correct dtype + new dispatch + tokenizer

5133b63 3 months ago

No virus

6.15 kB

	{
	"_name_or_path": "BlackSamorez/Mixtral-8x7B-Instruct-v0_1-AQLM-2Bit-1x16-hf",
	"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": {
	"in_group_size": 8,
	"linear_weights_not_to_quantize": [
	"model.layers.0.block_sparse_moe.gate.weight",
	"model.layers.0.input_layernorm.weight",
	"model.layers.0.post_attention_layernorm.weight",
	"model.layers.1.block_sparse_moe.gate.weight",
	"model.layers.1.input_layernorm.weight",
	"model.layers.1.post_attention_layernorm.weight",
	"model.layers.2.block_sparse_moe.gate.weight",
	"model.layers.2.input_layernorm.weight",
	"model.layers.2.post_attention_layernorm.weight",
	"model.layers.3.block_sparse_moe.gate.weight",
	"model.layers.3.input_layernorm.weight",
	"model.layers.3.post_attention_layernorm.weight",
	"model.layers.4.block_sparse_moe.gate.weight",
	"model.layers.4.input_layernorm.weight",
	"model.layers.4.post_attention_layernorm.weight",
	"model.layers.5.block_sparse_moe.gate.weight",
	"model.layers.5.input_layernorm.weight",
	"model.layers.5.post_attention_layernorm.weight",
	"model.layers.6.block_sparse_moe.gate.weight",
	"model.layers.6.input_layernorm.weight",
	"model.layers.6.post_attention_layernorm.weight",
	"model.layers.7.block_sparse_moe.gate.weight",
	"model.layers.7.input_layernorm.weight",
	"model.layers.7.post_attention_layernorm.weight",
	"model.layers.8.block_sparse_moe.gate.weight",
	"model.layers.8.input_layernorm.weight",
	"model.layers.8.post_attention_layernorm.weight",
	"model.layers.9.block_sparse_moe.gate.weight",
	"model.layers.9.input_layernorm.weight",
	"model.layers.9.post_attention_layernorm.weight",
	"model.layers.10.block_sparse_moe.gate.weight",
	"model.layers.10.input_layernorm.weight",
	"model.layers.10.post_attention_layernorm.weight",
	"model.layers.11.block_sparse_moe.gate.weight",
	"model.layers.11.input_layernorm.weight",
	"model.layers.11.post_attention_layernorm.weight",
	"model.layers.12.block_sparse_moe.gate.weight",
	"model.layers.12.input_layernorm.weight",
	"model.layers.12.post_attention_layernorm.weight",
	"model.layers.13.block_sparse_moe.gate.weight",
	"model.layers.13.input_layernorm.weight",
	"model.layers.13.post_attention_layernorm.weight",
	"model.layers.14.block_sparse_moe.gate.weight",
	"model.layers.14.input_layernorm.weight",
	"model.layers.14.post_attention_layernorm.weight",
	"model.layers.15.block_sparse_moe.gate.weight",
	"model.layers.15.input_layernorm.weight",
	"model.layers.15.post_attention_layernorm.weight",
	"model.layers.16.block_sparse_moe.gate.weight",
	"model.layers.16.input_layernorm.weight",
	"model.layers.16.post_attention_layernorm.weight",
	"model.layers.17.block_sparse_moe.gate.weight",
	"model.layers.17.input_layernorm.weight",
	"model.layers.17.post_attention_layernorm.weight",
	"model.layers.18.block_sparse_moe.gate.weight",
	"model.layers.18.input_layernorm.weight",
	"model.layers.18.post_attention_layernorm.weight",
	"model.layers.19.block_sparse_moe.gate.weight",
	"model.layers.19.input_layernorm.weight",
	"model.layers.19.post_attention_layernorm.weight",
	"model.layers.20.block_sparse_moe.gate.weight",
	"model.layers.20.input_layernorm.weight",
	"model.layers.20.post_attention_layernorm.weight",
	"model.layers.21.block_sparse_moe.gate.weight",
	"model.layers.21.input_layernorm.weight",
	"model.layers.21.post_attention_layernorm.weight",
	"model.layers.22.block_sparse_moe.gate.weight",
	"model.layers.22.input_layernorm.weight",
	"model.layers.22.post_attention_layernorm.weight",
	"model.layers.23.block_sparse_moe.gate.weight",
	"model.layers.23.input_layernorm.weight",
	"model.layers.23.post_attention_layernorm.weight",
	"model.layers.24.block_sparse_moe.gate.weight",
	"model.layers.24.input_layernorm.weight",
	"model.layers.24.post_attention_layernorm.weight",
	"model.layers.25.block_sparse_moe.gate.weight",
	"model.layers.25.input_layernorm.weight",
	"model.layers.25.post_attention_layernorm.weight",
	"model.layers.26.block_sparse_moe.gate.weight",
	"model.layers.26.input_layernorm.weight",
	"model.layers.26.post_attention_layernorm.weight",
	"model.layers.27.block_sparse_moe.gate.weight",
	"model.layers.27.input_layernorm.weight",
	"model.layers.27.post_attention_layernorm.weight",
	"model.layers.28.block_sparse_moe.gate.weight",
	"model.layers.28.input_layernorm.weight",
	"model.layers.28.post_attention_layernorm.weight",
	"model.layers.29.block_sparse_moe.gate.weight",
	"model.layers.29.input_layernorm.weight",
	"model.layers.29.post_attention_layernorm.weight",
	"model.layers.30.block_sparse_moe.gate.weight",
	"model.layers.30.input_layernorm.weight",
	"model.layers.30.post_attention_layernorm.weight",
	"model.layers.31.block_sparse_moe.gate.weight",
	"model.layers.31.input_layernorm.weight",
	"model.layers.31.post_attention_layernorm.weight",
	"model.embed_tokens.weight",
	"model.norm.weight",
	"lm_head.weight"
	],
	"nbits_per_codebook": 16,
	"num_codebooks": 1,
	"out_group_size": 1,
	"quant_method": "aqlm"
	},
	"rms_norm_eps": 1e-05,
	"rope_theta": 1000000.0,
	"router_aux_loss_coef": 0.02,
	"sliding_window": null,
	"tie_word_embeddings": false,
	"torch_dtype": "float16",
	"transformers_version": "4.38.0",
	"use_cache": true,
	"vocab_size": 32000
	}