|
{ |
|
"_name_or_path": "yzsydlc/qwen-primeai-int8", |
|
"architectures": [ |
|
"QWenLMHeadModel" |
|
], |
|
"attn_dropout_prob": 0.0, |
|
"auto_map": { |
|
"AutoConfig": "yzsydlc/qwen-primeai-int8--configuration_qwen.QWenConfig", |
|
"AutoModelForCausalLM": "yzsydlc/qwen-primeai-int8--modeling_qwen.QWenLMHeadModel" |
|
}, |
|
"bf16": false, |
|
"emb_dropout_prob": 0.0, |
|
"fp16": true, |
|
"fp32": false, |
|
"hidden_size": 4096, |
|
"initializer_range": 0.02, |
|
"intermediate_size": 22016, |
|
"kv_channels": 128, |
|
"layer_norm_epsilon": 1e-06, |
|
"max_position_embeddings": 32768, |
|
"model_type": "qwen", |
|
"no_bias": true, |
|
"num_attention_heads": 32, |
|
"num_hidden_layers": 32, |
|
"onnx_safe": null, |
|
"quantization_config": { |
|
"batch_size": 1, |
|
"bits": 8, |
|
"block_name_to_quantize": null, |
|
"cache_block_outputs": true, |
|
"damp_percent": 0.01, |
|
"dataset": null, |
|
"desc_act": false, |
|
"exllama_config": { |
|
"version": 1 |
|
}, |
|
"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 |
|
}, |
|
"rotary_emb_base": 10000, |
|
"rotary_pct": 1.0, |
|
"scale_attn_weights": true, |
|
"seq_length": 8192, |
|
"softmax_in_fp32": false, |
|
"tie_word_embeddings": false, |
|
"tokenizer_class": "QWenTokenizer", |
|
"torch_dtype": "float16", |
|
"transformers_version": "4.38.1", |
|
"use_cache": true, |
|
"use_cache_kernel": false, |
|
"use_cache_quantization": false, |
|
"use_dynamic_ntk": true, |
|
"use_flash_attn": true, |
|
"use_logn_attn": true, |
|
"vocab_size": 151936 |
|
} |
|
|