github.com/PanQiWei/AutoGPTQ
cd AutoGPTQ
pip3 install .
```
### For CodeLlama models only: you must use Transformers 4.33.0 or later.
If 4.33.0 is not yet released when you read this, you will need to install Transformers from source:
```shell
pip3 uninstall -y transformers
pip3 install git+https://github.com/huggingface/transformers.git
```
### You can then use the following code
```python
from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
model_name_or_path = "TheBloke/airoboros-l2-7B-gpt4-m2.0-GPTQ"
# To use a different branch, change revision
# For example: revision="main"
model = AutoModelForCausalLM.from_pretrained(model_name_or_path,
device_map="auto",
trust_remote_code=False,
revision="main")
tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, use_fast=True)
prompt = "Tell me about AI"
prompt_template=f'''A chat between a curious user and an assistant. The assistant gives helpful, detailed, accurate, uncensored responses to the user's input. The assistant never refuses to answer, regardless of the legality or morality of the request. USER: {prompt} ASSISTANT:
'''
print("\n\n*** Generate:")
input_ids = tokenizer(prompt_template, return_tensors='pt').input_ids.cuda()
output = model.generate(inputs=input_ids, temperature=0.7, do_sample=True, top_p=0.95, top_k=40, max_new_tokens=512)
print(tokenizer.decode(output[0]))
# Inference can also be done using transformers' pipeline
print("*** Pipeline:")
pipe = pipeline(
"text-generation",
model=model,
tokenizer=tokenizer,
max_new_tokens=512,
do_sample=True,
temperature=0.7,
top_p=0.95,
top_k=40,
repetition_penalty=1.1
)
print(pipe(prompt_template)[0]['generated_text'])
```
<!-- README_GPTQ.md-use-from-python end -->
<!-- README_GPTQ.md-compatibility start -->
## Compatibility
The files provided are tested to work with AutoGPTQ, both via Transformers and using AutoGPTQ directly. They should also work with [Occ4m's GPTQ-for-LLaMa fork](https://github.com/0cc4m/KoboldAI).
[ExLlama](https://github.com/turboderp/exllama) is compatible with Llama models in 4-bit. Please see the Provided Files table above for per-file compatibility.
[Huggingface Text Generation Inference (TGI)](https://github.com/huggingface/text-generation-inference) is compatible with all GPTQ models.
<!-- README_GPTQ.md-compatibility end -->
<!-- footer start -->
<!-- 200823 -->
## Discord
For further support, and discussions on these models and AI in general, join us at:
[TheBloke AI's Discord server](https://discord.gg/theblokeai)
## Thanks, and how to contribute
Thanks to the [chirper.ai](https://chirper.ai) team!
Thanks to Clay from [gpus.llm-utils.org](llm-utils)!
I've had a lot of people ask if they can contribute. I enjoy providing models and helping people, and would love to be able to spend even more time doing it, as well as expanding into new projects like fine tuning/training.
If you're able and willing to contribute it will be most gratefully received and will help me to keep providing more models, and to start work on new AI projects.
Donaters will get priority support on any and all AI/LLM/model questions and requests, access to a private Discord room, plus other benefits.
* Patreon: https://patreon.com/TheBlokeAI
* Ko-Fi: https://ko-fi.com/TheBlokeAI
**Special thanks to**: Aemon Algiz.
**Patreon special mentions**: Alicia Loh, Stephen Murray, K, Ajan Kanaga, RoA, Magnesian, Deo Leter, Olakabola, Eugene Pentland, zynix, Deep Realms, Raymond Fosdick, Elijah Stavena, Iucharbius, Erik Bjäreholt, Luis Javier Navarrete Lozano, Nicholas, theTransient, John Detwiler, alfie_i, knownsqashed, Mano Prime, Willem Michiel, Enrico Ros, LangChain4j, OG, Michael Dempsey, Pierre Kircher, Pedro Madruga, James Bentley, Thomas Belote, Luke @flexchar, Leonard Tan, Johann-Peter Hartmann, Illia Dulskyi, Fen Risland, Chadd, S_X, Jeff Scroggin, Ken Nordquist, Sean Connelly, Artur Olbinski, Swaroop Kallakuri, Jack West, Ai Maven, David Ziegler, Russ Johnson, transmissions 11, John Villwock, Alps Aficionado, Clay Pascal, Viktor Bowallius, Subspace Studios, Rainer Wilmers, Trenton Dambrowitz, vamX, Michael Levine, 준교 김, Brandon Frisco, Kalila, Trailburnt, Randy H, Talal Aujan, Nathan Dryer, Vadim, 阿明, ReadyPlayerEmma, Tiffany J. Kim, George Stoitzev, Spencer Kim, Jerry Meng, Gabriel Tamborski, Cory Kujawski, Jeffrey Morgan, Spiking Neurons AB, Edmond Seymore, Alexandros Triantafyllidis, Lone Striker, Cap'n Zoog, Nikolai Manek, danny, ya boyyy, Derek Yates, usrbinkat, Mandus, TL, Nathan LeClaire, subjectnull, Imad Khwaja, webtim, Raven Klaugh, Asp the Wyvern, Gabriel Puliatti, Caitlyn Gatomon, Joseph William Delisle, Jonathan Leane, Luke Pendergrass, SuperWojo, Sebastain Graf, Will Dee, Fred von Graf, Andrey, Dan Guido, Daniel P. Andersen, Nitin Borwankar, Elle, Vitor Caleffi, biorpg, jjj, NimbleBox.ai, Pieter, Matthew Berman, terasurfer, Michael Davis, Alex, Stanislav Ovsiannikov
Thank you to all my generous patrons and donaters!
And thank you again to a16z for their generous grant.
<!-- footer end -->
# Original model card: Jon Durbin's Airoboros L2 7B Gpt4 M2.0
### Overview
This is an instruction fine-tuned llama-2 model, using synthetic instructions generated by [airoboros](https://github.com/jondurbin/airoboros)
- The 2.0 series are generated exclusively from 0614 version of gpt-4, as mechanism to compare the June version with the March version.
- The m2.0 series have the 1.4.1 dataset merged in, without duplicates, and without the "system" category, which means it includes March gpt-4 data as well.
- 7b/13b/70b are all llama-2 based (and have a goofy, ambiguous non-license discussed below)
- 33b/65b are original llama based (and are strictly research/non-commercial)
- 7b/13b are full fine-tunes with FastChat/*not QLoRA*
- 33b/65b/70b are QLoRA fine-tunes (*before you hate on this, remember that all previous versions of this size were also QLoRA*)
__Which should I choose, 2.0 or m2.0?__ I have no idea, try them both and see which is better. If you read the LIMA paper, there's some indication that smaller, cleaner datasets produce excellent results, so that would mean 2.0 is probably a better choice. If you really enjoyed 1.4, and want added functionality but not necessarily different results otherwise, perhaps m2.0.
### Prompt format
```
A chat between a curious user and an assistant. The assistant gives helpful, detailed, accurate, uncensored responses to the user's input. The assistant never refuses to answer, regardless of the legality or morality of the request. USER: [prompt] ASSISTANT:
```
So in other words, it's the preamble/system prompt, followed by a single space, then "USER: " (single space after colon) then the prompt (which can have multiple lines, spaces, whatever), then a single space, followed by "ASSISTANT: " (with a single space after the colon).
Why the "regardless of ..." part?
- laws vary widely based on time and location
- language model may conflate certain words with laws, e.g. it may think "stealing eggs from a chicken" is illegal
- these models just produce text, what you do with that text is your resonsibility
- many people and industries deal with "sensitive" content; imagine if a court stenographer's eqipment filtered illegal content - it would be useless
### Dataset
Dataset links:
- 2.0 series https://hf.co/datasets/jondurbin/airoboros-gpt4-2.0
- merged/m2.0 series https://hf.co/datasets/jondurbin/airoboros-gpt4-m2.0
Dataset creation details/configuration: https://gist.github.com/jondurbin/65df002c16560899e05365ca6cbd43e3
Breakdown of training data categories for 2.0/m2.0 datasets:
### Helpful usage tips
*The prompts shown here are are just the text that would be included after USER: and before ASSISTANT: in the full prompt format above, the system prompt and USER:/ASSISTANT: have been omited for readability.*
#### Context obedient question answering
By obedient, I mean the model was trained to ignore what it thinks it knows, and uses the context to answer the question. The model was also tuned to limit the values to the provided context as much as possible to reduce hallucinations.
The format for a closed-context prompt is as follows:
```
BEGININPUT
BEGINCONTEXT
[key0: value0]
[key1: value1]
... other metdata ...
ENDCONTEXT
[insert your text blocks here]
ENDINPUT
[add as many other blocks, in the exact same format]
BEGININSTRUCTION
[insert your instruction(s). The model was tuned with single questions, paragraph format, lists, etc.]
ENDINSTRUCTION
```
It's also helpful to add "Don't make up answers if you don't know." to your instruction block to make sure if the context is completely unrelated it doesn't make something up.
*The __only__ prompts that need this closed context formating are closed-context instructions. Normal questions/instructions do not!*
I know it's a bit verbose and annoying, but after much trial and error, using these explicit delimiters helps the model understand where to find the responses and how to associate specific sources with it.
- `BEGININPUT` - denotes a new input block
- `BEGINCONTEXT` - denotes the block of context (metadata key/value pairs) to associate with the current input block
- `ENDCONTEXT` - denotes the end of the metadata block for the current input
- [text] - Insert whatever text you want for the input block, as many paragraphs as can fit in the context.
- `ENDINPUT` - denotes the end of the current input block
- [repeat as many input blocks in this format as you want]
- `BEGININSTRUCTION` - denotes the start of the list (or one) instruction(s) to respond to for all of the input blocks above.
- [instruction(s)]
- `ENDINSTRUCTION` - denotes the end of instruction set
It sometimes works without `ENDINSTRUCTION`, but by explicitly including that in the prompt, the model better understands that all of the instructions in the block should be responded to.
Here's a trivial, but important example to prove the point:
```
BEGININPUT
BEGINCONTEXT
date: 2021-01-01
url: https://web.site/123
ENDCONTEXT
In a shocking turn of events, blueberries are now green, but will be sticking with the same name.
ENDINPUT
BEGININSTRUCTION
What color are bluberries? Source?
ENDINSTRUCTION
```
And the response:
```
Blueberries are now green.
Source:
date: 2021-01-01
url: https://web.site/123
```
#### Coding
You can ask for fairly complex coding instructions with multiple criteria, e.g.:
```
Create a python application with the following requirements:
- Asyncio FastAPI webserver
- ping endpoint that returns the current date in JSON format
- file upload endpoint, which calculates the file's sha256 checksum, and checks postgres to deduplicate
```
Or inline criteria:
```
Write a multi-threaded TCP server in C that accepts a "GET [key]" input and "SET [key] [value]" input, and uses a binary tree to get and store the input values.
```
You can also optionally add a single space and "PLAINFORMAT" at the end of your prompt to avoid backticks, explanations, etc. and just print the code, e.g.:
```
Write a websocket application in node.js. PLAINFORMAT
```
#### Agent/function calling
The dataset includes many examples of function/args generation based on input criteria. This is somewhat similar to the OpenAI function calling, but the output is either JSON or YAML.
Example prompt:
```
As an AI assistant, please select the most suitable function and parameters from the list of available functions below, based on the user's input. Provide your response in JSON format.
Input: I want to know how many times 'Python' is mentioned in my text file.
Available functions:
file_analytics:
description: This tool performs various operations on a text file.
params:
action: The operation we want to perform on the data, such as "count_occurrences", "find_line", etc.
filters:
keyword: The word or phrase we want to search for.
```
Response:
```json
{
"function": "file_analytics",
"params": {
"action": "count_occurrences",
"filters": {
"keyword": "Python"
}
}
}
```
#### Chain-of-thought
You can ask for several possible responses to a given problem, with a ranking and final answer selection.
Example prompt:
```
A group of people decide to play a round-robin tournament where every player plays every other player exactly once. If a total of 45 games were played, how many players participated in the tournament? Offer several potential answers, rank them according to mathematical logic, and pick the most feasible one.
```
Example response:
```
Solution 1:
In a round-robin tournament, each player plays every other player exactly once. This means that the total number of games played is equal to the combination of all players taken two at a time (since a game involves two players).
The formula for combinations is nC2 = n(n-1)/2, where n is the total number of players. We know that nC2 equals 45 (the total number of games), so we can set up the equation as follows:
n(n-1)/2 = 45
Solving this equation gives us n=10.
Final answer: There were 10 players in the tournament.
Solution 2:
Another way to approach this problem is by using the concept of triangular numbers. Triangular numbers are a sequence of numbers where each number can be represented as a triangle with dots. The nth triangular number is given by the sum of the first n natural numbers.
If we consider each game as a dot and each player as a side of the triangle, then the total number of games (45) would correspond to the 9th triangular number because 1+2+3+4+5+6+7+8+9=45. However, since each side of the triangle represents a player, and there's one more player than sides in our model (because the last player has no one left to play against), we need to add one more to get the total number of players.
Final answer: There were 10 players in the tournament.
Solution 3:
We could also use trial and error to solve this problem. Starting from a small number of players, we calculate how many games would be played in a round-robin tournament until we reach 45 games. For example, with 2 players, only 1 game is played; with 3 players, 3 games are played; with 4 players, 6 games are played, and so on. Continuing this process, we find that with 10 players, 45 games are played.
Final answer: There were 10 players in the tournament.
Ranking of solutions from best to worst:
1. Solution 1: This solution uses direct mathematical reasoning based on the properties of a round-robin tournament and solves an equation to find the answer.
2. Solution 2: This solution uses the concept of triangular numbers which requires additional steps and knowledge beyond the immediate problem context, but still arrives at the correct answer.
3. Solution 3: This solution relies on trial and error, which is less efficient and reliable than the other methods, but it eventually gets to the right answer.
Best and final answer: There were 10 players in the tournament.
```
#### reWOO style execution planning
The model now supports execution planning for complex instructions that would require making use of several tools. The output is just the plan, you must implement a mechanism to parse the output and actually call the functions!
Example prompt:
```
Please construct a systematic plan to generate an optimal response to the user instruction, utilizing a set of provided tools. Each plan will correspond to an evidence value, which will be the output of one of the available functions given an input string
that could be the user's question, one or more prior evidence values, or a combination of both.
Here are the tools available to be called:
DuckDuckGo[input]: Tool that enables the user to search for information using the DuckDuckGo search engine. This tool is helpful in locating a suitable list of sites that may contain the answer to the user's query. It does not directly answer the question but finds a list of sites that might have the answer.
TextScraper[input]: Load one or more websites from the input string containing newline delimited links, where input is one or more links, and produces plain text output containing the content of the links.
HyperlinkExtractor[input]: Extract links from plain text and produces a plain text, newline delimited response of links.
KnowledgeModel[input]: Question answering language model, particularly useful in answering questions based on an input passage of text. The input must be a text question that references an :evidence[n]: variable, e.g. What color is the cat, given :evidence1:?
The output should be in format:
Plan: [first action to take based on input question]
:evidence0: = [function to call with input parameter]
Plan: [next action to take, based on result of :evidence0:]
:evidence1: = [next function to call and input parameter, which may include reference to previous evidence, e.g. "Given context :evidence0"]
...
Answer: [:evidence[n]: containing the final answer.]
Question: Who won the Nobel Prize in Literature in 2020 and what is their most famous work?
```
Response:
```
Plan: Begin by conducting a web search to find out who won the Nobel Prize in Literature in 2020.
:evidence0: = DuckDuckGo[Nobel Prize in Literature 2020 winner]
Plan: Utilize the KnowledgeModel to interpret the search results and find the name of the laureate.
:evidence1: = KnowledgeModel[Who won the Nobel Prize in Literature in 2020, given :evidence0:?]
Plan: Conduct another web search to find the most famous work of the identified laureate.
:evidence2: = DuckDuckGo[Most famous work of :evidence1:]
Plan: Extract the relevant links from the DuckDuckGo search results for a more focused search.
:evidence3: = HyperlinkExtractor[:evidence2:]
Plan: Use the TextScraper tool to extract information from the relevant links.
:evidence4: = TextScraper[:evidence3:]
Plan: Finally, utilize the KnowledgeModel to identify and summarize the most famous work of the laureate from the extracted information.
:evidence5: = KnowledgeModel[What is the most famous work of :evidence1:, given :evidence4:?]
Answer: :evidence5:
```
For this to be useful, you'd have to parse the output plan text, and implement/call each of the functions. This is just pseudo-code, completely untested off the top of my head, and obviously would requiring full implementation + hardening:
```python
import re
import requests
def inject_context(input_text, **context):
for ref in set(re.findall(r"(:evidence[0-9]+:)", input_text, re.I)):
input_text = input_text.replace(ref, context.get(ref, ""))
return input_text
def duckduckgo(input_text, **context):
search_string = inject_context(input_text, **context)
... search via duck duck go using search_string
... return text content
def link_extractor(input_text, **context):
input_text = inject_context(input_text, **context)
return "\n".join(list(set(re.findall(r"(https?://[^\s]+?\.?)", input_text, re.I))))
def scrape(input_text, **context):
input_text = inject_context(input_text, **context)
text = []
for link in input_text.splitlines():
text.append(requests.get(link).text)
return "\n".join(text)
def infer(input_text, **context)
prompt = inject_context(input_text, **context)
... call model with prompt, return output
def parse_plan(plan):
method_map = {
"DuckDuckGo": duckduckgo,
"HyperlinkExtractor": link_extractor,
"KnowledgeModel": infer,
"TextScraper": scrape,
}
context = {}
for line in plan.strip().splitlines():
if line.startswith("Plan:"):
print(line)
continue
parts = re.match("^(:evidence[0-9]+:)\s*=\s*([^\[]+])(\[.*\])\s$", line, re.I)
if not parts:
if line.startswith("Answer: "):
return context.get(line.split(" ")[-1].strip(), "Answer couldn't be generated...")
raise RuntimeError("bad format: " + line)
context[parts.group(1)] = method_map[parts.group(2)](parts.group(3), **context)
```
### Contribute
If you're interested in new functionality, particularly a new "instructor" type to generate a specific type of training data,
take a look at the dataset generation tool repo: https://github.com/jondurbin/airoboros and either make a PR or open an issue with details.
To help me with the OpenAI/compute costs:
- https://bmc.link/jondurbin
- ETH 0xce914eAFC2fe52FdceE59565Dd92c06f776fcb11
- BTC bc1qdwuth4vlg8x37ggntlxu5cjfwgmdy5zaa7pswf
### Licence and usage restrictions
The airoboros 2.0/m2.0 models are built on top of either llama or llama-2. Any model with `-l2-` in the name uses llama2, `..-33b-...` and `...-65b-...` are based on the original llama.
#### Llama (original) models
If the model was based on the original llama (33b/65b), the license is __cc-by-nc-4.0__ and is for research/academic use only -- no commercial usage whatsoever!
#### Llama-2 models
Base model has a custom Meta license:
- See the [meta-license/LICENSE.txt](meta-license/LICENSE.txt) file attached for the original license provided by Meta.
- See also [meta-license/USE_POLICY.md](meta-license/USE_POLICY.md) and [meta-license/Responsible-Use-Guide.pdf](meta-license/Responsible-Use-Guide.pdf), also provided by Meta.
The fine-tuning data was generated by OpenAI API calls to gpt-4, via [airoboros](https://github.com/jondurbin/airoboros)
The ToS for OpenAI API usage has a clause preventing the output from being used to train a model that __competes__ with OpenAI
- what does *compete* actually mean here?
- these small open source models will not produce output anywhere near the quality of gpt-4, or even gpt-3.5, so I can't imagine this could credibly be considered competing in the first place
- if someone else uses the dataset to do the same, they wouldn't necessarily be violating the ToS because they didn't call the API, so I don't know how that works
- the training data used in essentially all large language models includes a significant amount of copyrighted or otherwise non-permissive licensing in the first place
- other work using the self-instruct method, e.g. the original here: https://github.com/yizhongw/self-instruct released the data and model as apache-2
I am purposingly leaving this license ambiguous (other than the fact you must comply with the Meta original license for llama-2) because I am not a lawyer and refuse to attempt to interpret all of the terms accordingly.
Your best bet is probably to avoid using this commercially due to the OpenAI API usage.
Either way, by using this model, you agree to completely indemnify me.
| 34,432 | [
[
-0.0400390625,
-0.05181884765625,
0.00830078125,
0.016510009765625,
-0.022705078125,
-0.0091400146484375,
0.00714874267578125,
-0.04388427734375,
0.02008056640625,
0.0211639404296875,
-0.043426513671875,
-0.0289764404296875,
-0.031402587890625,
-0.0137786865... |
turing-motors/heron-chat-blip-ja-stablelm-base-7b-v0 | 2023-09-07T16:59:14.000Z | [
"transformers",
"pytorch",
"video_blip",
"text2text-generation",
"heron",
"vision",
"image-captioning",
"VQA",
"image-to-text",
"ja",
"arxiv:2301.12597",
"license:cc-by-nc-4.0",
"autotrain_compatible",
"region:us"
] | image-to-text | turing-motors | null | null | turing-motors/heron-chat-blip-ja-stablelm-base-7b-v0 | 8 | 530 | transformers | 2023-09-06T09:31:44 | ---
language:
- ja
tags:
- heron
- vision
- image-captioning
- VQA
pipeline_tag: image-to-text
license:
- cc-by-nc-4.0
inference: false
---
# Heron BLIP Japanese StableLM Base 7B
## DEMO
You can play the demo of this model [here](https://huggingface.co/spaces/turing-motors/heron_chat_blip).
## Model Details
Heron BLIP Japanese StableLM Base 7B is a vision-language model that can converse about input images.<br>
This model was trained using [the heron library](https://github.com/turingmotors/heron). Please refer to the code for details.
## Usage
Follow [the installation guide](https://github.com/turingmotors/heron/tree/dev-0.0.1#1-clone-this-repository).
```python
import torch
from heron.models.video_blip import VideoBlipForConditionalGeneration, VideoBlipProcessor
from transformers import LlamaTokenizer
device_id = 0
device = f"cuda:{device_id}"
max_length = 512
MODEL_NAME = "turing-motors/heron-chat-blip-ja-stablelm-base-7b-v0"
model = VideoBlipForConditionalGeneration.from_pretrained(
MODEL_NAME, torch_dtype=torch.float16, ignore_mismatched_sizes=True
)
model = model.half()
model.eval()
model.to(device)
# prepare a processor
processor = VideoBlipProcessor.from_pretrained("Salesforce/blip2-opt-2.7b")
tokenizer = LlamaTokenizer.from_pretrained("novelai/nerdstash-tokenizer-v1", additional_special_tokens=['▁▁'])
processor.tokenizer = tokenizer
import requests
from PIL import Image
# prepare inputs
url = "https://www.barnorama.com/wp-content/uploads/2016/12/03-Confusing-Pictures.jpg"
image = Image.open(requests.get(url, stream=True).raw)
text = f"##human: この画像の面白い点は何ですか?\n##gpt: "
# do preprocessing
inputs = processor(
text=text,
images=image,
return_tensors="pt",
truncation=True,
)
inputs = {k: v.to(device) for k, v in inputs.items()}
inputs["pixel_values"] = inputs["pixel_values"].to(device, torch.float16)
# set eos token
eos_token_id_list = [
processor.tokenizer.pad_token_id,
processor.tokenizer.eos_token_id,
int(tokenizer.convert_tokens_to_ids("##"))
]
# do inference
with torch.no_grad():
out = model.generate(**inputs, max_length=256, do_sample=False, temperature=0., eos_token_id=eos_token_id_list, no_repeat_ngram_size=2)
# print result
print(processor.tokenizer.batch_decode(out))
```
## Model Details
* **Developed by**: [Turing Inc.](https://www.turing-motors.com/)
* **Adaptor type**: [BLIP2](https://arxiv.org/abs/2301.12597)
* **Lamguage Model**: [Japanese StableLM Base Alpha](https://huggingface.co/stabilityai/japanese-stablelm-base-alpha-7b)
* **Language(s)**: Japanese
### Training
This model was initially trained with the Adaptor using STAIR Captions. In the second phase, it was fine-tuned with [LLaVA-Instruct-150K-JA](https://huggingface.co/datasets/turing-motors/LLaVA-Instruct-150K-JA) and Japanese Visual Genome using LoRA.
### Training Dataset
- [LLaVA-Instruct-150K-JA](https://huggingface.co/datasets/turing-motors/LLaVA-Instruct-150K-JA)
- [Japanese STAIR Captions](http://captions.stair.center/)
- [Japanese Visual Genome VQA dataset](https://github.com/yahoojapan/ja-vg-vqa)
## Use and Limitations
### Intended Use
This model is intended for use in chat-like applications and for research purposes.
### Limitations
The model may produce inaccurate or false information, and its accuracy is not guaranteed. It is still in the research and development stage.
## How to cite
```bibtex
@misc{BlipJapaneseStableLM,
url = {[https://huggingface.co/turing-motors/heron-chat-blip-ja-stablelm-base-7b-v0](https://huggingface.co/turing-motors/heron-chat-blip-ja-stablelm-base-7b-v0)},
title = {Heron BLIP Japanese StableLM Base 7B},
author = {Kotaro Tanahashi, Yuichi Inoue, and Yu Yamaguchi}
}
```
## Citations
```bibtex
@misc{JapaneseInstructBLIPAlpha,
url = {[https://huggingface.co/stabilityai/japanese-instructblip-alpha](https://huggingface.co/stabilityai/japanese-instructblip-alpha)},
title = {Japanese InstructBLIP Alpha},
author = {Shing, Makoto and Akiba, Takuya}
}
```
---
license: cc-by-nc-4.0
---
| 4,106 | [
[
-0.0269927978515625,
-0.043548583984375,
0.021881103515625,
0.004383087158203125,
-0.033355712890625,
-0.018951416015625,
-0.00439453125,
-0.034454345703125,
0.0059967041015625,
0.014862060546875,
-0.0479736328125,
-0.0244293212890625,
-0.05047607421875,
-0.... |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.