| { |
| "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, |
| "model_type": "", |
| "prefix_lm": false, |
| "qk_ln": false, |
| "softmax_scale": null, |
| "torch_dtype": "bfloat16" |
| }, |
| "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": "cpu", |
| "initializer_range": 0.02, |
| "layer_norm_epsilon": 1e-05, |
| "learned_pos_emb": true, |
| "logit_scale": null, |
| "max_seq_len": 8192, |
| "model_type": "mpt", |
| "n_heads": 64, |
| "n_layers": 48, |
| "no_bias": true, |
| "norm_type": "low_precision_layernorm", |
| "quantization_config": { |
| "bits": 4, |
| "checkpoint_format": "gptq", |
| "desc_act": false, |
| "group_size": 128, |
| "lm_head": false, |
| "meta": { |
| "damp_auto_increment": 0.0025, |
| "damp_percent": 0.01, |
| "mse": 0.0, |
| "quantizer": [ |
| "gptqmodel:2.2.0" |
| ], |
| "static_groups": false, |
| "true_sequential": true, |
| "uri": "https://github.com/modelcloud/gptqmodel" |
| }, |
| "pack_dtype": "int32", |
| "quant_method": "gptq", |
| "sym": true |
| }, |
| "resid_pdrop": 0, |
| "tokenizer_name": "sam-mosaic/gpt-neox-20b-chatml", |
| "torch_dtype": "bfloat16", |
| "transformers_version": "4.53.2", |
| "use_cache": false, |
| "verbose": 0, |
| "vocab_size": 50432 |
| } |
|
|
