Files
ModelHub XC ef53f4cc43 初始化项目,由ModelHub XC社区提供模型
Model: micymike/CodeMate-Qwen-1.5B-32K-Distilled-on-Claude-Fable-5
Source: Original Platform
2026-09-11 07:44:14 +08:00

65 lines
1.5 KiB
JSON

{
"architectures": [
"Qwen2ForCausalLM"
],
"attention_dropout": 0.0,
"bos_token_id": null,
"dtype": "bfloat16",
"eos_token_id": 151643,
"hidden_act": "silu",
"hidden_size": 1536,
"initializer_range": 0.02,
"intermediate_size": 8960,
"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_type": "qwen2",
"num_attention_heads": 12,
"num_hidden_layers": 28,
"num_key_value_heads": 2,
"pad_token_id": 151665,
"rms_norm_eps": 1e-06,
"rope_parameters": {
"factor": 4.0,
"original_max_position_embeddings": 8192,
"rope_theta": 1000000.0,
"rope_type": "yarn"
},
"rope_theta": 1000000.0,
"sliding_window": null,
"tie_word_embeddings": true,
"transformers_version": "5.12.1",
"unsloth_version": "2026.6.8",
"use_cache": true,
"use_sliding_window": false,
"vocab_size": 151936
}