Instructions to use openbmb/VisCPM-Chat with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use openbmb/VisCPM-Chat with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="openbmb/VisCPM-Chat", trust_remote_code=True)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("openbmb/VisCPM-Chat", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download config.json from openbmb/VisCPM-Chat: direct link, hf CLI and curl.
- Browser
- Download file 740 Bytes
-
https://huggingface.co/openbmb/VisCPM-Chat/resolve/main/config.json
- Command line
-
hf download hf://openbmb/VisCPM-Chat/config.json
-
curl -L -o config.json https://huggingface.co/openbmb/VisCPM-Chat/resolve/main/config.json
740 Bytes
| { | |
| "_from_model_config": true, | |
| "_name_or_path": "openbmb/viscpmchat-bee-10b", | |
| "architectures": [ | |
| "VisCpmBeeForCausalLM" | |
| ], | |
| "auto_map": { | |
| "AutoConfig": "configuration_viscpmchatbee.VisCpmChatBeeConfig", | |
| "AutoModel": "modeling_cpmbee.VisCpmBeeForCausalLM", | |
| "AutoModelForCausalLM": "modeling_cpmbee.VisCpmBeeForCausalLM" | |
| }, | |
| "vocab_size": 86583, | |
| "hidden_size": 4096, | |
| "dim_ff" : 10240, | |
| "num_hidden_layers" : 48, | |
| "num_attention_heads": 32, | |
| "dim_head" : 128, | |
| "dropout_p" : 0.0, | |
| "position_bias_num_buckets" : 256, | |
| "position_bias_num_segment_buckets": 256, | |
| "position_bias_max_distance" : 2048, | |
| "vision_dim": 1024, | |
| "query_num": 64, | |
| "eps" : 1e-6, | |
| "half" : true, | |
| "model_type": "viscpmchatbee" | |
| } | |