|
|
--- |
|
|
base_model: deepseek-ai/DeepSeek-R1-Distill-Qwen-14B |
|
|
library_name: transformers |
|
|
license: mit |
|
|
tags: |
|
|
- safe |
|
|
languages: |
|
|
- en |
|
|
- zh |
|
|
pipeline_tag: text-generation |
|
|
--- |
|
|
|
|
|
# RealSafe-R1-14B |
|
|
|
|
|
The model card and source code can be found at https://huggingface.co/papers/2504.10081. |
|
|
|
|
|
# File information |
|
|
|
|
|
The repository contains the following file information: |
|
|
|
|
|
Filename: tokenizer.json |
|
|
Content: "Content of the file is larger than 50 KB, too long to display." |
|
|
|
|
|
Filename: all_results.json |
|
|
Content: { |
|
|
"epoch": 0.9934065934065934, |
|
|
"total_flos": 42342023168000.0, |
|
|
"train_loss": 0.8060129891454646, |
|
|
"train_runtime": 2449.51, |
|
|
"train_samples_per_second": 5.943, |
|
|
"train_steps_per_second": 0.046 |
|
|
} |
|
|
|
|
|
Filename: model.safetensors.index.json |
|
|
Content: { |
|
|
"metadata": { |
|
|
"total_size": 29540067328 |
|
|
}, |
|
|
"weight_map": { |
|
|
"lm_head.weight": "model-00006-of-00006.safetensors", |
|
|
"model.embed_tokens.weight": "model-00001-of-00006.safetensors", |
|
|
"model.layers.0.input_layernorm.weight": "model-00001-of-00006.safetensors", |
|
|
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00006.safetensors", |
|
|
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00006.safetensors", |
|
|
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00006.safetensors", |
|
|
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00006.safetensors", |
|
|
"model.layers.0.self_attn.k_proj.bias": "model-00001-of-00006.safetensors", |
|
|
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00006.safetensors", |
|
|
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00006.safetensors", |
|
|
"model.layers.0.self_attn.q_proj.bias": "model-00001-of-00006.safetensors", |
|
|
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00006.safetensors", |
|
|
"model.layers.0.self_attn.v_proj.bias": "model-00001-of-00006.safetensors", |
|
|
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00006.safetensors", |
|
|
"model.layers.1.input_layernorm.weight": "model-00001-of-00006.safetensors", |
|
|
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00006.safetensors", |
|
|
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00006.safetensors", |
|
|
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00006.safetensors", |
|
|
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00006.safetensors", |
|
|
"model.layers.1.self_attn.k_proj.bias": "model-00001-of-00006.safetensors", |
|
|
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00006.safetensors", |
|
|
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00006.safetensors", |
|
|
"model.layers.1.self_attn.q_proj.bias": "model-00001-of-00006.safetensors", |
|
|
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00006.safetensors", |
|
|
"model.layers.1.self_attn.v_proj.bias": "model-00001-of-00006.safetensors", |
|
|
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00006.safetensors", |
|
|
"model.layers.10.input_layernorm.weight": "model-00002-of-00006.safetensors", |
|
|
"model.layers.10.mlp.down_proj.weight": "model-00002-of-00006.safetensors", |
|
|
"model.layers.10.mlp.gate_proj.weight": "model-00002-of-00006.safetensors", |
|
|
"model.layers.10.mlp.up_proj.weight": "model-00002-of-00006.safetensors", |
|
|
"model.layers.10.post_attention_layernorm.weight": "model-00002-of-00006.safetensors", |
|
|
"model.layers.10.self_attn.k_proj.bias": "model-00002-of-00006.safetensors", |
|
|
"model.layers.10.self_attn.k_proj.weight": "model-00002-of-00006.safetensors", |
|
|
"model.layers.10.self_attn.o_proj.weight": "model-00002-of-00006.safetensors", |
|
|
"model.layers.10.self_attn.q_proj.bias": "model-00002-of-00006.safetensors", |
|
|
"model.layers.10.self_attn.q_proj.weight": "model-00002-of-00006.safetensors", |
|
|
"model.layers.10.self_attn.v_proj.bias": "model-00002-of-00006.safetensors", |
|
|
"model.layers.10.self_attn.v_proj.weight": "model-00002-of-00006.safetensors", |
|
|
"model.layers.11.input_layernorm.weight": "model-00002-of-00006.safetensors", |
|
|
"model.layers.11.mlp.down_proj.weight": "model-00002-of-00006.safetensors", |
|
|
"model.layers.11.mlp.gate_proj.weight": "model-00002-of-00006.safetensors", |
|
|
"model.layers.11.mlp.up_proj.weight": "model-00002-of-00006.safetensors", |
|
|
"model.layers.11.post_attention_layernorm.weight": "model-00002-of-00006.safetensors", |
|
|
"model.layers.11.self_attn.k_proj.bias": "model-00002-of-00006.safetensors", |
|
|
"model.layers.11.self_attn.k_proj.weight": "model-00002-of-00006.safetensors", |
|
|
"model.layers.11.self_attn.o_proj.weight": "model-00002-of-00006.safetensors", |
|
|
"model.layers.11.self_attn.q_proj.bias": "model-00002-of-00006.safetensors", |
|
|
"model.layers.11.self_attn.q_proj.weight": "model-00002-of-00006.safetensors", |
|
|
"model.layers.11.self_attn.v_proj.bias": "model-00002-of-00006.safetensors", |
|
|
"model.layers.11.self_attn.v_proj.weight": "model-00002-of-00006.safetensors", |
|
|
"model.layers.12.input_layernorm.weight": "model-00002-of-00006.safetensors", |
|
|
"model.layers.12.mlp.down_proj.weight": "model-00002-of-00006.safetensors", |
|
|
"model.layers.12.mlp.gate_proj.weight": "model-00002-of-00006.safetensors", |
|
|
"model.layers.12.mlp.up_proj.weight": "model-00002-of-00006.safetensors", |
|
|
"model.layers.12.post_attention_layernorm.weight": "model-00002-of-00006.safetensors", |
|
|
"model.layers.12.self_attn.k_proj.bias": "model-00002-of-00006.safetensors", |
|
|
"model.layers.12.self_attn.k_proj.weight": "model-00002-of-00006.safetensors", |
|
|
"model.layers.12.self_attn.o_proj.weight": "model-00002-of-00006.safetensors", |
|
|
"model.layers.12.self_attn.q_proj.bias": "model-00002-of-00006.safetensors", |
|
|
"model.layers.12.self_attn.q_proj.weight": "model-00002-of-00006.safetensors", |
|
|
"model.layers.12.self_attn.v_proj.bias": "model-00002-of-00006.safetensors", |
|
|
"model.layers.12.self_attn.v_proj.weight": "model-00002-of-00006.safetensors", |
|
|
"model.layers.13.input_layernorm.weight": "model-00002-of-00006.safetensors", |
|
|
"model.layers.13.mlp.down_proj.weight": "model-00002-of-00006.safetensors", |
|
|
"model.layers.13.mlp.gate_proj.weight": "model-00002-of-00006.safetensors", |
|
|
"model.layers.13.mlp.up_proj.weight": "model-00002-of-00006.safetensors", |
|
|
"model.layers.13.post_attention_layernorm.weight": "model-00002-of-00006.safetensors", |
|
|
"model.layers.13.self_attn.k_proj.bias": "model-00002-of-00006.safetensors", |
|
|
"model.layers.13.self_attn.k_proj.weight": "model-00002-of-00006.safetensors", |
|
|
"model.layers.13.self_attn.o_proj.weight": "model-00002-of-00006.safetensors", |
|
|
"model.layers.13.self_attn.q_proj.bias": "model-00002-of-00006.safetensors", |
|
|
"model.layers.13.self_attn.q_proj.weight": "model-00002-of-00006.safetensors", |
|
|
"model.layers.13.self_attn.v_proj.bias": "model-00002-of-00006.safetensors", |
|
|
"model.layers.13.self_attn.v_proj.weight": "model-00002-of-00006.safetensors", |
|
|
"model.layers.14.input_layernorm.weight": "model-00003-of-00006.safetensors", |
|
|
"model.layers.14.mlp.down_proj.weight": "model-00003-of-00006.safetensors", |
|
|
"model.layers.14.mlp.gate_proj.weight": "model-00003-of-00006.safetensors", |
|
|
"model.layers.14.mlp.up_proj.weight": "model-00003-of-00006.safetensors", |
|
|
"model.layers.14.post_attention_layernorm.weight": "model-00003-of-00006.safetensors", |
|
|
"model.layers.14.self_attn.k_proj.bias": "model-00002-of-00006.safetensors", |
|
|
"model.layers.14.self_attn.k_proj.weight": "model-00002-of-00006.safetensors", |
|
|
"model.layers.14.self_attn.o_proj.weight": "model-00002-of-00006.safetensors", |
|
|
"model.layers.14.self_attn.q_proj.bias": "model-00002-of-00006.safetensors", |
|
|
"model.layers.14.self_attn.q_proj.weight": "model-00002-of-00006.safetensors", |
|
|
"model.layers.14.self_attn.v_proj.bias": "model-00002-of-00006.safetensors", |
|
|
"model.layers.14.self_attn.v_proj.weight": "model-00002-of-00006.safetensors", |
|
|
"model.layers.15.input_layernorm.weight": "model-00003-of-00006.safetensors", |
|
|
"model.layers.15.mlp.down_proj.weight": "model-00003-of-00006.safetensors", |
|
|
"model.layers.15.mlp.gate_proj.weight": "model-00003-of-00006.safetensors", |
|
|
"model.layers.15.mlp.up_proj.weight": "model-00003-of-00006.safetensors", |
|
|
"model.layers.15.post_attention_layernorm.weight": "model-00003-of-00006.safetensors", |
|
|
"model.layers.15.self_attn.k_proj.bias": "model-00003-of-00006.safetensors", |
|
|
"model.layers.15.self_attn.k_proj.weight": "model-00003-of-00006.safetensors", |
|
|
"model.layers.15.self_attn.o_proj.weight": "model-00003-of-00006.safetensors", |
|
|
"model.layers.15.self_attn.q_proj.bias": "model-00003-of-00006.safetensors", |
|
|
"model.layers.15.self_attn.q_proj.weight": "model-00003-of-00006.safetensors", |
|
|
"model.layers.15.self_attn.v_proj.bias": "model-00003-of-00006.safetensors", |
|
|
"model.layers.15.self_attn.v_proj.weight": "model-00003-of-00006.safetensors", |
|
|
"model.layers.16.input_layernorm.weight": "model-00003-of-00006.safetensors", |
|
|
"model.layers.16.mlp.down_proj.weight": "model-00003-of-00006.safetensors", |
|
|
"model.layers.16.mlp.gate_proj.weight": "model-00003-of-00006.safetensors", |
|
|
"model.layers.16.mlp.up_proj.weight": "model-00003-of-00006.safetensors", |
|
|
"model.layers.16.post_attention_layernorm.weight": "model-00003-of-00006.safetensors", |
|
|
"model.layers.16.self_attn.k_proj.bias": "model-00003-of-00006.safetensors", |
|
|
"model.layers.16.self_attn.k_proj.weight": "model-00003-of-00006.safetensors", |
|
|
"model.layers.16.self_attn.o_proj.weight": "model-00003-of-00006.safetensors", |
|
|
"model.layers.16.self_attn.q_proj.bias": "model-00003-of-00006.safetensors", |
|
|
"model.layers.16.self_attn.q_proj.weight": "model-00003-of-00006.safetensors", |
|
|
"model.layers.16.self_attn.v_proj.bias": "model-00003-of-00006.safetensors", |
|
|
"model.layers.16.self_attn.v_proj.weight": "model-00003-of-00006.safetensors", |
|
|
"model.layers.17.input_layernorm.weight": "model-00003-of-00006.safetensors", |
|
|
"model.layers.17.mlp.down_proj.weight": "model-00003-of-00006.safetensors", |
|
|
"model.layers.17.mlp.gate_proj.weight": "model-00003-of-00006.safetensors", |
|
|
"model.layers.17.mlp.up_proj.weight": "model-00003-of-00006.safetensors", |
|
|
"model.layers.17.post_attention_layernorm.weight": "model-00003-of-00006.safetensors", |
|
|
"model.layers.17.self_attn.k_proj.bias": "model-00003-of-00006.safetensors", |
|
|
"model.layers.17.self_attn.k_proj.weight": "model-00003-of-00006.safetensors", |
|
|
"model.layers.17.self_attn.o_proj.weight": "model-00003-of-00006.safetensors", |
|
|
"model.layers.17.self_attn.q_proj.bias": "model-00003-of-00006.safetensors", |
|
|
"model.layers.17.self_attn.q_proj.weight": "model-00003-of-00006.safetensors", |
|
|
"model.layers.17.self_attn.v_proj.bias": "model-00003-of-00006.safetensors", |
|
|
"model.layers.17.self_attn.v_proj.weight": "model-00003-of-00006.safetensors", |
|
|
"model.layers.18.input_layernorm.weight": "model-00003-of-00006.safetensors", |
|
|
"model.layers.18.mlp.down_proj.weight": "model-00003-of-00006.safetensors", |
|
|
"model.layers.18.mlp.gate_proj.weight": "model-00003-of-00006.safetensors", |
|
|
"model.layers.18.mlp.up_proj.weight": "model-00003-of-00006.safetensors", |
|
|
"model.layers.18.post_attention_layernorm.weight": "model-00003-of-00006.safetensors", |
|
|
"model.layers.18.self_attn.k_proj.bias": "model-00003-of-00006.safetensors", |
|
|
"model.layers.18.self_attn.k_proj.weight": "model-00003-of-00006.safetensors", |
|
|
"model.layers.18.self_attn.o_proj.weight": "model-00003-of-00006.safetensors", |
|
|
"model.layers.18.self_attn.q_proj.bias": "model-00003-of-00006.safetensors", |
|
|
"model.layers.18.self_attn.q_proj.weight": "model-00003-of-00006.safetensors", |
|
|
"model.layers.18.self_attn.v_proj.bias": "model-00003-of-00006.safetensors", |
|
|
"model.layers.18.self_attn.v_proj.weight": "model-00003-of-00006.safetensors", |
|
|
"model.layers.19.input_layernorm.weight": "model-00003-of-00006.safetensors", |
|
|
"model.layers.19.mlp.down_proj.weight": "model-00003-of-00006.safetensors", |
|
|
"model.layers.19.mlp.gate_proj.weight": "model-00003-of-00006.safetensors", |
|
|
"model.layers.19.mlp.up_proj.weight": "model-00003-of-00006.safetensors", |
|
|
"model.layers.19.post_attention_layernorm.weight": "model-00003-of-00006.safetensors", |
|
|
"model.layers.19.self_attn.k_proj.bias": "model-00003-of-00006.safetensors", |
|
|
"model.layers.19.self_attn.k_proj.weight": "model-00003-of-00006.safetensors", |
|
|
"model.layers.19.self_attn.o_proj.weight": "model-00003-of-00006.safetensors", |
|
|
"model.layers.19.self_attn.q_proj.bias": "model-00003-of-00006.safetensors", |
|
|
"model.layers.19.self_attn.q_proj.weight": "model-00003-of-00006.safetensors", |
|
|
"model.layers.19.self_attn.v_proj.bias": "model-00003-of-00006.safetensors", |
|
|
"model.layers.19.self_attn.v_proj.weight": "model-00003-of-00006.safetensors", |
|
|
"model.layers.2.input_layernorm.weight": "model-00001-of-00006.safetensors", |
|
|
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00006.safetensors", |
|
|
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00006.safetensors", |
|
|
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00006.safetensors", |
|
|
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00006.safetensors", |
|
|
"model.layers.2.self_attn.k_proj.bias": "model-00001-of-00006.safetensors", |
|
|
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00006.safetensors", |
|
|
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00006.safetensors", |
|
|
"model.layers.2.self_attn.q_proj.bias": "model-00001-of-00006.safetensors", |
|
|
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00006.safetensors", |
|
|
"model.layers.2.self_attn.v_proj.bias": "model-00001-of-00006.safetensors", |
|
|
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00006.safetensors", |
|
|
"model.layers.20.input_layernorm.weight": "model-00003-of-00006.safetensors", |
|
|
"model.layers.20.mlp.down_proj.weight": "model-00003-of-00006.safetensors", |
|
|
"model.layers.20.mlp.gate_proj.weight": "model-00003-of-00006.safetensors", |
|
|
"model.layers.20.mlp.up_proj.weight": "model-00003-of-00006.safetensors", |
|
|
"model.layers.20.post_attention_layernorm.weight": "model-00003-of-00006.safetensors", |
|
|
"model.layers.20.self_attn.k_proj.bias": "model-00003-of-00006.safetensors", |
|
|
"model.layers.20.self_attn.k_proj.weight": "model-00003-of-00006.safetensors", |
|
|
"model.layers.20.self_attn.o_proj.weight": "model-00003-of-00006.safetensors", |
|
|
"model.layers.20.self_attn.q_proj.bias": "model-00003-of-00006.safetensors", |
|
|
"model.layers.20.self_attn.q_proj.weight": "model-00003-of-00006.safetensors", |
|
|
"model.layers.20.self_attn.v_proj.bias": "model-00003-of-00006.safetensors", |
|
|
"model.layers.20.self_attn.v_proj.weight": "model-00003-of-00006.safetensors", |
|
|
"model.layers.21.input_layernorm.weight": "model-00003-of-00006.safetensors", |
|
|
"model.layers.21.mlp.down_proj.weight": "model-00003-of-00006.safetensors", |
|
|
"model.layers.21.mlp.gate_proj.weight": "model-00003-of-00006.safetensors", |
|
|
"model.layers.21.mlp.up_proj.weight": "model-00003-of-00006.safetensors", |
|
|
"model.layers.21.post_attention_layernorm.weight": "model-00003-of-00006.safetensors", |
|
|
"model.layers.21.self_attn.k_proj.bias": "model-00003-of-00006.safetensors", |
|
|
"model.layers.21.self_attn.k_proj.weight": "model-00003-of-00006.safetensors", |
|
|
"model.layers.21.self_attn.o_proj.weight": "model-00003-of-00006.safetensors", |
|
|
"model.layers.21.self_attn.q_proj.bias": "model-00003-of-00006.safetensors", |
|
|
"model.layers.21.self_attn.q_proj.weight": "model-00003-of-00006.safetensors", |
|
|
"model.layers.21.self_attn.v_proj.bias": "model-00003-of-00006.safetensors", |
|
|
"model.layers.21.self_attn.v_proj.weight": "model-00003-of-00006.safetensors", |
|
|
"model.layers.22.input_layernorm.weight": "model-00003-of-00006.safetensors", |
|
|
"model.layers.22.mlp.down_proj.weight": "model-00003-of-00006.safetensors", |
|
|
"model.layers.22.mlp.gate_proj.weight": "model-00003-of-00006.safetensors", |
|
|
"model.layers.22.mlp.up_proj.weight": "model-00003-of-00006.safetensors", |
|
|
"model.layers.22.post_attention_layernorm.weight": "model-00003-of-00006.safetensors", |
|
|
"model.layers.22.self_attn.k_proj.bias": "model-00003-of-00006.safetensors", |
|
|
"model.layers.22.self_attn.k_proj.weight": "model-00003-of-00006.safetensors", |
|
|
"model.layers.22.self_attn.o_proj.weight": "model-00003-of-00006.safetensors", |
|
|
"model.layers.22.self_attn.q_proj.bias": "model-00003-of-00006.safetensors", |
|
|
"model.layers.22.self_attn.q_proj.weight": "model-00003-of-00006.safetensors", |
|
|
"model.layers.22.self_attn.v_proj.bias": "model-00003-of-00006.safetensors", |
|
|
"model.layers.22.self_attn.v_proj.weight": "model-00 |
