OpenTransformer commited on
Commit
5950fda
·
verified ·
1 Parent(s): 1d33f42

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 +31 -0
  2. deepseek-r1-1.5b-ternary/model_layers_10_self_attn_o_proj_weight.pos +3 -0
  3. deepseek-r1-1.5b-ternary/model_layers_11_mlp_up_proj_weight.neg +3 -0
  4. deepseek-r1-1.5b-ternary/model_layers_12_mlp_down_proj_weight.pos +3 -0
  5. deepseek-r1-1.5b-ternary/model_layers_12_self_attn_q_proj_weight.pos +3 -0
  6. deepseek-r1-1.5b-ternary/model_layers_13_mlp_up_proj_weight.pos +3 -0
  7. deepseek-r1-1.5b-ternary/model_layers_13_self_attn_q_proj_weight.neg +3 -0
  8. deepseek-r1-1.5b-ternary/model_layers_14_mlp_down_proj_weight.neg +3 -0
  9. deepseek-r1-1.5b-ternary/model_layers_14_mlp_up_proj_weight.pos +3 -0
  10. deepseek-r1-1.5b-ternary/model_layers_15_mlp_up_proj_weight.neg +3 -0
  11. deepseek-r1-1.5b-ternary/model_layers_15_self_attn_q_proj_weight.pos +3 -0
  12. deepseek-r1-1.5b-ternary/model_layers_18_mlp_down_proj_weight.neg +3 -0
  13. deepseek-r1-1.5b-ternary/model_layers_18_mlp_down_proj_weight.pos +3 -0
  14. deepseek-r1-1.5b-ternary/model_layers_19_mlp_down_proj_weight.neg +3 -0
  15. deepseek-r1-1.5b-ternary/model_layers_1_self_attn_o_proj_weight.pos +3 -0
  16. deepseek-r1-1.5b-ternary/model_layers_20_mlp_gate_proj_weight.pos +3 -0
  17. deepseek-r1-1.5b-ternary/model_layers_21_self_attn_q_proj_weight.neg +3 -0
  18. deepseek-r1-1.5b-ternary/model_layers_23_self_attn_q_proj_weight.neg +3 -0
  19. deepseek-r1-1.5b-ternary/model_layers_24_mlp_up_proj_weight.pos +3 -0
  20. deepseek-r1-1.5b-ternary/model_layers_25_mlp_gate_proj_weight.neg +3 -0
  21. deepseek-r1-1.5b-ternary/model_layers_25_mlp_up_proj_weight.neg +3 -0
  22. deepseek-r1-1.5b-ternary/model_layers_26_mlp_down_proj_weight.neg +3 -0
  23. deepseek-r1-1.5b-ternary/model_layers_26_mlp_up_proj_weight.neg +3 -0
  24. deepseek-r1-1.5b-ternary/model_layers_26_self_attn_o_proj_weight.neg +3 -0
  25. deepseek-r1-1.5b-ternary/model_layers_27_self_attn_o_proj_weight.pos +3 -0
  26. deepseek-r1-1.5b-ternary/model_layers_3_mlp_gate_proj_weight.neg +3 -0
  27. deepseek-r1-1.5b-ternary/model_layers_5_mlp_gate_proj_weight.pos +3 -0
  28. deepseek-r1-1.5b-ternary/model_layers_6_self_attn_o_proj_weight.neg +3 -0
  29. deepseek-r1-1.5b-ternary/model_layers_7_mlp_down_proj_weight.pos +3 -0
  30. deepseek-r1-1.5b-ternary/model_layers_7_mlp_gate_proj_weight.pos +3 -0
  31. deepseek-r1-1.5b-ternary/model_layers_8_self_attn_q_proj_weight.neg +3 -0
  32. deepseek-r1-1.5b-ternary/model_layers_9_self_attn_q_proj_weight.neg +3 -0
  33. deepseek-r1-1.5b-unary4/model_layers_10_self_attn_k_proj_weight.scales +0 -0
  34. deepseek-r1-1.5b-unary4/model_layers_11_self_attn_k_proj_bias.fp16 +0 -0
  35. deepseek-r1-1.5b-unary4/model_layers_11_self_attn_k_proj_weight.sign +0 -0
  36. deepseek-r1-1.5b-unary4/model_layers_11_self_attn_q_proj_bias.fp16 +0 -0
  37. deepseek-r1-1.5b-unary4/model_layers_13_input_layernorm_weight.fp16 +0 -0
  38. deepseek-r1-1.5b-unary4/model_layers_13_self_attn_k_proj_weight.scales +0 -0
  39. deepseek-r1-1.5b-unary4/model_layers_14_self_attn_q_proj_bias.fp16 +0 -0
  40. deepseek-r1-1.5b-unary4/model_layers_15_mlp_gate_proj_weight.scales +0 -0
  41. deepseek-r1-1.5b-unary4/model_layers_16_mlp_down_proj_weight.scales +0 -0
  42. deepseek-r1-1.5b-unary4/model_layers_16_self_attn_v_proj_bias.fp16 +0 -0
  43. deepseek-r1-1.5b-unary4/model_layers_17_input_layernorm_weight.fp16 +0 -0
  44. deepseek-r1-1.5b-unary4/model_layers_17_self_attn_q_proj_bias.fp16 +0 -0
  45. deepseek-r1-1.5b-unary4/model_layers_17_self_attn_v_proj_weight.scales +0 -0
  46. deepseek-r1-1.5b-unary4/model_layers_17_self_attn_v_proj_weight.sign +0 -0
  47. deepseek-r1-1.5b-unary4/model_layers_18_input_layernorm_weight.fp16 +0 -0
  48. deepseek-r1-1.5b-unary4/model_layers_18_mlp_up_proj_weight.scales +0 -0
  49. deepseek-r1-1.5b-unary4/model_layers_1_self_attn_q_proj_bias.fp16 +0 -0
  50. deepseek-r1-1.5b-unary4/model_layers_20_self_attn_q_proj_weight.scales +0 -0
.gitattributes CHANGED
@@ -3232,3 +3232,34 @@ qwen3-4b-log-unary/model_layers_9_self_attn_k_proj_weight.planes filter=lfs diff
3232
  qwen3-4b-log-unary/model_layers_2_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
3233
  qwen3-4b-log-unary/model_layers_10_self_attn_v_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
3234
  qwen3-4b-log-unary/model_layers_21_self_attn_k_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3232
  qwen3-4b-log-unary/model_layers_2_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
3233
  qwen3-4b-log-unary/model_layers_10_self_attn_v_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
3234
  qwen3-4b-log-unary/model_layers_21_self_attn_k_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
3235
+ deepseek-r1-1.5b-ternary/model_layers_27_self_attn_o_proj_weight.pos filter=lfs diff=lfs merge=lfs -text
3236
+ deepseek-r1-1.5b-ternary/model_layers_18_mlp_down_proj_weight.pos filter=lfs diff=lfs merge=lfs -text
3237
+ deepseek-r1-1.5b-ternary/model_layers_18_mlp_down_proj_weight.neg filter=lfs diff=lfs merge=lfs -text
3238
+ deepseek-r1-1.5b-ternary/model_layers_13_mlp_up_proj_weight.pos filter=lfs diff=lfs merge=lfs -text
3239
+ deepseek-r1-1.5b-ternary/model_layers_12_mlp_down_proj_weight.pos filter=lfs diff=lfs merge=lfs -text
3240
+ deepseek-r1-1.5b-ternary/model_layers_23_self_attn_q_proj_weight.neg filter=lfs diff=lfs merge=lfs -text
3241
+ deepseek-r1-1.5b-ternary/model_layers_6_self_attn_o_proj_weight.neg filter=lfs diff=lfs merge=lfs -text
3242
+ deepseek-r1-1.5b-ternary/model_layers_15_self_attn_q_proj_weight.pos filter=lfs diff=lfs merge=lfs -text
3243
+ deepseek-r1-1.5b-ternary/model_layers_5_mlp_gate_proj_weight.pos filter=lfs diff=lfs merge=lfs -text
3244
+ deepseek-r1-1.5b-ternary/model_layers_26_mlp_up_proj_weight.neg filter=lfs diff=lfs merge=lfs -text
3245
+ deepseek-r1-1.5b-ternary/model_layers_12_self_attn_q_proj_weight.pos filter=lfs diff=lfs merge=lfs -text
3246
+ deepseek-r1-1.5b-ternary/model_layers_3_mlp_gate_proj_weight.neg filter=lfs diff=lfs merge=lfs -text
3247
+ deepseek-r1-1.5b-ternary/model_layers_21_self_attn_q_proj_weight.neg filter=lfs diff=lfs merge=lfs -text
3248
+ deepseek-r1-1.5b-ternary/model_layers_7_mlp_down_proj_weight.pos filter=lfs diff=lfs merge=lfs -text
3249
+ deepseek-r1-1.5b-ternary/model_layers_24_mlp_up_proj_weight.pos filter=lfs diff=lfs merge=lfs -text
3250
+ deepseek-r1-1.5b-ternary/model_layers_9_self_attn_q_proj_weight.neg filter=lfs diff=lfs merge=lfs -text
3251
+ deepseek-r1-1.5b-ternary/model_layers_26_mlp_down_proj_weight.neg filter=lfs diff=lfs merge=lfs -text
3252
+ deepseek-r1-1.5b-ternary/model_layers_19_mlp_down_proj_weight.neg filter=lfs diff=lfs merge=lfs -text
3253
+ deepseek-r1-1.5b-ternary/model_layers_20_mlp_gate_proj_weight.pos filter=lfs diff=lfs merge=lfs -text
3254
+ deepseek-r1-1.5b-ternary/model_layers_13_self_attn_q_proj_weight.neg filter=lfs diff=lfs merge=lfs -text
3255
+ deepseek-r1-1.5b-ternary/model_layers_1_self_attn_o_proj_weight.pos filter=lfs diff=lfs merge=lfs -text
3256
+ deepseek-r1-1.5b-ternary/model_layers_8_self_attn_q_proj_weight.neg filter=lfs diff=lfs merge=lfs -text
3257
+ deepseek-r1-1.5b-ternary/model_layers_25_mlp_up_proj_weight.neg filter=lfs diff=lfs merge=lfs -text
3258
+ deepseek-r1-1.5b-ternary/model_layers_11_mlp_up_proj_weight.neg filter=lfs diff=lfs merge=lfs -text
3259
+ deepseek-r1-1.5b-ternary/model_layers_25_mlp_gate_proj_weight.neg filter=lfs diff=lfs merge=lfs -text
3260
+ deepseek-r1-1.5b-ternary/model_layers_10_self_attn_o_proj_weight.pos filter=lfs diff=lfs merge=lfs -text
3261
+ deepseek-r1-1.5b-ternary/model_layers_26_self_attn_o_proj_weight.neg filter=lfs diff=lfs merge=lfs -text
3262
+ deepseek-r1-1.5b-ternary/model_layers_14_mlp_down_proj_weight.neg filter=lfs diff=lfs merge=lfs -text
3263
+ deepseek-r1-1.5b-ternary/model_layers_7_mlp_gate_proj_weight.pos filter=lfs diff=lfs merge=lfs -text
3264
+ deepseek-r1-1.5b-ternary/model_layers_15_mlp_up_proj_weight.neg filter=lfs diff=lfs merge=lfs -text
3265
+ deepseek-r1-1.5b-ternary/model_layers_14_mlp_up_proj_weight.pos filter=lfs diff=lfs merge=lfs -text
deepseek-r1-1.5b-ternary/model_layers_10_self_attn_o_proj_weight.pos ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b3219043486dbae59c2b67bbe335fa99c97a12363bab0b049bec80ba47e208e9
3
+ size 294912
deepseek-r1-1.5b-ternary/model_layers_11_mlp_up_proj_weight.neg ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f6121e942585b457d197d6460dfdd693ce544acad8d97be9f5472c0ee09b1093
3
+ size 1720320
deepseek-r1-1.5b-ternary/model_layers_12_mlp_down_proj_weight.pos ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:42007875947bdaf3867b60facdd7f9c9e64487cfd9b350ec186ef884c691ef19
3
+ size 1720320
deepseek-r1-1.5b-ternary/model_layers_12_self_attn_q_proj_weight.pos ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:615b7807bf718aaf811ec54722315a2663ec5e8f46a519eb9c1a1207468a7480
3
+ size 294912
deepseek-r1-1.5b-ternary/model_layers_13_mlp_up_proj_weight.pos ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ede9305151ecac8e169f64dcd10e903d4b1f542c0ab952a9bdb4427605378bdf
3
+ size 1720320
deepseek-r1-1.5b-ternary/model_layers_13_self_attn_q_proj_weight.neg ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1db74416504f8dbe868293124fbae567b0de09f58b80b1382ea253d4fee2fb76
3
+ size 294912
deepseek-r1-1.5b-ternary/model_layers_14_mlp_down_proj_weight.neg ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4f2e650fe8017b2925e9d78fec93b8829e4e0ef6916fee26246754219fbc7eb3
3
+ size 1720320
deepseek-r1-1.5b-ternary/model_layers_14_mlp_up_proj_weight.pos ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d470eb097a253bb241760be942b2b0fcac8933768be4b3fad19d03854c7633f8
3
+ size 1720320
deepseek-r1-1.5b-ternary/model_layers_15_mlp_up_proj_weight.neg ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:630ef541ef172c024bd1ee9f3bcb2db91c6c3c1b7ac24a4ee4db5dc601d21d1d
3
+ size 1720320
deepseek-r1-1.5b-ternary/model_layers_15_self_attn_q_proj_weight.pos ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9fe3a3f00f81c650926f634fcd5374deb35a307a911d7bb4fbb4f190b7b383ce
3
+ size 294912
deepseek-r1-1.5b-ternary/model_layers_18_mlp_down_proj_weight.neg ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f275de47fd65df82147056e373b968d0bd11d3879cea5844939eeace1f7d77c0
3
+ size 1720320
deepseek-r1-1.5b-ternary/model_layers_18_mlp_down_proj_weight.pos ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2c81c38d4c401106e3f10f95cdda545b4d3307b386f868d8d59fb9798cecbd00
3
+ size 1720320
deepseek-r1-1.5b-ternary/model_layers_19_mlp_down_proj_weight.neg ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eaebe5842363c5354a5a2afb3cd6fa02931fc402c25271ced949305ee0b80f4f
3
+ size 1720320
deepseek-r1-1.5b-ternary/model_layers_1_self_attn_o_proj_weight.pos ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a815e3e856c8cafe8078d40d9062d83408e1b388a218e8007d4d6f54265802e9
3
+ size 294912
deepseek-r1-1.5b-ternary/model_layers_20_mlp_gate_proj_weight.pos ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bba38a2db9baffbeb85ff35bf8607a6abaf1274049e6e3f5a8ca40c56eec2623
3
+ size 1720320
deepseek-r1-1.5b-ternary/model_layers_21_self_attn_q_proj_weight.neg ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a040d0fe2e4f47e68897c0eadbf13d265faeb82f24e2d7a125b7b4239e13c3cb
3
+ size 294912
deepseek-r1-1.5b-ternary/model_layers_23_self_attn_q_proj_weight.neg ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1726b282393f54777e7708786ac284cf0de8fc4afa1d5d85ebe7dd71528bfea3
3
+ size 294912
deepseek-r1-1.5b-ternary/model_layers_24_mlp_up_proj_weight.pos ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e7a37fee03c94e1ccf22e5068df68bab2c5bb8b7fcbcbba8250ca316dd45cbf9
3
+ size 1720320
deepseek-r1-1.5b-ternary/model_layers_25_mlp_gate_proj_weight.neg ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:17b08f276defa535f96f1125f34fecd554964f9e235de989e0f995b819cf5b64
3
+ size 1720320
deepseek-r1-1.5b-ternary/model_layers_25_mlp_up_proj_weight.neg ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bdaaab57de6df8e9b2ee666a175a62bd9c44610a5eed7cd2cda159abe12c87d7
3
+ size 1720320
deepseek-r1-1.5b-ternary/model_layers_26_mlp_down_proj_weight.neg ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c1895b4a47d16357d1ef606e5907e17617e9b09ca6f32cff60e0881fb6765b10
3
+ size 1720320
deepseek-r1-1.5b-ternary/model_layers_26_mlp_up_proj_weight.neg ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:90d517473f2ddd0936aca1f6ee1191d1543db8405ca3ac45919c09919166ebeb
3
+ size 1720320
deepseek-r1-1.5b-ternary/model_layers_26_self_attn_o_proj_weight.neg ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d299eaa6b418388971671d706aab8ab90cb30151356cb9981fc6d3cba6c93e8d
3
+ size 294912
deepseek-r1-1.5b-ternary/model_layers_27_self_attn_o_proj_weight.pos ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:716bd70955ee24bbe346691641068d528df6c57e0f5398cc4f2b49fc31622646
3
+ size 294912
deepseek-r1-1.5b-ternary/model_layers_3_mlp_gate_proj_weight.neg ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c874147270d86a22c92080a5cd466481ee44b40e007b03e179329f4658d85eb6
3
+ size 1720320
deepseek-r1-1.5b-ternary/model_layers_5_mlp_gate_proj_weight.pos ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c1188f623b15b89ccfabe6d967c5ef0136845f685e1c2d321fa34283d31c9948
3
+ size 1720320
deepseek-r1-1.5b-ternary/model_layers_6_self_attn_o_proj_weight.neg ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cb399f3ee5642e440e6bc9fc2e950134048bbb70587b3664004ea6faa9a45f08
3
+ size 294912
deepseek-r1-1.5b-ternary/model_layers_7_mlp_down_proj_weight.pos ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5609c675d2f3084b82d82ee2728f13f808713f525f6262890f297b336ef4af3e
3
+ size 1720320
deepseek-r1-1.5b-ternary/model_layers_7_mlp_gate_proj_weight.pos ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:841011e739626de31758b4f1e01879b9c0ee4890891bb6ef51533d20fe36aff9
3
+ size 1720320
deepseek-r1-1.5b-ternary/model_layers_8_self_attn_q_proj_weight.neg ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9746c8acdc6101e41f4ae2de4536f616a13ea39c5412758cebdf51465fe1c369
3
+ size 294912
deepseek-r1-1.5b-ternary/model_layers_9_self_attn_q_proj_weight.neg ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:54e038e4336db2e45d85c099397a1c687a830db23974883fcb48c5afb63daf52
3
+ size 294912
deepseek-r1-1.5b-unary4/model_layers_10_self_attn_k_proj_weight.scales ADDED
Binary file (1.02 kB). View file
 
deepseek-r1-1.5b-unary4/model_layers_11_self_attn_k_proj_bias.fp16 ADDED
Binary file (512 Bytes). View file
 
deepseek-r1-1.5b-unary4/model_layers_11_self_attn_k_proj_weight.sign ADDED
Binary file (49.2 kB). View file
 
deepseek-r1-1.5b-unary4/model_layers_11_self_attn_q_proj_bias.fp16 ADDED
Binary file (3.07 kB). View file
 
deepseek-r1-1.5b-unary4/model_layers_13_input_layernorm_weight.fp16 ADDED
Binary file (3.07 kB). View file
 
deepseek-r1-1.5b-unary4/model_layers_13_self_attn_k_proj_weight.scales ADDED
Binary file (1.02 kB). View file
 
deepseek-r1-1.5b-unary4/model_layers_14_self_attn_q_proj_bias.fp16 ADDED
Binary file (3.07 kB). View file
 
deepseek-r1-1.5b-unary4/model_layers_15_mlp_gate_proj_weight.scales ADDED
Binary file (35.8 kB). View file
 
deepseek-r1-1.5b-unary4/model_layers_16_mlp_down_proj_weight.scales ADDED
Binary file (6.14 kB). View file
 
deepseek-r1-1.5b-unary4/model_layers_16_self_attn_v_proj_bias.fp16 ADDED
Binary file (512 Bytes). View file
 
deepseek-r1-1.5b-unary4/model_layers_17_input_layernorm_weight.fp16 ADDED
Binary file (3.07 kB). View file
 
deepseek-r1-1.5b-unary4/model_layers_17_self_attn_q_proj_bias.fp16 ADDED
Binary file (3.07 kB). View file
 
deepseek-r1-1.5b-unary4/model_layers_17_self_attn_v_proj_weight.scales ADDED
Binary file (1.02 kB). View file
 
deepseek-r1-1.5b-unary4/model_layers_17_self_attn_v_proj_weight.sign ADDED
Binary file (49.2 kB). View file
 
deepseek-r1-1.5b-unary4/model_layers_18_input_layernorm_weight.fp16 ADDED
Binary file (3.07 kB). View file
 
deepseek-r1-1.5b-unary4/model_layers_18_mlp_up_proj_weight.scales ADDED
Binary file (35.8 kB). View file
 
deepseek-r1-1.5b-unary4/model_layers_1_self_attn_q_proj_bias.fp16 ADDED
Binary file (3.07 kB). View file
 
deepseek-r1-1.5b-unary4/model_layers_20_self_attn_q_proj_weight.scales ADDED
Binary file (6.14 kB). View file