Text Generation
Transformers
Safetensors
llama
text-generation-inference
4-bit precision
awq
PuddleJumper-13B-AWQ / config.json
TheBloke's picture
Update for Transformers AWQ support
5da42ec
raw
history blame contribute delete
797 Bytes
{
"_name_or_path": "/home/pikal/Coding/everythinglm/OpenOrca-Platypus2-13B",
"architectures": [
"LlamaForCausalLM"
],
"bos_token_id": 1,
"eos_token_id": 2,
"hidden_act": "silu",
"hidden_size": 5120,
"initializer_range": 0.02,
"intermediate_size": 13824,
"max_position_embeddings": 4096,
"model_type": "llama",
"num_attention_heads": 40,
"num_hidden_layers": 40,
"num_key_value_heads": 40,
"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": 32002,
"quantization_config": {
"quant_method": "awq",
"zero_point": true,
"group_size": 128,
"bits": 4,
"version": "gemm"
}
}