OpenTransformer commited on
Commit
597c6a8
·
verified ·
1 Parent(s): 54c5b36

Add files using upload-large-folder tool

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. .gitattributes +125 -0
  2. deepseek-r1-1.5b-ternary/model_layers_0_mlp_down_proj_weight.neg +3 -0
  3. deepseek-r1-1.5b-ternary/model_layers_0_self_attn_q_proj_weight.neg +3 -0
  4. deepseek-r1-1.5b-ternary/model_layers_10_mlp_down_proj_weight.pos +3 -0
  5. deepseek-r1-1.5b-ternary/model_layers_10_mlp_gate_proj_weight.pos +3 -0
  6. deepseek-r1-1.5b-ternary/model_layers_10_mlp_up_proj_weight.neg +3 -0
  7. deepseek-r1-1.5b-ternary/model_layers_10_self_attn_q_proj_weight.neg +3 -0
  8. deepseek-r1-1.5b-ternary/model_layers_10_self_attn_q_proj_weight.pos +3 -0
  9. deepseek-r1-1.5b-ternary/model_layers_11_mlp_gate_proj_weight.neg +3 -0
  10. deepseek-r1-1.5b-ternary/model_layers_11_self_attn_o_proj_weight.pos +3 -0
  11. deepseek-r1-1.5b-ternary/model_layers_11_self_attn_q_proj_weight.pos +3 -0
  12. deepseek-r1-1.5b-ternary/model_layers_12_mlp_gate_proj_weight.neg +3 -0
  13. deepseek-r1-1.5b-ternary/model_layers_12_mlp_gate_proj_weight.pos +3 -0
  14. deepseek-r1-1.5b-ternary/model_layers_12_self_attn_o_proj_weight.pos +3 -0
  15. deepseek-r1-1.5b-ternary/model_layers_12_self_attn_q_proj_weight.neg +3 -0
  16. deepseek-r1-1.5b-ternary/model_layers_13_mlp_down_proj_weight.neg +3 -0
  17. deepseek-r1-1.5b-ternary/model_layers_13_mlp_down_proj_weight.pos +3 -0
  18. deepseek-r1-1.5b-ternary/model_layers_13_mlp_gate_proj_weight.pos +3 -0
  19. deepseek-r1-1.5b-ternary/model_layers_14_mlp_gate_proj_weight.neg +3 -0
  20. deepseek-r1-1.5b-ternary/model_layers_14_mlp_up_proj_weight.neg +3 -0
  21. deepseek-r1-1.5b-ternary/model_layers_14_self_attn_q_proj_weight.neg +3 -0
  22. deepseek-r1-1.5b-ternary/model_layers_14_self_attn_q_proj_weight.pos +3 -0
  23. deepseek-r1-1.5b-ternary/model_layers_15_mlp_up_proj_weight.pos +3 -0
  24. deepseek-r1-1.5b-ternary/model_layers_15_self_attn_q_proj_weight.neg +3 -0
  25. deepseek-r1-1.5b-ternary/model_layers_16_mlp_down_proj_weight.neg +3 -0
  26. deepseek-r1-1.5b-ternary/model_layers_16_mlp_down_proj_weight.pos +3 -0
  27. deepseek-r1-1.5b-ternary/model_layers_16_mlp_gate_proj_weight.neg +3 -0
  28. deepseek-r1-1.5b-ternary/model_layers_16_self_attn_o_proj_weight.pos +3 -0
  29. deepseek-r1-1.5b-ternary/model_layers_17_mlp_up_proj_weight.neg +3 -0
  30. deepseek-r1-1.5b-ternary/model_layers_17_self_attn_o_proj_weight.neg +3 -0
  31. deepseek-r1-1.5b-ternary/model_layers_17_self_attn_o_proj_weight.pos +3 -0
  32. deepseek-r1-1.5b-ternary/model_layers_18_mlp_gate_proj_weight.neg +3 -0
  33. deepseek-r1-1.5b-ternary/model_layers_18_mlp_up_proj_weight.neg +3 -0
  34. deepseek-r1-1.5b-ternary/model_layers_18_self_attn_o_proj_weight.neg +3 -0
  35. deepseek-r1-1.5b-ternary/model_layers_18_self_attn_q_proj_weight.neg +3 -0
  36. deepseek-r1-1.5b-ternary/model_layers_18_self_attn_q_proj_weight.pos +3 -0
  37. deepseek-r1-1.5b-ternary/model_layers_19_mlp_down_proj_weight.pos +3 -0
  38. deepseek-r1-1.5b-ternary/model_layers_19_mlp_gate_proj_weight.neg +3 -0
  39. deepseek-r1-1.5b-ternary/model_layers_19_self_attn_o_proj_weight.neg +3 -0
  40. deepseek-r1-1.5b-ternary/model_layers_1_mlp_down_proj_weight.pos +3 -0
  41. deepseek-r1-1.5b-ternary/model_layers_1_mlp_gate_proj_weight.neg +3 -0
  42. deepseek-r1-1.5b-ternary/model_layers_1_mlp_up_proj_weight.pos +3 -0
  43. deepseek-r1-1.5b-ternary/model_layers_1_self_attn_o_proj_weight.neg +3 -0
  44. deepseek-r1-1.5b-ternary/model_layers_1_self_attn_q_proj_weight.pos +3 -0
  45. deepseek-r1-1.5b-ternary/model_layers_20_mlp_down_proj_weight.neg +3 -0
  46. deepseek-r1-1.5b-ternary/model_layers_20_mlp_gate_proj_weight.neg +3 -0
  47. deepseek-r1-1.5b-ternary/model_layers_20_mlp_up_proj_weight.neg +3 -0
  48. deepseek-r1-1.5b-ternary/model_layers_20_mlp_up_proj_weight.pos +3 -0
  49. deepseek-r1-1.5b-ternary/model_layers_20_self_attn_q_proj_weight.neg +3 -0
  50. deepseek-r1-1.5b-ternary/model_layers_21_mlp_down_proj_weight.pos +3 -0
.gitattributes CHANGED
@@ -2932,3 +2932,128 @@ deepseek-r1-1.5b-unary4/model_layers_23_mlp_down_proj_weight.planes filter=lfs d
2932
  deepseek-r1-1.5b-unary4/model_layers_25_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
2933
  deepseek-r1-1.5b-unary4/model_layers_2_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
2934
  deepseek-r1-1.5b-unary4/model_layers_5_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2932
  deepseek-r1-1.5b-unary4/model_layers_25_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
2933
  deepseek-r1-1.5b-unary4/model_layers_2_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
2934
  deepseek-r1-1.5b-unary4/model_layers_5_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
2935
+ deepseek-r1-1.5b-unary4/model_layers_0_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
2936
+ deepseek-r1-1.5b-unary4/model_layers_19_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
2937
+ deepseek-r1-1.5b-unary4/model_layers_27_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
2938
+ deepseek-r1-1.5b-unary4/model_layers_3_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
2939
+ deepseek-r1-1.5b-unary4/model_layers_16_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
2940
+ deepseek-r1-1.5b-unary4/model_layers_27_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
2941
+ qwen3-4b-log5-unary/model_layers_31_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
2942
+ qwen3-4b-log5-unary/model_layers_11_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
2943
+ qwen3-4b-log5-unary/model_layers_34_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
2944
+ qwen3-4b-log5-unary/model_layers_18_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
2945
+ qwen3-4b-log5-unary/model_layers_5_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
2946
+ qwen3-4b-log5-unary/model_layers_25_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
2947
+ qwen3-4b-log5-unary/model_layers_17_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
2948
+ qwen3-4b-log5-unary/model_layers_5_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
2949
+ qwen3-4b-log5-unary/model_layers_6_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
2950
+ qwen3-4b-log5-unary/model_layers_33_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
2951
+ qwen3-4b-log5-unary/model_layers_0_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
2952
+ qwen3-4b-log5-unary/model_layers_18_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
2953
+ qwen3-4b-log5-unary/model_layers_17_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
2954
+ qwen3-4b-log5-unary/model_layers_21_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
2955
+ qwen3-4b-log5-unary/model_layers_2_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
2956
+ qwen3-4b-log5-unary/model_layers_6_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
2957
+ qwen3-4b-log5-unary/model_layers_25_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
2958
+ qwen3-4b-log5-unary/model_layers_29_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
2959
+ deepseek-r1-1.5b-ternary/model_layers_18_self_attn_o_proj_weight.neg filter=lfs diff=lfs merge=lfs -text
2960
+ deepseek-r1-1.5b-ternary/model_layers_4_mlp_gate_proj_weight.pos filter=lfs diff=lfs merge=lfs -text
2961
+ deepseek-r1-1.5b-ternary/model_layers_25_mlp_down_proj_weight.neg filter=lfs diff=lfs merge=lfs -text
2962
+ deepseek-r1-1.5b-ternary/model_layers_3_self_attn_o_proj_weight.pos filter=lfs diff=lfs merge=lfs -text
2963
+ deepseek-r1-1.5b-ternary/model_layers_24_self_attn_q_proj_weight.neg filter=lfs diff=lfs merge=lfs -text
2964
+ deepseek-r1-1.5b-ternary/model_layers_23_mlp_gate_proj_weight.pos filter=lfs diff=lfs merge=lfs -text
2965
+ deepseek-r1-1.5b-ternary/model_layers_24_mlp_up_proj_weight.neg filter=lfs diff=lfs merge=lfs -text
2966
+ deepseek-r1-1.5b-ternary/model_layers_11_self_attn_q_proj_weight.pos filter=lfs diff=lfs merge=lfs -text
2967
+ deepseek-r1-1.5b-ternary/model_layers_8_self_attn_q_proj_weight.pos filter=lfs diff=lfs merge=lfs -text
2968
+ deepseek-r1-1.5b-ternary/model_layers_10_mlp_gate_proj_weight.pos filter=lfs diff=lfs merge=lfs -text
2969
+ deepseek-r1-1.5b-ternary/model_layers_2_self_attn_q_proj_weight.pos filter=lfs diff=lfs merge=lfs -text
2970
+ deepseek-r1-1.5b-ternary/model_layers_16_mlp_down_proj_weight.pos filter=lfs diff=lfs merge=lfs -text
2971
+ deepseek-r1-1.5b-ternary/model_layers_22_self_attn_o_proj_weight.pos filter=lfs diff=lfs merge=lfs -text
2972
+ deepseek-r1-1.5b-ternary/model_layers_17_self_attn_o_proj_weight.pos filter=lfs diff=lfs merge=lfs -text
2973
+ deepseek-r1-1.5b-ternary/model_layers_12_mlp_gate_proj_weight.neg filter=lfs diff=lfs merge=lfs -text
2974
+ deepseek-r1-1.5b-ternary/model_layers_17_mlp_up_proj_weight.neg filter=lfs diff=lfs merge=lfs -text
2975
+ deepseek-r1-1.5b-ternary/model_layers_6_self_attn_o_proj_weight.pos filter=lfs diff=lfs merge=lfs -text
2976
+ deepseek-r1-1.5b-ternary/model_layers_4_self_attn_o_proj_weight.pos filter=lfs diff=lfs merge=lfs -text
2977
+ deepseek-r1-1.5b-ternary/model_layers_1_mlp_gate_proj_weight.neg filter=lfs diff=lfs merge=lfs -text
2978
+ deepseek-r1-1.5b-ternary/model_layers_21_mlp_up_proj_weight.pos filter=lfs diff=lfs merge=lfs -text
2979
+ deepseek-r1-1.5b-ternary/model_layers_4_mlp_down_proj_weight.neg filter=lfs diff=lfs merge=lfs -text
2980
+ deepseek-r1-1.5b-ternary/model_layers_16_self_attn_o_proj_weight.pos filter=lfs diff=lfs merge=lfs -text
2981
+ deepseek-r1-1.5b-ternary/model_layers_20_mlp_gate_proj_weight.neg filter=lfs diff=lfs merge=lfs -text
2982
+ deepseek-r1-1.5b-ternary/model_layers_0_mlp_down_proj_weight.neg filter=lfs diff=lfs merge=lfs -text
2983
+ deepseek-r1-1.5b-ternary/model_layers_1_self_attn_q_proj_weight.pos filter=lfs diff=lfs merge=lfs -text
2984
+ deepseek-r1-1.5b-ternary/model_layers_6_mlp_down_proj_weight.pos filter=lfs diff=lfs merge=lfs -text
2985
+ deepseek-r1-1.5b-ternary/model_layers_12_self_attn_o_proj_weight.pos filter=lfs diff=lfs merge=lfs -text
2986
+ deepseek-r1-1.5b-ternary/model_layers_15_self_attn_q_proj_weight.neg filter=lfs diff=lfs merge=lfs -text
2987
+ deepseek-r1-1.5b-ternary/model_layers_13_mlp_down_proj_weight.neg filter=lfs diff=lfs merge=lfs -text
2988
+ deepseek-r1-1.5b-ternary/model_layers_1_self_attn_o_proj_weight.neg filter=lfs diff=lfs merge=lfs -text
2989
+ deepseek-r1-1.5b-ternary/model_layers_20_self_attn_q_proj_weight.neg filter=lfs diff=lfs merge=lfs -text
2990
+ deepseek-r1-1.5b-ternary/model_layers_1_mlp_down_proj_weight.pos filter=lfs diff=lfs merge=lfs -text
2991
+ deepseek-r1-1.5b-ternary/model_layers_20_mlp_down_proj_weight.neg filter=lfs diff=lfs merge=lfs -text
2992
+ deepseek-r1-1.5b-ternary/model_layers_12_self_attn_q_proj_weight.neg filter=lfs diff=lfs merge=lfs -text
2993
+ deepseek-r1-1.5b-ternary/model_layers_7_mlp_gate_proj_weight.neg filter=lfs diff=lfs merge=lfs -text
2994
+ deepseek-r1-1.5b-ternary/model_layers_21_mlp_down_proj_weight.pos filter=lfs diff=lfs merge=lfs -text
2995
+ deepseek-r1-1.5b-ternary/model_layers_25_mlp_down_proj_weight.pos filter=lfs diff=lfs merge=lfs -text
2996
+ deepseek-r1-1.5b-ternary/model_layers_0_self_attn_q_proj_weight.neg filter=lfs diff=lfs merge=lfs -text
2997
+ deepseek-r1-1.5b-ternary/model_layers_24_self_attn_o_proj_weight.pos filter=lfs diff=lfs merge=lfs -text
2998
+ deepseek-r1-1.5b-ternary/model_layers_25_self_attn_o_proj_weight.neg filter=lfs diff=lfs merge=lfs -text
2999
+ deepseek-r1-1.5b-ternary/model_layers_20_mlp_up_proj_weight.neg filter=lfs diff=lfs merge=lfs -text
3000
+ deepseek-r1-1.5b-ternary/model_layers_7_mlp_up_proj_weight.neg filter=lfs diff=lfs merge=lfs -text
3001
+ deepseek-r1-1.5b-ternary/model_layers_10_self_attn_q_proj_weight.pos filter=lfs diff=lfs merge=lfs -text
3002
+ deepseek-r1-1.5b-ternary/model_layers_26_self_attn_o_proj_weight.pos filter=lfs diff=lfs merge=lfs -text
3003
+ deepseek-r1-1.5b-ternary/model_layers_7_self_attn_q_proj_weight.neg filter=lfs diff=lfs merge=lfs -text
3004
+ deepseek-r1-1.5b-ternary/model_layers_3_self_attn_q_proj_weight.pos filter=lfs diff=lfs merge=lfs -text
3005
+ deepseek-r1-1.5b-ternary/model_layers_12_mlp_gate_proj_weight.pos filter=lfs diff=lfs merge=lfs -text
3006
+ deepseek-r1-1.5b-ternary/model_layers_16_mlp_down_proj_weight.neg filter=lfs diff=lfs merge=lfs -text
3007
+ deepseek-r1-1.5b-ternary/model_layers_10_self_attn_q_proj_weight.neg filter=lfs diff=lfs merge=lfs -text
3008
+ deepseek-r1-1.5b-ternary/model_layers_23_self_attn_o_proj_weight.neg filter=lfs diff=lfs merge=lfs -text
3009
+ deepseek-r1-1.5b-ternary/model_layers_18_self_attn_q_proj_weight.pos filter=lfs diff=lfs merge=lfs -text
3010
+ deepseek-r1-1.5b-ternary/model_layers_27_self_attn_q_proj_weight.pos filter=lfs diff=lfs merge=lfs -text
3011
+ deepseek-r1-1.5b-ternary/model_layers_14_self_attn_q_proj_weight.pos filter=lfs diff=lfs merge=lfs -text
3012
+ deepseek-r1-1.5b-ternary/model_layers_9_mlp_gate_proj_weight.pos filter=lfs diff=lfs merge=lfs -text
3013
+ deepseek-r1-1.5b-ternary/model_layers_21_self_attn_o_proj_weight.neg filter=lfs diff=lfs merge=lfs -text
3014
+ deepseek-r1-1.5b-ternary/model_layers_23_mlp_down_proj_weight.pos filter=lfs diff=lfs merge=lfs -text
3015
+ deepseek-r1-1.5b-ternary/model_layers_27_mlp_down_proj_weight.neg filter=lfs diff=lfs merge=lfs -text
3016
+ deepseek-r1-1.5b-ternary/model_layers_25_mlp_up_proj_weight.pos filter=lfs diff=lfs merge=lfs -text
3017
+ deepseek-r1-1.5b-ternary/model_layers_19_mlp_gate_proj_weight.neg filter=lfs diff=lfs merge=lfs -text
3018
+ deepseek-r1-1.5b-ternary/model_layers_26_mlp_gate_proj_weight.pos filter=lfs diff=lfs merge=lfs -text
3019
+ deepseek-r1-1.5b-ternary/model_layers_19_mlp_down_proj_weight.pos filter=lfs diff=lfs merge=lfs -text
3020
+ deepseek-r1-1.5b-ternary/model_layers_3_self_attn_o_proj_weight.neg filter=lfs diff=lfs merge=lfs -text
3021
+ deepseek-r1-1.5b-ternary/model_layers_13_mlp_gate_proj_weight.pos filter=lfs diff=lfs merge=lfs -text
3022
+ deepseek-r1-1.5b-ternary/model_layers_2_mlp_gate_proj_weight.pos filter=lfs diff=lfs merge=lfs -text
3023
+ deepseek-r1-1.5b-ternary/model_layers_11_self_attn_o_proj_weight.pos filter=lfs diff=lfs merge=lfs -text
3024
+ deepseek-r1-1.5b-ternary/model_layers_24_self_attn_o_proj_weight.neg filter=lfs diff=lfs merge=lfs -text
3025
+ deepseek-r1-1.5b-ternary/model_layers_1_mlp_up_proj_weight.pos filter=lfs diff=lfs merge=lfs -text
3026
+ deepseek-r1-1.5b-ternary/model_layers_26_self_attn_q_proj_weight.neg filter=lfs diff=lfs merge=lfs -text
3027
+ deepseek-r1-1.5b-ternary/model_layers_22_self_attn_q_proj_weight.neg filter=lfs diff=lfs merge=lfs -text
3028
+ deepseek-r1-1.5b-ternary/model_layers_26_mlp_up_proj_weight.pos filter=lfs diff=lfs merge=lfs -text
3029
+ deepseek-r1-1.5b-ternary/model_layers_5_self_attn_q_proj_weight.neg filter=lfs diff=lfs merge=lfs -text
3030
+ deepseek-r1-1.5b-ternary/model_layers_10_mlp_down_proj_weight.pos filter=lfs diff=lfs merge=lfs -text
3031
+ deepseek-r1-1.5b-ternary/model_layers_14_self_attn_q_proj_weight.neg filter=lfs diff=lfs merge=lfs -text
3032
+ deepseek-r1-1.5b-ternary/model_layers_26_self_attn_q_proj_weight.pos filter=lfs diff=lfs merge=lfs -text
3033
+ deepseek-r1-1.5b-ternary/model_layers_25_mlp_gate_proj_weight.pos filter=lfs diff=lfs merge=lfs -text
3034
+ deepseek-r1-1.5b-ternary/model_layers_10_mlp_up_proj_weight.neg filter=lfs diff=lfs merge=lfs -text
3035
+ deepseek-r1-1.5b-ternary/model_layers_18_self_attn_q_proj_weight.neg filter=lfs diff=lfs merge=lfs -text
3036
+ deepseek-r1-1.5b-ternary/model_layers_18_mlp_up_proj_weight.neg filter=lfs diff=lfs merge=lfs -text
3037
+ deepseek-r1-1.5b-ternary/model_layers_20_mlp_up_proj_weight.pos filter=lfs diff=lfs merge=lfs -text
3038
+ deepseek-r1-1.5b-ternary/model_layers_7_mlp_up_proj_weight.pos filter=lfs diff=lfs merge=lfs -text
3039
+ deepseek-r1-1.5b-ternary/model_layers_2_mlp_down_proj_weight.neg filter=lfs diff=lfs merge=lfs -text
3040
+ deepseek-r1-1.5b-ternary/model_layers_17_self_attn_o_proj_weight.neg filter=lfs diff=lfs merge=lfs -text
3041
+ deepseek-r1-1.5b-ternary/model_layers_27_mlp_up_proj_weight.pos filter=lfs diff=lfs merge=lfs -text
3042
+ deepseek-r1-1.5b-ternary/model_layers_9_mlp_up_proj_weight.neg filter=lfs diff=lfs merge=lfs -text
3043
+ deepseek-r1-1.5b-ternary/model_layers_22_mlp_gate_proj_weight.pos filter=lfs diff=lfs merge=lfs -text
3044
+ deepseek-r1-1.5b-ternary/model_layers_11_mlp_gate_proj_weight.neg filter=lfs diff=lfs merge=lfs -text
3045
+ deepseek-r1-1.5b-ternary/model_layers_9_mlp_down_proj_weight.neg filter=lfs diff=lfs merge=lfs -text
3046
+ deepseek-r1-1.5b-ternary/model_layers_3_mlp_gate_proj_weight.pos filter=lfs diff=lfs merge=lfs -text
3047
+ deepseek-r1-1.5b-ternary/model_layers_21_self_attn_q_proj_weight.pos filter=lfs diff=lfs merge=lfs -text
3048
+ deepseek-r1-1.5b-ternary/model_layers_14_mlp_up_proj_weight.neg filter=lfs diff=lfs merge=lfs -text
3049
+ deepseek-r1-1.5b-ternary/model_layers_13_mlp_down_proj_weight.pos filter=lfs diff=lfs merge=lfs -text
3050
+ deepseek-r1-1.5b-ternary/model_layers_23_self_attn_o_proj_weight.pos filter=lfs diff=lfs merge=lfs -text
3051
+ deepseek-r1-1.5b-ternary/model_layers_5_mlp_gate_proj_weight.neg filter=lfs diff=lfs merge=lfs -text
3052
+ deepseek-r1-1.5b-ternary/model_layers_16_mlp_gate_proj_weight.neg filter=lfs diff=lfs merge=lfs -text
3053
+ deepseek-r1-1.5b-ternary/model_layers_22_self_attn_q_proj_weight.pos filter=lfs diff=lfs merge=lfs -text
3054
+ deepseek-r1-1.5b-ternary/model_layers_15_mlp_up_proj_weight.pos filter=lfs diff=lfs merge=lfs -text
3055
+ deepseek-r1-1.5b-ternary/model_layers_23_mlp_gate_proj_weight.neg filter=lfs diff=lfs merge=lfs -text
3056
+ deepseek-r1-1.5b-ternary/model_layers_18_mlp_gate_proj_weight.neg filter=lfs diff=lfs merge=lfs -text
3057
+ deepseek-r1-1.5b-ternary/model_layers_14_mlp_gate_proj_weight.neg filter=lfs diff=lfs merge=lfs -text
3058
+ deepseek-r1-1.5b-ternary/model_layers_19_self_attn_o_proj_weight.neg filter=lfs diff=lfs merge=lfs -text
3059
+ deepseek-r1-1.5b-ternary/model_layers_4_self_attn_q_proj_weight.neg filter=lfs diff=lfs merge=lfs -text
deepseek-r1-1.5b-ternary/model_layers_0_mlp_down_proj_weight.neg ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9370199575082915bf0ccdf9a74ca02e0476d4814058a3a348fd1538d94d1fce
3
+ size 1720320
deepseek-r1-1.5b-ternary/model_layers_0_self_attn_q_proj_weight.neg ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a0039040b13a81f1277457ec040789066e6f1f91955330878afb46c37cdaba49
3
+ size 294912
deepseek-r1-1.5b-ternary/model_layers_10_mlp_down_proj_weight.pos ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f7ceb4ae115ebeb4ee2f0995e4b819dbdff72719cbc7fb55c674cc1b307d8a6
3
+ size 1720320
deepseek-r1-1.5b-ternary/model_layers_10_mlp_gate_proj_weight.pos ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b96cf85032c14e1c817b06edaf27c1b3fa340d3dd197ac066fee8cb72065be3
3
+ size 1720320
deepseek-r1-1.5b-ternary/model_layers_10_mlp_up_proj_weight.neg ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fddf0f6fb2efc721468ca19e2ed5e8468c9a3a3c7023d3c1fc421d41e1a1f6e7
3
+ size 1720320
deepseek-r1-1.5b-ternary/model_layers_10_self_attn_q_proj_weight.neg ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fcc67b018afb15aa2e4b9278a650bfea3d6d190783bdbf7a0ceac6cb6c64e6d7
3
+ size 294912
deepseek-r1-1.5b-ternary/model_layers_10_self_attn_q_proj_weight.pos ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ef3ece652607bca621f5993dae017430835124aef9760ff918b4abec6b3b37e
3
+ size 294912
deepseek-r1-1.5b-ternary/model_layers_11_mlp_gate_proj_weight.neg ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a714ab1bed0c02992d9f4532b6e792daaac2fb83e3d191447dbfa817ced9402
3
+ size 1720320
deepseek-r1-1.5b-ternary/model_layers_11_self_attn_o_proj_weight.pos ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:73ade90f3747624606c352e12b27d58dbb3f885a6bdecf5f19cd939ee5fea6e0
3
+ size 294912
deepseek-r1-1.5b-ternary/model_layers_11_self_attn_q_proj_weight.pos ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:438f13bcf050c06d09542ed5c040500d1fc852b6a55e11a3d2faa09dfbac42da
3
+ size 294912
deepseek-r1-1.5b-ternary/model_layers_12_mlp_gate_proj_weight.neg ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b0fc71961836421a06386d8a027d3dd9753eadbcaba69461a336979d0520ce12
3
+ size 1720320
deepseek-r1-1.5b-ternary/model_layers_12_mlp_gate_proj_weight.pos ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:884090015f65c803c2fcea824fd5bda6113b4d332adee97c86147a2f52af2d22
3
+ size 1720320
deepseek-r1-1.5b-ternary/model_layers_12_self_attn_o_proj_weight.pos ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ccdb5b8f3e29e5331f01c1d1f7e683f77bc05d8b796b44d3111949e9bf7ddddb
3
+ size 294912
deepseek-r1-1.5b-ternary/model_layers_12_self_attn_q_proj_weight.neg ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:abf3bd47b000b5e5dd6a50452f917fa6ba04d96b039f4298553daa257a36dfc4
3
+ size 294912
deepseek-r1-1.5b-ternary/model_layers_13_mlp_down_proj_weight.neg ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d71389161a089240222f2ad45175321c212015fbfa85386fa1fb9ec07af52af
3
+ size 1720320
deepseek-r1-1.5b-ternary/model_layers_13_mlp_down_proj_weight.pos ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e97c598734b7c981ed94f78ec54d2ca56efc639c01b39a1a2fa29108a27c8306
3
+ size 1720320
deepseek-r1-1.5b-ternary/model_layers_13_mlp_gate_proj_weight.pos ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fc64cb3cd12262fc430969d96cdb60154c2190439b5e6a55865b5f88231b31b0
3
+ size 1720320
deepseek-r1-1.5b-ternary/model_layers_14_mlp_gate_proj_weight.neg ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f8556b05b781bd3bbb8d1062bf89817a94a7a720a8590348b1b242e681e1ae40
3
+ size 1720320
deepseek-r1-1.5b-ternary/model_layers_14_mlp_up_proj_weight.neg ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd51bfdf413da284a4195279e69400dd0f8b3f6a04e357c6a40164f166c4c2ed
3
+ size 1720320
deepseek-r1-1.5b-ternary/model_layers_14_self_attn_q_proj_weight.neg ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc195c105edbe42cab3f16a889de305f86ad541ac74586b23f6b5308d2d6fd20
3
+ size 294912
deepseek-r1-1.5b-ternary/model_layers_14_self_attn_q_proj_weight.pos ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a25c8cf0274dc57234925f38b6b93896aab0ff540cae11ec59bea32f6e3fa705
3
+ size 294912
deepseek-r1-1.5b-ternary/model_layers_15_mlp_up_proj_weight.pos ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fa23ac7e657418c24d3cd4cdc6e9df48f967d63f477a50dedf4b9f6a3a95f069
3
+ size 1720320
deepseek-r1-1.5b-ternary/model_layers_15_self_attn_q_proj_weight.neg ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:87c78eea22c56a264f8cdc1247d870967edd7dc45d84b157e49e658a57ac17ab
3
+ size 294912
deepseek-r1-1.5b-ternary/model_layers_16_mlp_down_proj_weight.neg ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c1db612017d762a1eb279157ac1e1e91ea6e515065be47a198c10c50fbfa9c6b
3
+ size 1720320
deepseek-r1-1.5b-ternary/model_layers_16_mlp_down_proj_weight.pos ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:60b53dfc6b6a77e0533ced6e12377e1678ad8fd45446e75a43d42672da84b46d
3
+ size 1720320
deepseek-r1-1.5b-ternary/model_layers_16_mlp_gate_proj_weight.neg ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:889bc934475e9a8f5e54007331376ac761170c78dceded83e6656cb25c7a7eca
3
+ size 1720320
deepseek-r1-1.5b-ternary/model_layers_16_self_attn_o_proj_weight.pos ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5027e40f35ad1ddc30c1703da3d13b01559c29dafb81285fae1f2e936d06c8a8
3
+ size 294912
deepseek-r1-1.5b-ternary/model_layers_17_mlp_up_proj_weight.neg ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1b30d05ffdca71e195d3f0352f5a5acea250115d6a56ae83c9d36feac395f9f1
3
+ size 1720320
deepseek-r1-1.5b-ternary/model_layers_17_self_attn_o_proj_weight.neg ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d14e6048ec05fec1c7c77a7f2f847adbda898a30bafcf7e379fc454829a9b5dc
3
+ size 294912
deepseek-r1-1.5b-ternary/model_layers_17_self_attn_o_proj_weight.pos ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:269a859b3b8c8d8621a5f5f743009e09420e17351b715e988ccbc6178cd95b1a
3
+ size 294912
deepseek-r1-1.5b-ternary/model_layers_18_mlp_gate_proj_weight.neg ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f294394f556e76a1d9121b9a1d2d1c3f0cbc7d08d49da1d397813cddffcab7a7
3
+ size 1720320
deepseek-r1-1.5b-ternary/model_layers_18_mlp_up_proj_weight.neg ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c190e08a05529e90ad8d51bc381b619d4f0b33d408555d99646ce971361fef4
3
+ size 1720320
deepseek-r1-1.5b-ternary/model_layers_18_self_attn_o_proj_weight.neg ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9925152ce669f27a1d01781dcdf0185f126ab50e676f920bce91db5c71ada1c8
3
+ size 294912
deepseek-r1-1.5b-ternary/model_layers_18_self_attn_q_proj_weight.neg ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:70f0e3a9a966268cbaefa9e7a824fb8f132ae583bcab48aa55d73989e8f18313
3
+ size 294912
deepseek-r1-1.5b-ternary/model_layers_18_self_attn_q_proj_weight.pos ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c515ecf4c4b0052b822041b16fefee33300a9f7713cca678cc0ea1dd0e785b5a
3
+ size 294912
deepseek-r1-1.5b-ternary/model_layers_19_mlp_down_proj_weight.pos ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:802f1022ce6f45731de642c1f8f5c05aaa38bdfe00960ce6dadf4ee35abad259
3
+ size 1720320
deepseek-r1-1.5b-ternary/model_layers_19_mlp_gate_proj_weight.neg ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b90b7276235e0c32b8fc6b5c777b9e81808d91d6fc5900f518adf35fa53a82de
3
+ size 1720320
deepseek-r1-1.5b-ternary/model_layers_19_self_attn_o_proj_weight.neg ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a949790db960aa2279875eb706222fc4bed59d6a4f871aed451097a89fe730c
3
+ size 294912
deepseek-r1-1.5b-ternary/model_layers_1_mlp_down_proj_weight.pos ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8f295e24b5622ae9d1ae1484a0df465d8d351cafaf7c7d32607dd9e3efcb15ac
3
+ size 1720320
deepseek-r1-1.5b-ternary/model_layers_1_mlp_gate_proj_weight.neg ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd92b643d402cb41f72b06266f1ca03dccb359add6fdd8568d2126ee2b9f9304
3
+ size 1720320
deepseek-r1-1.5b-ternary/model_layers_1_mlp_up_proj_weight.pos ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e9d8bac3e0a74e1d5fe34557b069ea974bccd0f9b61df5fe0d648fd06997ff47
3
+ size 1720320
deepseek-r1-1.5b-ternary/model_layers_1_self_attn_o_proj_weight.neg ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c634d9f61351ec7f9ba51f79f44ea380908487468853c5c3095d0e33fe50eae9
3
+ size 294912
deepseek-r1-1.5b-ternary/model_layers_1_self_attn_q_proj_weight.pos ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b4b90f80b1652f7408917360dea8a9b81a343f679c08eaeb6a5b7dedc2efd570
3
+ size 294912
deepseek-r1-1.5b-ternary/model_layers_20_mlp_down_proj_weight.neg ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:49f808ef1e1c4c1f07beedf251420ceb5c04f763456956bb2a13101ee5bc42cc
3
+ size 1720320
deepseek-r1-1.5b-ternary/model_layers_20_mlp_gate_proj_weight.neg ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d119cbcad7adfb88b9fe58ab7f45ddddc3095a059de077bf846f2bc77be52acb
3
+ size 1720320
deepseek-r1-1.5b-ternary/model_layers_20_mlp_up_proj_weight.neg ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:31adfc9bfbb63e1dc5e6ddc30fb331b9069e895f6bf756167458b297ef620b44
3
+ size 1720320
deepseek-r1-1.5b-ternary/model_layers_20_mlp_up_proj_weight.pos ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4c25592e7e5f59a75c9ba312a43001a4795e88960fe4787de4e094e4c07a5696
3
+ size 1720320
deepseek-r1-1.5b-ternary/model_layers_20_self_attn_q_proj_weight.neg ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b58daf42ec4283e7cd760df14c7528155ed561af8988cde5c19baa76aba3ceac
3
+ size 294912
deepseek-r1-1.5b-ternary/model_layers_21_mlp_down_proj_weight.pos ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:999f377760edb1648e7c8bbe898432a96b1cd75b278336aba74176ede4c393ee
3
+ size 1720320