|
{
|
|
"_name_or_path": "prithivMLmods/QwQ-LCoT-7B-Instruct",
|
|
"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,
|
|
"pad_token_id": 151665,
|
|
"quantization_config": {
|
|
"bnb_4bit_compute_dtype": "float16",
|
|
"bnb_4bit_quant_type": "nf4",
|
|
"bnb_4bit_use_double_quant": true,
|
|
"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": "float16",
|
|
"transformers_version": "4.46.3",
|
|
"unsloth_fixed": true,
|
|
"unsloth_version": "2024.12.4",
|
|
"use_cache": true,
|
|
"use_sliding_window": false,
|
|
"vocab_size": 152064
|
|
}
|
|
|