Instructions to use ltg/deberta-xxlarge-fixed with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use ltg/deberta-xxlarge-fixed with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="ltg/deberta-xxlarge-fixed", trust_remote_code=True)# Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("ltg/deberta-xxlarge-fixed", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use ltg/deberta-xxlarge-fixed with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "ltg/deberta-xxlarge-fixed" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "ltg/deberta-xxlarge-fixed", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/ltg/deberta-xxlarge-fixed
- SGLang
How to use ltg/deberta-xxlarge-fixed 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 "ltg/deberta-xxlarge-fixed" \ --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": "ltg/deberta-xxlarge-fixed", "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 "ltg/deberta-xxlarge-fixed" \ --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": "ltg/deberta-xxlarge-fixed", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use ltg/deberta-xxlarge-fixed with Docker Model Runner:
docker model run hf.co/ltg/deberta-xxlarge-fixed
Update generation_config.json
Browse files- generation_config.json +0 -5
generation_config.json
CHANGED
|
@@ -4,11 +4,6 @@
|
|
| 4 |
"eos_token_id": 2,
|
| 5 |
"pad_token_id": 0,
|
| 6 |
"transformers_version": "4.36.0",
|
| 7 |
-
"top_k": 64,
|
| 8 |
-
"top_p": 0.9,
|
| 9 |
-
"repetition_penalty": 1.0,
|
| 10 |
-
"sample": true,
|
| 11 |
-
"temperature": 0.3,
|
| 12 |
"max_new_tokens": 512,
|
| 13 |
"use_cache": false
|
| 14 |
}
|
|
|
|
| 4 |
"eos_token_id": 2,
|
| 5 |
"pad_token_id": 0,
|
| 6 |
"transformers_version": "4.36.0",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 7 |
"max_new_tokens": 512,
|
| 8 |
"use_cache": false
|
| 9 |
}
|