Hugging Face's logo

rwkv-x-dev
/
rwkv-x-playground

Model card Files Community
201

[WIP] [GHA] trainer-v4-unit-test/model-init.ipynb result models (multi-commit b91ffc85a896fc23176f32d755676faf798e33a983efad6dff3512e618d3e861)

#55
by picocreator - opened
base: refs/heads/main
←
from: refs/pr/55
Discussion Files changed
+59393
-1840193
This view is limited to 50 files because it contains too many changes.  See the raw diff here.
Files changed (50) hide show
  1. .gitattributes +0 -55
  2. actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/model/BaseV5-C-Tune5.pth +0 -3
  3. actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/model/EWR-1B5-E0_1-mem-ctx-8k.pth +0 -3
  4. actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/model/L6-D4096-E0_1-neox-v5base-init.pth +0 -3
  5. actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/model/L6-D512-neox-init.pth +0 -3
  6. actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/model/WaveV5-C-Tune5.pth +0 -3
  7. actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/model/v5-L6-D1024-E0_1-enwiki-4k.pth +0 -3
  8. actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/model/v5-L6-D1024-E0_1-enwiki-instruct.pth +0 -3
  9. actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/model/v5-L6-D1024-E0_1-neox-init.pth +0 -3
  10. actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/model/v5-L6-D128-E0_1-enwiki-4k.pth +0 -3
  11. actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/model/v5-L6-D128-E0_1-enwiki-instruct.pth +0 -3
  12. actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/model/v5-L6-D128-E0_1-neox-init.pth +0 -3
  13. actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/model/v5-L6-D2048-E0_1-mem-ctx-8k.pth +0 -3
  14. actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/model/v5-L6-D256-E0_1-enwiki-4k.pth +0 -3
  15. actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/model/v5-L6-D256-E0_1-enwiki-instruct.pth +0 -3
  16. actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/model/v5-L6-D256-E0_1-neox-init.pth +0 -3
  17. actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/model/v5-L6-D4096-E0_1-mem-ctx-8k.pth +0 -3
  18. actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/model/v5-L6-D512-E0_1-enwiki-4k.pth +0 -3
  19. actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/model/v5-L6-D512-E0_1-enwiki-instruct.pth +0 -3
  20. actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/model/v5-L6-D512-E0_1-neox-init.pth +0 -3
  21. actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/model/v5-L96-D1024-E0_1-enwiki-4k.pth +0 -3
  22. actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/model/v5-L96-D1024-E0_1-enwiki-instruct.pth +0 -3
  23. actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/model/v5-L96-D1024-E0_1-mem-ctx-512.pth +0 -3
  24. actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/model/v5-L96-D1024-E0_1-mem-instruct.pth +0 -3
  25. actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/model/v5-hs2x-L6-D2048-E0_1-mem-ctx-8k.pth +0 -3
  26. actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/model/v5-hs2x-L6-D4096-E0_1-enwiki-4k.pth +0 -3
  27. actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/model/v5-hs2x-L6-D4096-E0_1-enwiki-instruct.pth +0 -3
  28. actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/model/v5-hs2x-L6-D4096-E0_1-mem-ctx-8k.pth +0 -3
  29. actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/model/v5wave-1B5-E0_1-ctx-16k-preview-30p.pth +0 -3
  30. actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/output/experiment/memory-bench/Benchmark-V5.ipynb +0 -0
  31. actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/output/experiment/memory-bench/Benchmark-V5headsize2x.ipynb +0 -0
  32. actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/output/experiment/memory-bench/Benchmark-V5wavenet.ipynb +0 -0
  33. actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/output/experiment/memory-bench/logs/BaseV5-C-Tune5-16k.csv +0 -3
  34. actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/output/experiment/memory-bench/logs/BaseV5-C-Tune5-1k.csv +0 -0
  35. actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/output/experiment/memory-bench/logs/BaseV5-C-Tune5-4k.csv +0 -3
  36. actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/output/experiment/memory-bench/logs/WavenetV5-C-Tune5-16k.csv +0 -3
  37. actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/output/experiment/memory-bench/logs/WavenetV5-C-Tune5-1k.csv +0 -0
  38. actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/output/experiment/memory-bench/logs/WavenetV5-C-Tune5-4k.csv +0 -3
  39. actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/output/experiment/memory-bench/logs/v5-L6-D2048-E0_1-16k.csv +0 -3
  40. actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/output/experiment/memory-bench/logs/v5-L6-D2048-E0_1-1k.csv +0 -0
  41. actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/output/experiment/memory-bench/logs/v5-L6-D2048-E0_1-4k.csv +0 -3
  42. actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/output/experiment/memory-bench/logs/v5-L6-D4096-E0_1-16k.csv +0 -3
  43. actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/output/experiment/memory-bench/logs/v5-L6-D4096-E0_1-1k.csv +0 -0
  44. actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/output/experiment/memory-bench/logs/v5-L6-D4096-E0_1-4k.csv +0 -3
  45. actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/output/experiment/memory-bench/logs/v5-hs2x-L6-D2048-E0_1-16k.csv +0 -3
  46. actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/output/experiment/memory-bench/logs/v5-hs2x-L6-D2048-E0_1-1k.csv +0 -0
  47. actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/output/experiment/memory-bench/logs/v5-hs2x-L6-D2048-E0_1-4k.csv +0 -3
  48. actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/output/experiment/memory-bench/logs/v5-hs2x-L6-D4096-E0_1-16k.csv +0 -3
  49. actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/output/experiment/memory-bench/logs/v5-hs2x-L6-D4096-E0_1-1k.csv +0 -0
  50. actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/output/experiment/memory-bench/logs/v5-hs2x-L6-D4096-E0_1-4k.csv +0 -3
.gitattributes CHANGED
@@ -50,58 +50,3 @@ experiment/memory-bench/logs/WavenetV5-C-Tune5-4k.csv filter=lfs diff=lfs merge=
50
  experiment/memory-bench/logs/v5wave-13-1B5-E0_1-ctx-16k-16k.csv filter=lfs diff=lfs merge=lfs -text
51
  experiment/memory-bench/logs/v5wave-13-1B5-E0_1-ctx-16k-4k.csv filter=lfs diff=lfs merge=lfs -text
52
  experiment/rwkv-x-exp/v5-headsize32/v5-L6-D2048-E1e-1-ctx4k-part2.ipynb filter=lfs diff=lfs merge=lfs -text
53
- actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/output/experiment/memory-bench/logs/v5-L6-D4096-E0_1-4k.csv filter=lfs diff=lfs merge=lfs -text
54
- actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/output/experiment/memory-bench/logs/v5-L6-D4096-E0_1-16k.csv filter=lfs diff=lfs merge=lfs -text
55
- actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/output/experiment/memory-bench/logs/v5-L6-D2048-E0_1-16k.csv filter=lfs diff=lfs merge=lfs -text
56
- actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/output/experiment/memory-bench/logs/v5-L6-D2048-E0_1-4k.csv filter=lfs diff=lfs merge=lfs -text
57
- actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/output/experiment/memory-bench/logs/BaseV5-C-Tune5-4k.csv filter=lfs diff=lfs merge=lfs -text
58
- actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/output/experiment/memory-bench/logs/BaseV5-C-Tune5-16k.csv filter=lfs diff=lfs merge=lfs -text
59
- actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/output/experiment/rwkv-x-exp/v5-small-model/v5-L6-ctx4k-models-part1.ipynb filter=lfs diff=lfs merge=lfs -text
60
- actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/output/experiment/memory-bench/logs/v5wave-13-1B5-E0_1-ctx-16k-4k.csv filter=lfs diff=lfs merge=lfs -text
61
- actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/output/experiment/memory-bench/logs/WavenetV5-C-Tune5-4k.csv filter=lfs diff=lfs merge=lfs -text
62
- actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/output/experiment/memory-bench/logs/WavenetV5-C-Tune5-16k.csv filter=lfs diff=lfs merge=lfs -text
63
- actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/output/experiment/memory-bench/logs/v5wave-13-1B5-E0_1-ctx-16k-16k.csv filter=lfs diff=lfs merge=lfs -text
64
- actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/output/experiment/memory-bench/logs/v5-hs2x-L6-D4096-E0_1-4k.csv filter=lfs diff=lfs merge=lfs -text
65
- actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/output/experiment/memory-bench/logs/v5-hs2x-L6-D2048-E0_1-4k.csv filter=lfs diff=lfs merge=lfs -text
66
- actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/output/experiment/memory-bench/logs/v5-hs2x-L6-D2048-E0_1-16k.csv filter=lfs diff=lfs merge=lfs -text
67
- actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/output/experiment/memory-bench/logs/v5-hs2x-L6-D4096-E0_1-16k.csv filter=lfs diff=lfs merge=lfs -text
68
- experiment/memory-bench/actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/output/experiment/memory-bench/logs/WavenetV5-C-Tune5-4k.csv filter=lfs diff=lfs merge=lfs -text
69
- experiment/memory-bench/actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/output/experiment/memory-bench/logs/v5wave-13-1B5-E0_1-ctx-16k-4k.csv filter=lfs diff=lfs merge=lfs -text
70
- experiment/memory-bench/actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/output/experiment/memory-bench/logs/WavenetV5-C-Tune5-16k.csv filter=lfs diff=lfs merge=lfs -text
71
- experiment/memory-bench/actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/output/experiment/memory-bench/logs/v5wave-13-1B5-E0_1-ctx-16k-16k.csv filter=lfs diff=lfs merge=lfs -text
72
- experiment/memory-bench/actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/output/experiment/memory-bench/logs/v5-hs2x-L6-D4096-E0_1-16k.csv filter=lfs diff=lfs merge=lfs -text
73
- experiment/memory-bench/actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/output/experiment/memory-bench/logs/v5-hs2x-L6-D2048-E0_1-4k.csv filter=lfs diff=lfs merge=lfs -text
74
- experiment/memory-bench/actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/output/experiment/memory-bench/logs/v5-hs2x-L6-D4096-E0_1-4k.csv filter=lfs diff=lfs merge=lfs -text
75
- experiment/memory-bench/actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/output/experiment/memory-bench/logs/v5-hs2x-L6-D2048-E0_1-16k.csv filter=lfs diff=lfs merge=lfs -text
76
- experiment/memory-bench/actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/output/experiment/memory-bench/logs/v5-L6-D4096-E0_1-4k.csv filter=lfs diff=lfs merge=lfs -text
77
- experiment/memory-bench/actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/output/experiment/memory-bench/logs/v5-L6-D4096-E0_1-16k.csv filter=lfs diff=lfs merge=lfs -text
78
- experiment/memory-bench/actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/output/experiment/memory-bench/logs/v5-L6-D2048-E0_1-16k.csv filter=lfs diff=lfs merge=lfs -text
79
- experiment/memory-bench/actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/output/experiment/memory-bench/logs/v5-L6-D2048-E0_1-4k.csv filter=lfs diff=lfs merge=lfs -text
80
- experiment/memory-bench/actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/output/experiment/memory-bench/logs/BaseV5-C-Tune5-4k.csv filter=lfs diff=lfs merge=lfs -text
81
- experiment/memory-bench/actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/output/experiment/memory-bench/logs/BaseV5-C-Tune5-16k.csv filter=lfs diff=lfs merge=lfs -text
82
- experiment/memory-bench/logs/v5-L96-D1024-E0_1-mem-ctx-8k-16k.csv filter=lfs diff=lfs merge=lfs -text
83
- experiment/memory-bench/logs/v5-L96-D1024-E0_1-mem-ctx-8k-4k.csv filter=lfs diff=lfs merge=lfs -text
84
- experiment/rwkv-x-exp/v5-slim-memory/v5-L6-D1024-E1e-1-ctx4k.ipynb filter=lfs diff=lfs merge=lfs -text
85
- experiment/memory-bench/logs/v5-L6-D1024-E0_1-4k.csv filter=lfs diff=lfs merge=lfs -text
86
- experiment/memory-bench/logs/v5-L6-D1024-E0_1-16k.csv filter=lfs diff=lfs merge=lfs -text
87
- experiment/rwkv-x-exp/v5-r3-memory/L12-D2048-E1e-1-ctx4k/part1.ipynb filter=lfs diff=lfs merge=lfs -text
88
- experiment/rwkv-x-exp/v5-r3-memory/L6-D2048-E1e-1-ctx4k/part1.ipynb filter=lfs diff=lfs merge=lfs -text
89
- experiment/rwkv-x-exp/v5-r3-memory/L6-D2048-E1e-1-ctx4k/part2.ipynb filter=lfs diff=lfs merge=lfs -text
90
- experiment/rwkv-x-exp/v5-r3-memory/L12-D2048-E1e-1-ctx4k/part2.ipynb filter=lfs diff=lfs merge=lfs -text
91
- experiment/rwkv-x-exp/v5-r3-memory/L6-D2560-E1e-1-ctx4k/part1.ipynb filter=lfs diff=lfs merge=lfs -text
92
- experiment/rwkv-x-exp/v5-r3-memory/L6-D2560-E1e-1-ctx4k/stage2.ipynb filter=lfs diff=lfs merge=lfs -text
93
- experiment/rwkv-x-exp/v5-r3-memory/L6-D2048-E1e-1-ctx4k/stage2.ipynb filter=lfs diff=lfs merge=lfs -text
94
- experiment/rwkv-x-exp/v5-r3-memory/L6-D2560-E1e-1-ctx4k/stage3.ipynb filter=lfs diff=lfs merge=lfs -text
95
- experiment/rwkv-x-exp/v5-r3-memory/L6-D2048-E1e-1-ctx4k/stage3.ipynb filter=lfs diff=lfs merge=lfs -text
96
- experiment/rwkv-x-exp/v5-r3-memory/L6-D2560-E1e-1-ctx4k/stage4.ipynb filter=lfs diff=lfs merge=lfs -text
97
- experiment/rwkv-x-exp/v5-r3-memory/L6-D2048-E1e-1-ctx4k/stage4.ipynb filter=lfs diff=lfs merge=lfs -text
98
- experiment/rwkv-x-exp/v5-r3-memory/L6-D2560-E1e-1-ctx4k/stage5.ipynb filter=lfs diff=lfs merge=lfs -text
99
- experiment/rwkv-x-exp/v5-r3-memory/L6-D2048-E1e-1-ctx4k/stage5.ipynb filter=lfs diff=lfs merge=lfs -text
100
- experiment/rwkv-x-exp/multi-size-train/v5-L6-D2048-part1.ipynb filter=lfs diff=lfs merge=lfs -text
101
- experiment/rwkv-x-exp/multi-size-train/v5-L6-D2048-baseline.ipynb filter=lfs diff=lfs merge=lfs -text
102
- experiment/rwkv-x-exp/multi-size-train/v5-L12-D2048-part1.ipynb filter=lfs diff=lfs merge=lfs -text
103
- experiment/rwkv-x-exp/multi-size-train/v5-L12-D2048-baseline.ipynb filter=lfs diff=lfs merge=lfs -text
104
- experiment/rwkv-x-exp/multi-size-train/v5-L6+6-D2048-overwrite-naive.ipynb filter=lfs diff=lfs merge=lfs -text
105
- experiment/rwkv-x-exp/multi-size-train/v5-L6-D2048-split-train.ipynb filter=lfs diff=lfs merge=lfs -text
106
- experiment/rwkv-x-exp/multi-size-train/v5-L6+6-D2048-layer-expansion.ipynb filter=lfs diff=lfs merge=lfs -text
107
- experiment/rwkv-x-exp/multi-size-train/v5-L6-D2048-split-baseline.ipynb filter=lfs diff=lfs merge=lfs -text
 
50
  experiment/memory-bench/logs/v5wave-13-1B5-E0_1-ctx-16k-16k.csv filter=lfs diff=lfs merge=lfs -text
51
  experiment/memory-bench/logs/v5wave-13-1B5-E0_1-ctx-16k-4k.csv filter=lfs diff=lfs merge=lfs -text
52
  experiment/rwkv-x-exp/v5-headsize32/v5-L6-D2048-E1e-1-ctx4k-part2.ipynb filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/model/BaseV5-C-Tune5.pth DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:c1f89b4d653a240f6f165d25988b51f6db36bf8a2388707e3e3242af751575eb
3
- size 6060483063
 
 
 
 
actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/model/EWR-1B5-E0_1-mem-ctx-8k.pth DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:e886ffafd5148b502a00b1c10c847ca918cec61c4c956956a2fe9811c210029b
3
- size 6060483163
 
 
 
 
actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/model/L6-D4096-E0_1-neox-v5base-init.pth DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:5fdf8b34dfb337e5677c71c89013f66dabfff5b844520329451ffe5299ae6dcf
3
- size 3441599365
 
 
 
 
actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/model/L6-D512-neox-init.pth DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:60269f265ddf104301da3c4422e70e55769033b4cb9b60211d0a6c2e9476ac30
3
- size 143969077
 
 
 
 
actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/model/WaveV5-C-Tune5.pth DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:48045b979353a97a1211e32942dbf40429ef7894646a64233474b2aa317ddf61
3
- size 6060483063
 
 
 
 
actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/model/v5-L6-D1024-E0_1-enwiki-4k.pth DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:ab343d0e50cd3a52cede75e5c2b650f95a41cf88b0da2411448c4247d4a25017
3
- size 369695877
 
 
 
 
actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/model/v5-L6-D1024-E0_1-enwiki-instruct.pth DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:7b30e9a16a930f54e083acd612a2fba7ec0179339480b5583990c254c9e3a469
3
- size 369696645
 
 
 
 
actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/model/v5-L6-D1024-E0_1-neox-init.pth DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:49bc99ce6fe8b0580cd8b57ca42d8b807a5f15a9fd1c1b09150a994144158cd2
3
- size 369696389
 
 
 
 
actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/model/v5-L6-D128-E0_1-enwiki-4k.pth DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:f04a76e0d9c98c841e2cb9e6e2443537434ae0c1bf5b69c252fbd2df41359576
3
- size 28355205
 
 
 
 
actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/model/v5-L6-D128-E0_1-enwiki-instruct.pth DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:469ac12ec361ff3d955bad6239de9dfcee9c879f7bb6175108da45ef3c4f772f
3
- size 28355973
 
 
 
 
actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/model/v5-L6-D128-E0_1-neox-init.pth DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:0d1d7a74547dad04465d73683e7c1d699d20bd7b32003483a7003d21c06be4dd
3
- size 28355717
 
 
 
 
actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/model/v5-L6-D2048-E0_1-mem-ctx-8k.pth DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:87b64f45529c2049a8b044b7e7c0338a9ede8ba8259d17d987d8e73f8a34fd75
3
- size 1066508293
 
 
 
 
actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/model/v5-L6-D256-E0_1-enwiki-4k.pth DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:3499009e9b276202f1419639a0751d7ec66ed6231947399893a6f981f1c66f33
3
- size 61783045
 
 
 
 
actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/model/v5-L6-D256-E0_1-enwiki-instruct.pth DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:4982c9bf1d7e75cdf79c2e9260e1ce6c0dc88a8facd23e6548ffa708d5484fc5
3
- size 61783813
 
 
 
 
actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/model/v5-L6-D256-E0_1-neox-init.pth DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:ef3b2734a738a5a66dd5e420114cc34e97f63d14f263badfbca70b101284d8f1
3
- size 61783557
 
 
 
 
actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/model/v5-L6-D4096-E0_1-mem-ctx-8k.pth DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:5f93b1f6f6f7fb2193130a3a51f8ed41a0541b1b5eab100ca9318c8218d481fa
3
- size 3441599237
 
 
 
 
actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/model/v5-L6-D512-E0_1-enwiki-4k.pth DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:aec02826363b9bca931efb4300f738bef1c6911fdb5d57b17dba32cfe389c1d1
3
- size 143973381
 
 
 
 
actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/model/v5-L6-D512-E0_1-enwiki-instruct.pth DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:fa0989a4ff42916b96c781fb0750950a4afffcb4e48e2198ca8f3d1c4859f3d5
3
- size 143974149
 
 
 
 
actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/model/v5-L6-D512-E0_1-neox-init.pth DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:c1a2c07be4e413849df37adc9b4b9911683580d3ed0e189ae4435d5a17831863
3
- size 143973893
 
 
 
 
actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/model/v5-L96-D1024-E0_1-enwiki-4k.pth DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:cf564bd00443254a3460507c8f020d65f3f7de6598329ad60d7ceb74fdf94786
3
- size 2825974771
 
 
 
 
actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/model/v5-L96-D1024-E0_1-enwiki-instruct.pth DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:a11abb9b4cc27b0a3a906dbbc60f2573ec771bfac5a9b53d10faf5eadcb4dc6c
3
- size 2825986339
 
 
 
 
actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/model/v5-L96-D1024-E0_1-mem-ctx-512.pth DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:893167b0eb69142597da713f1d1a3b7c14cedbd34e677e45adc13979ae756e67
3
- size 2825978627
 
 
 
 
actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/model/v5-L96-D1024-E0_1-mem-instruct.pth DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:e4720aecaffc1c46bb2042aba3737f920fd1e914e04aa8590ac0d1f62b7ce8f8
3
- size 2825980555
 
 
 
 
actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/model/v5-hs2x-L6-D2048-E0_1-mem-ctx-8k.pth DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:c8e3cb04e7c511cb2a2756ba15243c0ef7c725d520fcbe4489f86ea6cb59ccbd
3
- size 1066508165
 
 
 
 
actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/model/v5-hs2x-L6-D4096-E0_1-enwiki-4k.pth DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:0e0909d8eb648dc218a3d5e8cfddf83d0432b49dd5bd94bd985cfbb996b4aefd
3
- size 3441598981
 
 
 
 
actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/model/v5-hs2x-L6-D4096-E0_1-enwiki-instruct.pth DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:9a5f01da724918f3c5108c62c74c4e1d905c72cffc87aa1d3b6b704e354dab31
3
- size 3441599749
 
 
 
 
actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/model/v5-hs2x-L6-D4096-E0_1-mem-ctx-8k.pth DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:fae9799e56fd469c6c1694dae6ae77f78130c06d340e945a3dc8e8ea2bd4e5bb
3
- size 3441599109
 
 
 
 
actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/model/v5wave-1B5-E0_1-ctx-16k-preview-30p.pth DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:4fc2147a91988ee149a65724bb8868047a346778179907c1aea4dd28f19fe695
3
- size 3030376021
 
 
 
 
actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/output/experiment/memory-bench/Benchmark-V5.ipynb DELETED
The diff for this file is too large to render. See raw diff
 
actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/output/experiment/memory-bench/Benchmark-V5headsize2x.ipynb DELETED
The diff for this file is too large to render. See raw diff
 
actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/output/experiment/memory-bench/Benchmark-V5wavenet.ipynb DELETED
The diff for this file is too large to render. See raw diff
 
actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/output/experiment/memory-bench/logs/BaseV5-C-Tune5-16k.csv DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:3b131e25f5a022b59f3a80de7054ed0fc02d23ba0c88109799a463362bcd091d
3
- size 118790470
 
 
 
 
actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/output/experiment/memory-bench/logs/BaseV5-C-Tune5-1k.csv DELETED
The diff for this file is too large to render. See raw diff
 
actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/output/experiment/memory-bench/logs/BaseV5-C-Tune5-4k.csv DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:d5b6dfd18ae9886dfef7b40490e01709bed3a6fb6ae80c1b71d4e579fe33bec3
3
- size 14197389
 
 
 
 
actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/output/experiment/memory-bench/logs/WavenetV5-C-Tune5-16k.csv DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:217618d0c19899377b069e62a6e77afa82e8a9ed457969c867fcf91671bd4590
3
- size 118528649
 
 
 
 
actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/output/experiment/memory-bench/logs/WavenetV5-C-Tune5-1k.csv DELETED
The diff for this file is too large to render. See raw diff
 
actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/output/experiment/memory-bench/logs/WavenetV5-C-Tune5-4k.csv DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:26c73b549f5d4dd5d30d23be2fe638b4a3ced564d9e88f457bdd4ce78c4d5657
3
- size 14282765
 
 
 
 
actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/output/experiment/memory-bench/logs/v5-L6-D2048-E0_1-16k.csv DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:75d9d09b51300d41bd9f4ffc5aa20e5e8433bf5120e50bcc840f50c55d8b164a
3
- size 118428057
 
 
 
 
actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/output/experiment/memory-bench/logs/v5-L6-D2048-E0_1-1k.csv DELETED
The diff for this file is too large to render. See raw diff
 
actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/output/experiment/memory-bench/logs/v5-L6-D2048-E0_1-4k.csv DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:aa4f4a3f30a08194d38c0ea2b9f5991cd4bbc6224cc47fd98f067a34b50ffe38
3
- size 14551219
 
 
 
 
actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/output/experiment/memory-bench/logs/v5-L6-D4096-E0_1-16k.csv DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:16471c2afb16c0a1af294ca554513787e419bdebd0345a073c296d080e100141
3
- size 118660437
 
 
 
 
actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/output/experiment/memory-bench/logs/v5-L6-D4096-E0_1-1k.csv DELETED
The diff for this file is too large to render. See raw diff
 
actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/output/experiment/memory-bench/logs/v5-L6-D4096-E0_1-4k.csv DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:e2808d046aa2c87afc129face7b54ca66dc5027337164178d1a539a6681732de
3
- size 14457770
 
 
 
 
actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/output/experiment/memory-bench/logs/v5-hs2x-L6-D2048-E0_1-16k.csv DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:cc8bd295cca08778440274952c6613f5ae4e30861e08d98c42309ba0c3dd12c6
3
- size 119288105
 
 
 
 
actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/output/experiment/memory-bench/logs/v5-hs2x-L6-D2048-E0_1-1k.csv DELETED
The diff for this file is too large to render. See raw diff
 
actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/output/experiment/memory-bench/logs/v5-hs2x-L6-D2048-E0_1-4k.csv DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:9274891623b8ba5382ec6a4ced0244f14561f67fe6c35d5c8b76d4aff5a8cb41
3
- size 14356636
 
 
 
 
actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/output/experiment/memory-bench/logs/v5-hs2x-L6-D4096-E0_1-16k.csv DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:d3be5d11c2f97341ff29450b3ce3773205defd379ccace659365b628b55a25ee
3
- size 118987824
 
 
 
 
actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/output/experiment/memory-bench/logs/v5-hs2x-L6-D4096-E0_1-1k.csv DELETED
The diff for this file is too large to render. See raw diff
 
actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/output/experiment/memory-bench/logs/v5-hs2x-L6-D4096-E0_1-4k.csv DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:3dba39db6e8fe0ecf0bacb125ab4b446669b72ab72e7fdef61b9a9c38f063597
3
- size 14315317