malhajar/phi-2-meditron-GGUF

Quantized GGUF model files for phi-2-meditron from malhajar

Name	Quant method	Size
phi-2-meditron.fp16.gguf	fp16	5.56 GB
phi-2-meditron.q2_k.gguf	q2_k	1.17 GB
phi-2-meditron.q3_k_m.gguf	q3_k_m	1.48 GB
phi-2-meditron.q4_k_m.gguf	q4_k_m	1.79 GB
phi-2-meditron.q5_k_m.gguf	q5_k_m	2.07 GB
phi-2-meditron.q6_k.gguf	q6_k	2.29 GB
phi-2-meditron.q8_0.gguf	q8_0	2.96 GB

Original Model Card:

Model Card for Model ID

phi-2-meditron is a finetuned version of epfl-llm/meditron-7b using SFT Training on the Meditron 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: microsoft/phi-2

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/phi-2-meditron"
model = AutoModelForCausalLM.from_pretrained(model_name_or_path,
                                             device_map="auto",
                                             torch_dtype=torch.float16,
                                              trust_remote_code= True,
                                             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)