| { | |
| "_name_or_path": "/tmp/tmpcjdwac_a", | |
| "alibi": true, | |
| "alibi_bias_max": 8, | |
| "architectures": [ | |
| "MosaicGPT" | |
| ], | |
| "attn_clip_qkv": null, | |
| "attn_impl": "torch", | |
| "attn_pdrop": 0, | |
| "attn_qk_ln": true, | |
| "attn_uses_sequence_id": false, | |
| "auto_map": { | |
| "AutoConfig": "configuration_mosaic_gpt.MosaicGPTConfig", | |
| "AutoModelForCausalLM": "mosaic_gpt.MosaicGPT" | |
| }, | |
| "d_model": 2048, | |
| "emb_init_std": null, | |
| "emb_init_uniform_lim": null, | |
| "emb_pdrop": 0, | |
| "embedding_fraction": 1.0, | |
| "fan_mode": "fan_in", | |
| "init_device": "cpu", | |
| "init_div_is_residual": true, | |
| "init_gain": 0, | |
| "init_nonlinearity": "relu", | |
| "init_std": 0.02, | |
| "logit_scale": null, | |
| "low_precision_layernorm": true, | |
| "max_seq_len": 2048, | |
| "mlp_ratio": 4, | |
| "model_type": "mosaic_gpt", | |
| "n_heads": 16, | |
| "n_layers": 24, | |
| "no_bias": true, | |
| "param_init_fn": "kaiming_normal_", | |
| "prefix_lm": false, | |
| "quantization_config": { | |
| "bnb_4bit_compute_dtype": "bfloat16", | |
| "bnb_4bit_quant_type": "fp4", | |
| "bnb_4bit_use_double_quant": true, | |
| "llm_int8_enable_fp32_cpu_offload": false, | |
| "llm_int8_has_fp16_weight": false, | |
| "llm_int8_skip_modules": [ | |
| "lm_head" | |
| ], | |
| "llm_int8_threshold": 6.0, | |
| "load_in_4bit": true, | |
| "load_in_8bit": false, | |
| "quant_method": "bitsandbytes" | |
| }, | |
| "resid_pdrop": 0, | |
| "softmax_scale": null, | |
| "tokenizer_name": "EleutherAI/gpt-neox-20b", | |
| "torch_dtype": "float16", | |
| "transformers_version": "4.37.1", | |
| "use_cache": false, | |
| "verbose": 0, | |
| "vocab_size": 50432 | |
| } | |