SmolLM-1.7B-AWQ-4bit / config.json
Hariprasath28's picture
Upload folder using huggingface_hub
7d94fa3 verified
raw
history blame contribute delete
972 Bytes
{
"_name_or_path": "/root/.cache/huggingface/hub/models--HuggingFaceTB--SmolLM-1.7B/snapshots/673a07602ca1191e5bc2ddda428e2f608a0a14c0",
"architectures": [
"LlamaForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": 0,
"eos_token_id": 0,
"hidden_act": "silu",
"hidden_size": 2048,
"initializer_range": 0.02,
"intermediate_size": 8192,
"max_position_embeddings": 2048,
"mlp_bias": false,
"model_type": "llama",
"num_attention_heads": 32,
"num_hidden_layers": 24,
"num_key_value_heads": 32,
"pretraining_tp": 1,
"quantization_config": {
"bits": 4,
"group_size": 128,
"modules_to_not_convert": null,
"quant_method": "awq",
"version": "gemm",
"zero_point": true
},
"rms_norm_eps": 1e-05,
"rope_scaling": null,
"rope_theta": 10000.0,
"tie_word_embeddings": true,
"torch_dtype": "float16",
"transformers_version": "4.41.2",
"use_cache": true,
"vocab_size": 49152
}