MaziyarPanahi's picture
End of training
516151b verified
raw
history blame
1.23 kB
{
"_name_or_path": "NousResearch/Nous-Hermes-2-Mixtral-8x7B-SFT",
"architectures": [
"MixtralForCausalLM"
],
"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": "mixtral",
"num_attention_heads": 32,
"num_experts_per_tok": 2,
"num_hidden_layers": 32,
"num_key_value_heads": 8,
"num_local_experts": 8,
"output_router_logits": false,
"quantization_config": {
"_load_in_4bit": true,
"_load_in_8bit": false,
"bnb_4bit_compute_dtype": "bfloat16",
"bnb_4bit_quant_type": "nf4",
"bnb_4bit_use_double_quant": true,
"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": true,
"load_in_8bit": false,
"quant_method": "bitsandbytes"
},
"rms_norm_eps": 1e-05,
"rope_theta": 1000000.0,
"router_aux_loss_coef": 0.02,
"sliding_window": null,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.38.0.dev0",
"use_cache": false,
"vocab_size": 32002
}