akameswa/mixtral-4x7b-instruct-code

1{2  "_name_or_path": "unsloth/mistral-7b-instruct-v0.2-bnb-4bit",3  "architectures": [4    "MixtralForCausalLM"5  ],6  "attention_dropout": 0.0,7  "bos_token_id": 1,8  "eos_token_id": 2,9  "hidden_act": "silu",10  "hidden_size": 4096,11  "initializer_range": 0.02,12  "intermediate_size": 14336,13  "max_position_embeddings": 32768,14  "model_type": "mixtral",15  "num_attention_heads": 32,16  "num_experts_per_tok": 2,17  "num_hidden_layers": 32,18  "num_key_value_heads": 8,19  "num_local_experts": 4,20  "output_router_logits": false,21  "pad_token_id": 0,22  "quantization_config": {23    "bnb_4bit_compute_dtype": "bfloat16",24    "bnb_4bit_quant_type": "nf4",25    "bnb_4bit_use_double_quant": true,26    "llm_int8_enable_fp32_cpu_offload": false,27    "llm_int8_has_fp16_weight": false,28    "llm_int8_skip_modules": null,29    "llm_int8_threshold": 6.0,30    "load_in_4bit": true,31    "load_in_8bit": false,32    "quant_method": "bitsandbytes"33  },34  "rms_norm_eps": 1e-05,35  "rope_theta": 1000000.0,36  "router_aux_loss_coef": 0.001,37  "sliding_window": null,38  "tie_word_embeddings": false,39  "torch_dtype": "float16",40  "transformers_version": "4.39.3",41  "use_cache": true,42  "vocab_size": 3200043}44