41f1869a85
Model: ModelCloud.AI/Qwen2.5-Coder-32B-Instruct-gptqmodel-4bit-vortex-v1 Source: Original Platform
51 lines
1.3 KiB
JSON
51 lines
1.3 KiB
JSON
{
|
|
"_attn_implementation_autoset": true,
|
|
"_name_or_path": "/monster/data/lrl/qwen2.5_coder_32b_quant/Q_upload/",
|
|
"architectures": [
|
|
"Qwen2ForCausalLM"
|
|
],
|
|
"attention_dropout": 0.0,
|
|
"bos_token_id": 151643,
|
|
"eos_token_id": 151645,
|
|
"hidden_act": "silu",
|
|
"hidden_size": 5120,
|
|
"initializer_range": 0.02,
|
|
"intermediate_size": 27648,
|
|
"max_position_embeddings": 32768,
|
|
"max_window_layers": 70,
|
|
"model_type": "qwen2",
|
|
"num_attention_heads": 40,
|
|
"num_hidden_layers": 64,
|
|
"num_key_value_heads": 8,
|
|
"quantization_config": {
|
|
"bits": 4,
|
|
"checkpoint_format": "gptq",
|
|
"damp_auto_increment": 0.0015,
|
|
"damp_percent": 0.005,
|
|
"desc_act": true,
|
|
"dynamic": null,
|
|
"group_size": 32,
|
|
"lm_head": false,
|
|
"meta": {
|
|
"damp_auto_increment": 0.0015,
|
|
"damp_percent": 0.005,
|
|
"quantizer": "gptqmodel:1.2.0-dev",
|
|
"uri": "https://github.com/modelcloud/gptqmodel"
|
|
},
|
|
"quant_method": "gptq",
|
|
"static_groups": false,
|
|
"sym": true,
|
|
"true_sequential": true
|
|
},
|
|
"rms_norm_eps": 1e-06,
|
|
"rope_scaling": null,
|
|
"rope_theta": 1000000.0,
|
|
"sliding_window": null,
|
|
"tie_word_embeddings": false,
|
|
"torch_dtype": "bfloat16",
|
|
"transformers_version": "4.46.2",
|
|
"use_cache": true,
|
|
"use_sliding_window": false,
|
|
"vocab_size": 152064
|
|
}
|