Instructions to use MasterControlAIML/Qwen2.5-7b-Answer-Distractor-MCQ-Generation-merged-16bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use MasterControlAIML/Qwen2.5-7b-Answer-Distractor-MCQ-Generation-merged-16bit with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="MasterControlAIML/Qwen2.5-7b-Answer-Distractor-MCQ-Generation-merged-16bit")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("MasterControlAIML/Qwen2.5-7b-Answer-Distractor-MCQ-Generation-merged-16bit") model = AutoModelForCausalLM.from_pretrained("MasterControlAIML/Qwen2.5-7b-Answer-Distractor-MCQ-Generation-merged-16bit") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use MasterControlAIML/Qwen2.5-7b-Answer-Distractor-MCQ-Generation-merged-16bit with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "MasterControlAIML/Qwen2.5-7b-Answer-Distractor-MCQ-Generation-merged-16bit" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "MasterControlAIML/Qwen2.5-7b-Answer-Distractor-MCQ-Generation-merged-16bit", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/MasterControlAIML/Qwen2.5-7b-Answer-Distractor-MCQ-Generation-merged-16bit
- SGLang
How to use MasterControlAIML/Qwen2.5-7b-Answer-Distractor-MCQ-Generation-merged-16bit with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "MasterControlAIML/Qwen2.5-7b-Answer-Distractor-MCQ-Generation-merged-16bit" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "MasterControlAIML/Qwen2.5-7b-Answer-Distractor-MCQ-Generation-merged-16bit", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "MasterControlAIML/Qwen2.5-7b-Answer-Distractor-MCQ-Generation-merged-16bit" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "MasterControlAIML/Qwen2.5-7b-Answer-Distractor-MCQ-Generation-merged-16bit", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Unsloth Studio new
How to use MasterControlAIML/Qwen2.5-7b-Answer-Distractor-MCQ-Generation-merged-16bit with Unsloth Studio:
Install Unsloth Studio (macOS, Linux, WSL)
curl -fsSL https://unsloth.ai/install.sh | sh # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for MasterControlAIML/Qwen2.5-7b-Answer-Distractor-MCQ-Generation-merged-16bit to start chatting
Install Unsloth Studio (Windows)
irm https://unsloth.ai/install.ps1 | iex # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for MasterControlAIML/Qwen2.5-7b-Answer-Distractor-MCQ-Generation-merged-16bit to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for MasterControlAIML/Qwen2.5-7b-Answer-Distractor-MCQ-Generation-merged-16bit to start chatting
Load model with FastModel
pip install unsloth from unsloth import FastModel model, tokenizer = FastModel.from_pretrained( model_name="MasterControlAIML/Qwen2.5-7b-Answer-Distractor-MCQ-Generation-merged-16bit", max_seq_length=2048, ) - Docker Model Runner
How to use MasterControlAIML/Qwen2.5-7b-Answer-Distractor-MCQ-Generation-merged-16bit with Docker Model Runner:
docker model run hf.co/MasterControlAIML/Qwen2.5-7b-Answer-Distractor-MCQ-Generation-merged-16bit
Uploaded model
- Model Usage: Given a context paragraph and a question, generate answer option and three distractor options (total 4 mcqs)
- Training Data: MedMCQA with enhanced context (https://huggingface.co/datasets/MasterControlAIML/Medmcqa-For-FinetuningQwen)
- Developed by: MasterControl
- License: apache-2.0
- Finetuned from model : unsloth/qwen2.5-7b-bnb-4bit
- Eval Dataset : https://huggingface.co/datasets/MasterControlAIML/Eval_Answer_Distractors_MCQs
Template to prompt
alpaca_prompt = """Below is an instruction that describes a task, paired with an input that provides further context. Write a response that appropriately completes the request.
Instruction: {}
Input: {}
Response: {}"""
Example for answer-distractors generation use case:
Below is an instruction that describes a task, paired with an input that provides further context. Write a response that appropriately completes the request.
Instruction:
Based on the context paragraph and question in input, generate a correct answer and three distractor options from the context paragraph:
Input:
Context Paragraph: In pediatric cases of liver failure, the prognosis and risk factors for mortality are varied and can depend greatly on several critical components. While children generally have a somewhat more favorable outcome compared to adults, certain factors can significantly increase the risk of mortality. Notably, sepsis, particularly caused by Gram-negative bacteria, is seen as the most important prognostic factor for death in these cases. This type of infection can lead to severe complications, increasing the risk of mortality despite medical interventions.On the other hand, factors such as increasing transaminases and bilirubin levels are often monitored but are not considered as pivotal in predicting mortality outcomes. Similarly, while an increasing prothrombin time, which reflects coagulation status, may raise important clinical concerns, it does not have a direct correlation to transplant or post-transplant survival according to current pediatric assessments. Additionally, other poor prognostic indicators include liver failure due to specific causes like Wilson disease or idiopathic origins, the occurrence of Stage IV hepatic encephalopathy where brain stem herniation is a major threat, age being less than one year, severe hemorrhage, renal failure, and the need for dialysis before transplantation. Understanding these risk factors aids in managing expectations and planning for comprehensive care in cases of pediatric liver failure.
Question: In a child with active liver failure, the most important prognosis factor for death is –
Response:
Correct Answer: Sepsis Distractors: Increasing transaminases,Increasing bilirubin,Increasing prothrombin time<|endoftext|>
This qwen2 model was trained 2x faster with Unsloth and Huggingface's TRL library.
- Downloads last month
- 6
