{ | |
"_name_or_path": "BlackSamorez/Llama-2-7b-AQLM-2Bit-8x8-hf", | |
"architectures": [ | |
"LlamaForCausalLM" | |
], | |
"attention_bias": false, | |
"attention_dropout": 0.0, | |
"bos_token_id": 1, | |
"eos_token_id": 2, | |
"hidden_act": "silu", | |
"hidden_size": 4096, | |
"initializer_range": 0.02, | |
"intermediate_size": 11008, | |
"max_position_embeddings": 4096, | |
"model_type": "llama", | |
"num_attention_heads": 32, | |
"num_hidden_layers": 32, | |
"num_key_value_heads": 32, | |
"pretraining_tp": 1, | |
"quantization_config": { | |
"in_group_size": 32, | |
"linear_weights_not_to_quantize": [ | |
"model.embed_tokens.weight", | |
"lm_head.weight" | |
], | |
"nbits_per_codebook": 8, | |
"num_codebooks": 8, | |
"out_group_size": 1, | |
"quant_method": "aqlm" | |
}, | |
"rms_norm_eps": 1e-05, | |
"rope_scaling": null, | |
"rope_theta": 10000.0, | |
"tie_word_embeddings": false, | |
"torch_dtype": "float32", | |
"transformers_version": "4.38.0", | |
"use_cache": true, | |
"vocab_size": 32000 | |
} | |