|
--- |
|
library_name: peft |
|
base_model: mistralai/Mixtral-8x7B-Instruct-v0.1 |
|
datasets: |
|
- ruslanmv/ai-medical-chatbot |
|
--- |
|
|
|
# Model Card for Medical-Mixtral-7B-v1.5k |
|
|
|
## Model Details |
|
|
|
### Model Description |
|
|
|
The Medical-Mixtral-7B-v1.5k is a fine-tuned Mixtral model for answering medical assistance questions. This model is a novel version of mistralai/Mixtral-8x7B-Instruct-v0.1, adapted to a subset of 1.5k records from the AI Medical Chatbot dataset, which contains 250k records. The purpose of this model is to provide a ready chatbot to answer questions related to medical assistance. |
|
|
|
### Model Sources [optional] |
|
|
|
## How to Get Started with the Model |
|
|
|
Use the code below to get started with the model. |
|
|
|
```python |
|
from transformers import AutoModelForCausalLM, AutoTokenizer |
|
|
|
# Define the name of your fine-tuned model |
|
finetuned_model = 'ruslanmv/Medical-Mixtral-7B-v1.5k' |
|
|
|
# Load tokenizer |
|
tokenizer = AutoTokenizer.from_pretrained(finetuned_model, trust_remote_code=True) |
|
|
|
# Load the model with the provided adapter configuration and weights |
|
model_pretrained = AutoModelForCausalLM.from_pretrained(finetuned_model, trust_remote_code=True, torch_dtype=torch.float16) |
|
|
|
messages = [ |
|
{'role': 'user', 'content': 'What should I do to reduce my weight gained due to genetic hypothyroidism?'}, |
|
{'role': 'assistant', 'content': ''}, |
|
] |
|
|
|
input_ids = tokenizer.apply_chat_template(messages, return_tensors='pt').to('cuda') |
|
|
|
outputs = model_pretrained.generate(input_ids, max_new_tokens=500) |
|
print(tokenizer.decode(outputs[0], skip_special_tokens=True)) |
|
``` |
|
|
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.10.0 |
|
|
|
|
|
Please fill in the missing parts with the relevant information for your model. Let me know if you need further assistance! |
