gemma-2-9b-gptq-4bit / config.json
lrl-modelcloud's picture
Upload folder using huggingface_hub (#1)
f9f6090 verified
raw
history blame
1.3 kB
{
"_name_or_path": "/model/gemma-2-9b",
"architectures": [
"Gemma2ForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"attn_logit_softcapping": 50.0,
"bos_token_id": 2,
"cache_implementation": "hybrid",
"eos_token_id": 1,
"final_logit_softcapping": 30.0,
"head_dim": 256,
"hidden_act": "gelu_pytorch_tanh",
"hidden_activation": "gelu_pytorch_tanh",
"hidden_size": 3584,
"initializer_range": 0.02,
"intermediate_size": 14336,
"max_position_embeddings": 8192,
"model_type": "gemma2",
"num_attention_heads": 16,
"num_hidden_layers": 42,
"num_key_value_heads": 8,
"pad_token_id": 0,
"quantization_config": {
"bits": 4,
"checkpoint_format": "gptq",
"damp_percent": 0.01,
"desc_act": true,
"group_size": 128,
"lm_head": false,
"meta": {
"quantizer": "gptqmodel:0.9.1"
},
"model_file_base_name": null,
"model_name_or_path": null,
"quant_method": "gptq",
"static_groups": false,
"sym": true,
"true_sequential": true
},
"query_pre_attn_scalar": 224,
"rms_norm_eps": 1e-06,
"rope_theta": 10000.0,
"sliding_window": 4096,
"sliding_window_size": 4096,
"torch_dtype": "bfloat16",
"transformers_version": "4.43.0.dev0",
"use_cache": true,
"vocab_size": 256000
}