Instructions to use ljsabc/Fujisaki-int4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use ljsabc/Fujisaki-int4 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="ljsabc/Fujisaki-int4", trust_remote_code=True)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("ljsabc/Fujisaki-int4", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download config.json from ljsabc/Fujisaki-int4: direct link, hf CLI and curl.
- Browser
- Download file 802 Bytes
-
https://huggingface.co/ljsabc/Fujisaki-int4/resolve/main/config.json
- Command line
-
hf download hf://ljsabc/Fujisaki-int4/config.json
-
curl -L -o config.json https://huggingface.co/ljsabc/Fujisaki-int4/resolve/main/config.json
802 Bytes
| { | |
| "_name_or_path": "THUDM/chatglm-6b", | |
| "architectures": [ | |
| "ChatGLMForConditionalGeneration" | |
| ], | |
| "auto_map": { | |
| "AutoConfig": "configuration_chatglm.ChatGLMConfig", | |
| "AutoModel": "modeling_chatglm.ChatGLMForConditionalGeneration", | |
| "AutoModelForSeq2SeqLM": "modeling_chatglm.ChatGLMForConditionalGeneration" | |
| }, | |
| "bos_token_id": 150004, | |
| "eos_token_id": 150005, | |
| "hidden_size": 4096, | |
| "inner_hidden_size": 16384, | |
| "layernorm_epsilon": 1e-05, | |
| "max_sequence_length": 2048, | |
| "model_type": "chatglm", | |
| "num_attention_heads": 32, | |
| "num_layers": 28, | |
| "pad_token_id": 20003, | |
| "position_encoding_2d": true, | |
| "quantization_bit": 4, | |
| "quantization_embeddings": false, | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.27.1", | |
| "use_cache": true, | |
| "vocab_size": 150528 | |
| } | |