| { |
| "_name_or_path": "./agrimi-7.5B-dolly", |
| "activation_dropout": 0.0, |
| "activation_function": "gelu", |
| "architectures": [ |
| "XGLMForCausalLM" |
| ], |
| "attention_dropout": 0.1, |
| "attention_heads": 32, |
| "bos_token_id": 0, |
| "d_model": 4096, |
| "decoder_start_token_id": 2, |
| "dropout": 0.1, |
| "eos_token_id": 2, |
| "ffn_dim": 16384, |
| "init_std": 0.02, |
| "layerdrop": 0.0, |
| "max_position_embeddings": 2048, |
| "model_type": "xglm", |
| "num_layers": 32, |
| "pad_token_id": 1, |
| "quantization_config": { |
| "bnb_4bit_compute_dtype": "float32", |
| "bnb_4bit_quant_type": "fp4", |
| "bnb_4bit_use_double_quant": false, |
| "llm_int8_enable_fp32_cpu_offload": false, |
| "llm_int8_has_fp16_weight": false, |
| "llm_int8_skip_modules": null, |
| "llm_int8_threshold": 6.0, |
| "load_in_4bit": false, |
| "load_in_8bit": true |
| }, |
| "scale_embedding": true, |
| "torch_dtype": "float16", |
| "transformers_version": "4.30.0.dev0", |
| "use_cache": true, |
| "vocab_size": 256008 |
| } |
|
|