--- license: apache-2.0 library_name: peft tags: - mistral datasets: - jondurbin/airoboros-2.2.1 inference: false pipeline_tag: text-generation base_model: mistralai/Mistral-7B-v0.1 ---
# Mistral-7B-Instruct-v0.1 A pretrained generative language model with 7 billion parameters geared towards instruction-following capabilities. ## Model Details This model was built via parameter-efficient finetuning of the [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) base model on the [jondurbin/airoboros-2.2.1](https://huggingface.co/datasets/jondurbin/airoboros-2.2.1) dataset. - **Developed by:** Daniel Furman - **Model type:** Causal language model (clm) - **Language(s) (NLP):** English - **License:** Apache 2.0 - **Finetuned from model:** [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) ## Evaluation Results | Metric | Value | |-----------------------|-------| | MMLU (5-shot) | Coming | | ARC (25-shot) | Coming | | HellaSwag (10-shot) | Coming | | TruthfulQA (0-shot) | Coming | | Avg. | Coming | We use Eleuther.AI's [Language Model Evaluation Harness](https://github.com/EleutherAI/lm-evaluation-harness) to run the benchmark tests above, the same version as Hugging Face's [Open LLM Leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard). ## Basic Usage
Setup ```python !pip install -q -U transformers peft torch accelerate einops sentencepiece ``` ```python import torch from peft import PeftModel, PeftConfig from transformers import ( AutoModelForCausalLM, AutoTokenizer, ) ``` ```python peft_model_id = "dfurman/Mistral-7B-Instruct-v0.1" config = PeftConfig.from_pretrained(peft_model_id) tokenizer = AutoTokenizer.from_pretrained( peft_model_id, use_fast=True, trust_remote_code=True, ) model = AutoModelForCausalLM.from_pretrained( config.base_model_name_or_path, torch_dtype=torch.float16, device_map="auto", trust_remote_code=True, ) model = PeftModel.from_pretrained( model, peft_model_id ) ```
```python messages = [ {"role": "user", "content": "Tell me a recipe for a mai tai."}, ] print("\n\n*** Prompt:") input_ids = tokenizer.apply_chat_template( messages, tokenize=True, return_tensors="pt", ) print(tokenizer.decode(input_ids[0])) ```
Prompt ```python " [INST] Tell me a recipe for a mai tai. [/INST]" ```
```python print("\n\n*** Generate:") with torch.autocast("cuda", dtype=torch.bfloat16): output = model.generate( input_ids=input_ids.cuda(), max_new_tokens=1024, do_sample=True, temperature=0.7, return_dict_in_generate=True, eos_token_id=tokenizer.eos_token_id, pad_token_id=tokenizer.pad_token_id, repetition_penalty=1.2, no_repeat_ngram_size=5, ) response = tokenizer.decode( output["sequences"][0][len(input_ids[0]):], skip_special_tokens=True ) print(response) ```
Generation ```python """1 oz light rum ½ oz dark rum ¼ oz orange curaçao 2 oz pineapple juice ¾ oz lime juice Dash of orgeat syrup (optional) Splash of grenadine (for garnish, optional) Lime wheel and cherry garnishes (optional) Shake all ingredients except the splash of grenadine in a cocktail shaker over ice. Strain into an old-fashioned glass filled with fresh ice cubes. Gently pour the splash of grenadine down the side of the glass so that it sinks to the bottom. Add garnishes as desired.""" ```
## Speeds, Sizes, Times | runtime / 50 tokens (sec) | GPU | dtype | VRAM (GB) | |:-----------------------------:|:---------------------:|:-------------:|:-----------------------:| | 3.21 | 1x A100 (40 GB SXM) | torch.bfloat16 | 16 | ## Training It took ~2 hours to train 2 epochs on 1x A100 (40 GB SXM). ### Prompt Format This model was finetuned with the following format: ```python tokenizer.chat_template = "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST] ' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token + ' ' }}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}" ``` This format is available as a [chat template](https://huggingface.co/docs/transformers/main/chat_templating) via the `apply_chat_template()` method. Here's an illustrative example: ```python messages = [ {"role": "user", "content": "Tell me a recipe for a mai tai."}, {"role": "assistant", "content": "1 oz light rum\n½ oz dark rum\n¼ oz orange curaçao\n2 oz pineapple juice\n¾ oz lime juice\nDash of orgeat syrup (optional)\nSplash of grenadine (for garnish, optional)\nLime wheel and cherry garnishes (optional)\n\nShake all ingredients except the splash of grenadine in a cocktail shaker over ice. Strain into an old-fashioned glass filled with fresh ice cubes. Gently pour the splash of grenadine down the side of the glass so that it sinks to the bottom. Add garnishes as desired."}, {"role": "user", "content": "How can I make it more upscale and luxurious?"}, ] print("\n\n*** Prompt:") input_ids = tokenizer.apply_chat_template( messages, tokenize=True, return_tensors="pt", ) print(tokenizer.decode(input_ids[0])) ```
Output ```python """ [INST] Tell me a recipe for a mai tai. [/INST] 1 oz light rum\n½ oz dark rum\n (...) Add garnishes as desired. [INST] How can I make it more upscale and luxurious? [/INST]""" ```
### Training Hyperparameters We use the [SFTTrainer](https://huggingface.co/docs/trl/main/en/sft_trainer) from `trl` to fine-tune LLMs on instruction-following datasets. See [here](https://github.com/daniel-furman/sft-demos/blob/main/src/sft/mistral/sft_Mistral_7B_Instruct_v0_1_peft.ipynb) for the finetuning code, which contains an exhaustive view of the hyperparameters employed. The following `TrainingArguments` config was used: - output_dir = "./results" - num_train_epochs = 3 - auto_find_batch_size = True - gradient_accumulation_steps = 1 - optim = "paged_adamw_32bit" - save_strategy = "epoch" - learning_rate = 3e-4 - lr_scheduler_type = "cosine" - warmup_ratio = 0.03 - logging_strategy = "steps" - logging_steps = 25 - evaluation_strategy = "epoch" - prediction_loss_only = True - bf16 = True The following `bitsandbytes` quantization config was used: - quant_method: bitsandbytes - load_in_8bit: False - load_in_4bit: True - llm_int8_threshold: 6.0 - llm_int8_skip_modules: None - llm_int8_enable_fp32_cpu_offload: False - llm_int8_has_fp16_weight: False - bnb_4bit_quant_type: nf4 - bnb_4bit_use_double_quant: False - bnb_4bit_compute_dtype: bfloat16 ## Model Card Contact dryanfurman at gmail ## Mistral Research Citation ``` @misc{jiang2023mistral, title={Mistral 7B}, author={Albert Q. Jiang and Alexandre Sablayrolles and Arthur Mensch and Chris Bamford and Devendra Singh Chaplot and Diego de las Casas and Florian Bressand and Gianna Lengyel and Guillaume Lample and Lucile Saulnier and Lélio Renard Lavaud and Marie-Anne Lachaux and Pierre Stock and Teven Le Scao and Thibaut Lavril and Thomas Wang and Timothée Lacroix and William El Sayed}, year={2023}, eprint={2310.06825}, archivePrefix={arXiv}, primaryClass={cs.CL} } ``` ## Framework versions - PEFT 0.6.3.dev0