Text Generation
Transformers
TensorBoard
Safetensors
opt
trl
sft
Generated from Trainer
text-generation-inference
Instructions to use kibru/tmp_trainer with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use kibru/tmp_trainer with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="kibru/tmp_trainer")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("kibru/tmp_trainer") model = AutoModelForCausalLM.from_pretrained("kibru/tmp_trainer", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use kibru/tmp_trainer with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "kibru/tmp_trainer" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "kibru/tmp_trainer", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/kibru/tmp_trainer
- SGLang
How to use kibru/tmp_trainer 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 "kibru/tmp_trainer" \ --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": "kibru/tmp_trainer", "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 "kibru/tmp_trainer" \ --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": "kibru/tmp_trainer", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use kibru/tmp_trainer with Docker Model Runner:
docker model run hf.co/kibru/tmp_trainer
Download adapter_config.json from kibru/tmp_trainer: direct link, hf CLI and curl.
- Browser
- Download file 576 Bytes
-
https://huggingface.co/kibru/tmp_trainer/resolve/main/adapter_config.json
- Command line
-
hf download hf://kibru/tmp_trainer/adapter_config.json
-
curl -L -o adapter_config.json https://huggingface.co/kibru/tmp_trainer/resolve/main/adapter_config.json
576 Bytes
| { | |
| "alpha_pattern": {}, | |
| "auto_mapping": null, | |
| "base_model_name_or_path": "meta-llama/Llama-2-7b-hf", | |
| "bias": "none", | |
| "fan_in_fan_out": false, | |
| "inference_mode": true, | |
| "init_lora_weights": true, | |
| "layers_pattern": null, | |
| "layers_to_transform": null, | |
| "loftq_config": {}, | |
| "lora_alpha": 32, | |
| "lora_dropout": 0.1, | |
| "megatron_config": null, | |
| "megatron_core": "megatron.core", | |
| "modules_to_save": null, | |
| "peft_type": "LORA", | |
| "r": 16, | |
| "rank_pattern": {}, | |
| "revision": null, | |
| "target_modules": [ | |
| "v_proj", | |
| "q_proj" | |
| ], | |
| "task_type": "CAUSAL_LM" | |
| } |