Hugging Face's logo

EasyDeL
/
DeepSeek-V4-Flash

Text Generation
JAX
easydel
deepseek_v4
tpu
mixture-of-experts
Model card Files
xet
 Community
erfanzar commited on
Commit
b4e8fca
·
verified ·
1 Parent(s): 3f368f1

Add checkpoint shards (898/1285 dirs)

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 +8 -0
  2. model/model/layers/35/mlp/experts/up_proj/weight/.zarray +1 -0
  3. model/model/layers/35/mlp/experts/up_proj/weight/0.0.0 +3 -0
  4. model/model/layers/35/mlp/experts/up_proj/weight/1.0.0 +3 -0
  5. model/model/layers/35/mlp/experts/up_proj/weight/2.0.0 +3 -0
  6. model/model/layers/35/mlp/experts/up_proj/weight/3.0.0 +3 -0
  7. model/model/layers/35/mlp/experts/up_proj/weight/4.0.0 +3 -0
  8. model/model/layers/35/mlp/experts/up_proj/weight/5.0.0 +3 -0
  9. model/model/layers/35/mlp/experts/up_proj/weight/6.0.0 +3 -0
  10. model/model/layers/35/mlp/experts/up_proj/weight/7.0.0 +3 -0
  11. model/model/layers/35/mlp/gate/e_score_correction_bias/.zarray +1 -0
  12. model/model/layers/35/mlp/gate/e_score_correction_bias/0 +0 -0
  13. model/model/layers/35/mlp/gate/weight/.zarray +1 -0
  14. model/model/layers/35/mlp/gate/weight/0.0 +3 -0
  15. model/model/layers/35/mlp/shared_experts/down_proj/weight/.zarray +1 -0
  16. model/model/layers/35/mlp/shared_experts/down_proj/weight/0.0 +3 -0
  17. model/model/layers/35/mlp/shared_experts/gate_up_proj/weight/.zarray +1 -0
  18. model/model/layers/35/mlp/shared_experts/gate_up_proj/weight/0.0 +3 -0
  19. model/model/layers/35/post_attention_layernorm/weight/.zarray +1 -0
  20. model/model/layers/35/post_attention_layernorm/weight/0 +0 -0
  21. model/model/layers/35/self_attn/compressor/gate_proj/weight/.zarray +1 -0
  22. model/model/layers/35/self_attn/compressor/gate_proj/weight/0.0 +3 -0
  23. model/model/layers/35/self_attn/compressor/kv_norm/weight/.zarray +1 -0
  24. model/model/layers/35/self_attn/compressor/kv_norm/weight/0 +0 -0
  25. model/model/layers/35/self_attn/compressor/kv_proj/weight/.zarray +1 -0
  26. model/model/layers/35/self_attn/compressor/kv_proj/weight/0.0 +3 -0
  27. model/model/layers/35/self_attn/compressor/position_bias/.zarray +1 -0
  28. model/model/layers/35/self_attn/compressor/position_bias/0.0 +3 -0
  29. model/model/layers/35/self_attn/kv_norm/weight/.zarray +1 -0
  30. model/model/layers/35/self_attn/kv_norm/weight/0 +0 -0
  31. model/model/layers/35/self_attn/kv_proj/weight/.zarray +1 -0
  32. model/model/layers/35/self_attn/kv_proj/weight/0.0 +3 -0
  33. model/model/layers/35/self_attn/o_a_proj/weight/.zarray +1 -0
  34. model/model/layers/35/self_attn/o_a_proj/weight/0.0 +3 -0
  35. model/model/layers/35/self_attn/o_b_proj/weight/.zarray +1 -0
  36. model/model/layers/35/self_attn/o_b_proj/weight/0.0 +3 -0
  37. model/model/layers/35/self_attn/q_a_norm/weight/.zarray +1 -0
  38. model/model/layers/35/self_attn/q_a_norm/weight/0 +0 -0
  39. model/model/layers/35/self_attn/q_a_proj/weight/.zarray +1 -0
  40. model/model/layers/35/self_attn/q_a_proj/weight/0.0 +3 -0
  41. model/model/layers/35/self_attn/q_b_proj/weight/.zarray +1 -0
  42. model/model/layers/35/self_attn/q_b_proj/weight/0.0 +3 -0
  43. model/model/layers/35/self_attn/sinks/.zarray +1 -0
  44. model/model/layers/35/self_attn/sinks/0 +0 -0
  45. model/model/layers/36/attn_hc/base/.zarray +1 -0
  46. model/model/layers/36/attn_hc/base/0 +0 -0
  47. model/model/layers/36/attn_hc/fn/.zarray +1 -0
  48. model/model/layers/36/attn_hc/fn/0.0 +3 -0
  49. model/model/layers/36/attn_hc/scale/.zarray +1 -0
  50. model/model/layers/36/attn_hc/scale/0 +0 -0
.gitattributes CHANGED
@@ -18475,3 +18475,11 @@ model/model/layers/35/mlp/experts/gate_proj/weight/4.0.0 filter=lfs diff=lfs mer
18475
  model/model/layers/35/mlp/experts/gate_proj/weight/5.0.0 filter=lfs diff=lfs merge=lfs -text
18476
  model/model/layers/35/mlp/experts/gate_proj/weight/6.0.0 filter=lfs diff=lfs merge=lfs -text
18477
  model/model/layers/35/mlp/experts/gate_proj/weight/7.0.0 filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
18475
  model/model/layers/35/mlp/experts/gate_proj/weight/5.0.0 filter=lfs diff=lfs merge=lfs -text
18476
  model/model/layers/35/mlp/experts/gate_proj/weight/6.0.0 filter=lfs diff=lfs merge=lfs -text
18477
  model/model/layers/35/mlp/experts/gate_proj/weight/7.0.0 filter=lfs diff=lfs merge=lfs -text
18478
+ model/model/layers/35/mlp/experts/up_proj/weight/0.0.0 filter=lfs diff=lfs merge=lfs -text
18479
+ model/model/layers/35/mlp/experts/up_proj/weight/1.0.0 filter=lfs diff=lfs merge=lfs -text
18480
+ model/model/layers/35/mlp/experts/up_proj/weight/2.0.0 filter=lfs diff=lfs merge=lfs -text
18481
+ model/model/layers/35/mlp/experts/up_proj/weight/3.0.0 filter=lfs diff=lfs merge=lfs -text
18482
+ model/model/layers/35/mlp/experts/up_proj/weight/4.0.0 filter=lfs diff=lfs merge=lfs -text
18483
+ model/model/layers/35/mlp/experts/up_proj/weight/5.0.0 filter=lfs diff=lfs merge=lfs -text
18484
+ model/model/layers/35/mlp/experts/up_proj/weight/6.0.0 filter=lfs diff=lfs merge=lfs -text
18485
+ model/model/layers/35/mlp/experts/up_proj/weight/7.0.0 filter=lfs diff=lfs merge=lfs -text
model/model/layers/35/mlp/experts/up_proj/weight/.zarray ADDED
@@ -0,0 +1 @@
 
 
1
+ {"chunks":[32,4096,2048],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[256,4096,2048],"zarr_format":2}
model/model/layers/35/mlp/experts/up_proj/weight/0.0.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4bc88d9120c55afca32e680fa4fbf906c79202b1cbd467694c7070a4f27d53b0
3
+ size 175015722
model/model/layers/35/mlp/experts/up_proj/weight/1.0.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf42c1a20be133e14e10a51811215b526a2519cc57173057b9d5bc375fcdf026
3
+ size 174996196
model/model/layers/35/mlp/experts/up_proj/weight/2.0.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3cc81a3baacd2f596f84712a7983b4f35bb0e2332486810aed632ec16dfb9f73
3
+ size 175001316
model/model/layers/35/mlp/experts/up_proj/weight/3.0.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e3916bbd0ffa736811b4f360a218953f4bb34bbc2bbc64beef35d709449e2e20
3
+ size 175176528
model/model/layers/35/mlp/experts/up_proj/weight/4.0.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d999fbc04c5b5ba3cfc4edc7ee7a1b81b702d75f7cb60ce4c9716ea1fe1fcb76
3
+ size 174974520
model/model/layers/35/mlp/experts/up_proj/weight/5.0.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf4b7e8bc044e14550286702f355ef88f289df9db7f2111dd402289b21731acd
3
+ size 175085909
model/model/layers/35/mlp/experts/up_proj/weight/6.0.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7dd498f99c0482b94a3c8cd6e4953f5e6b6b45bf03c95fa1cef57c9503dcb5b2
3
+ size 175090050
model/model/layers/35/mlp/experts/up_proj/weight/7.0.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5b21f6c462fa3fe33f4ef860d26dd97e4900730e36f9f62280b47d31ff68d1de
3
+ size 175062035
model/model/layers/35/mlp/gate/e_score_correction_bias/.zarray ADDED
@@ -0,0 +1 @@
 
 
1
+ {"chunks":[256],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[256],"zarr_format":2}
model/model/layers/35/mlp/gate/e_score_correction_bias/0 ADDED
Binary file (136 Bytes). View file
 
model/model/layers/35/mlp/gate/weight/.zarray ADDED
@@ -0,0 +1 @@
 
 
1
+ {"chunks":[4096,256],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[4096,256],"zarr_format":2}
model/model/layers/35/mlp/gate/weight/0.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:814ae09fa63f2aaf22923bb442682f4fa2421668f487c5d166715d21c033a2c6
3
+ size 1634835
model/model/layers/35/mlp/shared_experts/down_proj/weight/.zarray ADDED
@@ -0,0 +1 @@
 
 
1
+ {"chunks":[2048,4096],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[2048,4096],"zarr_format":2}
model/model/layers/35/mlp/shared_experts/down_proj/weight/0.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8154822bde7041b4feaa4079ab46393c2384df16066c480b33d06c1430d025ab
3
+ size 9160627
model/model/layers/35/mlp/shared_experts/gate_up_proj/weight/.zarray ADDED
@@ -0,0 +1 @@
 
 
1
+ {"chunks":[4096,4096],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[4096,4096],"zarr_format":2}
model/model/layers/35/mlp/shared_experts/gate_up_proj/weight/0.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e347a1cc514cffcba0057465a51f39c6e973bc7d4341f2be37992a1f9ecc363
3
+ size 18451291
model/model/layers/35/post_attention_layernorm/weight/.zarray ADDED
@@ -0,0 +1 @@
 
 
1
+ {"chunks":[4096],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[4096],"zarr_format":2}
model/model/layers/35/post_attention_layernorm/weight/0 ADDED
Binary file (2.1 kB). View file
 
model/model/layers/35/self_attn/compressor/gate_proj/weight/.zarray ADDED
@@ -0,0 +1 @@
 
 
1
+ {"chunks":[4096,512],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[4096,512],"zarr_format":2}
model/model/layers/35/self_attn/compressor/gate_proj/weight/0.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ce66ce9722808e205c717c1fa850ab07bcfe9647dbdde2ef78aa2b38d4a3b070
3
+ size 3278458
model/model/layers/35/self_attn/compressor/kv_norm/weight/.zarray ADDED
@@ -0,0 +1 @@
 
 
1
+ {"chunks":[512],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[512],"zarr_format":2}
model/model/layers/35/self_attn/compressor/kv_norm/weight/0 ADDED
Binary file (631 Bytes). View file
 
model/model/layers/35/self_attn/compressor/kv_proj/weight/.zarray ADDED
@@ -0,0 +1 @@
 
 
1
+ {"chunks":[4096,512],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[4096,512],"zarr_format":2}
model/model/layers/35/self_attn/compressor/kv_proj/weight/0.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2643f13afc6c01876b1441d5bc72a95a76279acd654b44a55256563719085ba7
3
+ size 3284144
model/model/layers/35/self_attn/compressor/position_bias/.zarray ADDED
@@ -0,0 +1 @@
 
 
1
+ {"chunks":[128,512],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[128,512],"zarr_format":2}
model/model/layers/35/self_attn/compressor/position_bias/0.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fb7ead66798fd43fb4ebf4da7e58f7293cf5ca8130fc57396dbcb5b2be879102
3
+ size 102388
model/model/layers/35/self_attn/kv_norm/weight/.zarray ADDED
@@ -0,0 +1 @@
 
 
1
+ {"chunks":[512],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[512],"zarr_format":2}
model/model/layers/35/self_attn/kv_norm/weight/0 ADDED
Binary file (494 Bytes). View file
 
model/model/layers/35/self_attn/kv_proj/weight/.zarray ADDED
@@ -0,0 +1 @@
 
 
1
+ {"chunks":[4096,512],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[4096,512],"zarr_format":2}
model/model/layers/35/self_attn/kv_proj/weight/0.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:071951b1223d9c50b193dcde40b20b44bc1f1e51f111306b381e52cd3a041eb3
3
+ size 2296061
model/model/layers/35/self_attn/o_a_proj/weight/.zarray ADDED
@@ -0,0 +1 @@
 
 
1
+ {"chunks":[4096,8192],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[4096,8192],"zarr_format":2}
model/model/layers/35/self_attn/o_a_proj/weight/0.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d6950f1adf8940e4926a9541d1006d2222703a8c868805a9f71a90c35e66c369
3
+ size 36728190
model/model/layers/35/self_attn/o_b_proj/weight/.zarray ADDED
@@ -0,0 +1 @@
 
 
1
+ {"chunks":[8192,4096],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[8192,4096],"zarr_format":2}
model/model/layers/35/self_attn/o_b_proj/weight/0.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4113b65659d6d8d5b494241defedb18999cbacc3215fa2c47bd973ece32da94f
3
+ size 36739346
model/model/layers/35/self_attn/q_a_norm/weight/.zarray ADDED
@@ -0,0 +1 @@
 
 
1
+ {"chunks":[1024],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[1024],"zarr_format":2}
model/model/layers/35/self_attn/q_a_norm/weight/0 ADDED
Binary file (1.11 kB). View file
 
model/model/layers/35/self_attn/q_a_proj/weight/.zarray ADDED
@@ -0,0 +1 @@
 
 
1
+ {"chunks":[4096,1024],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[4096,1024],"zarr_format":2}
model/model/layers/35/self_attn/q_a_proj/weight/0.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:86d359b31776f1b56360840929e3a4d2d8b0e43a88f2fedbfaa42e94ec3ad126
3
+ size 4591253
model/model/layers/35/self_attn/q_b_proj/weight/.zarray ADDED
@@ -0,0 +1 @@
 
 
1
+ {"chunks":[1024,32768],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[1024,32768],"zarr_format":2}
model/model/layers/35/self_attn/q_b_proj/weight/0.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fc2bfff442efaa7e0652c9f00ca32b05181e7abc68fa18c4d93287d1c6f66514
3
+ size 36798934
model/model/layers/35/self_attn/sinks/.zarray ADDED
@@ -0,0 +1 @@
 
 
1
+ {"chunks":[64],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[64],"zarr_format":2}
model/model/layers/35/self_attn/sinks/0 ADDED
Binary file (127 Bytes). View file
 
model/model/layers/36/attn_hc/base/.zarray ADDED
@@ -0,0 +1 @@
 
 
1
+ {"chunks":[24],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[24],"zarr_format":2}
model/model/layers/36/attn_hc/base/0 ADDED
Binary file (57 Bytes). View file
 
model/model/layers/36/attn_hc/fn/.zarray ADDED
@@ -0,0 +1 @@
 
 
1
+ {"chunks":[24,16384],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[24,16384],"zarr_format":2}
model/model/layers/36/attn_hc/fn/0.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c8384abf9d81133c48da3b5ddbdf75ebd196792959c6a9fb86dfca52fd8b98e8
3
+ size 621863
model/model/layers/36/attn_hc/scale/.zarray ADDED
@@ -0,0 +1 @@
 
 
1
+ {"chunks":[3],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[3],"zarr_format":2}
model/model/layers/36/attn_hc/scale/0 ADDED
Binary file (15 Bytes). View file