OpenTransformer commited on
Commit
b63bc73
·
verified ·
1 Parent(s): 104d6a1

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 +38 -0
  2. deepseek-r1-1.5b-packed/model_layers_0_mlp_gate_proj_weight.mags +3 -0
  3. deepseek-r1-1.5b-packed/model_layers_0_mlp_up_proj_weight.signs +3 -0
  4. deepseek-r1-1.5b-packed/model_layers_0_self_attn_q_proj_weight.signs +3 -0
  5. deepseek-r1-1.5b-packed/model_layers_11_mlp_gate_proj_weight.mags +3 -0
  6. deepseek-r1-1.5b-packed/model_layers_11_mlp_gate_proj_weight.signs +3 -0
  7. deepseek-r1-1.5b-packed/model_layers_12_mlp_gate_proj_weight.mags +3 -0
  8. deepseek-r1-1.5b-packed/model_layers_15_mlp_gate_proj_weight.mags +3 -0
  9. deepseek-r1-1.5b-packed/model_layers_17_mlp_down_proj_weight.signs +3 -0
  10. deepseek-r1-1.5b-packed/model_layers_17_mlp_gate_proj_weight.signs +3 -0
  11. deepseek-r1-1.5b-packed/model_layers_18_self_attn_k_proj_weight.mags +3 -0
  12. deepseek-r1-1.5b-packed/model_layers_19_mlp_down_proj_weight.signs +3 -0
  13. deepseek-r1-1.5b-packed/model_layers_1_mlp_up_proj_weight.mags +3 -0
  14. deepseek-r1-1.5b-packed/model_layers_1_self_attn_o_proj_weight.signs +3 -0
  15. deepseek-r1-1.5b-packed/model_layers_21_mlp_up_proj_weight.mags +3 -0
  16. deepseek-r1-1.5b-packed/model_layers_21_self_attn_k_proj_weight.mags +3 -0
  17. deepseek-r1-1.5b-packed/model_layers_21_self_attn_o_proj_weight.mags +3 -0
  18. deepseek-r1-1.5b-packed/model_layers_22_mlp_down_proj_weight.mags +3 -0
  19. deepseek-r1-1.5b-packed/model_layers_22_mlp_gate_proj_weight.mags +3 -0
  20. deepseek-r1-1.5b-packed/model_layers_22_self_attn_o_proj_weight.signs +3 -0
  21. deepseek-r1-1.5b-packed/model_layers_22_self_attn_q_proj_weight.mags +3 -0
  22. deepseek-r1-1.5b-packed/model_layers_23_self_attn_v_proj_weight.mags +3 -0
  23. deepseek-r1-1.5b-packed/model_layers_26_self_attn_k_proj_weight.mags +3 -0
  24. deepseek-r1-1.5b-packed/model_layers_26_self_attn_v_proj_weight.mags +3 -0
  25. deepseek-r1-1.5b-packed/model_layers_27_mlp_down_proj_weight.signs +3 -0
  26. deepseek-r1-1.5b-packed/model_layers_27_mlp_up_proj_weight.signs +3 -0
  27. deepseek-r1-1.5b-packed/model_layers_27_self_attn_k_proj_weight.mags +3 -0
  28. deepseek-r1-1.5b-packed/model_layers_27_self_attn_q_proj_weight.mags +3 -0
  29. deepseek-r1-1.5b-packed/model_layers_2_mlp_down_proj_weight.signs +3 -0
  30. deepseek-r1-1.5b-packed/model_layers_4_mlp_down_proj_weight.mags +3 -0
  31. deepseek-r1-1.5b-packed/model_layers_4_self_attn_o_proj_weight.signs +3 -0
  32. deepseek-r1-1.5b-packed/model_layers_5_self_attn_o_proj_weight.signs +3 -0
  33. deepseek-r1-1.5b-packed/model_layers_5_self_attn_q_proj_weight.signs +3 -0
  34. deepseek-r1-1.5b-packed/model_layers_7_self_attn_v_proj_weight.mags +3 -0
  35. deepseek-r1-1.5b-packed/model_layers_8_mlp_down_proj_weight.mags +3 -0
  36. deepseek-r1-1.5b-packed/model_layers_8_mlp_up_proj_weight.mags +3 -0
  37. deepseek-r1-1.5b-packed/model_layers_9_self_attn_o_proj_weight.mags +3 -0
  38. deepseek-r1-1.5b-packed/model_layers_9_self_attn_q_proj_weight.mags +3 -0
  39. deepseek-r1-1.5b-packed/model_layers_9_self_attn_v_proj_weight.mags +3 -0
  40. deepseek-r1-1.5b-unary/model_layers_0_post_attention_layernorm_weight.fp16 +0 -0
  41. deepseek-r1-1.5b-unary/model_layers_10_self_attn_k_proj_bias.fp16 +0 -0
  42. deepseek-r1-1.5b-unary/model_layers_12_self_attn_v_proj_weight.sign +0 -0
  43. deepseek-r1-1.5b-unary/model_layers_13_self_attn_k_proj_weight.sign +0 -0
  44. deepseek-r1-1.5b-unary/model_layers_14_input_layernorm_weight.fp16 +0 -0
  45. deepseek-r1-1.5b-unary/model_layers_19_self_attn_k_proj_weight.scales +0 -0
  46. deepseek-r1-1.5b-unary/model_layers_21_mlp_gate_proj_weight.scales +0 -0
  47. deepseek-r1-1.5b-unary/model_layers_2_input_layernorm_weight.fp16 +0 -0
  48. deepseek-r1-1.5b-unary/model_layers_2_self_attn_k_proj_weight.sign +0 -0
  49. deepseek-r1-1.5b-unary/model_layers_2_self_attn_q_proj_weight.scales +0 -0
  50. deepseek-r1-1.5b-unary/model_layers_8_self_attn_v_proj_bias.fp16 +0 -0
.gitattributes CHANGED
@@ -3421,3 +3421,41 @@ deepseek-r1-1.5b-ternary/model_layers_17_mlp_down_proj_weight.neg filter=lfs dif
3421
  deepseek-r1-1.5b-ternary/model_layers_14_mlp_down_proj_weight.pos filter=lfs diff=lfs merge=lfs -text
3422
  deepseek-r1-1.5b-ternary/model_layers_10_mlp_down_proj_weight.neg filter=lfs diff=lfs merge=lfs -text
3423
  deepseek-r1-1.5b-ternary/model_layers_23_mlp_down_proj_weight.neg filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3421
  deepseek-r1-1.5b-ternary/model_layers_14_mlp_down_proj_weight.pos filter=lfs diff=lfs merge=lfs -text
3422
  deepseek-r1-1.5b-ternary/model_layers_10_mlp_down_proj_weight.neg filter=lfs diff=lfs merge=lfs -text
3423
  deepseek-r1-1.5b-ternary/model_layers_23_mlp_down_proj_weight.neg filter=lfs diff=lfs merge=lfs -text
3424
+ deepseek-r1-1.5b-packed/model_layers_9_self_attn_v_proj_weight.mags filter=lfs diff=lfs merge=lfs -text
3425
+ deepseek-r1-1.5b-packed/model_layers_15_mlp_gate_proj_weight.mags filter=lfs diff=lfs merge=lfs -text
3426
+ deepseek-r1-1.5b-packed/model_layers_21_self_attn_k_proj_weight.mags filter=lfs diff=lfs merge=lfs -text
3427
+ deepseek-r1-1.5b-packed/model_layers_18_self_attn_k_proj_weight.mags filter=lfs diff=lfs merge=lfs -text
3428
+ deepseek-r1-1.5b-packed/model_layers_9_self_attn_o_proj_weight.mags filter=lfs diff=lfs merge=lfs -text
3429
+ deepseek-r1-1.5b-packed/model_layers_22_mlp_gate_proj_weight.mags filter=lfs diff=lfs merge=lfs -text
3430
+ deepseek-r1-1.5b-packed/model_layers_8_mlp_down_proj_weight.mags filter=lfs diff=lfs merge=lfs -text
3431
+ deepseek-r1-1.5b-packed/model_layers_27_mlp_up_proj_weight.signs filter=lfs diff=lfs merge=lfs -text
3432
+ deepseek-r1-1.5b-packed/model_layers_27_self_attn_k_proj_weight.mags filter=lfs diff=lfs merge=lfs -text
3433
+ deepseek-r1-1.5b-packed/model_layers_7_self_attn_v_proj_weight.mags filter=lfs diff=lfs merge=lfs -text
3434
+ deepseek-r1-1.5b-packed/model_layers_22_self_attn_q_proj_weight.mags filter=lfs diff=lfs merge=lfs -text
3435
+ deepseek-r1-1.5b-packed/model_layers_2_mlp_down_proj_weight.signs filter=lfs diff=lfs merge=lfs -text
3436
+ deepseek-r1-1.5b-packed/model_layers_21_mlp_up_proj_weight.mags filter=lfs diff=lfs merge=lfs -text
3437
+ deepseek-r1-1.5b-packed/model_layers_21_self_attn_o_proj_weight.mags filter=lfs diff=lfs merge=lfs -text
3438
+ deepseek-r1-1.5b-packed/model_layers_22_self_attn_o_proj_weight.signs filter=lfs diff=lfs merge=lfs -text
3439
+ deepseek-r1-1.5b-packed/model_layers_27_mlp_down_proj_weight.signs filter=lfs diff=lfs merge=lfs -text
3440
+ deepseek-r1-1.5b-packed/model_layers_23_self_attn_v_proj_weight.mags filter=lfs diff=lfs merge=lfs -text
3441
+ deepseek-r1-1.5b-packed/model_layers_26_self_attn_v_proj_weight.mags filter=lfs diff=lfs merge=lfs -text
3442
+ deepseek-r1-1.5b-packed/model_layers_5_self_attn_o_proj_weight.signs filter=lfs diff=lfs merge=lfs -text
3443
+ deepseek-r1-1.5b-packed/model_layers_4_mlp_down_proj_weight.mags filter=lfs diff=lfs merge=lfs -text
3444
+ deepseek-r1-1.5b-packed/model_layers_0_self_attn_q_proj_weight.signs filter=lfs diff=lfs merge=lfs -text
3445
+ deepseek-r1-1.5b-packed/model_layers_11_mlp_gate_proj_weight.signs filter=lfs diff=lfs merge=lfs -text
3446
+ deepseek-r1-1.5b-packed/model_layers_17_mlp_gate_proj_weight.signs filter=lfs diff=lfs merge=lfs -text
3447
+ deepseek-r1-1.5b-packed/model_layers_5_self_attn_q_proj_weight.signs filter=lfs diff=lfs merge=lfs -text
3448
+ deepseek-r1-1.5b-packed/model_layers_0_mlp_gate_proj_weight.mags filter=lfs diff=lfs merge=lfs -text
3449
+ deepseek-r1-1.5b-packed/model_layers_12_mlp_gate_proj_weight.mags filter=lfs diff=lfs merge=lfs -text
3450
+ deepseek-r1-1.5b-packed/model_layers_22_mlp_down_proj_weight.mags filter=lfs diff=lfs merge=lfs -text
3451
+ deepseek-r1-1.5b-packed/model_layers_27_self_attn_q_proj_weight.mags filter=lfs diff=lfs merge=lfs -text
3452
+ deepseek-r1-1.5b-packed/model_layers_1_mlp_up_proj_weight.mags filter=lfs diff=lfs merge=lfs -text
3453
+ deepseek-r1-1.5b-packed/model_layers_11_mlp_gate_proj_weight.mags filter=lfs diff=lfs merge=lfs -text
3454
+ deepseek-r1-1.5b-packed/model_layers_17_mlp_down_proj_weight.signs filter=lfs diff=lfs merge=lfs -text
3455
+ deepseek-r1-1.5b-packed/model_layers_26_self_attn_k_proj_weight.mags filter=lfs diff=lfs merge=lfs -text
3456
+ deepseek-r1-1.5b-packed/model_layers_4_self_attn_o_proj_weight.signs filter=lfs diff=lfs merge=lfs -text
3457
+ deepseek-r1-1.5b-packed/model_layers_0_mlp_up_proj_weight.signs filter=lfs diff=lfs merge=lfs -text
3458
+ deepseek-r1-1.5b-packed/model_layers_9_self_attn_q_proj_weight.mags filter=lfs diff=lfs merge=lfs -text
3459
+ deepseek-r1-1.5b-packed/model_layers_1_self_attn_o_proj_weight.signs filter=lfs diff=lfs merge=lfs -text
3460
+ deepseek-r1-1.5b-packed/model_layers_8_mlp_up_proj_weight.mags filter=lfs diff=lfs merge=lfs -text
3461
+ deepseek-r1-1.5b-packed/model_layers_19_mlp_down_proj_weight.signs filter=lfs diff=lfs merge=lfs -text
deepseek-r1-1.5b-packed/model_layers_0_mlp_gate_proj_weight.mags ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1aebceeb5c49e7d2c6728a481dce38797e08581a14dd6cfe6ecd6a727521ee36
3
+ size 13762560
deepseek-r1-1.5b-packed/model_layers_0_mlp_up_proj_weight.signs ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:43b1f543227944a1af2750e991457b30cb7188988bc96d74d0a5dd89facf6877
3
+ size 1720320
deepseek-r1-1.5b-packed/model_layers_0_self_attn_q_proj_weight.signs ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:556096531abd03fc5e5f04c6d35b923f99fa220b279f136aea4b8d2af372d579
3
+ size 294912
deepseek-r1-1.5b-packed/model_layers_11_mlp_gate_proj_weight.mags ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:97c83c4abb47118c502329a959570a1215507e0dd66f9e84069b310aa1722e8f
3
+ size 13762560
deepseek-r1-1.5b-packed/model_layers_11_mlp_gate_proj_weight.signs ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2422715d9cb42eaefaff21120cfde70189525f51f0f51971cc5e950f1bdc48b2
3
+ size 1720320
deepseek-r1-1.5b-packed/model_layers_12_mlp_gate_proj_weight.mags ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:302f4a093385122723dafde2ba2592a94539b2ebe12c523e69f7142ec89a11b4
3
+ size 13762560
deepseek-r1-1.5b-packed/model_layers_15_mlp_gate_proj_weight.mags ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:070fc6282e43b0052bce403648d677e8106a2a380c2e9262f38e4dcd5cd24199
3
+ size 13762560
deepseek-r1-1.5b-packed/model_layers_17_mlp_down_proj_weight.signs ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:65b662b9a71e1c30f54e9781190dc2c4847527cdecdb022b85b3909d2b4c11cb
3
+ size 1720320
deepseek-r1-1.5b-packed/model_layers_17_mlp_gate_proj_weight.signs ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:edf4de964079986f1f878f816dd2eb0aab9f1a62a9fda213ee8520983b495442
3
+ size 1720320
deepseek-r1-1.5b-packed/model_layers_18_self_attn_k_proj_weight.mags ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:752879c949a10ddf33d214ca734944c9c231322aa5b8dfccac99bf0f4160694b
3
+ size 393216
deepseek-r1-1.5b-packed/model_layers_19_mlp_down_proj_weight.signs ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:010448aa44fe1534eb246e0934276a8f7abe72cd6fd654526b33f590239a4ead
3
+ size 1720320
deepseek-r1-1.5b-packed/model_layers_1_mlp_up_proj_weight.mags ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bba8ebd07fadb183794f9e793b29b2991f95b005ef5f9b2bd139fa6f27a4c5fc
3
+ size 13762560
deepseek-r1-1.5b-packed/model_layers_1_self_attn_o_proj_weight.signs ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:264d743b356d1c334878111aa6d1c1fbd184503bb3bc5e09618c4659ef84c4d6
3
+ size 294912
deepseek-r1-1.5b-packed/model_layers_21_mlp_up_proj_weight.mags ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:774b53819b9b8a03fadecd394347e52ffc411742c185cf2319980568b3143a4d
3
+ size 13762560
deepseek-r1-1.5b-packed/model_layers_21_self_attn_k_proj_weight.mags ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dd6051f5e803aef03a6189d91ed552950db96c01ff8d95f6a8f0b10802cdaca3
3
+ size 393216
deepseek-r1-1.5b-packed/model_layers_21_self_attn_o_proj_weight.mags ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f508641bd74b15cab5f8447096b62c8f215d82daab61c0459ebecf37035af34e
3
+ size 2359296
deepseek-r1-1.5b-packed/model_layers_22_mlp_down_proj_weight.mags ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cb3fd1a1415c48fcc8555907931b5c30148ddcca2698ac3c5d75185370fee750
3
+ size 13762560
deepseek-r1-1.5b-packed/model_layers_22_mlp_gate_proj_weight.mags ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:946039fa437eaf913c0253718c3c6debe813135bdd56c6f36bfa4e21844e7a9c
3
+ size 13762560
deepseek-r1-1.5b-packed/model_layers_22_self_attn_o_proj_weight.signs ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c226189bbb87071269d4ad03b322b637491172fe6d7d96289a914b071d7477fa
3
+ size 294912
deepseek-r1-1.5b-packed/model_layers_22_self_attn_q_proj_weight.mags ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6907845bc4ecc5a36df6c259e44456f8430eef36352b767d990e2c88ab01e609
3
+ size 2359296
deepseek-r1-1.5b-packed/model_layers_23_self_attn_v_proj_weight.mags ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f379a20c016047a33b4a3f93f5ba772dde679d1d5380d04194cb5a616ecb49f6
3
+ size 393216
deepseek-r1-1.5b-packed/model_layers_26_self_attn_k_proj_weight.mags ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:588563f62366d62a26ec4441ec1f916225f291894f4c87b21e0943d645f8cd06
3
+ size 393216
deepseek-r1-1.5b-packed/model_layers_26_self_attn_v_proj_weight.mags ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:42a311a1cd660cd05dac30c09aa50f156dcef871814576d09260d3f3af971aca
3
+ size 393216
deepseek-r1-1.5b-packed/model_layers_27_mlp_down_proj_weight.signs ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:07d27e5c15f9b50f5e6a781953c79efe06ce7d7596d476894237df2835027ee6
3
+ size 1720320
deepseek-r1-1.5b-packed/model_layers_27_mlp_up_proj_weight.signs ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d9119d5b576a6262380bbf062dd59b12f0b918f2413febf82d97523d0bc8c662
3
+ size 1720320
deepseek-r1-1.5b-packed/model_layers_27_self_attn_k_proj_weight.mags ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b9192789d7258981d648a90720f5803ae76aa45ef15fd1ad808dceb78528d049
3
+ size 393216
deepseek-r1-1.5b-packed/model_layers_27_self_attn_q_proj_weight.mags ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f389dd739bf059f5224c6da7b5174dc1100ce403ebfcab503b9cef7c7f2c581d
3
+ size 2359296
deepseek-r1-1.5b-packed/model_layers_2_mlp_down_proj_weight.signs ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4910406d2aff7bd205f58fcf484f9abd4b7efb7bb2a5740d5afc071e55cd2711
3
+ size 1720320
deepseek-r1-1.5b-packed/model_layers_4_mlp_down_proj_weight.mags ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e1bcab82d136da631759d9405c0c749661f2c0885a79a79351613900de7e5c53
3
+ size 13762560
deepseek-r1-1.5b-packed/model_layers_4_self_attn_o_proj_weight.signs ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e19c6b8b0ae5aa69d9cb6b05db7a21daef7e6738961f1b34c2313f49606caa41
3
+ size 294912
deepseek-r1-1.5b-packed/model_layers_5_self_attn_o_proj_weight.signs ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4c011f8749c3f0375bfdeacd01cc0543cc143243520ad81a832540af962e82e5
3
+ size 294912
deepseek-r1-1.5b-packed/model_layers_5_self_attn_q_proj_weight.signs ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ea502782ca87f1068f0d34260206df8b18c106eee96ce075fe5eecc7e9382cf4
3
+ size 294912
deepseek-r1-1.5b-packed/model_layers_7_self_attn_v_proj_weight.mags ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e5be274f0b9b14a48edc65aee157c19e5ff20c73c4d5bd43056413b92777a51b
3
+ size 393216
deepseek-r1-1.5b-packed/model_layers_8_mlp_down_proj_weight.mags ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:72b26c96f2eaf270ca50aed5b24aefb778b19b3e0e877d09ad9b377e9a6d14fb
3
+ size 13762560
deepseek-r1-1.5b-packed/model_layers_8_mlp_up_proj_weight.mags ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:55cdfc24d76a06204d9e3194fc94b0c3c886d24ce4e28304bd8c7f2461444c70
3
+ size 13762560
deepseek-r1-1.5b-packed/model_layers_9_self_attn_o_proj_weight.mags ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:83da93fab4f9f1858e84c194fa26e590277deb9000987817247773f2db8bee1c
3
+ size 2359296
deepseek-r1-1.5b-packed/model_layers_9_self_attn_q_proj_weight.mags ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7006658255e51471ba38a583a36085249f53e8043667c346a4ebb3f3062ea816
3
+ size 2359296
deepseek-r1-1.5b-packed/model_layers_9_self_attn_v_proj_weight.mags ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:14fde50d93aa4509ffde9814225ad374f98d7513043388d27b48bc5d650d2a8d
3
+ size 393216
deepseek-r1-1.5b-unary/model_layers_0_post_attention_layernorm_weight.fp16 ADDED
Binary file (3.07 kB). View file
 
deepseek-r1-1.5b-unary/model_layers_10_self_attn_k_proj_bias.fp16 ADDED
Binary file (512 Bytes). View file
 
deepseek-r1-1.5b-unary/model_layers_12_self_attn_v_proj_weight.sign ADDED
Binary file (49.2 kB). View file
 
deepseek-r1-1.5b-unary/model_layers_13_self_attn_k_proj_weight.sign ADDED
Binary file (49.2 kB). View file
 
deepseek-r1-1.5b-unary/model_layers_14_input_layernorm_weight.fp16 ADDED
Binary file (3.07 kB). View file
 
deepseek-r1-1.5b-unary/model_layers_19_self_attn_k_proj_weight.scales ADDED
Binary file (1.02 kB). View file
 
deepseek-r1-1.5b-unary/model_layers_21_mlp_gate_proj_weight.scales ADDED
Binary file (35.8 kB). View file
 
deepseek-r1-1.5b-unary/model_layers_2_input_layernorm_weight.fp16 ADDED
Binary file (3.07 kB). View file
 
deepseek-r1-1.5b-unary/model_layers_2_self_attn_k_proj_weight.sign ADDED
Binary file (49.2 kB). View file
 
deepseek-r1-1.5b-unary/model_layers_2_self_attn_q_proj_weight.scales ADDED
Binary file (6.14 kB). View file
 
deepseek-r1-1.5b-unary/model_layers_8_self_attn_v_proj_bias.fp16 ADDED
Binary file (512 Bytes). View file