meditron-7b-chat/README.md

language, license, tags, datasets, base_model, model-index

language	license	tags	datasets	base_model	model-index
en	llama2	Medicine	yahma/alpaca-cleaned	epfl-llm/meditron-7b	name results meditron-7b-chat task dataset metrics source type name text-generation Text Generation name type config split args AI2 Reasoning Challenge (25-Shot) ai2_arc ARC-Challenge test num_few_shot 25 type value name acc_norm 50.77 normalized accuracy url name https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=malhajar/meditron-7b-chat Open LLM Leaderboard task dataset metrics source type name text-generation Text Generation name type split args HellaSwag (10-Shot) hellaswag validation num_few_shot 10 type value name acc_norm 75.37 normalized accuracy url name https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=malhajar/meditron-7b-chat Open LLM Leaderboard task dataset metrics source type name text-generation Text Generation name type config split args MMLU (5-Shot) cais/mmlu all test num_few_shot 5 type value name acc 40.49 accuracy url name https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=malhajar/meditron-7b-chat Open LLM Leaderboard task dataset metrics source type name text-generation Text Generation name type config split args TruthfulQA (0-shot) truthful_qa multiple_choice validation num_few_shot 0 type value mc2 48.56 url name https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=malhajar/meditron-7b-chat Open LLM Leaderboard task dataset metrics source type name text-generation Text Generation name type config split args Winogrande (5-shot) winogrande winogrande_xl validation num_few_shot 5 type value name acc 73.16 accuracy url name https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=malhajar/meditron-7b-chat Open LLM Leaderboard task dataset metrics source type name text-generation Text Generation name type config split args GSM8k (5-shot) gsm8k main test num_few_shot 5 type value name acc 9.17 accuracy url name https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=malhajar/meditron-7b-chat Open LLM Leaderboard

Model Card for Model ID

meditron-7b-chat is a finetuned version of epfl-llm/meditron-7b using SFT Training on the Alpaca Dataset. This model can answer information about different excplicit ideas in medicine (see epfl-llm/meditron-7b for more info)

Model Description

• Finetuned by: Mohamad Alhajar
• Language(s) (NLP): English
• Finetuned from model: epfl-llm/meditron-7b

Prompt Template

### Instruction:

<prompt> (without the <>)

### Response:

How to Get Started with the Model

Use the code sample provided in the original post to interact with the model.

from transformers import AutoTokenizer,AutoModelForCausalLM
 
model_id = "malhajar/meditron-7b-chat"
model = AutoModelForCausalLM.from_pretrained(model_name_or_path,
                                             device_map="auto",
                                             torch_dtype=torch.float16,
                                             revision="main")

tokenizer = AutoTokenizer.from_pretrained(model_id)

question: "what is tract infection?"
# For generating a response
prompt = '''
### Instruction:
{question} 

### Response:'''
input_ids = tokenizer(prompt, return_tensors="pt").input_ids
output = model.generate(inputs=input_ids,max_new_tokens=512,pad_token_id=tokenizer.eos_token_id,top_k=50, do_sample=True,
        top_p=0.95)
response = tokenizer.decode(output[0])

print(response)

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	49.59
AI2 Reasoning Challenge (25-Shot)	50.77
HellaSwag (10-Shot)	75.37
MMLU (5-Shot)	40.49
TruthfulQA (0-shot)	48.56
Winogrande (5-shot)	73.16
GSM8k (5-shot)	9.17