| { |
| "_name_or_path": "chatglm-6b-int4", |
| "architectures": [ |
| "ChatGLMForConditionalGeneration" |
| ], |
| "auto_map": { |
| "AutoConfig": "configuration_chatglm.ChatGLMConfig", |
| "AutoModel": "modeling_chatglm.ChatGLMForConditionalGeneration", |
| "AutoModelForSeq2SeqLM": "modeling_chatglm.ChatGLMForConditionalGeneration" |
| }, |
| "bos_token_id": 130004, |
| "eos_token_id": 130005, |
| "gmask_token_id": 130001, |
| "hidden_size": 4096, |
| "inner_hidden_size": 16384, |
| "layernorm_epsilon": 1e-05, |
| "mask_token_id": 130000, |
| "max_sequence_length": 2048, |
| "model_type": "chatglm", |
| "num_attention_heads": 32, |
| "num_layers": 28, |
| "pad_token_id": 3, |
| "position_encoding_2d": true, |
| "pre_seq_len": 128, |
| "prefix_projection": false, |
| "quantization_bit": 4, |
| "quantization_embeddings": false, |
| "torch_dtype": "float16", |
| "transformers_version": "4.27.1", |
| "use_cache": true, |
| "vocab_size": 130528 |
| } |
|
|
