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- config.json +0 -3
- configuration_cloverlm.py +0 -6
config.json
CHANGED
|
@@ -23,9 +23,6 @@
|
|
| 23 |
"num_blocks": 29,
|
| 24 |
"num_hidden_layers": 29,
|
| 25 |
"num_key_value_heads": 7,
|
| 26 |
-
"quantization_config": {
|
| 27 |
-
"quant_method": "quartet2"
|
| 28 |
-
},
|
| 29 |
"quartet_2_impl": "pseudoquant",
|
| 30 |
"ratio": 4,
|
| 31 |
"scale_type": "1/sqrt(d)",
|
|
|
|
| 23 |
"num_blocks": 29,
|
| 24 |
"num_hidden_layers": 29,
|
| 25 |
"num_key_value_heads": 7,
|
|
|
|
|
|
|
|
|
|
| 26 |
"quartet_2_impl": "pseudoquant",
|
| 27 |
"ratio": 4,
|
| 28 |
"scale_type": "1/sqrt(d)",
|
configuration_cloverlm.py
CHANGED
|
@@ -23,7 +23,6 @@ class CloverLMConfig(PretrainedConfig):
|
|
| 23 |
num_attention_heads=None,
|
| 24 |
num_key_value_heads=None,
|
| 25 |
head_dim=None,
|
| 26 |
-
quantization_config=None,
|
| 27 |
**kwargs,
|
| 28 |
):
|
| 29 |
self.num_blocks = num_blocks
|
|
@@ -56,11 +55,6 @@ class CloverLMConfig(PretrainedConfig):
|
|
| 56 |
else heads // ratio
|
| 57 |
)
|
| 58 |
self.head_dim = head_dim if head_dim is not None else d_head
|
| 59 |
-
self.quantization_config = (
|
| 60 |
-
quantization_config
|
| 61 |
-
if quantization_config is not None
|
| 62 |
-
else {"quant_method": "quartet2"}
|
| 63 |
-
)
|
| 64 |
|
| 65 |
kwargs.pop("tie_word_embeddings", None)
|
| 66 |
super().__init__(
|
|
|
|
| 23 |
num_attention_heads=None,
|
| 24 |
num_key_value_heads=None,
|
| 25 |
head_dim=None,
|
|
|
|
| 26 |
**kwargs,
|
| 27 |
):
|
| 28 |
self.num_blocks = num_blocks
|
|
|
|
| 55 |
else heads // ratio
|
| 56 |
)
|
| 57 |
self.head_dim = head_dim if head_dim is not None else d_head
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 58 |
|
| 59 |
kwargs.pop("tie_word_embeddings", None)
|
| 60 |
super().__init__(
|