Text Generation
Transformers
Safetensors
English
llama
text-generation-inference
4-bit precision
awq
tulu-7B-AWQ / config.json
TheBloke's picture
Update for Transformers AWQ support
d1962c4
raw
history blame contribute delete
728 Bytes
{
"_name_or_path": "/workspace/process/tulu-7b/source",
"architectures": [
"LlamaForCausalLM"
],
"bos_token_id": 1,
"eos_token_id": 2,
"hidden_act": "silu",
"hidden_size": 4096,
"initializer_range": 0.02,
"intermediate_size": 11008,
"max_position_embeddings": 2048,
"model_type": "llama",
"num_attention_heads": 32,
"num_hidden_layers": 32,
"pad_token_id": 0,
"rms_norm_eps": 1e-06,
"tie_word_embeddings": false,
"torch_dtype": "float32",
"transformers_version": "4.30.0.dev0",
"use_cache": true,
"vocab_size": 32001,
"pretraining_tp": 1,
"quantization_config": {
"quant_method": "awq",
"zero_point": true,
"group_size": 128,
"bits": 4,
"version": "gemm"
}
}