Text Generation
Transformers
Safetensors
English
llama
text-generation-inference
4-bit precision
gptq
TheBloke's picture
Update for Transformers GPTQ support
9b07d06
raw
history blame contribute delete
888 Bytes
{
"_name_or_path": "upstage/Llama-2-70b-instruct-v2",
"architectures": [
"LlamaForCausalLM"
],
"bos_token_id": 1,
"eos_token_id": 2,
"hidden_act": "silu",
"hidden_size": 8192,
"initializer_range": 0.02,
"intermediate_size": 28672,
"max_position_embeddings": 4096,
"model_type": "llama",
"num_attention_heads": 64,
"num_hidden_layers": 80,
"num_key_value_heads": 8,
"pad_token_id": 0,
"pretraining_tp": 1,
"rms_norm_eps": 1e-05,
"rope_scaling": null,
"tie_word_embeddings": false,
"torch_dtype": "float16",
"transformers_version": "4.31.0",
"use_cache": true,
"vocab_size": 32000,
"quantization_config": {
"bits": 4,
"group_size": -1,
"damp_percent": 0.1,
"desc_act": true,
"sym": true,
"true_sequential": true,
"model_name_or_path": null,
"model_file_base_name": "model",
"quant_method": "gptq"
}
}