stella_en_1.5B_v5 / config.json
andrewqian123's picture
Upload model
eb4e967 verified
{
"_name_or_path": "/content/dunzhang/stella_en_1.5B_v5",
"architectures": [
"Qwen2Model"
],
"attention_dropout": 0.0,
"auto_map": {
"AutoModel": "modeling_qwen.Qwen2Model",
"AutoModelForCausalLM": "modeling_qwen.Qwen2ForCausalLM",
"AutoModelForSequenceClassification": "modeling_qwen.Qwen2ForSequenceClassification"
},
"bos_token_id": 151643,
"eos_token_id": 151643,
"hidden_act": "silu",
"hidden_size": 1536,
"initializer_range": 0.02,
"intermediate_size": 8960,
"max_position_embeddings": 131072,
"max_window_layers": 21,
"model_type": "qwen2",
"num_attention_heads": 12,
"num_hidden_layers": 28,
"num_key_value_heads": 2,
"quantization_config": {
"_load_in_4bit": true,
"_load_in_8bit": false,
"bnb_4bit_compute_dtype": "float32",
"bnb_4bit_quant_storage": "uint8",
"bnb_4bit_quant_type": "fp4",
"bnb_4bit_use_double_quant": false,
"llm_int8_enable_fp32_cpu_offload": false,
"llm_int8_has_fp16_weight": false,
"llm_int8_skip_modules": null,
"llm_int8_threshold": 6.0,
"load_in_4bit": true,
"load_in_8bit": false,
"quant_method": "bitsandbytes"
},
"rms_norm_eps": 1e-06,
"rope_scaling": null,
"rope_theta": 1000000.0,
"sliding_window": null,
"tie_word_embeddings": false,
"torch_dtype": "float32",
"transformers_version": "4.46.2",
"use_cache": true,
"use_sliding_window": false,
"vocab_size": 151646
}