xihc-ucb's picture
Upload FP8Qwen2ForCausalLM
94c4ed7 verified
raw
history blame
2.05 kB
{
"architectures": [
"FP8Qwen2ForCausalLM"
],
"attention_dropout": 0.0,
"auto_map": {
"AutoConfig": "configuration_fp8_qwen2.FP8Qwen2Config",
"AutoModel": "modeling_fp8_qwen2.FP8Qwen2Model",
"AutoModelForCausalLM": "modeling_fp8_qwen2.FP8Qwen2ForCausalLM",
"AutoModelForQuestionAnswering": "modeling_fp8_qwen2.FP8Qwen2ForQuestionAnswering",
"AutoModelForSequenceClassification": "modeling_fp8_qwen2.FP8Qwen2ForSequenceClassification",
"AutoModelForTokenClassification": "modeling_fp8_qwen2.FP8Qwen2ForTokenClassification"
},
"bos_token_id": 151643,
"dtype": "bfloat16",
"eos_token_id": 151645,
"fp8_config": {
"act_block_size": 16,
"float8_dtype": "torch.float8_e4m3fn",
"layer_name": "",
"mm_block_size": 128,
"quant_type": "DIV",
"training_mode": true
},
"hidden_act": "silu",
"hidden_size": 3584,
"initializer_range": 0.02,
"intermediate_size": 18944,
"layer_types": [
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention"
],
"max_position_embeddings": 32768,
"max_window_layers": 28,
"model_name_orig": "Qwen/Qwen2.5-7B-Instruct",
"model_type": "fp8_qwen2",
"num_attention_heads": 28,
"num_hidden_layers": 28,
"num_key_value_heads": 4,
"rms_norm_eps": 1e-06,
"rope_scaling": null,
"rope_theta": 1000000.0,
"sliding_window": null,
"tie_word_embeddings": false,
"transformers_version": "4.57.0",
"use_cache": true,
"use_sliding_window": false,
"vocab_size": 152064
}