INF-34B-Chat-AWQ / config.json
stgzr's picture
update tokenizer and model weights
738f2a8 verified
raw
history blame contribute delete
940 Bytes
{
"architectures": [
"INFLMForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"auto_map": {
"AutoConfig": "configuration_inflm.INFLMConfig",
"AutoModelForCausalLM": "modeling_inflm.INFLMForCausalLM"
},
"bos_token_id": 1,
"eos_token_id": 2,
"hidden_act": "silu",
"hidden_size": 8192,
"initializer_range": 0.02,
"intermediate_size": 22016,
"layer_norm_eps": 1e-05,
"max_position_embeddings": 32768,
"mlp_bias": false,
"model_type": "inflm",
"num_attention_heads": 64,
"num_hidden_layers": 48,
"num_key_value_heads": 8,
"pretraining_tp": 1,
"quantization_config": {
"bits": 4,
"group_size": 128,
"modules_to_not_convert": null,
"quant_method": "awq",
"version": "gemm",
"zero_point": true
},
"rope_scaling": null,
"rope_theta": 500000,
"tie_word_embeddings": false,
"torch_dtype": "float16",
"use_cache": false,
"vocab_size": 96512
}