Instructions to use SedatAl/Turkish_Law_ChatBot with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use SedatAl/Turkish_Law_ChatBot with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="SedatAl/Turkish_Law_ChatBot")# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("SedatAl/Turkish_Law_ChatBot", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use SedatAl/Turkish_Law_ChatBot with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "SedatAl/Turkish_Law_ChatBot" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "SedatAl/Turkish_Law_ChatBot", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/SedatAl/Turkish_Law_ChatBot
- SGLang
How to use SedatAl/Turkish_Law_ChatBot 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 "SedatAl/Turkish_Law_ChatBot" \ --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": "SedatAl/Turkish_Law_ChatBot", "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 "SedatAl/Turkish_Law_ChatBot" \ --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": "SedatAl/Turkish_Law_ChatBot", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Unsloth Desktop
- Docker Model Runner
How to use SedatAl/Turkish_Law_ChatBot with Docker Model Runner:
docker model run hf.co/SedatAl/Turkish_Law_ChatBot
Update config.json
Browse files- config.json +0 -14
config.json
CHANGED
|
@@ -19,20 +19,6 @@
|
|
| 19 |
"num_key_value_heads": 8,
|
| 20 |
"pad_token_id": 128004,
|
| 21 |
"pretraining_tp": 1,
|
| 22 |
-
"quantization_config": {
|
| 23 |
-
"_load_in_4bit": true,
|
| 24 |
-
"_load_in_8bit": false,
|
| 25 |
-
"bnb_4bit_compute_dtype": "bfloat16",
|
| 26 |
-
"bnb_4bit_quant_storage": "uint8",
|
| 27 |
-
"bnb_4bit_quant_type": "nf4",
|
| 28 |
-
"bnb_4bit_use_double_quant": true,
|
| 29 |
-
"llm_int8_enable_fp32_cpu_offload": false,
|
| 30 |
-
"llm_int8_has_fp16_weight": false,
|
| 31 |
-
"llm_int8_skip_modules": null,
|
| 32 |
-
"llm_int8_threshold": 6.0,
|
| 33 |
-
"load_in_4bit": true,
|
| 34 |
-
"load_in_8bit": false,
|
| 35 |
-
"quant_method": "bitsandbytes"
|
| 36 |
},
|
| 37 |
"rms_norm_eps": 1e-05,
|
| 38 |
"rope_scaling": {
|
|
|
|
| 19 |
"num_key_value_heads": 8,
|
| 20 |
"pad_token_id": 128004,
|
| 21 |
"pretraining_tp": 1,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 22 |
},
|
| 23 |
"rms_norm_eps": 1e-05,
|
| 24 |
"rope_scaling": {
|