File size: 1,386 Bytes
95d51d2 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 |
{
"_name_or_path": "mptk-1b",
"architectures": [
"MptForCausalLM"
],
"attn_config": {
"model_type": ""
},
"d_model": 2048,
"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": 16,
"n_layers": 24,
"no_bias": true,
"norm_type": "low_precision_layernorm",
"quantization_config": {
"_load_in_4bit": false,
"_load_in_8bit": true,
"bnb_4bit_compute_dtype": "float32",
"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": null,
"llm_int8_threshold": 6.0,
"load_in_4bit": false,
"load_in_8bit": true,
"quant_method": "bitsandbytes"
},
"resid_pdrop": 0,
"torch_dtype": "float16",
"transformers_version": "4.42.4",
"use_cache": false,
"verbose": 0,
"vocab_size": 50432
}
|