Text Generation
Transformers
Safetensors
llama
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Instructions to use FlyPig23/Llama3.2-3B_Paper_Impact_dataset_SFT_1ep with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use FlyPig23/Llama3.2-3B_Paper_Impact_dataset_SFT_1ep with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="FlyPig23/Llama3.2-3B_Paper_Impact_dataset_SFT_1ep") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("FlyPig23/Llama3.2-3B_Paper_Impact_dataset_SFT_1ep") model = AutoModelForCausalLM.from_pretrained("FlyPig23/Llama3.2-3B_Paper_Impact_dataset_SFT_1ep", device_map="auto") messages = [ {"role": "user", "content": "Who are you?"}, ] inputs = tokenizer.apply_chat_template( messages, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors="pt", ).to(model.device) outputs = model.generate(**inputs, max_new_tokens=256) print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use FlyPig23/Llama3.2-3B_Paper_Impact_dataset_SFT_1ep with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "FlyPig23/Llama3.2-3B_Paper_Impact_dataset_SFT_1ep" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "FlyPig23/Llama3.2-3B_Paper_Impact_dataset_SFT_1ep", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/FlyPig23/Llama3.2-3B_Paper_Impact_dataset_SFT_1ep
- SGLang
How to use FlyPig23/Llama3.2-3B_Paper_Impact_dataset_SFT_1ep 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 "FlyPig23/Llama3.2-3B_Paper_Impact_dataset_SFT_1ep" \ --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": "FlyPig23/Llama3.2-3B_Paper_Impact_dataset_SFT_1ep", "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 "FlyPig23/Llama3.2-3B_Paper_Impact_dataset_SFT_1ep" \ --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": "FlyPig23/Llama3.2-3B_Paper_Impact_dataset_SFT_1ep", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use FlyPig23/Llama3.2-3B_Paper_Impact_dataset_SFT_1ep with Docker Model Runner:
docker model run hf.co/FlyPig23/Llama3.2-3B_Paper_Impact_dataset_SFT_1ep
Download trainer_log.jsonl from FlyPig23/Llama3.2-3B_Paper_Impact_dataset_SFT_1ep: direct link, hf CLI and curl.
- Browser
- Download file 1.25 kB
-
https://huggingface.co/FlyPig23/Llama3.2-3B_Paper_Impact_dataset_SFT_1ep/resolve/main/trainer_log.jsonl
- Command line
-
hf download hf://FlyPig23/Llama3.2-3B_Paper_Impact_dataset_SFT_1ep/trainer_log.jsonl
-
curl -L -o trainer_log.jsonl https://huggingface.co/FlyPig23/Llama3.2-3B_Paper_Impact_dataset_SFT_1ep/resolve/main/trainer_log.jsonl
1.25 kB
| {"current_steps": 5, "total_steps": 34, "loss": 0.1823, "lr": 2e-05, "epoch": 0.14925373134328357, "percentage": 14.71, "elapsed_time": "0:02:16", "remaining_time": "0:13:11"} | |
| {"current_steps": 10, "total_steps": 34, "loss": 0.1069, "lr": 1.866025403784439e-05, "epoch": 0.29850746268656714, "percentage": 29.41, "elapsed_time": "0:04:34", "remaining_time": "0:10:59"} | |
| {"current_steps": 15, "total_steps": 34, "loss": 0.1004, "lr": 1.5000000000000002e-05, "epoch": 0.44776119402985076, "percentage": 44.12, "elapsed_time": "0:06:56", "remaining_time": "0:08:47"} | |
| {"current_steps": 20, "total_steps": 34, "loss": 0.1036, "lr": 1e-05, "epoch": 0.5970149253731343, "percentage": 58.82, "elapsed_time": "0:09:19", "remaining_time": "0:06:31"} | |
| {"current_steps": 25, "total_steps": 34, "loss": 0.1, "lr": 5.000000000000003e-06, "epoch": 0.746268656716418, "percentage": 73.53, "elapsed_time": "0:11:43", "remaining_time": "0:04:13"} | |
| {"current_steps": 30, "total_steps": 34, "loss": 0.0983, "lr": 1.339745962155613e-06, "epoch": 0.8955223880597015, "percentage": 88.24, "elapsed_time": "0:14:03", "remaining_time": "0:01:52"} | |
| {"current_steps": 34, "total_steps": 34, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "0:16:12", "remaining_time": "0:00:00"} | |