Instructions to use JunxiongWang/MambaByte_Code with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use JunxiongWang/MambaByte_Code with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="JunxiongWang/MambaByte_Code")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("JunxiongWang/MambaByte_Code", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use JunxiongWang/MambaByte_Code with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "JunxiongWang/MambaByte_Code" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "JunxiongWang/MambaByte_Code", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/JunxiongWang/MambaByte_Code
- SGLang
How to use JunxiongWang/MambaByte_Code 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 "JunxiongWang/MambaByte_Code" \ --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": "JunxiongWang/MambaByte_Code", "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 "JunxiongWang/MambaByte_Code" \ --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": "JunxiongWang/MambaByte_Code", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use JunxiongWang/MambaByte_Code with Docker Model Runner:
docker model run hf.co/JunxiongWang/MambaByte_Code
Update README.md
Browse files
README.md
CHANGED
|
@@ -19,7 +19,7 @@ model=MambaLMHeadModel.from_pretrained("JunxiongWang/MambaByte_Code", device='cu
|
|
| 19 |
|
| 20 |
text = "import torch"
|
| 21 |
text_byte = np.frombuffer(text.encode('utf-8'), dtype=np.uint8)
|
| 22 |
-
input_ids = torch.from_numpy(text_byte[None, :]).long().cuda()
|
| 23 |
|
| 24 |
sample = model.generate(
|
| 25 |
input_ids=input_ids,
|
|
|
|
| 19 |
|
| 20 |
text = "import torch"
|
| 21 |
text_byte = np.frombuffer(text.encode('utf-8'), dtype=np.uint8)
|
| 22 |
+
input_ids = torch.from_numpy(text_byte[None, :].copy()).long().cuda()
|
| 23 |
|
| 24 |
sample = model.generate(
|
| 25 |
input_ids=input_ids,
|