Text Generation
Transformers
Safetensors
English
cloverlm
causal-lm
quartet-ii
nvfp4
low-precision-training
pretrained
custom_code
Instructions to use daslab-testing/CloverLM with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use daslab-testing/CloverLM with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="daslab-testing/CloverLM", trust_remote_code=True)# Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("daslab-testing/CloverLM", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use daslab-testing/CloverLM with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "daslab-testing/CloverLM" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "daslab-testing/CloverLM", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/daslab-testing/CloverLM
- SGLang
How to use daslab-testing/CloverLM 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 "daslab-testing/CloverLM" \ --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": "daslab-testing/CloverLM", "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 "daslab-testing/CloverLM" \ --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": "daslab-testing/CloverLM", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use daslab-testing/CloverLM with Docker Model Runner:
docker model run hf.co/daslab-testing/CloverLM
Upload folder using huggingface_hub
Browse files- modeling_cloverlm.py +20 -2
modeling_cloverlm.py
CHANGED
|
@@ -255,13 +255,31 @@ class CloverLMForCausalLM(PreTrainedModel, GenerationMixin):
|
|
| 255 |
)
|
| 256 |
self.post_init()
|
| 257 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 258 |
@classmethod
|
| 259 |
def from_pretrained(cls, pretrained_model_name_or_path, *args, **kwargs):
|
| 260 |
import os
|
| 261 |
from safetensors import safe_open
|
| 262 |
|
| 263 |
-
st_path =
|
| 264 |
-
if
|
| 265 |
return super().from_pretrained(pretrained_model_name_or_path, *args, **kwargs)
|
| 266 |
|
| 267 |
with safe_open(st_path, framework="pt") as f:
|
|
|
|
| 255 |
)
|
| 256 |
self.post_init()
|
| 257 |
|
| 258 |
+
@classmethod
|
| 259 |
+
def _resolve_safetensors(cls, pretrained_model_name_or_path, **kwargs):
|
| 260 |
+
"""Locate model.safetensors for a local dir or Hub repo ID."""
|
| 261 |
+
import os
|
| 262 |
+
path = str(pretrained_model_name_or_path)
|
| 263 |
+
local = os.path.join(path, "model.safetensors")
|
| 264 |
+
if os.path.exists(local):
|
| 265 |
+
return local
|
| 266 |
+
try:
|
| 267 |
+
from huggingface_hub import hf_hub_download
|
| 268 |
+
return hf_hub_download(
|
| 269 |
+
repo_id=path,
|
| 270 |
+
filename="model.safetensors",
|
| 271 |
+
token=kwargs.get("token"),
|
| 272 |
+
)
|
| 273 |
+
except Exception:
|
| 274 |
+
return None
|
| 275 |
+
|
| 276 |
@classmethod
|
| 277 |
def from_pretrained(cls, pretrained_model_name_or_path, *args, **kwargs):
|
| 278 |
import os
|
| 279 |
from safetensors import safe_open
|
| 280 |
|
| 281 |
+
st_path = cls._resolve_safetensors(pretrained_model_name_or_path, **kwargs)
|
| 282 |
+
if st_path is None:
|
| 283 |
return super().from_pretrained(pretrained_model_name_or_path, *args, **kwargs)
|
| 284 |
|
| 285 |
with safe_open(st_path, framework="pt") as f:
|