BlackSamorez's picture
Upload GemmaForCausalLM
22ab77d verified
raw
history blame
2.87 kB
{
"_name_or_path": "/extra_disk_1/dkuznedelev/aqlm/gemma-2b-AQLM-2Bit-1x16-hf",
"architectures": [
"GemmaForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": 2,
"eos_token_id": 1,
"head_dim": 256,
"hidden_act": "gelu",
"hidden_size": 2048,
"initializer_range": 0.02,
"intermediate_size": 16384,
"max_position_embeddings": 8192,
"model_type": "gemma",
"num_attention_heads": 8,
"num_hidden_layers": 18,
"num_key_value_heads": 1,
"pad_token_id": 0,
"quantization_config": {
"in_group_size": 8,
"linear_weights_not_to_quantize": [
"model.layers.0.input_layernorm.weight",
"model.layers.0.post_attention_layernorm.weight",
"model.layers.1.input_layernorm.weight",
"model.layers.1.post_attention_layernorm.weight",
"model.layers.2.input_layernorm.weight",
"model.layers.2.post_attention_layernorm.weight",
"model.layers.3.input_layernorm.weight",
"model.layers.3.post_attention_layernorm.weight",
"model.layers.4.input_layernorm.weight",
"model.layers.4.post_attention_layernorm.weight",
"model.layers.5.input_layernorm.weight",
"model.layers.5.post_attention_layernorm.weight",
"model.layers.6.input_layernorm.weight",
"model.layers.6.post_attention_layernorm.weight",
"model.layers.7.input_layernorm.weight",
"model.layers.7.post_attention_layernorm.weight",
"model.layers.8.input_layernorm.weight",
"model.layers.8.post_attention_layernorm.weight",
"model.layers.9.input_layernorm.weight",
"model.layers.9.post_attention_layernorm.weight",
"model.layers.10.input_layernorm.weight",
"model.layers.10.post_attention_layernorm.weight",
"model.layers.11.input_layernorm.weight",
"model.layers.11.post_attention_layernorm.weight",
"model.layers.12.input_layernorm.weight",
"model.layers.12.post_attention_layernorm.weight",
"model.layers.13.input_layernorm.weight",
"model.layers.13.post_attention_layernorm.weight",
"model.layers.14.input_layernorm.weight",
"model.layers.14.post_attention_layernorm.weight",
"model.layers.15.input_layernorm.weight",
"model.layers.15.post_attention_layernorm.weight",
"model.layers.16.input_layernorm.weight",
"model.layers.16.post_attention_layernorm.weight",
"model.layers.17.input_layernorm.weight",
"model.layers.17.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-06,
"rope_scaling": null,
"rope_theta": 10000.0,
"torch_dtype": "float16",
"transformers_version": "4.38.2",
"use_cache": true,
"vocab_size": 256000
}