--- language: - fr - en license: mit library_name: transformers tags: - french - chocolatine datasets: - jpacifico/french-orca-dpo-pairs-revised pipeline_tag: text-generation model-index: - name: Chocolatine-14B-Instruct-4k-DPO results: - task: type: text-generation name: Text Generation dataset: name: IFEval (0-Shot) type: HuggingFaceH4/ifeval args: num_few_shot: 0 metrics: - type: inst_level_strict_acc and prompt_level_strict_acc value: 46.89 name: strict accuracy source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=jpacifico/Chocolatine-14B-Instruct-4k-DPO name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: BBH (3-Shot) type: BBH args: num_few_shot: 3 metrics: - type: acc_norm value: 48.02 name: normalized accuracy source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=jpacifico/Chocolatine-14B-Instruct-4k-DPO name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: MATH Lvl 5 (4-Shot) type: hendrycks/competition_math args: num_few_shot: 4 metrics: - type: exact_match value: 14.88 name: exact match source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=jpacifico/Chocolatine-14B-Instruct-4k-DPO name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: GPQA (0-shot) type: Idavidrein/gpqa args: num_few_shot: 0 metrics: - type: acc_norm value: 12.19 name: acc_norm source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=jpacifico/Chocolatine-14B-Instruct-4k-DPO name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: MuSR (0-shot) type: TAUR-Lab/MuSR args: num_few_shot: 0 metrics: - type: acc_norm value: 15.15 name: acc_norm source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=jpacifico/Chocolatine-14B-Instruct-4k-DPO name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: MMLU-PRO (5-shot) type: TIGER-Lab/MMLU-Pro config: main split: test args: num_few_shot: 5 metrics: - type: acc value: 41.82 name: accuracy source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=jpacifico/Chocolatine-14B-Instruct-4k-DPO name: Open LLM Leaderboard --- ### Chocolatine-14B-Instruct-4k-DPO DPO fine-tuned of [microsoft/Phi-3-medium-4k-instruct](https://huggingface.co/microsoft/Phi-3-medium-4k-instruct) (14B params) using the [jpacifico/french-orca-dpo-pairs-revised](https://huggingface.co/datasets/jpacifico/french-orca-dpo-pairs-revised) rlhf dataset. Training in French also improves the model in English, surpassing the performances of its base model. Window context = 4k tokens ### Benchmarks Submitted on the [OpenLLM Leaderboard](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard) (aug 2024) Results coming soon. ### MT-Bench-French Chocolatine-14B-Instruct-4k-DPO is outperforming GPT-3.5-Turbo and Phi-3-medium-4k-instruct on [MT-Bench-French](https://huggingface.co/datasets/bofenghuang/mt-bench-french), used with [multilingual-mt-bench](https://github.com/Peter-Devine/multilingual_mt_bench) ``` ########## First turn ########## score model turn Chocolatine-14B-Instruct-4k-DPO 1 8.6375 Phi-3-medium-4k-instruct 1 8.2250 gpt-3.5-turbo 1 8.1375 Chocolatine-3B-Instruct-DPO-Revised 1 7.9875 Daredevil-8B 1 7.8875 Chocolatine-3B-Instruct-DPO-v1.0 1 7.6875 NeuralDaredevil-8B-abliterated 1 7.6250 Phi-3-mini-4k-instruct 1 7.2125 Meta-Llama-3-8B-Instruct 1 7.1625 vigostral-7b-chat 1 6.7875 Mistral-7B-Instruct-v0.3 1 6.7500 Mistral-7B-Instruct-v0.2 1 6.2875 ########## Second turn ########## score model turn Chocolatine-3B-Instruct-DPO-Revised 2 7.937500 Phi-3-medium-4k-instruct 2 7.750000 Chocolatine-14B-Instruct-4k-DPO 2 7.737500 gpt-3.5-turbo 2 7.679167 Chocolatine-3B-Instruct-DPO-v1.0 2 7.612500 NeuralDaredevil-8B-abliterated 2 7.125000 Daredevil-8B 2 7.087500 Meta-Llama-3-8B-Instruct 2 6.800000 Mistral-7B-Instruct-v0.2 2 6.512500 Mistral-7B-Instruct-v0.3 2 6.500000 Phi-3-mini-4k-instruct 2 6.487500 vigostral-7b-chat 2 6.162500 ########## Average ########## score model Chocolatine-14B-Instruct-4k-DPO 8.187500 Phi-3-medium-4k-instruct 7.987500 Chocolatine-3B-Instruct-DPO-Revised 7.962500 gpt-3.5-turbo 7.908333 Chocolatine-3B-Instruct-DPO-v1.0 7.650000 Daredevil-8B 7.487500 NeuralDaredevil-8B-abliterated 7.375000 Meta-Llama-3-8B-Instruct 6.981250 Phi-3-mini-4k-instruct 6.850000 Mistral-7B-Instruct-v0.3 6.625000 vigostral-7b-chat 6.475000 Mistral-7B-Instruct-v0.2 6.400000 ``` ### Usage You can run this model using my [Colab notebook](https://github.com/jpacifico/Chocolatine-LLM/blob/main/Chocolatine_14B_inference_test_colab.ipynb) You can also run Chocolatine using the following code: ```python import transformers from transformers import AutoTokenizer # Format prompt message = [ {"role": "system", "content": "You are a helpful assistant chatbot."}, {"role": "user", "content": "What is a Large Language Model?"} ] tokenizer = AutoTokenizer.from_pretrained(new_model) prompt = tokenizer.apply_chat_template(message, add_generation_prompt=True, tokenize=False) # Create pipeline pipeline = transformers.pipeline( "text-generation", model=new_model, tokenizer=tokenizer ) # Generate text sequences = pipeline( prompt, do_sample=True, temperature=0.7, top_p=0.9, num_return_sequences=1, max_length=200, ) print(sequences[0]['generated_text']) ``` ### Limitations The Chocolatine model is a quick demonstration that a base model can be easily fine-tuned to achieve compelling performance. It does not have any moderation mechanism. - **Developed by:** Jonathan Pacifico, 2024 - **Model type:** LLM - **Language(s) (NLP):** French, English - **License:** MIT # [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard) Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_jpacifico__Chocolatine-14B-Instruct-4k-DPO) | Metric |Value| |-------------------|----:| |Avg. |29.83| |IFEval (0-Shot) |46.89| |BBH (3-Shot) |48.02| |MATH Lvl 5 (4-Shot)|14.88| |GPQA (0-shot) |12.19| |MuSR (0-shot) |15.15| |MMLU-PRO (5-shot) |41.82|