File size: 1,321 Bytes
e5f876e |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 |
{
"_name_or_path": "Qwen/Qwen2.5-7B-Instruct-1M",
"architectures": [
"Qwen2ForCausalLM"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"dual_chunk_attention_config": {
"chunk_size": 262144,
"local_size": 8192,
"original_max_position_embeddings": 262144
},
"eos_token_id": 151645,
"hidden_act": "silu",
"hidden_size": 3584,
"initializer_range": 0.02,
"intermediate_size": 18944,
"max_position_embeddings": 1010000,
"max_window_layers": 28,
"model_type": "qwen2",
"num_attention_heads": 28,
"num_hidden_layers": 28,
"num_key_value_heads": 4,
"quantization_config": {
"quant_config": {
"offload_meta": false,
"scale_quant_params": null,
"weight_quant_params": {
"axis": 1,
"channel_wise": true,
"group_size": 64,
"nbits": 4,
"optimize": true,
"round_zero": true,
"view_as_float": false
},
"zero_quant_params": null
},
"quant_method": "hqq",
"skip_modules": [
"lm_head"
]
},
"rms_norm_eps": 1e-05,
"rope_scaling": null,
"rope_theta": 10000000.0,
"sliding_window": null,
"tie_word_embeddings": false,
"torch_dtype": "float16",
"transformers_version": "4.48.2",
"use_cache": true,
"use_sliding_window": false,
"vocab_size": 152064
}
|