Add files using upload-large-folder tool
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- .gitattributes +720 -0
- deepseek-r1-1.5b-gunary/config.json +14 -0
- deepseek-r1-1.5b-gunary/lm_head_weight.fp16 +3 -0
- deepseek-r1-1.5b-gunary/model_embed_tokens_weight.fp16 +3 -0
- deepseek-r1-1.5b-gunary/model_layers_0_self_attn_k_proj_bias.fp16 +0 -0
- deepseek-r1-1.5b-gunary/model_layers_0_self_attn_k_proj_weight.sign +0 -0
- deepseek-r1-1.5b-gunary/model_layers_10_input_layernorm_weight.fp16 +0 -0
- deepseek-r1-1.5b-gunary/model_layers_10_self_attn_k_proj_weight.gscales +0 -0
- deepseek-r1-1.5b-gunary/model_layers_10_self_attn_q_proj_bias.fp16 +0 -0
- deepseek-r1-1.5b-gunary/model_layers_11_self_attn_k_proj_bias.fp16 +0 -0
- deepseek-r1-1.5b-gunary/model_layers_11_self_attn_k_proj_weight.sign +0 -0
- deepseek-r1-1.5b-gunary/model_layers_11_self_attn_q_proj_bias.fp16 +0 -0
- deepseek-r1-1.5b-gunary/model_layers_11_self_attn_v_proj_bias.fp16 +0 -0
- deepseek-r1-1.5b-gunary/model_layers_12_input_layernorm_weight.fp16 +0 -0
- deepseek-r1-1.5b-gunary/model_layers_12_self_attn_v_proj_weight.gscales +0 -0
- deepseek-r1-1.5b-gunary/model_layers_13_input_layernorm_weight.fp16 +0 -0
- deepseek-r1-1.5b-gunary/model_layers_13_self_attn_k_proj_bias.fp16 +0 -0
- deepseek-r1-1.5b-gunary/model_layers_13_self_attn_v_proj_weight.gscales +0 -0
- deepseek-r1-1.5b-gunary/model_layers_13_self_attn_v_proj_weight.sign +0 -0
- deepseek-r1-1.5b-gunary/model_layers_14_self_attn_k_proj_weight.gscales +0 -0
- deepseek-r1-1.5b-gunary/model_layers_14_self_attn_q_proj_bias.fp16 +0 -0
- deepseek-r1-1.5b-gunary/model_layers_14_self_attn_v_proj_bias.fp16 +0 -0
- deepseek-r1-1.5b-gunary/model_layers_15_self_attn_k_proj_weight.sign +0 -0
- deepseek-r1-1.5b-gunary/model_layers_16_self_attn_k_proj_weight.sign +0 -0
- deepseek-r1-1.5b-gunary/model_layers_16_self_attn_q_proj_bias.fp16 +0 -0
- deepseek-r1-1.5b-gunary/model_layers_16_self_attn_q_proj_weight.sign +3 -0
- deepseek-r1-1.5b-gunary/model_layers_16_self_attn_v_proj_bias.fp16 +0 -0
- deepseek-r1-1.5b-gunary/model_layers_16_self_attn_v_proj_weight.gscales +0 -0
- deepseek-r1-1.5b-gunary/model_layers_17_input_layernorm_weight.fp16 +0 -0
- deepseek-r1-1.5b-gunary/model_layers_17_post_attention_layernorm_weight.fp16 +0 -0
- deepseek-r1-1.5b-gunary/model_layers_17_self_attn_q_proj_bias.fp16 +0 -0
- deepseek-r1-1.5b-gunary/model_layers_17_self_attn_v_proj_weight.sign +0 -0
- deepseek-r1-1.5b-gunary/model_layers_18_input_layernorm_weight.fp16 +0 -0
- deepseek-r1-1.5b-gunary/model_layers_18_self_attn_k_proj_weight.sign +0 -0
- deepseek-r1-1.5b-gunary/model_layers_19_self_attn_k_proj_weight.sign +0 -0
- deepseek-r1-1.5b-gunary/model_layers_19_self_attn_q_proj_weight.planes +3 -0
- deepseek-r1-1.5b-gunary/model_layers_1_self_attn_q_proj_bias.fp16 +0 -0
- deepseek-r1-1.5b-gunary/model_layers_1_self_attn_v_proj_weight.sign +0 -0
- deepseek-r1-1.5b-gunary/model_layers_20_input_layernorm_weight.fp16 +0 -0
- deepseek-r1-1.5b-gunary/model_layers_20_post_attention_layernorm_weight.fp16 +0 -0
- deepseek-r1-1.5b-gunary/model_layers_20_self_attn_k_proj_bias.fp16 +0 -0
- deepseek-r1-1.5b-gunary/model_layers_20_self_attn_k_proj_weight.sign +0 -0
- deepseek-r1-1.5b-gunary/model_layers_21_post_attention_layernorm_weight.fp16 +0 -0
- deepseek-r1-1.5b-gunary/model_layers_21_self_attn_k_proj_weight.gscales +0 -0
- deepseek-r1-1.5b-gunary/model_layers_21_self_attn_v_proj_bias.fp16 +0 -0
- deepseek-r1-1.5b-gunary/model_layers_21_self_attn_v_proj_weight.gscales +0 -0
- deepseek-r1-1.5b-gunary/model_layers_22_self_attn_k_proj_weight.sign +0 -0
- deepseek-r1-1.5b-gunary/model_layers_22_self_attn_q_proj_bias.fp16 +0 -0
- deepseek-r1-1.5b-gunary/model_layers_22_self_attn_v_proj_weight.gscales +0 -0
- deepseek-r1-1.5b-gunary/model_layers_22_self_attn_v_proj_weight.sign +0 -0
.gitattributes
CHANGED
|
@@ -1797,3 +1797,723 @@ qwen3-4b-thinking-unary/model_layers_20_self_attn_q_proj_weight.planes filter=lf
|
|
| 1797 |
qwen3-4b-thinking-unary/model_layers_31_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1798 |
qwen3-4b-thinking-unary/model_layers_32_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1799 |
qwen3-4b-thinking-unary/model_layers_4_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1797 |
qwen3-4b-thinking-unary/model_layers_31_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1798 |
qwen3-4b-thinking-unary/model_layers_32_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1799 |
qwen3-4b-thinking-unary/model_layers_4_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1800 |
+
qwen3-4b-thinking-unary/model_layers_8_self_attn_v_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1801 |
+
qwen3-4b-thinking-unary/model_layers_6_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1802 |
+
qwen3-4b-thinking-unary/model_layers_11_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1803 |
+
qwen3-4b-thinking-unary/model_layers_3_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1804 |
+
qwen3-4b-thinking-unary/model_layers_7_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1805 |
+
qwen3-4b-thinking-unary/model_layers_16_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1806 |
+
qwen3-4b-thinking-unary/model_layers_11_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1807 |
+
qwen3-4b-thinking-unary/model_layers_8_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1808 |
+
qwen3-4b-thinking-unary/model_layers_20_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1809 |
+
qwen3-4b-thinking-unary/model_layers_7_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1810 |
+
qwen3-4b-thinking-unary/model_layers_7_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1811 |
+
qwen3-4b-thinking-unary/model_layers_19_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1812 |
+
qwen3-4b-thinking-unary/model_layers_7_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1813 |
+
qwen3-4b-thinking-unary/model_layers_32_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1814 |
+
qwen3-4b-thinking-unary/model_layers_17_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1815 |
+
qwen3-4b-thinking-unary/model_layers_21_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1816 |
+
qwen3-4b-thinking-unary/model_layers_34_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1817 |
+
qwen3-4b-thinking-unary/model_layers_26_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1818 |
+
qwen3-4b-thinking-unary/model_layers_22_self_attn_v_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1819 |
+
qwen3-4b-thinking-unary/model_layers_18_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1820 |
+
qwen3-4b-thinking-unary/model_layers_9_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1821 |
+
qwen3-4b-thinking-unary/model_layers_19_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1822 |
+
qwen3-4b-thinking-unary/model_layers_4_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1823 |
+
qwen3-4b-thinking-unary/model_layers_9_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1824 |
+
qwen3-4b-thinking-unary/model_layers_8_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1825 |
+
qwen3-4b-thinking-unary/model_layers_21_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1826 |
+
qwen3-4b-thinking-unary/model_layers_28_self_attn_k_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1827 |
+
qwen3-4b-thinking-unary/model_layers_35_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1828 |
+
qwen3-4b-thinking-unary/model_layers_25_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1829 |
+
qwen3-4b-thinking-unary/model_layers_13_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1830 |
+
qwen3-4b-thinking-unary/model_layers_1_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1831 |
+
qwen3-4b-thinking-unary/model_layers_13_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1832 |
+
qwen3-4b-thinking-unary/model_layers_10_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1833 |
+
qwen3-4b-thinking-unary/model_layers_11_self_attn_k_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1834 |
+
qwen3-4b-thinking-unary/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 1835 |
+
qwen3-4b-thinking-unary/model_layers_14_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1836 |
+
qwen3-4b-thinking-unary/model_layers_24_self_attn_k_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1837 |
+
qwen3-4b-thinking-unary/model_layers_17_self_attn_v_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1838 |
+
qwen3-4b-thinking-unary/model_layers_5_self_attn_k_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1839 |
+
qwen3-4b-thinking-unary/model_layers_24_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1840 |
+
qwen3-4b-thinking-unary/model_layers_9_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1841 |
+
qwen3-4b-thinking-unary/model_layers_17_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1842 |
+
qwen3-4b-thinking-unary/model_layers_8_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1843 |
+
qwen3-4b-thinking-unary/model_layers_24_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1844 |
+
qwen3-4b-thinking-unary/model_layers_12_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1845 |
+
qwen3-4b-thinking-unary/model_layers_12_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1846 |
+
qwen3-4b-thinking-unary/model_layers_23_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1847 |
+
qwen3-4b-thinking-unary/model_layers_1_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1848 |
+
qwen3-4b-thinking-unary/model_layers_3_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1849 |
+
qwen3-4b-thinking-unary/model_layers_23_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1850 |
+
qwen3-4b-thinking-unary/model_layers_22_self_attn_k_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1851 |
+
qwen3-4b-thinking-unary/model_layers_28_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1852 |
+
qwen3-4b-thinking-unary/model_layers_32_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1853 |
+
qwen3-4b-thinking-unary/model_layers_13_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1854 |
+
qwen3-4b-thinking-unary/model_layers_26_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1855 |
+
qwen3-4b-thinking-unary/model_layers_1_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1856 |
+
qwen3-4b-thinking-unary/model_layers_7_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1857 |
+
qwen3-4b-thinking-unary/model_layers_14_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1858 |
+
qwen3-4b-thinking-unary/model_layers_23_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1859 |
+
qwen3-4b-thinking-unary/model_layers_31_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1860 |
+
qwen3-4b-thinking-unary/model_layers_33_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1861 |
+
qwen3-4b-thinking-unary/model_layers_18_self_attn_k_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1862 |
+
qwen3-4b-thinking-unary/model_layers_35_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1863 |
+
qwen3-4b-thinking-unary/model_layers_23_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1864 |
+
qwen3-4b-thinking-unary/model_layers_2_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1865 |
+
qwen3-4b-thinking-unary/model_layers_16_self_attn_k_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1866 |
+
qwen3-4b-thinking-unary/model_layers_18_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1867 |
+
qwen3-4b-thinking-unary/model_layers_8_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1868 |
+
qwen3-4b-thinking-unary/model_layers_20_self_attn_k_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1869 |
+
deepseek-r1-1.5b-unary/model_embed_tokens_weight.fp16 filter=lfs diff=lfs merge=lfs -text
|
| 1870 |
+
qwen3-4b-thinking-unary/model_layers_6_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1871 |
+
qwen3-4b-thinking-unary/model_layers_23_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1872 |
+
qwen3-4b-thinking-unary/model_layers_15_self_attn_k_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1873 |
+
qwen3-4b-thinking-unary/model_layers_9_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1874 |
+
qwen3-4b-thinking-unary/model_layers_26_self_attn_v_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1875 |
+
qwen3-4b-thinking-unary/model_layers_23_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1876 |
+
qwen3-4b-thinking-unary/model_layers_29_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1877 |
+
qwen3-4b-thinking-unary/model_layers_26_self_attn_k_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1878 |
+
qwen3-4b-thinking-unary/model_layers_22_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1879 |
+
qwen3-4b-thinking-unary/model_layers_21_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1880 |
+
qwen3-4b-thinking-unary/model_layers_10_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1881 |
+
qwen3-4b-thinking-unary/model_layers_9_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1882 |
+
qwen3-4b-thinking-unary/model_layers_20_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1883 |
+
qwen3-4b-thinking-unary/model_layers_32_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1884 |
+
qwen3-4b-thinking-unary/model_layers_30_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1885 |
+
qwen3-4b-thinking-unary/model_layers_31_self_attn_v_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1886 |
+
qwen3-4b-thinking-unary/model_layers_18_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1887 |
+
qwen3-4b-thinking-unary/model_layers_32_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1888 |
+
qwen3-4b-thinking-unary/model_layers_21_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1889 |
+
qwen3-4b-thinking-unary/model_layers_35_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1890 |
+
qwen3-4b-thinking-unary/model_layers_25_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1891 |
+
qwen3-4b-thinking-unary/model_layers_25_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1892 |
+
qwen3-4b-thinking-unary/model_layers_34_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1893 |
+
qwen3-4b-thinking-unary/model_layers_11_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1894 |
+
qwen3-4b-thinking-unary/model_layers_6_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1895 |
+
qwen3-4b-thinking-unary/model_layers_19_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1896 |
+
qwen3-4b-thinking-unary/model_layers_1_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1897 |
+
qwen3-4b-thinking-unary/model_layers_0_self_attn_k_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1898 |
+
qwen3-4b-thinking-unary/model_layers_13_self_attn_v_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1899 |
+
qwen3-4b-thinking-unary/model_layers_7_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1900 |
+
qwen3-4b-thinking-unary/model_layers_30_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1901 |
+
qwen3-4b-thinking-unary/model_layers_30_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1902 |
+
qwen3-4b-thinking-unary/model_layers_16_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1903 |
+
qwen3-4b-thinking-unary/model_layers_1_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1904 |
+
qwen3-4b-thinking-unary/model_layers_14_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1905 |
+
qwen3-4b-thinking-unary/model_layers_28_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1906 |
+
qwen3-4b-thinking-unary/model_layers_30_self_attn_k_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1907 |
+
qwen3-4b-thinking-unary/model_layers_26_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1908 |
+
qwen3-4b-thinking-unary/model_layers_5_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1909 |
+
qwen3-4b-thinking-unary/model_layers_0_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1910 |
+
qwen3-4b-thinking-unary/model_layers_7_self_attn_v_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1911 |
+
qwen3-4b-thinking-unary/model_layers_9_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1912 |
+
qwen3-4b-thinking-unary/model_layers_29_self_attn_k_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1913 |
+
qwen3-4b-thinking-unary/model_layers_10_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1914 |
+
qwen3-4b-thinking-unary/model_layers_16_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1915 |
+
qwen3-4b-thinking-unary/model_layers_19_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1916 |
+
qwen3-4b-thinking-unary/model_layers_18_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1917 |
+
qwen3-4b-thinking-unary/model_layers_12_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1918 |
+
qwen3-4b-thinking-unary/model_layers_26_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1919 |
+
qwen3-4b-thinking-unary/model_layers_32_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1920 |
+
qwen3-4b-thinking-unary/model_layers_0_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1921 |
+
qwen3-4b-thinking-unary/model_layers_10_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1922 |
+
qwen3-4b-thinking-unary/model_layers_8_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1923 |
+
qwen3-4b-thinking-unary/model_layers_7_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1924 |
+
qwen3-4b-thinking-unary/model_layers_25_self_attn_k_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1925 |
+
qwen3-4b-thinking-unary/model_layers_6_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1926 |
+
qwen3-4b-thinking-unary/model_layers_24_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1927 |
+
qwen3-4b-thinking-unary/model_layers_29_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1928 |
+
qwen3-4b-thinking-unary/model_layers_15_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1929 |
+
qwen3-4b-thinking-unary/model_layers_35_self_attn_v_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1930 |
+
qwen3-4b-thinking-unary/model_layers_16_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1931 |
+
qwen3-4b-thinking-unary/model_layers_6_self_attn_k_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1932 |
+
qwen3-4b-thinking-unary/model_layers_14_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1933 |
+
qwen3-4b-thinking-unary/model_layers_29_self_attn_v_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1934 |
+
qwen3-4b-thinking-unary/model_layers_20_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1935 |
+
qwen3-4b-thinking-unary/model_layers_30_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1936 |
+
qwen3-4b-thinking-unary/model_layers_25_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1937 |
+
qwen3-4b-thinking-unary/model_layers_35_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1938 |
+
qwen3-4b-thinking-unary/model_layers_3_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1939 |
+
qwen3-4b-thinking-unary/model_layers_3_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1940 |
+
qwen3-4b-thinking-unary/model_layers_22_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1941 |
+
qwen3-4b-thinking-unary/model_layers_32_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1942 |
+
qwen3-4b-thinking-unary/model_layers_33_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1943 |
+
qwen3-4b-thinking-unary/model_layers_2_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1944 |
+
qwen3-4b-thinking-unary/model_layers_18_self_attn_v_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1945 |
+
qwen3-4b-thinking-unary/model_layers_12_self_attn_k_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1946 |
+
qwen3-4b-thinking-unary/model_layers_25_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1947 |
+
qwen3-4b-thinking-unary/model_layers_28_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1948 |
+
qwen3-4b-thinking-unary/model_layers_10_self_attn_v_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1949 |
+
qwen3-4b-thinking-unary/model_layers_9_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1950 |
+
qwen3-4b-thinking-unary/model_layers_21_self_attn_k_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1951 |
+
qwen3-4b-thinking-unary/model_layers_26_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1952 |
+
qwen3-4b-thinking-unary/model_layers_16_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1953 |
+
qwen3-4b-thinking-unary/model_layers_3_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1954 |
+
qwen3-4b-thinking-unary/model_layers_22_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1955 |
+
qwen3-4b-thinking-unary/model_layers_1_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1956 |
+
qwen3-4b-thinking-unary/model_layers_22_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1957 |
+
qwen3-4b-thinking-unary/model_layers_22_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1958 |
+
qwen3-4b-thinking-unary/model_layers_12_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1959 |
+
qwen3-4b-thinking-unary/model_layers_19_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1960 |
+
qwen3-4b-thinking-unary/model_layers_24_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1961 |
+
qwen3-4b-thinking-unary/model_layers_26_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1962 |
+
qwen3-4b-thinking-unary/model_layers_22_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1963 |
+
qwen3-4b-thinking-unary/model_layers_10_self_attn_k_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1964 |
+
qwen3-4b-thinking-unary/model_layers_13_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1965 |
+
qwen3-4b-thinking-unary/model_layers_0_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1966 |
+
qwen3-4b-thinking-unary/model_layers_15_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1967 |
+
qwen3-4b-thinking-unary/model_layers_21_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1968 |
+
qwen3-4b-thinking-unary/model_layers_5_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1969 |
+
qwen3-4b-thinking-unary/model_layers_26_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1970 |
+
qwen3-4b-thinking-unary/model_layers_18_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1971 |
+
qwen3-4b-thinking-unary/model_layers_12_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1972 |
+
qwen3-4b-thinking-unary/model_layers_11_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1973 |
+
qwen3-4b-thinking-unary/model_layers_30_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1974 |
+
qwen3-4b-thinking-unary/model_layers_11_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1975 |
+
qwen3-4b-thinking-unary/model_layers_7_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1976 |
+
qwen3-4b-thinking-unary/model_layers_4_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1977 |
+
qwen3-4b-thinking-unary/model_layers_2_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1978 |
+
qwen3-4b-thinking-unary/model_layers_14_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1979 |
+
qwen3-4b-thinking-unary/model_layers_20_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1980 |
+
qwen3-4b-thinking-unary/model_layers_27_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1981 |
+
qwen3-4b-thinking-unary/model_layers_19_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1982 |
+
qwen3-4b-thinking-unary/model_layers_17_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1983 |
+
qwen3-4b-thinking-unary/model_layers_26_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1984 |
+
qwen3-4b-thinking-unary/model_layers_14_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1985 |
+
qwen3-4b-thinking-unary/model_layers_15_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1986 |
+
qwen3-4b-thinking-unary/model_layers_19_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1987 |
+
qwen3-4b-thinking-unary/model_layers_29_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1988 |
+
qwen3-4b-thinking-unary/model_layers_6_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1989 |
+
qwen3-4b-thinking-unary/model_layers_35_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1990 |
+
qwen3-4b-thinking-unary/model_layers_9_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1991 |
+
qwen3-4b-thinking-unary/model_layers_10_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1992 |
+
qwen3-4b-thinking-unary/model_layers_2_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1993 |
+
qwen3-4b-thinking-unary/model_layers_31_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1994 |
+
qwen3-4b-thinking-unary/model_layers_5_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1995 |
+
qwen3-4b-thinking-unary/model_layers_4_self_attn_k_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1996 |
+
qwen3-4b-thinking-unary/model_layers_28_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1997 |
+
qwen3-4b-thinking-unary/model_layers_35_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1998 |
+
qwen3-4b-thinking-unary/model_layers_0_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1999 |
+
qwen3-4b-thinking-unary/model_layers_16_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2000 |
+
qwen3-4b-thinking-unary/model_layers_27_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2001 |
+
qwen3-4b-thinking-unary/model_layers_22_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2002 |
+
qwen3-4b-thinking-unary/model_layers_33_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2003 |
+
qwen3-4b-thinking-unary/model_layers_33_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2004 |
+
qwen3-4b-thinking-unary/model_layers_31_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2005 |
+
qwen3-4b-thinking-unary/model_layers_16_self_attn_v_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2006 |
+
qwen3-4b-thinking-unary/model_layers_15_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2007 |
+
qwen3-4b-thinking-unary/model_layers_24_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2008 |
+
qwen3-4b-thinking-unary/model_layers_27_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2009 |
+
qwen3-4b-thinking-unary/model_layers_16_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2010 |
+
qwen3-4b-thinking-unary/model_layers_17_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2011 |
+
qwen3-4b-thinking-unary/model_layers_6_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2012 |
+
qwen3-4b-thinking-unary/model_layers_4_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2013 |
+
qwen3-4b-thinking-unary/model_layers_13_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2014 |
+
qwen3-4b-thinking-unary/model_layers_17_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2015 |
+
qwen3-4b-thinking-unary/model_layers_17_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2016 |
+
qwen3-4b-thinking-unary/model_layers_9_self_attn_k_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2017 |
+
qwen3-4b-thinking-unary/model_layers_6_self_attn_v_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2018 |
+
qwen3-4b-thinking-unary/model_layers_9_self_attn_v_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2019 |
+
qwen3-4b-thinking-unary/model_layers_8_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2020 |
+
qwen3-4b-thinking-unary/model_layers_13_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2021 |
+
qwen3-4b-thinking-unary/model_layers_28_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2022 |
+
qwen3-4b-thinking-unary/model_layers_30_self_attn_v_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2023 |
+
qwen3-4b-thinking-unary/model_layers_4_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2024 |
+
qwen3-4b-thinking-unary/model_layers_19_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2025 |
+
qwen3-4b-thinking-unary/model_layers_10_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2026 |
+
qwen3-4b-thinking-unary/model_layers_15_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2027 |
+
qwen3-4b-thinking-unary/model_layers_4_self_attn_v_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2028 |
+
qwen3-4b-thinking-unary/model_layers_5_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2029 |
+
qwen3-4b-thinking-unary/model_layers_11_self_attn_v_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2030 |
+
qwen3-4b-thinking-unary/model_layers_21_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2031 |
+
qwen3-4b-thinking-unary/model_layers_12_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2032 |
+
qwen3-4b-thinking-unary/model_layers_18_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2033 |
+
qwen3-4b-thinking-unary/model_layers_25_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2034 |
+
qwen3-4b-thinking-unary/model_layers_9_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2035 |
+
qwen3-4b-thinking-unary/model_layers_3_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2036 |
+
qwen3-4b-thinking-unary/model_layers_0_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2037 |
+
qwen3-4b-thinking-unary/model_layers_1_self_attn_k_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2038 |
+
qwen3-4b-thinking-unary/model_layers_8_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2039 |
+
qwen3-4b-thinking-unary/model_layers_3_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2040 |
+
qwen3-4b-thinking-unary/model_layers_1_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2041 |
+
qwen3-4b-thinking-unary/model_layers_13_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2042 |
+
qwen3-4b-thinking-unary/model_layers_15_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2043 |
+
qwen3-4b-thinking-unary/model_layers_4_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2044 |
+
qwen3-4b-thinking-unary/model_layers_20_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2045 |
+
qwen3-4b-thinking-unary/model_layers_17_self_attn_k_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2046 |
+
qwen3-4b-thinking-unary/model_layers_5_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2047 |
+
qwen3-4b-thinking-unary/model_layers_20_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2048 |
+
qwen3-4b-thinking-unary/model_layers_34_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2049 |
+
qwen3-4b-thinking-unary/model_layers_24_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2050 |
+
qwen3-4b-thinking-unary/model_layers_24_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2051 |
+
qwen3-4b-thinking-unary/model_layers_20_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2052 |
+
qwen3-4b-thinking-unary/model_layers_21_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2053 |
+
qwen3-4b-thinking-unary/model_layers_13_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2054 |
+
qwen3-4b-thinking-unary/model_layers_16_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2055 |
+
qwen3-4b-thinking-unary/model_layers_22_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2056 |
+
qwen3-4b-thinking-unary/model_layers_25_self_attn_v_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2057 |
+
qwen3-4b-thinking-unary/model_layers_30_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2058 |
+
qwen3-4b-thinking-unary/model_layers_29_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2059 |
+
qwen3-4b-thinking-unary/model_layers_15_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2060 |
+
qwen3-4b-thinking-unary/model_layers_22_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2061 |
+
qwen3-4b-thinking-unary/model_layers_26_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2062 |
+
qwen3-4b-thinking-unary/model_layers_34_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2063 |
+
qwen3-4b-thinking-unary/model_layers_29_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2064 |
+
qwen3-4b-thinking-unary/model_layers_13_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2065 |
+
qwen3-4b-thinking-unary/model_layers_33_self_attn_v_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2066 |
+
qwen3-4b-thinking-unary/model_layers_35_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2067 |
+
qwen3-4b-thinking-unary/model_layers_16_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2068 |
+
qwen3-4b-thinking-unary/model_layers_24_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2069 |
+
qwen3-4b-thinking-unary/model_layers_33_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2070 |
+
qwen3-4b-thinking-unary/model_layers_23_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2071 |
+
qwen3-4b-thinking-unary/model_layers_9_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2072 |
+
qwen3-4b-thinking-unary/model_layers_29_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2073 |
+
qwen3-4b-thinking-unary/model_layers_0_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2074 |
+
qwen3-4b-thinking-unary/model_layers_27_self_attn_v_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2075 |
+
qwen3-4b-thinking-unary/model_layers_35_self_attn_k_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2076 |
+
qwen3-4b-thinking-unary/model_layers_19_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2077 |
+
qwen3-4b-thinking-unary/model_layers_24_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2078 |
+
qwen3-4b-thinking-unary/model_layers_28_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2079 |
+
qwen3-4b-thinking-unary/model_layers_29_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2080 |
+
qwen3-4b-thinking-unary/model_layers_20_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2081 |
+
qwen3-4b-thinking-unary/model_layers_15_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2082 |
+
qwen3-4b-thinking-unary/model_layers_15_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2083 |
+
qwen3-4b-thinking-unary/model_layers_14_self_attn_k_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2084 |
+
qwen3-4b-thinking-unary/model_layers_2_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2085 |
+
qwen3-4b-thinking-unary/model_layers_6_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2086 |
+
qwen3-4b-thinking-unary/model_layers_4_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2087 |
+
qwen3-4b-thinking-unary/model_layers_1_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2088 |
+
qwen3-4b-thinking-unary/model_layers_15_self_attn_v_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2089 |
+
qwen3-4b-thinking-unary/model_layers_10_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2090 |
+
qwen3-4b-thinking-unary/model_layers_2_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2091 |
+
qwen3-4b-thinking-unary/model_layers_27_self_attn_k_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2092 |
+
qwen3-4b-thinking-unary/model_layers_31_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2093 |
+
qwen3-4b-thinking-unary/model_layers_31_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2094 |
+
qwen3-4b-thinking-unary/model_layers_30_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2095 |
+
qwen3-4b-thinking-unary/model_layers_35_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2096 |
+
deepseek-r1-1.5b-gunary/model_layers_3_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2097 |
+
deepseek-r1-1.5b-gunary/model_layers_8_mlp_gate_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text
|
| 2098 |
+
deepseek-r1-1.5b-gunary/model_layers_19_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2099 |
+
deepseek-r1-1.5b-gunary/model_layers_16_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2100 |
+
deepseek-r1-1.5b-gunary/model_layers_27_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2101 |
+
deepseek-r1-1.5b-gunary/model_layers_27_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2102 |
+
qwen3-4b-proper-unary/model_layers_1_mlp_gate_proj_weight.usign filter=lfs diff=lfs merge=lfs -text
|
| 2103 |
+
qwen3-4b-proper-unary/model_layers_0_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2104 |
+
qwen3-4b-proper-unary/model_layers_0_self_attn_o_proj_weight.uslots filter=lfs diff=lfs merge=lfs -text
|
| 2105 |
+
qwen3-4b-proper-unary/model_layers_0_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2106 |
+
qwen3-4b-proper-unary/model_layers_1_self_attn_q_proj_weight.usign filter=lfs diff=lfs merge=lfs -text
|
| 2107 |
+
qwen3-4b-proper-unary/model_layers_12_self_attn_q_proj_weight.uslots filter=lfs diff=lfs merge=lfs -text
|
| 2108 |
+
qwen3-4b-proper-unary/model_layers_10_self_attn_q_proj_weight.uslots filter=lfs diff=lfs merge=lfs -text
|
| 2109 |
+
qwen3-4b-proper-unary/model_layers_11_mlp_gate_proj_weight.uslots filter=lfs diff=lfs merge=lfs -text
|
| 2110 |
+
qwen3-4b-proper-unary/model_layers_0_mlp_up_proj_weight.usign filter=lfs diff=lfs merge=lfs -text
|
| 2111 |
+
qwen3-4b-proper-unary/model_layers_10_mlp_gate_proj_weight.usign filter=lfs diff=lfs merge=lfs -text
|
| 2112 |
+
deepseek-r1-1.5b-gunary/lm_head_weight.fp16 filter=lfs diff=lfs merge=lfs -text
|
| 2113 |
+
qwen3-4b-proper-unary/model_layers_13_mlp_down_proj_weight.uslots filter=lfs diff=lfs merge=lfs -text
|
| 2114 |
+
qwen3-4b-proper-unary/model_layers_12_self_attn_k_proj_weight.usign filter=lfs diff=lfs merge=lfs -text
|
| 2115 |
+
qwen3-4b-proper-unary/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 2116 |
+
qwen3-4b-proper-unary/model_layers_10_self_attn_o_proj_weight.usign filter=lfs diff=lfs merge=lfs -text
|
| 2117 |
+
qwen3-4b-proper-unary/model_layers_0_self_attn_q_proj_weight.uslots filter=lfs diff=lfs merge=lfs -text
|
| 2118 |
+
qwen3-4b-proper-unary/model_layers_13_mlp_down_proj_weight.usign filter=lfs diff=lfs merge=lfs -text
|
| 2119 |
+
qwen3-4b-proper-unary/model_layers_10_self_attn_v_proj_weight.usign filter=lfs diff=lfs merge=lfs -text
|
| 2120 |
+
qwen3-4b-proper-unary/model_layers_1_self_attn_q_proj_weight.uslots filter=lfs diff=lfs merge=lfs -text
|
| 2121 |
+
qwen3-4b-proper-unary/model_layers_0_self_attn_o_proj_weight.slots filter=lfs diff=lfs merge=lfs -text
|
| 2122 |
+
qwen3-4b-proper-unary/model_layers_12_self_attn_v_proj_weight.uslots filter=lfs diff=lfs merge=lfs -text
|
| 2123 |
+
qwen3-4b-proper-unary/model_layers_10_self_attn_o_proj_weight.uslots filter=lfs diff=lfs merge=lfs -text
|
| 2124 |
+
qwen3-4b-proper-unary/model_layers_11_self_attn_o_proj_weight.usign filter=lfs diff=lfs merge=lfs -text
|
| 2125 |
+
qwen3-4b-proper-unary/model_layers_10_self_attn_q_proj_weight.usign filter=lfs diff=lfs merge=lfs -text
|
| 2126 |
+
qwen3-4b-proper-unary/model_layers_0_mlp_down_proj_weight.usign filter=lfs diff=lfs merge=lfs -text
|
| 2127 |
+
qwen3-4b-proper-unary/model_layers_1_mlp_up_proj_weight.uslots filter=lfs diff=lfs merge=lfs -text
|
| 2128 |
+
qwen3-4b-proper-unary/model_layers_11_mlp_up_proj_weight.usign filter=lfs diff=lfs merge=lfs -text
|
| 2129 |
+
qwen3-4b-proper-unary/model_layers_0_self_attn_v_proj_weight.slots filter=lfs diff=lfs merge=lfs -text
|
| 2130 |
+
qwen3-4b-proper-unary/model_layers_0_self_attn_k_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2131 |
+
qwen3-4b-proper-unary/model_layers_12_mlp_up_proj_weight.usign filter=lfs diff=lfs merge=lfs -text
|
| 2132 |
+
deepseek-r1-1.5b-gunary/model_embed_tokens_weight.fp16 filter=lfs diff=lfs merge=lfs -text
|
| 2133 |
+
qwen3-4b-proper-unary/model_layers_0_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2134 |
+
qwen3-4b-proper-unary/model_layers_12_mlp_down_proj_weight.uslots filter=lfs diff=lfs merge=lfs -text
|
| 2135 |
+
qwen3-4b-proper-unary/model_layers_0_self_attn_k_proj_weight.usign filter=lfs diff=lfs merge=lfs -text
|
| 2136 |
+
qwen3-4b-proper-unary/model_layers_12_mlp_down_proj_weight.usign filter=lfs diff=lfs merge=lfs -text
|
| 2137 |
+
qwen3-4b-proper-unary/model_layers_12_self_attn_o_proj_weight.usign filter=lfs diff=lfs merge=lfs -text
|
| 2138 |
+
qwen3-4b-proper-unary/model_layers_12_self_attn_o_proj_weight.uslots filter=lfs diff=lfs merge=lfs -text
|
| 2139 |
+
qwen3-4b-proper-unary/model_layers_10_mlp_down_proj_weight.uslots filter=lfs diff=lfs merge=lfs -text
|
| 2140 |
+
qwen3-4b-proper-unary/model_layers_0_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2141 |
+
qwen3-4b-proper-unary/model_layers_0_mlp_down_proj_weight.uslots filter=lfs diff=lfs merge=lfs -text
|
| 2142 |
+
qwen3-4b-proper-unary/model_layers_12_self_attn_v_proj_weight.usign filter=lfs diff=lfs merge=lfs -text
|
| 2143 |
+
qwen3-4b-proper-unary/model_layers_0_self_attn_v_proj_weight.usign filter=lfs diff=lfs merge=lfs -text
|
| 2144 |
+
qwen3-4b-proper-unary/model_layers_12_mlp_gate_proj_weight.uslots filter=lfs diff=lfs merge=lfs -text
|
| 2145 |
+
qwen3-4b-proper-unary/model_layers_11_self_attn_o_proj_weight.uslots filter=lfs diff=lfs merge=lfs -text
|
| 2146 |
+
qwen3-4b-proper-unary/model_layers_1_self_attn_v_proj_weight.uslots filter=lfs diff=lfs merge=lfs -text
|
| 2147 |
+
qwen3-4b-proper-unary/model_layers_1_mlp_gate_proj_weight.uslots filter=lfs diff=lfs merge=lfs -text
|
| 2148 |
+
qwen3-4b-proper-unary/model_layers_0_self_attn_o_proj_weight.usign filter=lfs diff=lfs merge=lfs -text
|
| 2149 |
+
qwen3-4b-proper-unary/model_layers_1_mlp_down_proj_weight.uslots filter=lfs diff=lfs merge=lfs -text
|
| 2150 |
+
qwen3-4b-proper-unary/model_layers_11_self_attn_q_proj_weight.usign filter=lfs diff=lfs merge=lfs -text
|
| 2151 |
+
qwen3-4b-proper-unary/model_layers_11_self_attn_v_proj_weight.usign filter=lfs diff=lfs merge=lfs -text
|
| 2152 |
+
qwen3-4b-proper-unary/model_layers_1_self_attn_o_proj_weight.uslots filter=lfs diff=lfs merge=lfs -text
|
| 2153 |
+
qwen3-4b-proper-unary/model_layers_11_mlp_down_proj_weight.uslots filter=lfs diff=lfs merge=lfs -text
|
| 2154 |
+
qwen3-4b-proper-unary/model_layers_10_mlp_up_proj_weight.uslots filter=lfs diff=lfs merge=lfs -text
|
| 2155 |
+
qwen3-4b-proper-unary/model_layers_12_mlp_gate_proj_weight.usign filter=lfs diff=lfs merge=lfs -text
|
| 2156 |
+
qwen3-4b-proper-unary/model_layers_10_self_attn_k_proj_weight.uslots filter=lfs diff=lfs merge=lfs -text
|
| 2157 |
+
qwen3-4b-proper-unary/model_layers_0_mlp_up_proj_weight.slots filter=lfs diff=lfs merge=lfs -text
|
| 2158 |
+
qwen3-4b-proper-unary/model_layers_11_mlp_down_proj_weight.usign filter=lfs diff=lfs merge=lfs -text
|
| 2159 |
+
qwen3-4b-proper-unary/model_layers_10_mlp_up_proj_weight.usign filter=lfs diff=lfs merge=lfs -text
|
| 2160 |
+
qwen3-4b-proper-unary/model_layers_0_self_attn_q_proj_weight.slots filter=lfs diff=lfs merge=lfs -text
|
| 2161 |
+
qwen3-4b-proper-unary/model_layers_11_self_attn_k_proj_weight.usign filter=lfs diff=lfs merge=lfs -text
|
| 2162 |
+
qwen3-4b-proper-unary/model_layers_12_self_attn_q_proj_weight.usign filter=lfs diff=lfs merge=lfs -text
|
| 2163 |
+
qwen3-4b-proper-unary/model_layers_0_mlp_gate_proj_weight.slots filter=lfs diff=lfs merge=lfs -text
|
| 2164 |
+
qwen3-4b-proper-unary/model_layers_12_self_attn_k_proj_weight.uslots filter=lfs diff=lfs merge=lfs -text
|
| 2165 |
+
qwen3-4b-proper-unary/model_layers_0_mlp_down_proj_weight.slots filter=lfs diff=lfs merge=lfs -text
|
| 2166 |
+
qwen3-4b-proper-unary/model_layers_0_self_attn_k_proj_weight.uslots filter=lfs diff=lfs merge=lfs -text
|
| 2167 |
+
qwen3-4b-proper-unary/model_layers_0_self_attn_v_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2168 |
+
qwen3-4b-proper-unary/model_layers_11_mlp_up_proj_weight.uslots filter=lfs diff=lfs merge=lfs -text
|
| 2169 |
+
qwen3-4b-proper-unary/model_layers_11_self_attn_v_proj_weight.uslots filter=lfs diff=lfs merge=lfs -text
|
| 2170 |
+
qwen3-4b-proper-unary/model_layers_0_self_attn_k_proj_weight.slots filter=lfs diff=lfs merge=lfs -text
|
| 2171 |
+
qwen3-4b-proper-unary/model_layers_11_mlp_gate_proj_weight.usign filter=lfs diff=lfs merge=lfs -text
|
| 2172 |
+
qwen3-4b-proper-unary/model_layers_10_self_attn_v_proj_weight.uslots filter=lfs diff=lfs merge=lfs -text
|
| 2173 |
+
qwen3-4b-proper-unary/model_layers_1_mlp_down_proj_weight.usign filter=lfs diff=lfs merge=lfs -text
|
| 2174 |
+
qwen3-4b-proper-unary/model_layers_1_self_attn_k_proj_weight.uslots filter=lfs diff=lfs merge=lfs -text
|
| 2175 |
+
qwen3-4b-proper-unary/model_layers_10_mlp_gate_proj_weight.uslots filter=lfs diff=lfs merge=lfs -text
|
| 2176 |
+
qwen3-4b-proper-unary/model_layers_1_self_attn_k_proj_weight.usign filter=lfs diff=lfs merge=lfs -text
|
| 2177 |
+
qwen3-4b-proper-unary/model_layers_12_mlp_up_proj_weight.uslots filter=lfs diff=lfs merge=lfs -text
|
| 2178 |
+
qwen3-4b-proper-unary/model_layers_10_self_attn_k_proj_weight.usign filter=lfs diff=lfs merge=lfs -text
|
| 2179 |
+
qwen3-4b-proper-unary/model_layers_1_self_attn_o_proj_weight.usign filter=lfs diff=lfs merge=lfs -text
|
| 2180 |
+
qwen3-4b-proper-unary/model_layers_0_mlp_gate_proj_weight.usign filter=lfs diff=lfs merge=lfs -text
|
| 2181 |
+
qwen3-4b-proper-unary/model_layers_0_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2182 |
+
qwen3-4b-proper-unary/model_layers_1_self_attn_v_proj_weight.usign filter=lfs diff=lfs merge=lfs -text
|
| 2183 |
+
qwen3-4b-proper-unary/model_layers_10_mlp_down_proj_weight.usign filter=lfs diff=lfs merge=lfs -text
|
| 2184 |
+
qwen3-4b-proper-unary/model_layers_11_self_attn_k_proj_weight.uslots filter=lfs diff=lfs merge=lfs -text
|
| 2185 |
+
qwen3-4b-proper-unary/model_layers_0_self_attn_q_proj_weight.usign filter=lfs diff=lfs merge=lfs -text
|
| 2186 |
+
qwen3-4b-proper-unary/model_layers_0_self_attn_v_proj_weight.uslots filter=lfs diff=lfs merge=lfs -text
|
| 2187 |
+
qwen3-4b-proper-unary/model_layers_11_self_attn_q_proj_weight.uslots filter=lfs diff=lfs merge=lfs -text
|
| 2188 |
+
qwen3-4b-proper-unary/model_layers_1_mlp_up_proj_weight.usign filter=lfs diff=lfs merge=lfs -text
|
| 2189 |
+
deepseek-r1-1.5b-unary/model_layers_11_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2190 |
+
deepseek-r1-1.5b-unary/model_layers_18_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2191 |
+
deepseek-r1-1.5b-unary/model_layers_6_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2192 |
+
deepseek-r1-1.5b-unary/model_layers_5_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2193 |
+
deepseek-r1-1.5b-unary/model_layers_25_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2194 |
+
deepseek-r1-1.5b-unary/model_layers_0_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2195 |
+
deepseek-r1-1.5b-unary/model_layers_17_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2196 |
+
deepseek-r1-1.5b-unary/model_layers_5_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2197 |
+
deepseek-r1-1.5b-unary/model_layers_18_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2198 |
+
deepseek-r1-1.5b-unary/model_layers_17_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2199 |
+
deepseek-r1-1.5b-unary/model_layers_25_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2200 |
+
deepseek-r1-1.5b-unary/model_layers_21_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2201 |
+
deepseek-r1-1.5b-unary/model_layers_2_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2202 |
+
deepseek-r1-1.5b-unary/model_layers_6_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2203 |
+
qwen3-4b-proper-unary/model_layers_0_mlp_up_proj_weight.uslots filter=lfs diff=lfs merge=lfs -text
|
| 2204 |
+
deepseek-r1-1.5b-unary/model_layers_23_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2205 |
+
deepseek-r1-1.5b-unary/model_layers_14_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2206 |
+
deepseek-r1-1.5b-unary/model_layers_4_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2207 |
+
deepseek-r1-1.5b-unary/model_layers_0_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2208 |
+
deepseek-r1-1.5b-unary/model_layers_10_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2209 |
+
deepseek-r1-1.5b-unary/model_layers_24_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2210 |
+
deepseek-r1-1.5b-unary/model_layers_14_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2211 |
+
deepseek-r1-1.5b-unary/model_layers_0_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2212 |
+
deepseek-r1-1.5b-unary/model_layers_22_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2213 |
+
deepseek-r1-1.5b-unary/model_layers_20_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2214 |
+
deepseek-r1-1.5b-unary/model_layers_4_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2215 |
+
deepseek-r1-1.5b-unary/model_layers_6_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2216 |
+
deepseek-r1-1.5b-unary/model_layers_3_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2217 |
+
deepseek-r1-1.5b-unary/model_layers_11_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2218 |
+
deepseek-r1-1.5b-unary/model_layers_16_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2219 |
+
deepseek-r1-1.5b-unary/model_layers_20_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2220 |
+
deepseek-r1-1.5b-unary/model_layers_7_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2221 |
+
deepseek-r1-1.5b-unary/model_layers_8_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2222 |
+
qwen3-4b-proper-unary/model_layers_0_mlp_gate_proj_weight.uslots filter=lfs diff=lfs merge=lfs -text
|
| 2223 |
+
deepseek-r1-1.5b-unary/model_layers_7_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2224 |
+
deepseek-r1-1.5b-unary/model_layers_7_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2225 |
+
deepseek-r1-1.5b-unary/model_layers_19_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2226 |
+
deepseek-r1-1.5b-unary/model_layers_11_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2227 |
+
deepseek-r1-1.5b-unary/model_layers_7_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2228 |
+
deepseek-r1-1.5b-unary/model_layers_21_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2229 |
+
deepseek-r1-1.5b-unary/model_layers_26_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2230 |
+
deepseek-r1-1.5b-unary/model_layers_19_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2231 |
+
deepseek-r1-1.5b-unary/model_layers_17_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2232 |
+
deepseek-r1-1.5b-unary/model_layers_9_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2233 |
+
deepseek-r1-1.5b-unary/model_layers_18_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2234 |
+
deepseek-r1-1.5b-unary/model_layers_4_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2235 |
+
deepseek-r1-1.5b-unary/model_layers_9_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2236 |
+
deepseek-r1-1.5b-unary/model_layers_8_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2237 |
+
deepseek-r1-1.5b-unary/model_layers_21_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2238 |
+
deepseek-r1-1.5b-unary/model_layers_13_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2239 |
+
deepseek-r1-1.5b-unary/model_layers_13_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2240 |
+
deepseek-r1-1.5b-unary/model_layers_25_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2241 |
+
deepseek-r1-1.5b-unary/model_layers_1_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2242 |
+
deepseek-r1-1.5b-unary/model_layers_10_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2243 |
+
deepseek-r1-1.5b-unary/model_layers_14_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2244 |
+
deepseek-r1-1.5b-unary/model_layers_24_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2245 |
+
deepseek-r1-1.5b-unary/model_layers_17_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2246 |
+
deepseek-r1-1.5b-unary/model_layers_9_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2247 |
+
deepseek-r1-1.5b-unary/model_layers_8_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2248 |
+
deepseek-r1-1.5b-unary/model_layers_24_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2249 |
+
deepseek-r1-1.5b-unary/model_layers_12_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2250 |
+
deepseek-r1-1.5b-unary/model_layers_23_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2251 |
+
deepseek-r1-1.5b-unary/model_layers_12_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2252 |
+
deepseek-r1-1.5b-unary/model_layers_3_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2253 |
+
deepseek-r1-1.5b-unary/model_layers_23_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2254 |
+
deepseek-r1-1.5b-unary/model_layers_26_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2255 |
+
deepseek-r1-1.5b-unary/model_layers_1_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2256 |
+
deepseek-r1-1.5b-unary/model_layers_13_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2257 |
+
deepseek-r1-1.5b-unary/model_layers_14_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2258 |
+
deepseek-r1-1.5b-unary/model_layers_1_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2259 |
+
deepseek-r1-1.5b-unary/model_layers_23_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2260 |
+
deepseek-r1-1.5b-unary/model_layers_3_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2261 |
+
deepseek-r1-1.5b-unary/model_layers_7_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2262 |
+
deepseek-r1-1.5b-unary/model_layers_23_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2263 |
+
deepseek-r1-1.5b-unary/model_layers_2_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2264 |
+
deepseek-r1-1.5b-unary/model_layers_18_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2265 |
+
deepseek-r1-1.5b-unary/model_layers_23_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2266 |
+
deepseek-r1-1.5b-unary/model_layers_9_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2267 |
+
deepseek-r1-1.5b-unary/model_layers_23_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2268 |
+
deepseek-r1-1.5b-unary/model_layers_8_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2269 |
+
deepseek-r1-1.5b-unary/model_layers_21_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2270 |
+
deepseek-r1-1.5b-unary/model_layers_22_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2271 |
+
deepseek-r1-1.5b-unary/model_layers_10_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2272 |
+
deepseek-r1-1.5b-unary/model_layers_20_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2273 |
+
deepseek-r1-1.5b-unary/model_layers_21_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2274 |
+
deepseek-r1-1.5b-unary/model_layers_9_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2275 |
+
deepseek-r1-1.5b-unary/model_layers_18_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2276 |
+
deepseek-r1-1.5b-unary/model_layers_25_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2277 |
+
deepseek-r1-1.5b-unary/model_layers_25_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2278 |
+
deepseek-r1-1.5b-unary/model_layers_19_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2279 |
+
deepseek-r1-1.5b-unary/model_layers_11_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2280 |
+
deepseek-r1-1.5b-unary/model_layers_6_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2281 |
+
deepseek-r1-1.5b-unary/model_layers_1_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2282 |
+
deepseek-r1-1.5b-unary/model_layers_1_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2283 |
+
deepseek-r1-1.5b-unary/model_layers_14_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2284 |
+
deepseek-r1-1.5b-unary/model_layers_7_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2285 |
+
deepseek-r1-1.5b-unary/model_layers_16_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2286 |
+
deepseek-r1-1.5b-unary/model_layers_5_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2287 |
+
deepseek-r1-1.5b-unary/model_layers_26_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2288 |
+
deepseek-r1-1.5b-unary/model_layers_0_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2289 |
+
deepseek-r1-1.5b-unary/model_layers_10_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2290 |
+
deepseek-r1-1.5b-unary/model_layers_9_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2291 |
+
deepseek-r1-1.5b-unary/model_layers_16_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2292 |
+
deepseek-r1-1.5b-unary/model_layers_19_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2293 |
+
deepseek-r1-1.5b-unary/model_layers_26_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2294 |
+
deepseek-r1-1.5b-unary/model_layers_12_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2295 |
+
deepseek-r1-1.5b-unary/model_layers_10_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2296 |
+
deepseek-r1-1.5b-unary/model_layers_18_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2297 |
+
deepseek-r1-1.5b-unary/model_layers_7_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2298 |
+
deepseek-r1-1.5b-unary/model_layers_8_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2299 |
+
deepseek-r1-1.5b-unary/model_layers_6_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2300 |
+
deepseek-r1-1.5b-unary/model_layers_24_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2301 |
+
deepseek-r1-1.5b-unary/model_layers_16_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2302 |
+
deepseek-r1-1.5b-unary/model_layers_15_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2303 |
+
deepseek-r1-1.5b-unary/model_layers_0_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2304 |
+
deepseek-r1-1.5b-unary/model_layers_25_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2305 |
+
deepseek-r1-1.5b-unary/model_layers_3_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2306 |
+
deepseek-r1-1.5b-unary/model_layers_20_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2307 |
+
deepseek-r1-1.5b-unary/model_layers_3_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2308 |
+
deepseek-r1-1.5b-unary/model_layers_22_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2309 |
+
deepseek-r1-1.5b-unary/model_layers_14_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2310 |
+
deepseek-r1-1.5b-unary/model_layers_2_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2311 |
+
deepseek-r1-1.5b-unary/model_layers_9_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2312 |
+
deepseek-r1-1.5b-unary/model_layers_26_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2313 |
+
deepseek-r1-1.5b-unary/model_layers_16_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2314 |
+
deepseek-r1-1.5b-unary/model_layers_3_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2315 |
+
deepseek-r1-1.5b-unary/model_layers_22_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2316 |
+
deepseek-r1-1.5b-unary/model_layers_25_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2317 |
+
deepseek-r1-1.5b-unary/model_layers_1_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2318 |
+
deepseek-r1-1.5b-unary/model_layers_22_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2319 |
+
deepseek-r1-1.5b-unary/model_layers_12_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2320 |
+
deepseek-r1-1.5b-unary/model_layers_22_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2321 |
+
deepseek-r1-1.5b-unary/model_layers_19_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2322 |
+
deepseek-r1-1.5b-unary/model_layers_26_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2323 |
+
deepseek-r1-1.5b-unary/model_layers_24_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2324 |
+
deepseek-r1-1.5b-unary/model_layers_22_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2325 |
+
deepseek-r1-1.5b-unary/model_layers_13_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2326 |
+
deepseek-r1-1.5b-unary/model_layers_0_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2327 |
+
deepseek-r1-1.5b-unary/model_layers_15_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2328 |
+
deepseek-r1-1.5b-unary/model_layers_18_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2329 |
+
deepseek-r1-1.5b-unary/model_layers_5_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2330 |
+
deepseek-r1-1.5b-unary/model_layers_21_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2331 |
+
deepseek-r1-1.5b-unary/model_layers_12_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2332 |
+
deepseek-r1-1.5b-unary/model_layers_11_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2333 |
+
deepseek-r1-1.5b-unary/model_layers_7_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2334 |
+
deepseek-r1-1.5b-unary/model_layers_26_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2335 |
+
deepseek-r1-1.5b-unary/model_layers_11_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2336 |
+
deepseek-r1-1.5b-unary/model_layers_4_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2337 |
+
deepseek-r1-1.5b-unary/model_layers_2_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2338 |
+
deepseek-r1-1.5b-unary/model_layers_14_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2339 |
+
deepseek-r1-1.5b-unary/model_layers_20_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2340 |
+
deepseek-r1-1.5b-unary/model_layers_19_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2341 |
+
deepseek-r1-1.5b-unary/model_layers_27_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2342 |
+
deepseek-r1-1.5b-unary/model_layers_14_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2343 |
+
deepseek-r1-1.5b-unary/model_layers_26_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2344 |
+
deepseek-r1-1.5b-unary/model_layers_15_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2345 |
+
deepseek-r1-1.5b-unary/model_layers_17_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2346 |
+
deepseek-r1-1.5b-unary/model_layers_19_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2347 |
+
deepseek-r1-1.5b-unary/model_layers_10_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2348 |
+
deepseek-r1-1.5b-unary/model_layers_2_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2349 |
+
deepseek-r1-1.5b-unary/model_layers_5_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2350 |
+
deepseek-r1-1.5b-unary/model_layers_16_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2351 |
+
qwen3-4b-thinking-unary/model_embed_tokens_weight.fp16 filter=lfs diff=lfs merge=lfs -text
|
| 2352 |
+
qwen3-4b-thinking-unary/model_layers_17_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2353 |
+
qwen3-4b-thinking-unary/model_layers_31_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2354 |
+
qwen3-4b-thinking-unary/model_layers_14_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2355 |
+
qwen3-4b-thinking-unary/model_layers_1_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2356 |
+
qwen3-4b-thinking-unary/model_layers_20_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2357 |
+
qwen3-4b-thinking-unary/model_layers_2_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2358 |
+
qwen3-4b-thinking-unary/model_layers_30_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2359 |
+
qwen3-4b-thinking-unary/model_layers_5_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2360 |
+
qwen3-4b-thinking-unary/model_layers_30_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2361 |
+
qwen3-4b-thinking-unary/model_layers_7_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2362 |
+
qwen3-4b-thinking-unary/model_layers_35_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2363 |
+
qwen3-4b-thinking-unary/model_layers_33_self_attn_k_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2364 |
+
qwen3-4b-thinking-unary/model_layers_35_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2365 |
+
qwen3-4b-thinking-unary/model_layers_34_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2366 |
+
qwen3-4b-thinking-unary/model_layers_23_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2367 |
+
qwen3-4b-thinking-unary/model_layers_28_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2368 |
+
qwen3-4b-thinking-unary/model_layers_16_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2369 |
+
qwen3-4b-thinking-unary/model_layers_11_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2370 |
+
qwen3-4b-thinking-unary/model_layers_32_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2371 |
+
qwen3-4b-thinking-unary/model_layers_7_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2372 |
+
qwen3-4b-thinking-unary/model_layers_4_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2373 |
+
qwen3-4b-thinking-unary/model_layers_34_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2374 |
+
qwen3-4b-thinking-unary/model_layers_13_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2375 |
+
qwen3-4b-thinking-unary/model_layers_28_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2376 |
+
qwen3-4b-thinking-unary/model_layers_15_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2377 |
+
qwen3-4b-thinking-unary/model_layers_1_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2378 |
+
qwen3-4b-thinking-unary/model_layers_12_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2379 |
+
qwen3-4b-thinking-unary/model_layers_3_self_attn_k_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2380 |
+
qwen3-4b-thinking-unary/model_layers_20_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2381 |
+
qwen3-4b-thinking-unary/model_layers_8_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2382 |
+
qwen3-4b-thinking-unary/model_layers_8_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2383 |
+
qwen3-4b-thinking-unary/model_layers_33_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2384 |
+
qwen3-4b-thinking-unary/model_layers_33_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2385 |
+
qwen3-4b-thinking-unary/model_layers_24_self_attn_v_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2386 |
+
qwen3-4b-thinking-unary/model_layers_30_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2387 |
+
qwen3-4b-thinking-unary/model_layers_0_self_attn_v_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2388 |
+
qwen3-4b-thinking-unary/model_layers_23_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2389 |
+
qwen3-4b-thinking-unary/model_layers_12_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2390 |
+
qwen3-4b-thinking-unary/model_layers_25_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2391 |
+
qwen3-4b-thinking-unary/model_layers_13_self_attn_k_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2392 |
+
qwen3-4b-thinking-unary/model_layers_2_self_attn_k_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2393 |
+
qwen3-4b-thinking-unary/model_layers_24_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2394 |
+
qwen3-4b-thinking-unary/model_layers_2_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2395 |
+
qwen3-4b-thinking-unary/model_layers_33_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2396 |
+
qwen3-4b-thinking-unary/model_layers_26_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2397 |
+
qwen3-4b-thinking-unary/model_layers_14_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2398 |
+
qwen3-4b-thinking-unary/model_layers_18_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2399 |
+
qwen3-4b-thinking-unary/model_layers_3_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2400 |
+
qwen3-4b-thinking-unary/model_layers_12_self_attn_v_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2401 |
+
qwen3-4b-thinking-unary/model_layers_5_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2402 |
+
qwen3-4b-thinking-unary/model_layers_11_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2403 |
+
qwen3-4b-thinking-unary/model_layers_28_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2404 |
+
qwen3-4b-thinking-unary/model_layers_29_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2405 |
+
qwen3-4b-thinking-unary/model_layers_31_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2406 |
+
qwen3-4b-thinking-unary/model_layers_20_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2407 |
+
qwen3-4b-thinking-unary/model_layers_17_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2408 |
+
qwen3-4b-thinking-unary/model_layers_0_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2409 |
+
qwen3-4b-thinking-unary/model_layers_14_self_attn_v_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2410 |
+
qwen3-4b-thinking-unary/model_layers_12_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2411 |
+
qwen3-4b-thinking-unary/model_layers_6_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2412 |
+
qwen3-4b-thinking-unary/model_layers_35_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2413 |
+
qwen3-4b-thinking-unary/model_layers_33_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2414 |
+
qwen3-4b-thinking-unary/model_layers_10_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2415 |
+
qwen3-4b-thinking-unary/model_layers_34_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2416 |
+
qwen3-4b-thinking-unary/model_layers_32_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2417 |
+
qwen3-4b-thinking-unary/model_layers_8_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2418 |
+
qwen3-4b-thinking-unary/model_layers_35_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2419 |
+
qwen3-4b-thinking-unary/model_layers_14_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2420 |
+
qwen3-4b-thinking-unary/model_layers_31_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2421 |
+
qwen3-4b-thinking-unary/model_layers_12_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2422 |
+
qwen3-4b-thinking-unary/model_layers_21_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2423 |
+
qwen3-4b-thinking-unary/model_layers_6_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2424 |
+
qwen3-4b-thinking-unary/model_layers_12_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2425 |
+
qwen3-4b-thinking-unary/model_layers_15_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2426 |
+
qwen3-4b-thinking-unary/model_layers_27_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2427 |
+
qwen3-4b-thinking-unary/model_layers_16_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2428 |
+
qwen3-4b-thinking-unary/model_layers_31_self_attn_k_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2429 |
+
qwen3-4b-thinking-unary/model_layers_26_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2430 |
+
qwen3-4b-thinking-unary/model_layers_7_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2431 |
+
qwen3-4b-thinking-unary/model_layers_11_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2432 |
+
qwen3-4b-thinking-unary/model_layers_15_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2433 |
+
qwen3-4b-thinking-unary/model_layers_10_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2434 |
+
qwen3-4b-thinking-unary/model_layers_8_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2435 |
+
qwen3-4b-thinking-unary/model_layers_9_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2436 |
+
qwen3-4b-thinking-unary/model_layers_1_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2437 |
+
qwen3-4b-thinking-unary/model_layers_32_self_attn_k_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2438 |
+
qwen3-4b-thinking-unary/model_layers_19_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2439 |
+
qwen3-4b-thinking-unary/model_layers_21_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2440 |
+
qwen3-4b-thinking-unary/model_layers_4_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2441 |
+
qwen3-4b-thinking-unary/model_layers_32_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2442 |
+
qwen3-4b-thinking-unary/model_layers_10_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2443 |
+
qwen3-4b-thinking-unary/model_layers_9_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2444 |
+
qwen3-4b-thinking-unary/model_layers_13_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2445 |
+
qwen3-4b-thinking-unary/model_layers_21_self_attn_v_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2446 |
+
qwen3-4b-thinking-unary/model_layers_5_self_attn_v_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2447 |
+
qwen3-4b-thinking-unary/model_layers_4_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2448 |
+
qwen3-4b-thinking-unary/model_layers_13_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2449 |
+
qwen3-4b-thinking-unary/model_layers_27_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2450 |
+
qwen3-4b-thinking-unary/model_layers_10_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2451 |
+
qwen3-4b-thinking-unary/model_layers_11_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2452 |
+
qwen3-4b-thinking-unary/model_layers_4_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2453 |
+
qwen3-4b-thinking-unary/model_layers_19_self_attn_v_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2454 |
+
qwen3-4b-thinking-unary/model_layers_29_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2455 |
+
qwen3-4b-thinking-unary/model_layers_18_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2456 |
+
qwen3-4b-thinking-unary/model_layers_23_self_attn_v_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2457 |
+
qwen3-4b-thinking-unary/model_layers_28_self_attn_v_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2458 |
+
qwen3-4b-thinking-unary/model_layers_26_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2459 |
+
qwen3-4b-thinking-unary/model_layers_32_self_attn_v_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2460 |
+
qwen3-4b-thinking-unary/model_layers_28_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2461 |
+
qwen3-4b-thinking-unary/model_layers_6_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2462 |
+
qwen3-4b-thinking-unary/model_layers_27_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2463 |
+
qwen3-4b-thinking-unary/model_layers_18_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2464 |
+
qwen3-4b-thinking-unary/model_layers_27_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2465 |
+
qwen3-4b-thinking-unary/model_layers_17_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2466 |
+
qwen3-4b-thinking-unary/model_layers_34_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2467 |
+
qwen3-4b-thinking-unary/model_layers_31_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2468 |
+
qwen3-4b-thinking-unary/model_layers_18_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2469 |
+
qwen3-4b-thinking-unary/model_layers_19_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2470 |
+
qwen3-4b-thinking-unary/model_layers_22_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2471 |
+
qwen3-4b-thinking-unary/model_layers_3_self_attn_v_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2472 |
+
qwen3-4b-thinking-unary/model_layers_31_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2473 |
+
qwen3-4b-thinking-unary/model_layers_22_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2474 |
+
qwen3-4b-thinking-unary/model_layers_11_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2475 |
+
qwen3-4b-thinking-unary/model_layers_7_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2476 |
+
qwen3-4b-thinking-unary/model_layers_3_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2477 |
+
qwen3-4b-thinking-unary/model_layers_32_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2478 |
+
qwen3-4b-thinking-unary/model_layers_8_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2479 |
+
qwen3-4b-thinking-unary/model_layers_21_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2480 |
+
qwen3-4b-thinking-unary/model_layers_32_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2481 |
+
qwen3-4b-thinking-unary/model_layers_34_self_attn_v_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2482 |
+
qwen3-4b-thinking-unary/model_layers_25_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2483 |
+
qwen3-4b-thinking-unary/model_layers_27_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2484 |
+
qwen3-4b-thinking-unary/model_layers_17_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2485 |
+
qwen3-4b-thinking-unary/model_layers_0_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2486 |
+
qwen3-4b-thinking-unary/model_layers_3_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2487 |
+
qwen3-4b-thinking-unary/model_layers_2_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2488 |
+
qwen3-4b-thinking-unary/model_layers_29_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2489 |
+
qwen3-4b-thinking-unary/model_layers_5_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2490 |
+
qwen3-4b-thinking-unary/model_layers_25_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2491 |
+
qwen3-4b-thinking-unary/model_layers_27_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2492 |
+
qwen3-4b-thinking-unary/model_layers_11_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2493 |
+
qwen3-4b-thinking-unary/model_layers_24_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2494 |
+
qwen3-4b-thinking-unary/model_layers_23_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2495 |
+
qwen3-4b-thinking-unary/model_layers_23_self_attn_k_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2496 |
+
qwen3-4b-thinking-unary/model_layers_5_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2497 |
+
qwen3-4b-thinking-unary/model_layers_14_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2498 |
+
qwen3-4b-thinking-unary/model_layers_2_self_attn_v_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2499 |
+
qwen3-4b-thinking-unary/model_layers_33_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2500 |
+
qwen3-4b-thinking-unary/model_layers_34_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2501 |
+
qwen3-4b-thinking-unary/model_layers_12_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2502 |
+
qwen3-4b-thinking-unary/model_layers_23_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2503 |
+
qwen3-4b-thinking-unary/model_layers_2_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2504 |
+
qwen3-4b-thinking-unary/model_layers_21_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2505 |
+
qwen3-4b-thinking-unary/model_layers_20_self_attn_v_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2506 |
+
qwen3-4b-thinking-unary/model_layers_34_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2507 |
+
qwen3-4b-thinking-unary/model_layers_1_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2508 |
+
qwen3-4b-thinking-unary/model_layers_25_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2509 |
+
qwen3-4b-thinking-unary/model_layers_2_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2510 |
+
qwen3-4b-thinking-unary/model_layers_5_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2511 |
+
qwen3-4b-thinking-unary/model_layers_0_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2512 |
+
qwen3-4b-thinking-unary/model_layers_3_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2513 |
+
qwen3-4b-thinking-unary/model_layers_7_self_attn_k_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2514 |
+
qwen3-4b-thinking-unary/model_layers_19_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2515 |
+
qwen3-4b-thinking-unary/model_layers_30_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2516 |
+
qwen3-4b-thinking-unary/model_layers_27_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2517 |
+
qwen3-4b-thinking-unary/model_layers_16_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2518 |
+
qwen3-4b-thinking-unary/model_layers_27_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2519 |
+
qwen3-4b-thinking-hf/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
deepseek-r1-1.5b-gunary/config.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"hidden_size": 1536,
|
| 3 |
+
"intermediate_size": 8960,
|
| 4 |
+
"num_attention_heads": 12,
|
| 5 |
+
"num_key_value_heads": 2,
|
| 6 |
+
"num_hidden_layers": 28,
|
| 7 |
+
"vocab_size": 151936,
|
| 8 |
+
"head_dim": 128,
|
| 9 |
+
"rope_theta": 1000000.0,
|
| 10 |
+
"rms_norm_eps": 1e-06,
|
| 11 |
+
"n_planes": 7,
|
| 12 |
+
"group_size": 32,
|
| 13 |
+
"quant_type": "unary_group"
|
| 14 |
+
}
|
deepseek-r1-1.5b-gunary/lm_head_weight.fp16
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cca68befcc8201afc0eb54623dd20bd2af92acfe3cff767e6f8e6c0ddad2a397
|
| 3 |
+
size 466747392
|
deepseek-r1-1.5b-gunary/model_embed_tokens_weight.fp16
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e55610c68685326d482c594ff3bb16141e71a0d219fe729211562ab630953c6e
|
| 3 |
+
size 466747392
|
deepseek-r1-1.5b-gunary/model_layers_0_self_attn_k_proj_bias.fp16
ADDED
|
Binary file (512 Bytes). View file
|
|
|
deepseek-r1-1.5b-gunary/model_layers_0_self_attn_k_proj_weight.sign
ADDED
|
Binary file (49.2 kB). View file
|
|
|
deepseek-r1-1.5b-gunary/model_layers_10_input_layernorm_weight.fp16
ADDED
|
Binary file (3.07 kB). View file
|
|
|
deepseek-r1-1.5b-gunary/model_layers_10_self_attn_k_proj_weight.gscales
ADDED
|
Binary file (49.2 kB). View file
|
|
|
deepseek-r1-1.5b-gunary/model_layers_10_self_attn_q_proj_bias.fp16
ADDED
|
Binary file (3.07 kB). View file
|
|
|
deepseek-r1-1.5b-gunary/model_layers_11_self_attn_k_proj_bias.fp16
ADDED
|
Binary file (512 Bytes). View file
|
|
|
deepseek-r1-1.5b-gunary/model_layers_11_self_attn_k_proj_weight.sign
ADDED
|
Binary file (49.2 kB). View file
|
|
|
deepseek-r1-1.5b-gunary/model_layers_11_self_attn_q_proj_bias.fp16
ADDED
|
Binary file (3.07 kB). View file
|
|
|
deepseek-r1-1.5b-gunary/model_layers_11_self_attn_v_proj_bias.fp16
ADDED
|
Binary file (512 Bytes). View file
|
|
|
deepseek-r1-1.5b-gunary/model_layers_12_input_layernorm_weight.fp16
ADDED
|
Binary file (3.07 kB). View file
|
|
|
deepseek-r1-1.5b-gunary/model_layers_12_self_attn_v_proj_weight.gscales
ADDED
|
Binary file (49.2 kB). View file
|
|
|
deepseek-r1-1.5b-gunary/model_layers_13_input_layernorm_weight.fp16
ADDED
|
Binary file (3.07 kB). View file
|
|
|
deepseek-r1-1.5b-gunary/model_layers_13_self_attn_k_proj_bias.fp16
ADDED
|
Binary file (512 Bytes). View file
|
|
|
deepseek-r1-1.5b-gunary/model_layers_13_self_attn_v_proj_weight.gscales
ADDED
|
Binary file (49.2 kB). View file
|
|
|
deepseek-r1-1.5b-gunary/model_layers_13_self_attn_v_proj_weight.sign
ADDED
|
Binary file (49.2 kB). View file
|
|
|
deepseek-r1-1.5b-gunary/model_layers_14_self_attn_k_proj_weight.gscales
ADDED
|
Binary file (49.2 kB). View file
|
|
|
deepseek-r1-1.5b-gunary/model_layers_14_self_attn_q_proj_bias.fp16
ADDED
|
Binary file (3.07 kB). View file
|
|
|
deepseek-r1-1.5b-gunary/model_layers_14_self_attn_v_proj_bias.fp16
ADDED
|
Binary file (512 Bytes). View file
|
|
|
deepseek-r1-1.5b-gunary/model_layers_15_self_attn_k_proj_weight.sign
ADDED
|
Binary file (49.2 kB). View file
|
|
|
deepseek-r1-1.5b-gunary/model_layers_16_self_attn_k_proj_weight.sign
ADDED
|
Binary file (49.2 kB). View file
|
|
|
deepseek-r1-1.5b-gunary/model_layers_16_self_attn_q_proj_bias.fp16
ADDED
|
Binary file (3.07 kB). View file
|
|
|
deepseek-r1-1.5b-gunary/model_layers_16_self_attn_q_proj_weight.sign
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e2b813fc3e9787f2d0bc03c73674ad124a10e24382e18b0b29acba670d9f8e33
|
| 3 |
+
size 294912
|
deepseek-r1-1.5b-gunary/model_layers_16_self_attn_v_proj_bias.fp16
ADDED
|
Binary file (512 Bytes). View file
|
|
|
deepseek-r1-1.5b-gunary/model_layers_16_self_attn_v_proj_weight.gscales
ADDED
|
Binary file (49.2 kB). View file
|
|
|
deepseek-r1-1.5b-gunary/model_layers_17_input_layernorm_weight.fp16
ADDED
|
Binary file (3.07 kB). View file
|
|
|
deepseek-r1-1.5b-gunary/model_layers_17_post_attention_layernorm_weight.fp16
ADDED
|
Binary file (3.07 kB). View file
|
|
|
deepseek-r1-1.5b-gunary/model_layers_17_self_attn_q_proj_bias.fp16
ADDED
|
Binary file (3.07 kB). View file
|
|
|
deepseek-r1-1.5b-gunary/model_layers_17_self_attn_v_proj_weight.sign
ADDED
|
Binary file (49.2 kB). View file
|
|
|
deepseek-r1-1.5b-gunary/model_layers_18_input_layernorm_weight.fp16
ADDED
|
Binary file (3.07 kB). View file
|
|
|
deepseek-r1-1.5b-gunary/model_layers_18_self_attn_k_proj_weight.sign
ADDED
|
Binary file (49.2 kB). View file
|
|
|
deepseek-r1-1.5b-gunary/model_layers_19_self_attn_k_proj_weight.sign
ADDED
|
Binary file (49.2 kB). View file
|
|
|
deepseek-r1-1.5b-gunary/model_layers_19_self_attn_q_proj_weight.planes
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a0b6dafcb3699083eab377e291ab7c7db974f7d4b5328d082e9d095667dc39d6
|
| 3 |
+
size 2064384
|
deepseek-r1-1.5b-gunary/model_layers_1_self_attn_q_proj_bias.fp16
ADDED
|
Binary file (3.07 kB). View file
|
|
|
deepseek-r1-1.5b-gunary/model_layers_1_self_attn_v_proj_weight.sign
ADDED
|
Binary file (49.2 kB). View file
|
|
|
deepseek-r1-1.5b-gunary/model_layers_20_input_layernorm_weight.fp16
ADDED
|
Binary file (3.07 kB). View file
|
|
|
deepseek-r1-1.5b-gunary/model_layers_20_post_attention_layernorm_weight.fp16
ADDED
|
Binary file (3.07 kB). View file
|
|
|
deepseek-r1-1.5b-gunary/model_layers_20_self_attn_k_proj_bias.fp16
ADDED
|
Binary file (512 Bytes). View file
|
|
|
deepseek-r1-1.5b-gunary/model_layers_20_self_attn_k_proj_weight.sign
ADDED
|
Binary file (49.2 kB). View file
|
|
|
deepseek-r1-1.5b-gunary/model_layers_21_post_attention_layernorm_weight.fp16
ADDED
|
Binary file (3.07 kB). View file
|
|
|
deepseek-r1-1.5b-gunary/model_layers_21_self_attn_k_proj_weight.gscales
ADDED
|
Binary file (49.2 kB). View file
|
|
|
deepseek-r1-1.5b-gunary/model_layers_21_self_attn_v_proj_bias.fp16
ADDED
|
Binary file (512 Bytes). View file
|
|
|
deepseek-r1-1.5b-gunary/model_layers_21_self_attn_v_proj_weight.gscales
ADDED
|
Binary file (49.2 kB). View file
|
|
|
deepseek-r1-1.5b-gunary/model_layers_22_self_attn_k_proj_weight.sign
ADDED
|
Binary file (49.2 kB). View file
|
|
|
deepseek-r1-1.5b-gunary/model_layers_22_self_attn_q_proj_bias.fp16
ADDED
|
Binary file (3.07 kB). View file
|
|
|
deepseek-r1-1.5b-gunary/model_layers_22_self_attn_v_proj_weight.gscales
ADDED
|
Binary file (49.2 kB). View file
|
|
|
deepseek-r1-1.5b-gunary/model_layers_22_self_attn_v_proj_weight.sign
ADDED
|
Binary file (49.2 kB). View file
|
|
|