Text Generation
Transformers
PyTorch
Safetensors
llama
Trained with AutoTrain
text-generation-inference
8-bit precision
Instructions to use Yhhxhfh/dgdggd with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Yhhxhfh/dgdggd with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Yhhxhfh/dgdggd")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("Yhhxhfh/dgdggd") model = AutoModelForCausalLM.from_pretrained("Yhhxhfh/dgdggd", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use Yhhxhfh/dgdggd with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Yhhxhfh/dgdggd" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Yhhxhfh/dgdggd", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/Yhhxhfh/dgdggd
- SGLang
How to use Yhhxhfh/dgdggd 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 "Yhhxhfh/dgdggd" \ --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": "Yhhxhfh/dgdggd", "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 "Yhhxhfh/dgdggd" \ --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": "Yhhxhfh/dgdggd", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use Yhhxhfh/dgdggd with Docker Model Runner:
docker model run hf.co/Yhhxhfh/dgdggd
Download params.json from Yhhxhfh/dgdggd: direct link, hf CLI and curl.
- Browser
- Download file 273 Bytes
-
https://huggingface.co/Yhhxhfh/dgdggd/resolve/main/params.json
- Command line
-
hf download hf://Yhhxhfh/dgdggd/params.json
-
curl -L -o params.json https://huggingface.co/Yhhxhfh/dgdggd/resolve/main/params.json
273 Bytes
| { | |
| "dim": 2048, | |
| "n_layers": 16, | |
| "n_heads": 32, | |
| "n_kv_heads": 8, | |
| "vocab_size": 128256, | |
| "ffn_dim_multiplier": 1.5, | |
| "multiple_of": 256, | |
| "norm_eps": 1e-05, | |
| "rope_theta": 500000.0, | |
| "use_scaled_rope": true, | |
| "quantization_args": { | |
| "group_size": 32 | |
| } | |
| } |