Instructions to use 0Tick/e621TagAutocomplete with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use 0Tick/e621TagAutocomplete with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="0Tick/e621TagAutocomplete")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("0Tick/e621TagAutocomplete")
model = AutoModelForCausalLM.from_pretrained("0Tick/e621TagAutocomplete")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use 0Tick/e621TagAutocomplete with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "0Tick/e621TagAutocomplete"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "0Tick/e621TagAutocomplete",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/0Tick/e621TagAutocomplete

SGLang

How to use 0Tick/e621TagAutocomplete with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "0Tick/e621TagAutocomplete" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "0Tick/e621TagAutocomplete",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "0Tick/e621TagAutocomplete" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "0Tick/e621TagAutocomplete",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use 0Tick/e621TagAutocomplete with Docker Model Runner:
```
docker model run hf.co/0Tick/e621TagAutocomplete
```

0Tick commited on Jun 7, 2023

Commit

7897c96

1 Parent(s): 75fc7c6

Trained with tags scrambled

Browse files

This is a new version of the model where the tags of each image were scrambled before training so it should have better completion features.

Files changed (7) hide show

config.json +1 -1
merges.txt +1 -1
pytorch_model.bin +2 -2
runs/Jun07_18-24-50_86e9400747d2/events.out.tfevents.1686162358.86e9400747d2.1933.0 +3 -0
runs/Jun07_18-24-50_86e9400747d2/events.out.tfevents.1686172708.86e9400747d2.1933.1 +3 -0
tokenizer.json +1 -0
tokenizer_config.json +1 -1

config.json CHANGED Viewed

@@ -40,7 +40,7 @@
     }
   },
   "torch_dtype": "float32",
-  "transformers_version": "4.27.0.dev0",
   "use_cache": true,
   "vocab_size": 50257
 }

     }
   },
   "torch_dtype": "float32",
+  "transformers_version": "4.30.0.dev0",
   "use_cache": true,
   "vocab_size": 50257
 }

merges.txt CHANGED Viewed

@@ -1,4 +1,4 @@
-#version: 0.2 - Trained by `huggingface/tokenizers`
 Ġ t
 Ġ a
 h e

+#version: 0.2
 Ġ t
 Ġ a
 h e

pytorch_model.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c5230f37a0f613c037dd8acdb4372be3eca15a188cde085e54f42f209e30695
-size 333970169

 version https://git-lfs.github.com/spec/v1
+oid sha256:794383dd0da7fc82de3d9453c8fa0731a3a9b2bc355fefa67329dd49b4b89db3
+size 327674773

runs/Jun07_18-24-50_86e9400747d2/events.out.tfevents.1686162358.86e9400747d2.1933.0 ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:9346d9e5048369d1962f2420f8d29b047e92d85be1e9b713bdd0faee2e16979b
+size 7088

runs/Jun07_18-24-50_86e9400747d2/events.out.tfevents.1686172708.86e9400747d2.1933.1 ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:c09a9b1deba394ba794c59b8e8b88c1e5925b183d33c2e1a1ce581a9eac369bb
+size 411

tokenizer.json CHANGED Viewed

@@ -39,6 +39,7 @@
     "continuing_subword_prefix": "",
     "end_of_word_suffix": "",
     "fuse_unk": false,
     "vocab": {
       "!": 0,
       "\"": 1,

     "continuing_subword_prefix": "",
     "end_of_word_suffix": "",
     "fuse_unk": false,
+    "byte_fallback": false,
     "vocab": {
       "!": 0,
       "\"": 1,

tokenizer_config.json CHANGED Viewed

@@ -1,9 +1,9 @@
 {
   "add_prefix_space": false,
   "bos_token": "<|endoftext|>",
   "eos_token": "<|endoftext|>",
   "model_max_length": 1024,
-  "special_tokens_map_file": null,
   "tokenizer_class": "GPT2Tokenizer",
   "unk_token": "<|endoftext|>"
 }

 {
   "add_prefix_space": false,
   "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
   "eos_token": "<|endoftext|>",
   "model_max_length": 1024,
   "tokenizer_class": "GPT2Tokenizer",
   "unk_token": "<|endoftext|>"
 }