sharpenb's picture
Upload folder using huggingface_hub (#1)
a1d0506 verified
{
"_name_or_path": "/ceph/hdd/staff/charpent/.cache/modelskj849mc5jd9vp034",
"architectures": [
"MPTForCausalLM"
],
"attn_config": {
"alibi": false,
"alibi_bias_max": 8,
"attn_impl": "torch",
"attn_pdrop": 0.0,
"attn_type": "multihead_attention",
"attn_uses_sequence_id": false,
"clip_qkv": null,
"prefix_lm": false,
"qk_gn": false,
"qk_ln": true,
"rope": false,
"rope_dail_config": {
"pos_idx_in_fp32": true,
"type": "original",
"xpos_scale_base": 512
},
"rope_hf_config": {
"factor": 1.0,
"type": "no_scaling"
},
"rope_impl": "dail",
"rope_theta": 10000,
"sliding_window_size": -1,
"softmax_scale": null
},
"auto_map": {
"AutoConfig": "configuration_mpt.MPTConfig",
"AutoModelForCausalLM": "modeling_mpt.MPTForCausalLM"
},
"d_model": 4096,
"emb_pdrop": 0.0,
"embedding_fraction": 0.1,
"expansion_ratio": 4,
"fc_type": "torch",
"ffn_config": {
"fc_type": "torch",
"ffn_type": "mptmlp"
},
"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_config_defaults": {
"init_std": 0.02
},
"init_device": "cpu",
"learned_pos_emb": true,
"logit_scale": "inv_sqrt_d_model",
"max_seq_len": 2048,
"model_type": "mpt",
"n_heads": 32,
"n_layers": 32,
"no_bias": false,
"norm_type": "low_precision_layernorm",
"quantization_config": {
"_load_in_4bit": true,
"_load_in_8bit": false,
"bnb_4bit_compute_dtype": "bfloat16",
"bnb_4bit_quant_storage": "uint8",
"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": [
"lm_head"
],
"llm_int8_threshold": 6.0,
"load_in_4bit": true,
"load_in_8bit": false,
"quant_method": "bitsandbytes"
},
"resid_pdrop": 0.0,
"torch_dtype": "float16",
"transformers_version": "4.42.4",
"use_cache": false,
"use_pad_tok_in_ffn": true,
"vocab_size": 256000
}