Instructions to use Webscripts/medscript-mistral-7b-qlora with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use Webscripts/medscript-mistral-7b-qlora with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("mistralai/Mistral-7B-Instruct-v0.3") model = PeftModel.from_pretrained(base_model, "Webscripts/medscript-mistral-7b-qlora") - Transformers
How to use Webscripts/medscript-mistral-7b-qlora with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Webscripts/medscript-mistral-7b-qlora") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("Webscripts/medscript-mistral-7b-qlora", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use Webscripts/medscript-mistral-7b-qlora with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Webscripts/medscript-mistral-7b-qlora" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Webscripts/medscript-mistral-7b-qlora", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/Webscripts/medscript-mistral-7b-qlora
- SGLang
How to use Webscripts/medscript-mistral-7b-qlora 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 "Webscripts/medscript-mistral-7b-qlora" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Webscripts/medscript-mistral-7b-qlora", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'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 "Webscripts/medscript-mistral-7b-qlora" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Webscripts/medscript-mistral-7b-qlora", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use Webscripts/medscript-mistral-7b-qlora with Docker Model Runner:
docker model run hf.co/Webscripts/medscript-mistral-7b-qlora
Download checkpoint-102/trainer_state.json from Webscripts/medscript-mistral-7b-qlora: direct link, hf CLI and curl.
- Browser
- Download file 2.91 kB
-
https://huggingface.co/Webscripts/medscript-mistral-7b-qlora/resolve/main/checkpoint-102/trainer_state.json
- Command line
-
hf download hf://Webscripts/medscript-mistral-7b-qlora/checkpoint-102/trainer_state.json
-
curl -L -o trainer_state.json https://huggingface.co/Webscripts/medscript-mistral-7b-qlora/resolve/main/checkpoint-102/trainer_state.json
2.91 kB
| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.0, | |
| "eval_steps": 500, | |
| "global_step": 102, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.29906542056074764, | |
| "learning_rate": 0.00019871817834144504, | |
| "loss": 0.9407, | |
| "mean_token_accuracy": 0.35524434726685283, | |
| "num_tokens": 241264.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.5981308411214953, | |
| "learning_rate": 0.00018865993063730004, | |
| "loss": 0.9849, | |
| "mean_token_accuracy": 0.33938964605331423, | |
| "num_tokens": 473645.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.897196261682243, | |
| "learning_rate": 0.00016956825506034867, | |
| "loss": 0.9593, | |
| "mean_token_accuracy": 0.34235219554975627, | |
| "num_tokens": 712343.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.1794392523364485, | |
| "learning_rate": 0.00014338837391175582, | |
| "loss": 0.9381, | |
| "mean_token_accuracy": 0.33994899512521476, | |
| "num_tokens": 936009.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.4785046728971962, | |
| "learning_rate": 0.00011278771616845061, | |
| "loss": 0.9865, | |
| "mean_token_accuracy": 0.33825155487284064, | |
| "num_tokens": 1170415.0, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.777570093457944, | |
| "learning_rate": 8.08841371298628e-05, | |
| "loss": 0.9682, | |
| "mean_token_accuracy": 0.3465846974402666, | |
| "num_tokens": 1407415.0, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 2.0598130841121494, | |
| "learning_rate": 5.092824479960625e-05, | |
| "loss": 0.947, | |
| "mean_token_accuracy": 0.34771046032574005, | |
| "num_tokens": 1636448.0, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 2.358878504672897, | |
| "learning_rate": 2.5972200292468464e-05, | |
| "loss": 0.9417, | |
| "mean_token_accuracy": 0.34379080319777133, | |
| "num_tokens": 1875647.0, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 2.6579439252336448, | |
| "learning_rate": 8.558737698418761e-06, | |
| "loss": 0.9681, | |
| "mean_token_accuracy": 0.3381199288181961, | |
| "num_tokens": 2112937.0, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 2.9570093457943925, | |
| "learning_rate": 4.62088705080177e-07, | |
| "loss": 0.9956, | |
| "mean_token_accuracy": 0.34778707958757876, | |
| "num_tokens": 2342803.0, | |
| "step": 100 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 102, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 100, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.1773315846476595e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |