forked from ailab/Qwen2-7B-Instruct-GPTQ-Int8
52 lines
1.2 KiB
JSON
52 lines
1.2 KiB
JSON
{
|
|
"architectures": [
|
|
"Qwen2ForCausalLM"
|
|
],
|
|
"attention_dropout": 0.0,
|
|
"bos_token_id": 151643,
|
|
"eos_token_id": 151645,
|
|
"hidden_act": "silu",
|
|
"hidden_size": 3584,
|
|
"initializer_range": 0.02,
|
|
"intermediate_size": 18944,
|
|
"max_position_embeddings": 32768,
|
|
"max_window_layers": 28,
|
|
"model_type": "qwen2",
|
|
"num_attention_heads": 28,
|
|
"num_hidden_layers": 28,
|
|
"num_key_value_heads": 4,
|
|
"quantization_config": {
|
|
"batch_size": 1,
|
|
"bits": 8,
|
|
"block_name_to_quantize": null,
|
|
"cache_block_outputs": true,
|
|
"damp_percent": 0.1,
|
|
"dataset": null,
|
|
"desc_act": false,
|
|
"exllama_config": {
|
|
"version": 2
|
|
},
|
|
"group_size": 128,
|
|
"max_input_length": null,
|
|
"model_seqlen": null,
|
|
"module_name_preceding_first_block": null,
|
|
"modules_in_block_to_quantize": null,
|
|
"pad_token_id": null,
|
|
"quant_method": "gptq",
|
|
"sym": true,
|
|
"tokenizer": null,
|
|
"true_sequential": true,
|
|
"use_cuda_fp16": false,
|
|
"use_exllama": true
|
|
},
|
|
"rms_norm_eps": 1e-06,
|
|
"rope_theta": 1000000.0,
|
|
"sliding_window": 131072,
|
|
"tie_word_embeddings": false,
|
|
"torch_dtype": "float16",
|
|
"transformers_version": "4.38.2",
|
|
"use_cache": true,
|
|
"use_sliding_window": false,
|
|
"vocab_size": 152064
|
|
}
|