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 +248 -0
- deepseek-r1-1.5b-gunary/model_layers_0_self_attn_v_proj_bias.fp16 +0 -0
- deepseek-r1-1.5b-gunary/model_layers_5_self_attn_v_proj_weight.gscales +0 -0
- deepseek-r1-1.5b-ternary/model_layers_0_mlp_down_proj_weight.pos +3 -0
- deepseek-r1-1.5b-ternary/model_layers_0_mlp_up_proj_weight.neg +3 -0
- deepseek-r1-1.5b-ternary/model_layers_0_mlp_up_proj_weight.pos +3 -0
- deepseek-r1-1.5b-ternary/model_layers_0_self_attn_o_proj_weight.neg +3 -0
- deepseek-r1-1.5b-ternary/model_layers_0_self_attn_o_proj_weight.pos +3 -0
- deepseek-r1-1.5b-ternary/model_layers_0_self_attn_q_proj_weight.pos +3 -0
- deepseek-r1-1.5b-ternary/model_layers_10_mlp_up_proj_weight.pos +3 -0
- deepseek-r1-1.5b-ternary/model_layers_11_mlp_down_proj_weight.neg +3 -0
- deepseek-r1-1.5b-ternary/model_layers_11_mlp_up_proj_weight.pos +3 -0
- deepseek-r1-1.5b-ternary/model_layers_11_self_attn_q_proj_weight.neg +3 -0
- deepseek-r1-1.5b-ternary/model_layers_12_mlp_down_proj_weight.neg +3 -0
- deepseek-r1-1.5b-ternary/model_layers_13_mlp_gate_proj_weight.neg +3 -0
- deepseek-r1-1.5b-ternary/model_layers_13_mlp_up_proj_weight.neg +3 -0
- deepseek-r1-1.5b-ternary/model_layers_13_self_attn_o_proj_weight.neg +3 -0
- deepseek-r1-1.5b-ternary/model_layers_13_self_attn_o_proj_weight.pos +3 -0
- deepseek-r1-1.5b-ternary/model_layers_13_self_attn_q_proj_weight.pos +3 -0
- deepseek-r1-1.5b-ternary/model_layers_14_mlp_gate_proj_weight.pos +3 -0
- deepseek-r1-1.5b-ternary/model_layers_15_mlp_down_proj_weight.neg +3 -0
- deepseek-r1-1.5b-ternary/model_layers_15_mlp_gate_proj_weight.pos +3 -0
- deepseek-r1-1.5b-ternary/model_layers_15_self_attn_o_proj_weight.neg +3 -0
- deepseek-r1-1.5b-ternary/model_layers_16_mlp_gate_proj_weight.pos +3 -0
- deepseek-r1-1.5b-ternary/model_layers_16_self_attn_o_proj_weight.neg +3 -0
- deepseek-r1-1.5b-ternary/model_layers_16_self_attn_q_proj_weight.neg +3 -0
- deepseek-r1-1.5b-ternary/model_layers_17_mlp_up_proj_weight.pos +3 -0
- deepseek-r1-1.5b-ternary/model_layers_17_self_attn_q_proj_weight.neg +3 -0
- deepseek-r1-1.5b-ternary/model_layers_17_self_attn_q_proj_weight.pos +3 -0
- deepseek-r1-1.5b-ternary/model_layers_18_mlp_gate_proj_weight.pos +3 -0
- deepseek-r1-1.5b-ternary/model_layers_19_mlp_gate_proj_weight.pos +3 -0
- deepseek-r1-1.5b-ternary/model_layers_19_mlp_up_proj_weight.neg +3 -0
- deepseek-r1-1.5b-ternary/model_layers_19_mlp_up_proj_weight.pos +3 -0
- deepseek-r1-1.5b-ternary/model_layers_19_self_attn_o_proj_weight.pos +3 -0
- deepseek-r1-1.5b-ternary/model_layers_1_mlp_up_proj_weight.neg +3 -0
- deepseek-r1-1.5b-ternary/model_layers_20_mlp_down_proj_weight.pos +3 -0
- deepseek-r1-1.5b-ternary/model_layers_20_self_attn_o_proj_weight.pos +3 -0
- deepseek-r1-1.5b-ternary/model_layers_20_self_attn_q_proj_weight.pos +3 -0
- deepseek-r1-1.5b-ternary/model_layers_21_mlp_down_proj_weight.neg +3 -0
- deepseek-r1-1.5b-ternary/model_layers_22_mlp_up_proj_weight.neg +3 -0
- deepseek-r1-1.5b-ternary/model_layers_22_self_attn_o_proj_weight.neg +3 -0
- deepseek-r1-1.5b-ternary/model_layers_24_mlp_down_proj_weight.neg +3 -0
- deepseek-r1-1.5b-ternary/model_layers_24_mlp_down_proj_weight.pos +3 -0
- deepseek-r1-1.5b-ternary/model_layers_24_mlp_gate_proj_weight.pos +3 -0
- deepseek-r1-1.5b-ternary/model_layers_24_self_attn_q_proj_weight.pos +3 -0
- deepseek-r1-1.5b-ternary/model_layers_25_self_attn_o_proj_weight.pos +3 -0
- deepseek-r1-1.5b-ternary/model_layers_25_self_attn_q_proj_weight.neg +3 -0
- deepseek-r1-1.5b-ternary/model_layers_26_mlp_down_proj_weight.pos +3 -0
- deepseek-r1-1.5b-ternary/model_layers_27_mlp_down_proj_weight.pos +3 -0
- deepseek-r1-1.5b-ternary/model_layers_27_mlp_gate_proj_weight.neg +3 -0
.gitattributes
CHANGED
|
@@ -2517,3 +2517,251 @@ qwen3-4b-thinking-unary/model_layers_27_self_attn_v_proj_weight.planes filter=lf
|
|
| 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
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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
|
| 2520 |
+
qwen3-4b-log5-unary/model_layers_29_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2521 |
+
qwen3-4b-log5-unary/model_layers_28_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2522 |
+
qwen3-4b-log5-unary/model_layers_23_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2523 |
+
qwen3-4b-log5-unary/model_layers_14_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2524 |
+
qwen3-4b-log5-unary/model_layers_14_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2525 |
+
qwen3-4b-log5-unary/model_layers_33_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2526 |
+
qwen3-4b-log5-unary/model_layers_34_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2527 |
+
qwen3-4b-log5-unary/model_layers_4_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2528 |
+
qwen3-4b-log5-unary/model_layers_0_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2529 |
+
qwen3-4b-log5-unary/model_layers_1_self_attn_v_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2530 |
+
qwen3-4b-log5-unary/model_layers_30_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2531 |
+
qwen3-4b-log5-unary/model_layers_8_self_attn_k_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2532 |
+
qwen3-4b-log5-unary/model_layers_34_self_attn_k_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2533 |
+
qwen3-4b-log5-unary/model_layers_10_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2534 |
+
qwen3-4b-log5-unary/model_layers_24_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2535 |
+
qwen3-4b-log5-unary/model_layers_28_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2536 |
+
qwen3-4b-log5-unary/model_layers_0_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2537 |
+
qwen3-4b-log5-unary/model_layers_20_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2538 |
+
qwen3-4b-log5-unary/model_layers_19_self_attn_k_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2539 |
+
qwen3-4b-log5-unary/model_layers_31_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2540 |
+
qwen3-4b-log5-unary/model_layers_22_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2541 |
+
qwen3-4b-log5-unary/model_layers_32_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2542 |
+
qwen3-4b-log5-unary/model_layers_11_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2543 |
+
qwen3-4b-log5-unary/model_layers_8_self_attn_v_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2544 |
+
qwen3-4b-log5-unary/model_layers_6_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2545 |
+
qwen3-4b-log5-unary/model_layers_4_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2546 |
+
qwen3-4b-log5-unary/model_layers_3_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2547 |
+
qwen3-4b-log5-unary/model_layers_16_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2548 |
+
qwen3-4b-log5-unary/model_layers_20_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2549 |
+
qwen3-4b-log5-unary/model_layers_7_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2550 |
+
qwen3-4b-log5-unary/model_layers_8_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2551 |
+
qwen3-4b-log5-unary/model_layers_11_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2552 |
+
qwen3-4b-log5-unary/model_layers_7_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2553 |
+
qwen3-4b-log5-unary/model_layers_7_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2554 |
+
qwen3-4b-log5-unary/model_layers_19_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2555 |
+
qwen3-4b-log5-unary/model_layers_34_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2556 |
+
qwen3-4b-log5-unary/model_layers_7_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2557 |
+
qwen3-4b-log5-unary/model_layers_17_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2558 |
+
qwen3-4b-log5-unary/model_layers_32_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2559 |
+
qwen3-4b-log5-unary/model_layers_21_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2560 |
+
qwen3-4b-log5-unary/model_layers_26_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2561 |
+
qwen3-4b-log5-unary/model_layers_22_self_attn_v_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2562 |
+
qwen3-4b-log5-unary/model_layers_19_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2563 |
+
qwen3-4b-log5-unary/model_layers_18_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2564 |
+
qwen3-4b-log5-unary/model_layers_9_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2565 |
+
qwen3-4b-log5-unary/model_layers_4_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2566 |
+
qwen3-4b-log5-unary/model_layers_25_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2567 |
+
qwen3-4b-log-unary/model_embed_tokens_weight.fp16 filter=lfs diff=lfs merge=lfs -text
|
| 2568 |
+
qwen3-4b-log5-unary/model_layers_9_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2569 |
+
qwen3-4b-log5-unary/model_layers_8_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2570 |
+
qwen3-4b-log5-unary/model_layers_28_self_attn_k_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2571 |
+
qwen3-4b-log5-unary/model_layers_21_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2572 |
+
qwen3-4b-log5-unary/model_layers_35_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2573 |
+
qwen3-4b-log5-unary/model_layers_13_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2574 |
+
qwen3-4b-log5-unary/model_layers_1_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2575 |
+
qwen3-4b-log5-unary/model_layers_13_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2576 |
+
qwen3-4b-log5-unary/model_layers_10_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2577 |
+
qwen3-4b-log5-unary/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 2578 |
+
qwen3-4b-log5-unary/model_layers_11_self_attn_k_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2579 |
+
qwen3-4b-log5-unary/model_layers_14_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2580 |
+
qwen3-4b-log5-unary/model_layers_24_self_attn_k_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2581 |
+
qwen3-4b-log5-unary/model_layers_17_self_attn_v_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2582 |
+
qwen3-4b-log5-unary/model_layers_5_self_attn_k_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2583 |
+
qwen3-4b-log5-unary/model_layers_24_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2584 |
+
qwen3-4b-log5-unary/model_layers_9_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2585 |
+
qwen3-4b-log5-unary/model_layers_17_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2586 |
+
qwen3-4b-log5-unary/model_layers_23_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2587 |
+
qwen3-4b-log5-unary/model_layers_8_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2588 |
+
qwen3-4b-log5-unary/model_layers_24_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2589 |
+
qwen3-4b-log5-unary/model_layers_12_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2590 |
+
qwen3-4b-log5-unary/model_layers_12_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2591 |
+
qwen3-4b-log5-unary/model_layers_3_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2592 |
+
qwen3-4b-log5-unary/model_layers_23_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2593 |
+
qwen3-4b-log5-unary/model_layers_1_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2594 |
+
qwen3-4b-log5-unary/model_layers_22_self_attn_k_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2595 |
+
qwen3-4b-log5-unary/model_layers_28_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2596 |
+
qwen3-4b-log5-unary/model_layers_32_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2597 |
+
qwen3-4b-log5-unary/model_layers_13_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2598 |
+
qwen3-4b-log5-unary/model_layers_26_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2599 |
+
qwen3-4b-log5-unary/model_layers_1_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2600 |
+
qwen3-4b-log5-unary/model_layers_14_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2601 |
+
qwen3-4b-log5-unary/model_layers_31_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2602 |
+
qwen3-4b-log5-unary/model_layers_23_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2603 |
+
qwen3-4b-log5-unary/model_layers_33_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2604 |
+
qwen3-4b-log5-unary/model_layers_18_self_attn_k_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2605 |
+
qwen3-4b-log5-unary/model_layers_7_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2606 |
+
qwen3-4b-log5-unary/model_layers_3_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2607 |
+
qwen3-4b-log5-unary/model_layers_35_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2608 |
+
qwen3-4b-log5-unary/model_layers_23_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2609 |
+
qwen3-4b-log5-unary/model_layers_16_self_attn_k_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2610 |
+
qwen3-4b-log5-unary/model_layers_2_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2611 |
+
qwen3-4b-log5-unary/model_layers_18_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2612 |
+
qwen3-4b-log5-unary/model_layers_20_self_attn_k_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2613 |
+
qwen3-4b-log5-unary/model_layers_8_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2614 |
+
qwen3-4b-log5-unary/model_layers_6_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2615 |
+
qwen3-4b-log5-unary/model_layers_23_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2616 |
+
qwen3-4b-log5-unary/model_layers_15_self_attn_k_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2617 |
+
qwen3-4b-log5-unary/model_layers_26_self_attn_v_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2618 |
+
qwen3-4b-log5-unary/model_layers_23_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2619 |
+
qwen3-4b-log5-unary/model_layers_9_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2620 |
+
qwen3-4b-log5-unary/model_layers_26_self_attn_k_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2621 |
+
qwen3-4b-log5-unary/model_layers_22_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2622 |
+
qwen3-4b-log5-unary/model_layers_29_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2623 |
+
qwen3-4b-log5-unary/model_layers_21_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2624 |
+
qwen3-4b-log5-unary/model_layers_10_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2625 |
+
qwen3-4b-log5-unary/model_layers_9_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2626 |
+
qwen3-4b-log5-unary/model_layers_20_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2627 |
+
qwen3-4b-log5-unary/model_layers_32_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2628 |
+
qwen3-4b-log5-unary/model_layers_21_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2629 |
+
qwen3-4b-log5-unary/model_layers_31_self_attn_v_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2630 |
+
qwen3-4b-log5-unary/model_layers_30_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2631 |
+
qwen3-4b-log5-unary/model_layers_18_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2632 |
+
qwen3-4b-log5-unary/model_layers_35_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2633 |
+
qwen3-4b-log5-unary/model_layers_32_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2634 |
+
qwen3-4b-log5-unary/model_layers_25_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2635 |
+
qwen3-4b-log5-unary/model_layers_25_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2636 |
+
qwen3-4b-log5-unary/model_layers_6_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2637 |
+
qwen3-4b-log5-unary/model_layers_34_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2638 |
+
qwen3-4b-log5-unary/model_layers_11_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2639 |
+
qwen3-4b-log5-unary/model_layers_19_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2640 |
+
qwen3-4b-log5-unary/model_layers_1_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2641 |
+
qwen3-4b-log5-unary/model_layers_0_self_attn_k_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2642 |
+
qwen3-4b-log5-unary/model_layers_30_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2643 |
+
qwen3-4b-log5-unary/model_layers_13_self_attn_v_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2644 |
+
qwen3-4b-log5-unary/model_layers_7_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2645 |
+
qwen3-4b-log5-unary/model_layers_1_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2646 |
+
qwen3-4b-log5-unary/model_layers_30_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2647 |
+
qwen3-4b-log5-unary/model_layers_16_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2648 |
+
qwen3-4b-log5-unary/model_layers_14_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2649 |
+
qwen3-4b-log5-unary/model_layers_28_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2650 |
+
qwen3-4b-log5-unary/model_layers_30_self_attn_k_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2651 |
+
qwen3-4b-log5-unary/model_layers_10_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2652 |
+
qwen3-4b-log5-unary/model_layers_0_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2653 |
+
qwen3-4b-log5-unary/model_layers_26_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2654 |
+
qwen3-4b-log5-unary/model_layers_7_self_attn_v_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2655 |
+
qwen3-4b-log5-unary/model_layers_5_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2656 |
+
qwen3-4b-log5-unary/model_layers_29_self_attn_k_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2657 |
+
qwen3-4b-log5-unary/model_layers_9_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2658 |
+
deepseek-r1-1.5b-unary4/lm_head_weight.fp16 filter=lfs diff=lfs merge=lfs -text
|
| 2659 |
+
qwen3-4b-log5-unary/model_layers_16_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2660 |
+
qwen3-4b-log5-unary/model_layers_19_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2661 |
+
qwen3-4b-log5-unary/model_layers_12_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2662 |
+
qwen3-4b-log5-unary/model_layers_18_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2663 |
+
qwen3-4b-log5-unary/model_layers_10_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2664 |
+
qwen3-4b-log5-unary/model_layers_26_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2665 |
+
qwen3-4b-log5-unary/model_layers_32_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2666 |
+
qwen3-4b-log5-unary/model_layers_7_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2667 |
+
qwen3-4b-log5-unary/model_layers_25_self_attn_k_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2668 |
+
qwen3-4b-log5-unary/model_layers_6_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2669 |
+
qwen3-4b-log5-unary/model_layers_8_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2670 |
+
qwen3-4b-log5-unary/model_layers_29_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2671 |
+
qwen3-4b-log5-unary/model_layers_24_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2672 |
+
qwen3-4b-log5-unary/model_layers_0_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2673 |
+
qwen3-4b-log5-unary/model_layers_35_self_attn_v_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2674 |
+
qwen3-4b-log5-unary/model_layers_15_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2675 |
+
qwen3-4b-log5-unary/model_layers_6_self_attn_k_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2676 |
+
qwen3-4b-log5-unary/model_layers_16_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2677 |
+
qwen3-4b-log5-unary/model_layers_29_self_attn_v_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2678 |
+
qwen3-4b-log5-unary/model_layers_30_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2679 |
+
qwen3-4b-log5-unary/model_layers_25_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2680 |
+
qwen3-4b-log5-unary/model_layers_20_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2681 |
+
qwen3-4b-log5-unary/model_layers_14_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2682 |
+
qwen3-4b-log5-unary/model_layers_3_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2683 |
+
qwen3-4b-log5-unary/model_layers_22_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2684 |
+
qwen3-4b-log5-unary/model_layers_3_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2685 |
+
qwen3-4b-log5-unary/model_layers_35_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2686 |
+
qwen3-4b-log5-unary/model_layers_32_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2687 |
+
qwen3-4b-log5-unary/model_layers_33_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2688 |
+
qwen3-4b-log5-unary/model_layers_18_self_attn_v_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2689 |
+
qwen3-4b-log5-unary/model_layers_12_self_attn_k_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2690 |
+
qwen3-4b-log5-unary/model_layers_2_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2691 |
+
qwen3-4b-log5-unary/model_layers_9_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2692 |
+
qwen3-4b-log5-unary/model_layers_10_self_attn_v_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 2693 |
+
qwen3-4b-log5-unary/model_layers_28_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 2694 |
+
deepseek-r1-1.5b-ternary/model_layers_17_self_attn_q_proj_weight.neg filter=lfs diff=lfs merge=lfs -text
|
| 2695 |
+
deepseek-r1-1.5b-ternary/model_layers_6_mlp_up_proj_weight.pos filter=lfs diff=lfs merge=lfs -text
|
| 2696 |
+
deepseek-r1-1.5b-ternary/model_layers_14_mlp_gate_proj_weight.pos filter=lfs diff=lfs merge=lfs -text
|
| 2697 |
+
deepseek-r1-1.5b-ternary/model_layers_0_mlp_down_proj_weight.pos filter=lfs diff=lfs merge=lfs -text
|
| 2698 |
+
deepseek-r1-1.5b-ternary/model_layers_24_mlp_down_proj_weight.neg filter=lfs diff=lfs merge=lfs -text
|
| 2699 |
+
deepseek-r1-1.5b-ternary/model_layers_20_self_attn_o_proj_weight.pos filter=lfs diff=lfs merge=lfs -text
|
| 2700 |
+
deepseek-r1-1.5b-ternary/model_layers_25_self_attn_o_proj_weight.pos filter=lfs diff=lfs merge=lfs -text
|
| 2701 |
+
deepseek-r1-1.5b-ternary/model_layers_27_mlp_down_proj_weight.pos filter=lfs diff=lfs merge=lfs -text
|
| 2702 |
+
deepseek-r1-1.5b-ternary/model_layers_8_self_attn_o_proj_weight.neg filter=lfs diff=lfs merge=lfs -text
|
| 2703 |
+
deepseek-r1-1.5b-ternary/model_layers_26_mlp_down_proj_weight.pos filter=lfs diff=lfs merge=lfs -text
|
| 2704 |
+
deepseek-r1-1.5b-ternary/model_layers_6_mlp_down_proj_weight.neg filter=lfs diff=lfs merge=lfs -text
|
| 2705 |
+
deepseek-r1-1.5b-ternary/model_layers_24_mlp_gate_proj_weight.pos filter=lfs diff=lfs merge=lfs -text
|
| 2706 |
+
deepseek-r1-1.5b-ternary/model_layers_0_self_attn_o_proj_weight.neg filter=lfs diff=lfs merge=lfs -text
|
| 2707 |
+
deepseek-r1-1.5b-ternary/model_layers_13_self_attn_q_proj_weight.pos filter=lfs diff=lfs merge=lfs -text
|
| 2708 |
+
deepseek-r1-1.5b-ternary/model_layers_11_mlp_up_proj_weight.pos filter=lfs diff=lfs merge=lfs -text
|
| 2709 |
+
deepseek-r1-1.5b-ternary/model_layers_0_self_attn_o_proj_weight.pos filter=lfs diff=lfs merge=lfs -text
|
| 2710 |
+
deepseek-r1-1.5b-ternary/model_layers_7_self_attn_o_proj_weight.pos filter=lfs diff=lfs merge=lfs -text
|
| 2711 |
+
deepseek-r1-1.5b-ternary/model_layers_9_mlp_up_proj_weight.pos filter=lfs diff=lfs merge=lfs -text
|
| 2712 |
+
deepseek-r1-1.5b-ternary/model_layers_19_self_attn_o_proj_weight.pos filter=lfs diff=lfs merge=lfs -text
|
| 2713 |
+
deepseek-r1-1.5b-ternary/model_layers_5_mlp_down_proj_weight.pos filter=lfs diff=lfs merge=lfs -text
|
| 2714 |
+
deepseek-r1-1.5b-ternary/model_layers_22_mlp_up_proj_weight.neg filter=lfs diff=lfs merge=lfs -text
|
| 2715 |
+
deepseek-r1-1.5b-ternary/model_layers_13_mlp_gate_proj_weight.neg filter=lfs diff=lfs merge=lfs -text
|
| 2716 |
+
deepseek-r1-1.5b-ternary/model_layers_15_mlp_down_proj_weight.neg filter=lfs diff=lfs merge=lfs -text
|
| 2717 |
+
deepseek-r1-1.5b-ternary/model_layers_0_mlp_up_proj_weight.pos filter=lfs diff=lfs merge=lfs -text
|
| 2718 |
+
deepseek-r1-1.5b-ternary/model_layers_21_mlp_down_proj_weight.neg filter=lfs diff=lfs merge=lfs -text
|
| 2719 |
+
deepseek-r1-1.5b-ternary/model_layers_7_self_attn_q_proj_weight.pos filter=lfs diff=lfs merge=lfs -text
|
| 2720 |
+
deepseek-r1-1.5b-ternary/model_layers_2_mlp_up_proj_weight.pos filter=lfs diff=lfs merge=lfs -text
|
| 2721 |
+
deepseek-r1-1.5b-ternary/model_layers_16_mlp_gate_proj_weight.pos filter=lfs diff=lfs merge=lfs -text
|
| 2722 |
+
deepseek-r1-1.5b-ternary/model_layers_13_self_attn_o_proj_weight.neg filter=lfs diff=lfs merge=lfs -text
|
| 2723 |
+
deepseek-r1-1.5b-ternary/model_layers_6_self_attn_q_proj_weight.pos filter=lfs diff=lfs merge=lfs -text
|
| 2724 |
+
deepseek-r1-1.5b-ternary/model_layers_15_self_attn_o_proj_weight.neg filter=lfs diff=lfs merge=lfs -text
|
| 2725 |
+
deepseek-r1-1.5b-ternary/model_layers_17_mlp_up_proj_weight.pos filter=lfs diff=lfs merge=lfs -text
|
| 2726 |
+
deepseek-r1-1.5b-ternary/model_layers_25_self_attn_q_proj_weight.neg filter=lfs diff=lfs merge=lfs -text
|
| 2727 |
+
deepseek-r1-1.5b-ternary/model_layers_15_mlp_gate_proj_weight.pos filter=lfs diff=lfs merge=lfs -text
|
| 2728 |
+
deepseek-r1-1.5b-ternary/model_layers_11_self_attn_q_proj_weight.neg filter=lfs diff=lfs merge=lfs -text
|
| 2729 |
+
deepseek-r1-1.5b-ternary/model_layers_19_mlp_gate_proj_weight.pos filter=lfs diff=lfs merge=lfs -text
|
| 2730 |
+
deepseek-r1-1.5b-ternary/model_layers_17_self_attn_q_proj_weight.pos filter=lfs diff=lfs merge=lfs -text
|
| 2731 |
+
deepseek-r1-1.5b-ternary/model_layers_0_self_attn_q_proj_weight.pos filter=lfs diff=lfs merge=lfs -text
|
| 2732 |
+
deepseek-r1-1.5b-ternary/model_layers_10_mlp_up_proj_weight.pos filter=lfs diff=lfs merge=lfs -text
|
| 2733 |
+
deepseek-r1-1.5b-ternary/model_layers_0_mlp_up_proj_weight.neg filter=lfs diff=lfs merge=lfs -text
|
| 2734 |
+
deepseek-r1-1.5b-ternary/model_layers_1_mlp_up_proj_weight.neg filter=lfs diff=lfs merge=lfs -text
|
| 2735 |
+
deepseek-r1-1.5b-ternary/model_layers_20_mlp_down_proj_weight.pos filter=lfs diff=lfs merge=lfs -text
|
| 2736 |
+
deepseek-r1-1.5b-ternary/model_layers_4_self_attn_q_proj_weight.pos filter=lfs diff=lfs merge=lfs -text
|
| 2737 |
+
deepseek-r1-1.5b-ternary/model_layers_8_mlp_down_proj_weight.neg filter=lfs diff=lfs merge=lfs -text
|
| 2738 |
+
deepseek-r1-1.5b-ternary/model_layers_2_mlp_gate_proj_weight.neg filter=lfs diff=lfs merge=lfs -text
|
| 2739 |
+
deepseek-r1-1.5b-ternary/model_layers_11_mlp_down_proj_weight.neg filter=lfs diff=lfs merge=lfs -text
|
| 2740 |
+
deepseek-r1-1.5b-ternary/model_layers_9_mlp_gate_proj_weight.neg filter=lfs diff=lfs merge=lfs -text
|
| 2741 |
+
deepseek-r1-1.5b-ternary/model_layers_2_self_attn_o_proj_weight.neg filter=lfs diff=lfs merge=lfs -text
|
| 2742 |
+
deepseek-r1-1.5b-ternary/model_layers_27_mlp_gate_proj_weight.neg filter=lfs diff=lfs merge=lfs -text
|
| 2743 |
+
deepseek-r1-1.5b-ternary/model_layers_13_mlp_up_proj_weight.neg filter=lfs diff=lfs merge=lfs -text
|
| 2744 |
+
deepseek-r1-1.5b-ternary/model_layers_8_mlp_up_proj_weight.neg filter=lfs diff=lfs merge=lfs -text
|
| 2745 |
+
deepseek-r1-1.5b-ternary/model_layers_18_mlp_gate_proj_weight.pos filter=lfs diff=lfs merge=lfs -text
|
| 2746 |
+
deepseek-r1-1.5b-ternary/model_layers_8_mlp_gate_proj_weight.pos filter=lfs diff=lfs merge=lfs -text
|
| 2747 |
+
deepseek-r1-1.5b-ternary/model_layers_20_self_attn_q_proj_weight.pos filter=lfs diff=lfs merge=lfs -text
|
| 2748 |
+
deepseek-r1-1.5b-ternary/model_layers_8_self_attn_o_proj_weight.pos filter=lfs diff=lfs merge=lfs -text
|
| 2749 |
+
deepseek-r1-1.5b-ternary/model_layers_27_self_attn_q_proj_weight.neg filter=lfs diff=lfs merge=lfs -text
|
| 2750 |
+
deepseek-r1-1.5b-ternary/model_layers_24_self_attn_q_proj_weight.pos filter=lfs diff=lfs merge=lfs -text
|
| 2751 |
+
deepseek-r1-1.5b-ternary/model_layers_2_mlp_down_proj_weight.pos filter=lfs diff=lfs merge=lfs -text
|
| 2752 |
+
deepseek-r1-1.5b-ternary/model_layers_13_self_attn_o_proj_weight.pos filter=lfs diff=lfs merge=lfs -text
|
| 2753 |
+
deepseek-r1-1.5b-ternary/model_layers_5_mlp_down_proj_weight.neg filter=lfs diff=lfs merge=lfs -text
|
| 2754 |
+
deepseek-r1-1.5b-ternary/model_layers_5_mlp_up_proj_weight.neg filter=lfs diff=lfs merge=lfs -text
|
| 2755 |
+
deepseek-r1-1.5b-ternary/model_layers_8_mlp_up_proj_weight.pos filter=lfs diff=lfs merge=lfs -text
|
| 2756 |
+
deepseek-r1-1.5b-ternary/model_layers_12_mlp_down_proj_weight.neg filter=lfs diff=lfs merge=lfs -text
|
| 2757 |
+
deepseek-r1-1.5b-ternary/model_layers_5_self_attn_o_proj_weight.neg filter=lfs diff=lfs merge=lfs -text
|
| 2758 |
+
deepseek-r1-1.5b-ternary/model_layers_27_self_attn_o_proj_weight.neg filter=lfs diff=lfs merge=lfs -text
|
| 2759 |
+
deepseek-r1-1.5b-ternary/model_layers_22_self_attn_o_proj_weight.neg filter=lfs diff=lfs merge=lfs -text
|
| 2760 |
+
deepseek-r1-1.5b-ternary/model_layers_27_mlp_up_proj_weight.neg filter=lfs diff=lfs merge=lfs -text
|
| 2761 |
+
deepseek-r1-1.5b-ternary/model_layers_19_mlp_up_proj_weight.pos filter=lfs diff=lfs merge=lfs -text
|
| 2762 |
+
deepseek-r1-1.5b-ternary/model_layers_24_mlp_down_proj_weight.pos filter=lfs diff=lfs merge=lfs -text
|
| 2763 |
+
deepseek-r1-1.5b-ternary/model_layers_16_self_attn_q_proj_weight.neg filter=lfs diff=lfs merge=lfs -text
|
| 2764 |
+
deepseek-r1-1.5b-ternary/model_layers_2_self_attn_o_proj_weight.pos filter=lfs diff=lfs merge=lfs -text
|
| 2765 |
+
deepseek-r1-1.5b-ternary/model_layers_19_mlp_up_proj_weight.neg filter=lfs diff=lfs merge=lfs -text
|
| 2766 |
+
deepseek-r1-1.5b-ternary/model_layers_9_self_attn_o_proj_weight.neg filter=lfs diff=lfs merge=lfs -text
|
| 2767 |
+
deepseek-r1-1.5b-ternary/model_layers_16_self_attn_o_proj_weight.neg filter=lfs diff=lfs merge=lfs -text
|
deepseek-r1-1.5b-gunary/model_layers_0_self_attn_v_proj_bias.fp16
ADDED
|
Binary file (512 Bytes). View file
|
|
|
deepseek-r1-1.5b-gunary/model_layers_5_self_attn_v_proj_weight.gscales
ADDED
|
Binary file (49.2 kB). View file
|
|
|
deepseek-r1-1.5b-ternary/model_layers_0_mlp_down_proj_weight.pos
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:62b5378fb65b0e6d38e4c3a2fd3cd08a64569b3da596e2234978d0ec3a77167c
|
| 3 |
+
size 1720320
|
deepseek-r1-1.5b-ternary/model_layers_0_mlp_up_proj_weight.neg
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3e94b58948e74314e1d27ac9d61975b860653f61b2d8eff06f86fd37227a4aa1
|
| 3 |
+
size 1720320
|
deepseek-r1-1.5b-ternary/model_layers_0_mlp_up_proj_weight.pos
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:619e625042427c3932cd491fa909817245c376ba32044a6f2e0808905357bb1b
|
| 3 |
+
size 1720320
|
deepseek-r1-1.5b-ternary/model_layers_0_self_attn_o_proj_weight.neg
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ccc575264a29da098da3b78559db3a84a2129c3e9bb8ea31786b466b88a3b1a3
|
| 3 |
+
size 294912
|
deepseek-r1-1.5b-ternary/model_layers_0_self_attn_o_proj_weight.pos
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6bba743450b99b08d9845f481c95f41edfbff94952d32dbf80805f9d550ceb2a
|
| 3 |
+
size 294912
|
deepseek-r1-1.5b-ternary/model_layers_0_self_attn_q_proj_weight.pos
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ff97d6db7c10a4cd5f316c5c2957a33ff5a57b2eec02e1078c37c99fbc8d4c25
|
| 3 |
+
size 294912
|
deepseek-r1-1.5b-ternary/model_layers_10_mlp_up_proj_weight.pos
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:24bf7cc352024d1f603d250a201bd571a006a93bcd1bc8e439bd58682c6f4492
|
| 3 |
+
size 1720320
|
deepseek-r1-1.5b-ternary/model_layers_11_mlp_down_proj_weight.neg
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ef669b8b552a13a80c39cb2b8f1a363b8aa2988535ccddd56775dbf7166bc528
|
| 3 |
+
size 1720320
|
deepseek-r1-1.5b-ternary/model_layers_11_mlp_up_proj_weight.pos
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1cf1fdca9ce2aa0911aee4f80032b508a4116142562b27f0e0e0a0fc3282b3e0
|
| 3 |
+
size 1720320
|
deepseek-r1-1.5b-ternary/model_layers_11_self_attn_q_proj_weight.neg
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:48b6cd43aee887243f539411a83873aa00711d030227035d3aed7ababb087f38
|
| 3 |
+
size 294912
|
deepseek-r1-1.5b-ternary/model_layers_12_mlp_down_proj_weight.neg
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9bf86395ecb72d04d8a2617afc0ee6c8e3e72b7c0e2fad8204661ba3256c41c2
|
| 3 |
+
size 1720320
|
deepseek-r1-1.5b-ternary/model_layers_13_mlp_gate_proj_weight.neg
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4cd16801e5491bd2372fea8435e0bdeda3d7d7d08e420e0a28d09fd98c850227
|
| 3 |
+
size 1720320
|
deepseek-r1-1.5b-ternary/model_layers_13_mlp_up_proj_weight.neg
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:587a574229e63174f4bdf31a07eb21997e85d7da551bedb6a6ac2be6d18dcbb6
|
| 3 |
+
size 1720320
|
deepseek-r1-1.5b-ternary/model_layers_13_self_attn_o_proj_weight.neg
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:571fbb793c19c519e2d9c484d9b7aad9a22818e028a3f4441d89f608e338fd3a
|
| 3 |
+
size 294912
|
deepseek-r1-1.5b-ternary/model_layers_13_self_attn_o_proj_weight.pos
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f592d4ef97653f3812b5ca724a90a6b9c10fe31974e5ff71389418f8920f3e6e
|
| 3 |
+
size 294912
|
deepseek-r1-1.5b-ternary/model_layers_13_self_attn_q_proj_weight.pos
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1fff537c8f38887b82083aecbed92b2b8dc5a4a375829b2760bfce08719b7d69
|
| 3 |
+
size 294912
|
deepseek-r1-1.5b-ternary/model_layers_14_mlp_gate_proj_weight.pos
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:372be321f22dc5de9163ba84cf3ac48ba63d8e609c420506cad54496b5ec6657
|
| 3 |
+
size 1720320
|
deepseek-r1-1.5b-ternary/model_layers_15_mlp_down_proj_weight.neg
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0f3c3d41f6d48e751e948114a1a007b9276233eccb276431bf4c7fe6038eca45
|
| 3 |
+
size 1720320
|
deepseek-r1-1.5b-ternary/model_layers_15_mlp_gate_proj_weight.pos
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c6641a6a35a20d1af81b9d867ddfb4c00818a5cd48f31b8a1c5d32a0209ece15
|
| 3 |
+
size 1720320
|
deepseek-r1-1.5b-ternary/model_layers_15_self_attn_o_proj_weight.neg
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4078bb99a0aa1df7f10e5ce704b0ac390c1b4b50c3ee3e879aa9086d665161ba
|
| 3 |
+
size 294912
|
deepseek-r1-1.5b-ternary/model_layers_16_mlp_gate_proj_weight.pos
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1a201cdbaddcabd2c3fae11ed6ffb1494148b1d3767376b0b09e9ba77744e152
|
| 3 |
+
size 1720320
|
deepseek-r1-1.5b-ternary/model_layers_16_self_attn_o_proj_weight.neg
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8866573a7730031f6727f2032b14d5aa529409ac0c6cba986e5af22d0535efbe
|
| 3 |
+
size 294912
|
deepseek-r1-1.5b-ternary/model_layers_16_self_attn_q_proj_weight.neg
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bcc5882cf2984a217980345db159e3ea819570f1bb32d6433d0cdcf65a179b1a
|
| 3 |
+
size 294912
|
deepseek-r1-1.5b-ternary/model_layers_17_mlp_up_proj_weight.pos
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7e324e2d9752680c667336f4839fb14945ce040822ecda3ac04f027e9460a633
|
| 3 |
+
size 1720320
|
deepseek-r1-1.5b-ternary/model_layers_17_self_attn_q_proj_weight.neg
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:65cd692f72c985a5ed909fb22f3c7ed8fd58e7d988bfbe6310412bd98e15dc0d
|
| 3 |
+
size 294912
|
deepseek-r1-1.5b-ternary/model_layers_17_self_attn_q_proj_weight.pos
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:46ca656ff67f1fc3b77de0fc890f1a6894986fc636d3e463db71174dd7a81a35
|
| 3 |
+
size 294912
|
deepseek-r1-1.5b-ternary/model_layers_18_mlp_gate_proj_weight.pos
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:79eff64b79119e79b984b5c24266b1dbbe38d0a0b6b2b48a46fb07baf880a852
|
| 3 |
+
size 1720320
|
deepseek-r1-1.5b-ternary/model_layers_19_mlp_gate_proj_weight.pos
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7d0f0c308526d3c68c4a3efa7bbf0522de8b386f5be88eed57639603a9d1aa34
|
| 3 |
+
size 1720320
|
deepseek-r1-1.5b-ternary/model_layers_19_mlp_up_proj_weight.neg
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:90b64e1a4e3ed8cd45f20658f5cd9f18868d597c95a53fe539aca9ce59ab313b
|
| 3 |
+
size 1720320
|
deepseek-r1-1.5b-ternary/model_layers_19_mlp_up_proj_weight.pos
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:62b0665c7bfb81ddf41f3ad80e246fdf911545661dfbc6f29ed777cf2b7f0670
|
| 3 |
+
size 1720320
|
deepseek-r1-1.5b-ternary/model_layers_19_self_attn_o_proj_weight.pos
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a37b742d18df0955e555127edc50b6e73070876803dca865adac46281c022170
|
| 3 |
+
size 294912
|
deepseek-r1-1.5b-ternary/model_layers_1_mlp_up_proj_weight.neg
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:53c65dc2de71d3f2559859f7acb5e114d1ca7f979823f440367a4ea51a46c09a
|
| 3 |
+
size 1720320
|
deepseek-r1-1.5b-ternary/model_layers_20_mlp_down_proj_weight.pos
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9ff6e71a912d5918547f7c4cdeb3a8d26f7f80b7609cc22a9d5d8bf0499c8578
|
| 3 |
+
size 1720320
|
deepseek-r1-1.5b-ternary/model_layers_20_self_attn_o_proj_weight.pos
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:588a0380cbabf1fcdc291a40380213d8c5cb9cc5329768d80718983903622362
|
| 3 |
+
size 294912
|
deepseek-r1-1.5b-ternary/model_layers_20_self_attn_q_proj_weight.pos
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:99ff6b610d0d4058d83bb7280ad98c420f57f7c3f02828710fb3720f24394b5b
|
| 3 |
+
size 294912
|
deepseek-r1-1.5b-ternary/model_layers_21_mlp_down_proj_weight.neg
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6ae898f8a79728c4e184db10d9338ea1ba4f61c2d38736bb8c563839d914e65c
|
| 3 |
+
size 1720320
|
deepseek-r1-1.5b-ternary/model_layers_22_mlp_up_proj_weight.neg
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6055ae0ae1b27830e11982c2c86d637ffa72044b675dd9671c06d9ea60fb7e25
|
| 3 |
+
size 1720320
|
deepseek-r1-1.5b-ternary/model_layers_22_self_attn_o_proj_weight.neg
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0c5b45ca1dfc8383125f0fffc08b7e0d6fb3198c74325bf872483c7405f8f0bf
|
| 3 |
+
size 294912
|
deepseek-r1-1.5b-ternary/model_layers_24_mlp_down_proj_weight.neg
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2afa608693bb6606d2beb3ba03bf8c5847e0ba9b2cce90316450a73d6e386626
|
| 3 |
+
size 1720320
|
deepseek-r1-1.5b-ternary/model_layers_24_mlp_down_proj_weight.pos
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b52069b7f6101270114ef09f329bf22e4827afba6bc354921db023662981af3f
|
| 3 |
+
size 1720320
|
deepseek-r1-1.5b-ternary/model_layers_24_mlp_gate_proj_weight.pos
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b4743b0b02dd129335accb1f0c236190ad3fa2014df56af9e97e9f3fffe44081
|
| 3 |
+
size 1720320
|
deepseek-r1-1.5b-ternary/model_layers_24_self_attn_q_proj_weight.pos
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:110dd02e26377c4773b01cca3d118bc63200084be4b2ae5b9dd71e21a2919816
|
| 3 |
+
size 294912
|
deepseek-r1-1.5b-ternary/model_layers_25_self_attn_o_proj_weight.pos
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:599bd331611b831ceb3aa6c9dcf9191506a48ccb77b1744c0f3c1133b844e127
|
| 3 |
+
size 294912
|
deepseek-r1-1.5b-ternary/model_layers_25_self_attn_q_proj_weight.neg
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:322de7134737d165c2473ceb53801c4dfb187438b13cc8435a4799590fbfce34
|
| 3 |
+
size 294912
|
deepseek-r1-1.5b-ternary/model_layers_26_mlp_down_proj_weight.pos
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:381e3160da1b4b26877352cef55404dac99bea72065699cb6b5090c5359dfbb4
|
| 3 |
+
size 1720320
|
deepseek-r1-1.5b-ternary/model_layers_27_mlp_down_proj_weight.pos
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3213ab2260679a335f28d6d365faaa41b6afad8e07ac3e43505f7f8a2f948f10
|
| 3 |
+
size 1720320
|
deepseek-r1-1.5b-ternary/model_layers_27_mlp_gate_proj_weight.neg
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7b43198a8b2d1d79ac1d3b5745cc36c0007b8b6503daf6807a4609a0f3e74ed5
|
| 3 |
+
size 1720320
|