bnjmnmarie's picture
Update config.json
36cf0c2 verified
{
"_name_or_path": "/root/.cache/huggingface/hub/models--meta-llama--Llama-3.1-8B-Instruct/snapshots/0e9e39f249a16976918f6564b8830bc894c89659",
"architectures": [
"LlamaForCausalLM"
],
"quantization_config": {
"bits": 2,
"dynamic": null,
"group_size": 128,
"desc_act": true,
"sym": true,
"lm_head": false,
"quant_method": "gptq",
"checkpoint_format": "gptq",
"meta": {
"quantizer": [
"gptqmodel:1.7.4"
],
"uri": "https://github.com/modelcloud/gptqmodel",
"damp_percent": 0.01,
"damp_auto_increment": 0.0025,
"static_groups": false,
"true_sequential": true
}
},
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": 128000,
"eos_token_id": [
128001,
128008,
128009
],
"head_dim": 128,
"hidden_act": "silu",
"hidden_size": 4096,
"initializer_range": 0.02,
"intermediate_size": 14336,
"max_position_embeddings": 131072,
"mlp_bias": false,
"model_type": "llama",
"num_attention_heads": 32,
"num_hidden_layers": 32,
"num_key_value_heads": 8,
"pretraining_tp": 1,
"rms_norm_eps": 1e-05,
"rope_scaling": {
"factor": 8.0,
"high_freq_factor": 4.0,
"low_freq_factor": 1.0,
"original_max_position_embeddings": 8192,
"rope_type": "llama3"
},
"rope_theta": 500000.0,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.48.1",
"use_cache": true,
"vocab_size": 128256
}