Remove leftovers

.gitattributes

@@ -33,3 +33,11 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+pytorch_model-00006-of-00007.bin filter=lfs diff=lfs merge=lfs -text
+pytorch_model-00007-of-00007.bin filter=lfs diff=lfs merge=lfs -text
+pytorch_model.bin.index.json filter=lfs diff=lfs merge=lfs -text
+pytorch_model-00001-of-00007.bin filter=lfs diff=lfs merge=lfs -text
+pytorch_model-00002-of-00007.bin filter=lfs diff=lfs merge=lfs -text
+pytorch_model-00003-of-00007.bin filter=lfs diff=lfs merge=lfs -text
+pytorch_model-00004-of-00007.bin filter=lfs diff=lfs merge=lfs -text
+pytorch_model-00005-of-00007.bin filter=lfs diff=lfs merge=lfs -text

4.8/README.md

@@ -1,115 +0,0 @@
----
-license: llama2
-model-index:
-- name: Phind-CodeLlama-34B-v1
-  results:
-  - task:
-      type: text-generation
-    dataset:
-      type: openai_humaneval
-      name: HumanEval
-    metrics:
-    - name: pass@1
-      type: pass@1
-      value: 73.8%
-      verified: false
-tags:
-- code llama
----
-
-# **Phind-CodeLlama-34B-v2**
-We've fine-tuned Phind-CodeLlama-34B-v1 on an additional 1.5B tokens high-quality programming-related data, achieving **73.8% pass@1** on HumanEval. It's the current state-of-the-art amongst open-source models.
-
-Furthermore, this model is **instruction-tuned** on the Alpaca/Vicuna format to be steerable and easy-to-use.
-
-More details can be found on our [blog post](https://www.phind.com/blog/code-llama-beats-gpt4).
-
-## Model Details
-This model is fine-tuned from Phind-CodeLlama-34B-v1 and achieves **73.8% pass@1** on HumanEval.
-
-Phind-CodeLlama-34B-v2 is **multi-lingual** and is proficient in Python, C/C++, TypeScript, Java, and more.
-
-## Dataset Details
-We fined-tuned on a proprietary dataset of 1.5B tokens of high quality programming problems and solutions. This dataset consists of instruction-answer pairs instead of code completion examples, making it structurally different from HumanEval. LoRA was not used -- both models are a native finetune. We used DeepSpeed ZeRO 3 and Flash Attention 2 to train these models in 15 hours on 32 A100-80GB GPUs. We used a sequence length of 4096 tokens.
-
-## How to Get Started with the Model
-
-Make sure to install Transformers from the main git branch:
-
-```bash
-pip install git+https://github.com/huggingface/transformers.git
-```
-
-## How to Prompt the Model
-This model accepts the Alpaca/Vicuna instruction format.
-
-For example: 
-
-```
-### System Prompt
-You are an intelligent programming assistant.
-
-### User Message
-Implement a linked list in C++
-
-### Assistant
-...
-```
-
-## How to reproduce HumanEval Results
-
-To reproduce our results:
-
-```python
-
-from transformers import AutoTokenizer, LlamaForCausalLM
-from human_eval.data import write_jsonl, read_problems
-from tqdm import tqdm
-
-# initialize the model
-
-model_path = "Phind/Phind-CodeLlama-34B-v2"
-model = LlamaForCausalLM.from_pretrained(model_path, device_map="auto")
-tokenizer = AutoTokenizer.from_pretrained(model_path)
-
-# HumanEval helper
-
-def generate_one_completion(prompt: str):
-    tokenizer.pad_token = tokenizer.eos_token
-    inputs = tokenizer(prompt, return_tensors="pt", truncation=True, max_length=4096)
-
-    # Generate
-    generate_ids = model.generate(inputs.input_ids.to("cuda"), max_new_tokens=384, do_sample=True, top_p=0.75, top_k=40, temperature=0.1)
-    completion = tokenizer.batch_decode(generate_ids, skip_special_tokens=True, clean_up_tokenization_spaces=False)[0]
-    completion = completion.replace(prompt, "").split("\n\n\n")[0]
-
-    return completion
-
-# perform HumanEval
-problems = read_problems()
-
-num_samples_per_task = 1
-samples = [
-    dict(task_id=task_id, completion=generate_one_completion(problems[task_id]["prompt"]))
-    for task_id in tqdm(problems)
-    for _ in range(num_samples_per_task)
-]
-write_jsonl("samples.jsonl", samples)
-
-# run `evaluate_functional_correctness samples.jsonl` in your HumanEval code sandbox
-```
-
-## Bias, Risks, and Limitations
-
-<!-- This section is meant to convey both technical and sociotechnical limitations. -->
-This model has undergone very limited testing. Additional safety testing should be performed before any real-world deployments.
-
-
-## Training details
-
-<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
-
-- **Hardware Type:** 32x A100-80GB
-- **Hours used:** 480 GPU-hours
-- **Cloud Provider:** AWS
-- **Compute Region:** us-east-1

4.8/config.json

@@ -1,26 +0,0 @@
-{
-  "_name_or_path": "/fsx/Phind-CodeLlama-34B-v1",
-  "architectures": [
-    "LlamaForCausalLM"
-  ],
-  "bos_token_id": 1,
-  "eos_token_id": 2,
-  "hidden_act": "silu",
-  "hidden_size": 8192,
-  "initializer_range": 0.02,
-  "intermediate_size": 22016,
-  "max_position_embeddings": 16384,
-  "model_type": "llama",
-  "num_attention_heads": 64,
-  "num_hidden_layers": 48,
-  "num_key_value_heads": 8,
-  "pretraining_tp": 1,
-  "rms_norm_eps": 1e-05,
-  "rope_scaling": null,
-  "rope_theta": 1000000,
-  "tie_word_embeddings": false,
-  "torch_dtype": "bfloat16",
-  "transformers_version": "4.33.0.dev0",
-  "use_cache": true,
-  "vocab_size": 32000
-}

4.8/generation_config.json

@@ -1,6 +0,0 @@
-{
-  "_from_model_config": true,
-  "bos_token_id": 1,
-  "eos_token_id": 2,
-  "transformers_version": "4.33.0.dev0"
-}

4.8/special_tokens_map.json

@@ -1,24 +0,0 @@
-{
-  "bos_token": {
-    "content": "<s>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
-  "eos_token": {
-    "content": "</s>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
-  "pad_token": "</s>",
-  "unk_token": {
-    "content": "<unk>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  }
-}

4.8/tokenizer.model

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
-size 499723

4.8/tokenizer_config.json

@@ -1,37 +0,0 @@
-{
-  "add_bos_token": true,
-  "add_eos_token": false,
-  "bos_token": {
-    "__type": "AddedToken",
-    "content": "<s>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
-  "clean_up_tokenization_spaces": false,
-  "eos_token": {
-    "__type": "AddedToken",
-    "content": "</s>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
-  "legacy": null,
-  "model_max_length": 4096,
-  "pad_token": null,
-  "padding_side": "right",
-  "sp_model_kwargs": {},
-  "spaces_between_special_tokens": false,
-  "tokenizer_class": "LlamaTokenizer",
-  "unk_token": {
-    "__type": "AddedToken",
-    "content": "<unk>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
-  "use_default_system_prompt": true
-}