Instructions to use openbmb/cpm-bee-2b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use openbmb/cpm-bee-2b with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="openbmb/cpm-bee-2b", trust_remote_code=True)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("openbmb/cpm-bee-2b", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use openbmb/cpm-bee-2b with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "openbmb/cpm-bee-2b" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "openbmb/cpm-bee-2b", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/openbmb/cpm-bee-2b
- SGLang
How to use openbmb/cpm-bee-2b 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 "openbmb/cpm-bee-2b" \ --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": "openbmb/cpm-bee-2b", "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 "openbmb/cpm-bee-2b" \ --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": "openbmb/cpm-bee-2b", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use openbmb/cpm-bee-2b with Docker Model Runner:
docker model run hf.co/openbmb/cpm-bee-2b
Gong Baitao commited on
Commit ·
1625156
1
Parent(s): c197e2f
fix repetition penalty
Browse files- modeling_cpmbee.py +2 -2
modeling_cpmbee.py
CHANGED
|
@@ -1840,10 +1840,10 @@ class CpmBeeForCausalLM(CpmBeePreTrainedModel):
|
|
| 1840 |
next_token_logits,
|
| 1841 |
batch_size,
|
| 1842 |
num_beams,
|
| 1843 |
-
|
| 1844 |
repetition_penalty,
|
| 1845 |
pred_start_index,
|
| 1846 |
-
|
| 1847 |
None,
|
| 1848 |
)
|
| 1849 |
|
|
|
|
| 1840 |
next_token_logits,
|
| 1841 |
batch_size,
|
| 1842 |
num_beams,
|
| 1843 |
+
input_ids,
|
| 1844 |
repetition_penalty,
|
| 1845 |
pred_start_index,
|
| 1846 |
+
input_ids.size(-1) - 1,
|
| 1847 |
None,
|
| 1848 |
)
|
| 1849 |
|