File size: 1,642 Bytes
c96e8ed |
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": "/workspace/process/discoresearch_discolm-mixtral-8x7b-v2/source",
"architectures": [
"MixtralForCausalLM"
],
"attention_dropout": 0.0,
"auto_map": {
"AutoConfig": "configuration_moe_mistral.MixtralConfig",
"AutoModelForCausalLM": "modeling_moe_mistral.MixtralForCausalLM"
},
"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_experts": 8,
"num_experts_per_token": 2,
"num_hidden_layers": 32,
"num_key_value_heads": 8,
"pad_token_id": 0,
"pretraining_tp": 1,
"quantization_config": {
"batch_size": 1,
"bits": 4,
"block_name_to_quantize": "model.layers",
"cache_block_outputs": true,
"damp_percent": 0.1,
"desc_act": true,
"exllama_config": {
"version": 1
},
"group_size": -1,
"max_input_length": null,
"model_seqlen": 4096,
"module_name_preceding_first_block": [
"model.embed_tokens"
],
"pad_token_id": null,
"quant_method": "gptq",
"sym": true,
"tokenizer": null,
"true_sequential": true,
"use_cuda_fp16": true,
"use_exllama": true
},
"rms_norm_eps": 1e-05,
"rope_theta": 1000000.0,
"tie_word_embeddings": false,
"torch_dtype": "float16",
"transformers_version": "4.36.0.dev0",
"use_cache": true,
"vocab_size": 32002
} |