Instructions to use Dwaipayan08/stack_exc_multilabel_instr_lm_head with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use Dwaipayan08/stack_exc_multilabel_instr_lm_head with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("google/gemma-2-2b-it") model = PeftModel.from_pretrained(base_model, "Dwaipayan08/stack_exc_multilabel_instr_lm_head") - Transformers
How to use Dwaipayan08/stack_exc_multilabel_instr_lm_head with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Dwaipayan08/stack_exc_multilabel_instr_lm_head") 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("Dwaipayan08/stack_exc_multilabel_instr_lm_head", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use Dwaipayan08/stack_exc_multilabel_instr_lm_head with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Dwaipayan08/stack_exc_multilabel_instr_lm_head" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Dwaipayan08/stack_exc_multilabel_instr_lm_head", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/Dwaipayan08/stack_exc_multilabel_instr_lm_head
- SGLang
How to use Dwaipayan08/stack_exc_multilabel_instr_lm_head 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 "Dwaipayan08/stack_exc_multilabel_instr_lm_head" \ --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": "Dwaipayan08/stack_exc_multilabel_instr_lm_head", "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 "Dwaipayan08/stack_exc_multilabel_instr_lm_head" \ --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": "Dwaipayan08/stack_exc_multilabel_instr_lm_head", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use Dwaipayan08/stack_exc_multilabel_instr_lm_head with Docker Model Runner:
docker model run hf.co/Dwaipayan08/stack_exc_multilabel_instr_lm_head
Download trainer_state.json from Dwaipayan08/stack_exc_multilabel_instr_lm_head: direct link, hf CLI and curl.
- Browser
- Download file 1.42 kB
-
https://huggingface.co/Dwaipayan08/stack_exc_multilabel_instr_lm_head/resolve/main/trainer_state.json
- Command line
-
hf download hf://Dwaipayan08/stack_exc_multilabel_instr_lm_head/trainer_state.json
-
curl -L -o trainer_state.json https://huggingface.co/Dwaipayan08/stack_exc_multilabel_instr_lm_head/resolve/main/trainer_state.json
1.42 kB
| { | |
| "best_global_step": 20, | |
| "best_metric": 0.3384554982185364, | |
| "best_model_checkpoint": "/content/models/gemma_qlora_lmh_inst/checkpoint-20", | |
| "epoch": 1.25, | |
| "eval_steps": 20, | |
| "global_step": 20, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "entropy": 1.7708985269069673, | |
| "epoch": 1.25, | |
| "grad_norm": 3.859375, | |
| "learning_rate": 4.0625000000000005e-06, | |
| "loss": 0.773, | |
| "mean_token_accuracy": 0.8001608535647392, | |
| "num_tokens": 64265.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "eval_entropy": 1.772031757980585, | |
| "eval_loss": 0.3384554982185364, | |
| "eval_mean_token_accuracy": 0.8753308840095997, | |
| "eval_num_tokens": 64265.0, | |
| "eval_runtime": 6.0558, | |
| "eval_samples_per_second": 82.565, | |
| "eval_steps_per_second": 5.284, | |
| "step": 20 | |
| } | |
| ], | |
| "logging_steps": 20, | |
| "max_steps": 32, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 20, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1003143202652160.0, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |