File size: 1,306 Bytes
122433d |
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 |
{
"_name_or_path": "/models/Mistral-7B-v0.1",
"architectures": [
"MistralForCausalLM"
],
"attention_dropout": 0.0,
"bos_token_id": 1,
"eos_token_id": 2,
"hidden_act": "silu",
"hidden_size": 4096,
"initializer_range": 0.02,
"intermediate_size": 14336,
"max_position_embeddings": 32768,
"model_type": "mistral",
"num_attention_heads": 32,
"num_hidden_layers": 32,
"num_key_value_heads": 8,
"quantization_config": {
"amp": true,
"autoround_version": "0.2.0.dev",
"backend": "gptq:exllamav2",
"bits": 4,
"data_type": "int",
"dataset": "NeelNanda/pile-10k",
"enable_minmax_tuning": true,
"enable_quanted_input": true,
"extra_config": {
"lm_head": {
"bits": 4,
"data_type": "int",
"group_size": 128,
"sym": false
}
},
"gradient_accumulate_steps": 1,
"group_size": 128,
"iters": 1000,
"lr": 0.001,
"minmax_lr": 0.001,
"quant_method": "intel/auto-round",
"scale_dtype": "torch.float16",
"seqlen": 2048,
"sym": false,
"train_bs": 8
},
"rms_norm_eps": 1e-05,
"rope_theta": 10000.0,
"sliding_window": 4096,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.40.2",
"use_cache": true,
"vocab_size": 32000
}
|