kusakana/ReasoningQAT-Qwen3-1.7B-3bit
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

初始化项目，由ModelHub XC社区提供模型

Browse Source 
Model: kusakana/ReasoningQAT-Qwen3-1.7B-3bit
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-05-10 08:49:08 +08:00
commit c01c94eefe
12 changed files with 151863 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
config.json Normal file
View File

@@ -0,0 +1 @@
{"architectures": ["Qwen3ForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "dtype": "float16", "eos_token_id": 151645, "head_dim": 128, "hidden_act": "silu", "hidden_size": 2048, "initializer_range": 0.02, "intermediate_size": 6144, "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": 40960, "max_window_layers": 28, "model_type": "qwen3", "num_attention_heads": 16, "num_hidden_layers": 28, "num_key_value_heads": 8, "pad_token_id": 151645, "rms_norm_eps": 1e-06, "rope_scaling": null, "rope_theta": 1000000, "sliding_window": null, "tie_word_embeddings": true, "transformers_version": "4.56.0", "use_cache": true, "use_sliding_window": false, "vocab_size": 151936, "torch_dtype": "bfloat16"}