Instructions to use Rexopia/HawkLM-demo with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Rexopia/HawkLM-demo with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Rexopia/HawkLM-demo", trust_remote_code=True)# Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("Rexopia/HawkLM-demo", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use Rexopia/HawkLM-demo with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Rexopia/HawkLM-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-demo", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/Rexopia/HawkLM-demo
- SGLang
How to use Rexopia/HawkLM-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-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-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-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-demo", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use Rexopia/HawkLM-demo with Docker Model Runner:
docker model run hf.co/Rexopia/HawkLM-demo
fast update
Browse files- tokenization_hawk.py +5 -2
tokenization_hawk.py
CHANGED
|
@@ -40,15 +40,18 @@ VOCAB_FILES_NAMES = {
|
|
| 40 |
|
| 41 |
PRETRAINED_VOCAB_FILES_MAP = {
|
| 42 |
"vocab_file": {
|
| 43 |
-
"hawk-demo": "/
|
|
|
|
| 44 |
},
|
| 45 |
"merges_file": {
|
| 46 |
-
"hawk-demo": "/
|
|
|
|
| 47 |
},
|
| 48 |
}
|
| 49 |
|
| 50 |
PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = {
|
| 51 |
"hawk-demo": 1024,
|
|
|
|
| 52 |
}
|
| 53 |
|
| 54 |
|
|
|
|
| 40 |
|
| 41 |
PRETRAINED_VOCAB_FILES_MAP = {
|
| 42 |
"vocab_file": {
|
| 43 |
+
"hawk-demo": "https://huggingface.co/Rexopia/HawkLM-demo/blob/main/vocab.json",
|
| 44 |
+
"hawk-chat-demo": "https://huggingface.co/Rexopia/HawkLM-Chat-demo/blob/main/vocab.json",
|
| 45 |
},
|
| 46 |
"merges_file": {
|
| 47 |
+
"hawk-demo": "https://huggingface.co/Rexopia/HawkLM-demo/blob/main/merges.txt",
|
| 48 |
+
"hawk-chat-demo": "https://huggingface.co/Rexopia/HawkLM-Chat-demo/blob/main/merges.txt",
|
| 49 |
},
|
| 50 |
}
|
| 51 |
|
| 52 |
PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = {
|
| 53 |
"hawk-demo": 1024,
|
| 54 |
+
"hawk-chat-demo": 1024,
|
| 55 |
}
|
| 56 |
|
| 57 |
|