Instructions to use Rexopia/HawkLM-Chat-demo with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Rexopia/HawkLM-Chat-demo with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Rexopia/HawkLM-Chat-demo", trust_remote_code=True)# Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("Rexopia/HawkLM-Chat-demo", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use Rexopia/HawkLM-Chat-demo with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Rexopia/HawkLM-Chat-demo" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Rexopia/HawkLM-Chat-demo", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/Rexopia/HawkLM-Chat-demo
- SGLang
How to use Rexopia/HawkLM-Chat-demo 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 "Rexopia/HawkLM-Chat-demo" \ --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": "Rexopia/HawkLM-Chat-demo", "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 "Rexopia/HawkLM-Chat-demo" \ --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": "Rexopia/HawkLM-Chat-demo", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use Rexopia/HawkLM-Chat-demo with Docker Model Runner:
docker model run hf.co/Rexopia/HawkLM-Chat-demo
update latest
Browse files- configuration_hawk.py +1 -1
configuration_hawk.py
CHANGED
|
@@ -80,6 +80,6 @@ class HawkConfig(PretrainedConfig):
|
|
| 80 |
self.bos_token_id = bos_token_id
|
| 81 |
self.eos_token_id = eos_token_id
|
| 82 |
|
| 83 |
-
self.rotary_dim =
|
| 84 |
|
| 85 |
super().__init__(bos_token_id=bos_token_id, eos_token_id=eos_token_id, **kwargs)
|
|
|
|
| 80 |
self.bos_token_id = bos_token_id
|
| 81 |
self.eos_token_id = eos_token_id
|
| 82 |
|
| 83 |
+
self.rotary_dim = 64 # TODO Fixed for Hawk demo
|
| 84 |
|
| 85 |
super().__init__(bos_token_id=bos_token_id, eos_token_id=eos_token_id, **kwargs)
|