| { |
| "_name_or_path": "mosaicml/mpt-30b-instruct", |
| "architectures": [ |
| "MPTForCausalLM" |
| ], |
| "attn_config": { |
| "alibi": true, |
| "alibi_bias_max": 8, |
| "attn_impl": "torch", |
| "attn_pdrop": 0, |
| "attn_type": "multihead_attention", |
| "attn_uses_sequence_id": false, |
| "clip_qkv": null, |
| "prefix_lm": false, |
| "qk_ln": false, |
| "softmax_scale": null |
| }, |
| "auto_map": { |
| "AutoConfig": "mosaicml/mpt-30b-instruct--configuration_mpt.MPTConfig", |
| "AutoModelForCausalLM": "mosaicml/mpt-30b-instruct--modeling_mpt.MPTForCausalLM" |
| }, |
| "d_model": 7168, |
| "emb_pdrop": 0, |
| "embedding_fraction": 1.0, |
| "expansion_ratio": 4, |
| "init_config": { |
| "emb_init_std": null, |
| "emb_init_uniform_lim": null, |
| "fan_mode": "fan_in", |
| "init_div_is_residual": true, |
| "init_gain": 0.0, |
| "init_nonlinearity": "relu", |
| "init_std": null, |
| "name": "kaiming_normal_", |
| "verbose": 0 |
| }, |
| "init_device": "cuda:0", |
| "learned_pos_emb": true, |
| "logit_scale": null, |
| "max_seq_len": 16384, |
| "model_type": "mpt", |
| "n_heads": 64, |
| "n_layers": 48, |
| "no_bias": true, |
| "norm_type": "low_precision_layernorm", |
| "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, |
| "quant_method": "bitsandbytes" |
| }, |
| "resid_pdrop": 0, |
| "tokenizer_name": "EleutherAI/gpt-neox-20b", |
| "torch_dtype": "bfloat16", |
| "transformers_version": "4.33.0.dev0", |
| "use_cache": false, |
| "verbose": 0, |
| "vocab_size": 50432 |
| } |
|
|
