Instructions to use openbmb/cpm-ant-10b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use openbmb/cpm-ant-10b with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="openbmb/cpm-ant-10b")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("openbmb/cpm-ant-10b") model = AutoModelForCausalLM.from_pretrained("openbmb/cpm-ant-10b", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use openbmb/cpm-ant-10b with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "openbmb/cpm-ant-10b" # 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-ant-10b", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/openbmb/cpm-ant-10b
- SGLang
How to use openbmb/cpm-ant-10b 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-ant-10b" \ --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-ant-10b", "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-ant-10b" \ --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-ant-10b", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use openbmb/cpm-ant-10b with Docker Model Runner:
docker model run hf.co/openbmb/cpm-ant-10b
Update config.json
Browse files- config.json +3 -3
config.json
CHANGED
|
@@ -7,7 +7,7 @@
|
|
| 7 |
"bos_token_id": 6,
|
| 8 |
"dim_ff": 10240,
|
| 9 |
"dim_head": 128,
|
| 10 |
-
"
|
| 11 |
"dropout_p": 0.0,
|
| 12 |
"eos_token_id": 7,
|
| 13 |
"eps": 1e-06,
|
|
@@ -16,8 +16,8 @@
|
|
| 16 |
"max_new_tokens": 50,
|
| 17 |
"model_type": "cpmant",
|
| 18 |
"num_beams": 3,
|
| 19 |
-
"
|
| 20 |
-
"
|
| 21 |
"pad_token_id": 0,
|
| 22 |
"position_bias_max_distance": 2048,
|
| 23 |
"position_bias_num_buckets": 512,
|
|
|
|
| 7 |
"bos_token_id": 6,
|
| 8 |
"dim_ff": 10240,
|
| 9 |
"dim_head": 128,
|
| 10 |
+
"hidden_size": 4096,
|
| 11 |
"dropout_p": 0.0,
|
| 12 |
"eos_token_id": 7,
|
| 13 |
"eps": 1e-06,
|
|
|
|
| 16 |
"max_new_tokens": 50,
|
| 17 |
"model_type": "cpmant",
|
| 18 |
"num_beams": 3,
|
| 19 |
+
"num_attention_heads": 32,
|
| 20 |
+
"num_hidden_layers": 48,
|
| 21 |
"pad_token_id": 0,
|
| 22 |
"position_bias_max_distance": 2048,
|
| 23 |
"position_bias_num_buckets": 512,
|