60B-MoE-Coder-v2 / config.json
cloudyu's picture
Upload folder using huggingface_hub
cc89d38 verified
{
"_name_or_path": "cloudyu/4bit_quant_TomGrc_FusionNet_34Bx2_MoE_v0.1_DPO",
"architectures": [
"MixtralForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": 1,
"eos_token_id": 2,
"hidden_act": "silu",
"hidden_size": 7168,
"initializer_range": 0.02,
"intermediate_size": 20480,
"max_position_embeddings": 200000,
"model_type": "mixtral",
"num_attention_heads": 56,
"num_experts_per_tok": 2,
"num_hidden_layers": 60,
"num_key_value_heads": 8,
"num_local_experts": 2,
"output_router_logits": false,
"pad_token_id": 0,
"pretraining_tp": 1,
"quantization_config": {
"bnb_4bit_compute_dtype": "float32",
"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": true,
"load_in_8bit": false,
"quant_method": "bitsandbytes"
},
"rms_norm_eps": 1e-05,
"rope_scaling": null,
"rope_theta": 5000000.0,
"router_aux_loss_coef": 0.001,
"sliding_window": null,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.37.2",
"use_cache": true,
"vocab_size": 64000
}