HuggingSara commited on
Commit
a6c61ac
1 Parent(s): 5111a9b

Upload model

Browse files
Files changed (41) hide show
  1. config.json +30 -0
  2. model-00001-of-00039.safetensors +3 -0
  3. model-00002-of-00039.safetensors +3 -0
  4. model-00003-of-00039.safetensors +3 -0
  5. model-00004-of-00039.safetensors +3 -0
  6. model-00005-of-00039.safetensors +3 -0
  7. model-00006-of-00039.safetensors +3 -0
  8. model-00007-of-00039.safetensors +3 -0
  9. model-00008-of-00039.safetensors +3 -0
  10. model-00009-of-00039.safetensors +3 -0
  11. model-00010-of-00039.safetensors +3 -0
  12. model-00011-of-00039.safetensors +3 -0
  13. model-00012-of-00039.safetensors +3 -0
  14. model-00013-of-00039.safetensors +3 -0
  15. model-00014-of-00039.safetensors +3 -0
  16. model-00015-of-00039.safetensors +3 -0
  17. model-00016-of-00039.safetensors +3 -0
  18. model-00017-of-00039.safetensors +3 -0
  19. model-00018-of-00039.safetensors +3 -0
  20. model-00019-of-00039.safetensors +3 -0
  21. model-00020-of-00039.safetensors +3 -0
  22. model-00021-of-00039.safetensors +3 -0
  23. model-00022-of-00039.safetensors +3 -0
  24. model-00023-of-00039.safetensors +3 -0
  25. model-00024-of-00039.safetensors +3 -0
  26. model-00025-of-00039.safetensors +3 -0
  27. model-00026-of-00039.safetensors +3 -0
  28. model-00027-of-00039.safetensors +3 -0
  29. model-00028-of-00039.safetensors +3 -0
  30. model-00029-of-00039.safetensors +3 -0
  31. model-00030-of-00039.safetensors +3 -0
  32. model-00031-of-00039.safetensors +3 -0
  33. model-00032-of-00039.safetensors +3 -0
  34. model-00033-of-00039.safetensors +3 -0
  35. model-00034-of-00039.safetensors +3 -0
  36. model-00035-of-00039.safetensors +3 -0
  37. model-00036-of-00039.safetensors +3 -0
  38. model-00037-of-00039.safetensors +3 -0
  39. model-00038-of-00039.safetensors +3 -0
  40. model-00039-of-00039.safetensors +3 -0
  41. model.safetensors.index.json +1001 -0
config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/home/fahad.khan/sara.pieri/axolotl/qlora-out/BiMediX_en",
3
+ "architectures": [
4
+ "MixtralModel"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 1,
8
+ "eos_token_id": 2,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 4096,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 14336,
13
+ "max_position_embeddings": 32768,
14
+ "model_type": "mixtral",
15
+ "num_attention_heads": 32,
16
+ "num_experts_per_tok": 2,
17
+ "num_hidden_layers": 32,
18
+ "num_key_value_heads": 8,
19
+ "num_local_experts": 8,
20
+ "output_router_logits": true,
21
+ "rms_norm_eps": 1e-05,
22
+ "rope_theta": 1000000.0,
23
+ "router_aux_loss_coef": 0.02,
24
+ "sliding_window": null,
25
+ "tie_word_embeddings": false,
26
+ "torch_dtype": "float32",
27
+ "transformers_version": "4.36.2",
28
+ "use_cache": false,
29
+ "vocab_size": 32000
30
+ }
model-00001-of-00039.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d95494ba91d29314eea19f85620877117fa92114adb448e38aa9b6e9d07b3ed
3
+ size 4920052576
model-00002-of-00039.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:55fc165d77b275e6b9940a9110aee92466bee77fcb3a423eeecef4ea9476e990
3
+ size 4865559752
model-00003-of-00039.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f96aac1b88daa8c1d1adc7eab7800490fbfb8ed7d6d893171c1bd6973dcfb90d
3
+ size 4865559752
model-00004-of-00039.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:704129c16fd993aac76b30ea5be481038ad2c24a91dbf7595c4fa9e840a86b7f
3
+ size 4865559752
model-00005-of-00039.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:564780bcbe6223c942a98ae62d244f194c1d2f5606f0837587cee1c179a5deec
3
+ size 4865559752
model-00006-of-00039.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ffea71911d4fc2c6d5674d7be97fa45b9f3eaf358877d248a710980a045191ba
3
+ size 4932504136
model-00007-of-00039.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e17033c737d961743d61198759821671640297d5b6e01f384a7bab4384ab94e
3
+ size 4865559752
model-00008-of-00039.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a987102936812783ef2173aadf1a6eeb7876c001ec9de384efe19f9c391332fe
3
+ size 4865559752
model-00009-of-00039.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c3d1de59d35256a6959cf627ab986ad4cf1ca0be8d30666b0174071d9ec835fe
3
+ size 4865559752
model-00010-of-00039.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:29f36b00098a1f806a1345ad1d15e9789e0ada18e06edd921f18081e1dcd3a80
3
+ size 4865559752
model-00011-of-00039.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e27933ae6b8e8322898e1d95e9e9612be0fb810ae290135ae4b36ab1d118da74
3
+ size 4865559752
model-00012-of-00039.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d838b9830bd44250768fc7a2cf0670256421fa6c29450eaf5c088f3b069865d5
3
+ size 4999646096
model-00013-of-00039.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9fd55684266784f8652e237e9b0ccc4fd60b344725de0d6f6f47514754f04b27
3
+ size 4798417824
model-00014-of-00039.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:09fea597cac2ce6a63d990b705b5b904cdeb0c41f93911ffbd74a329c8f70e42
3
+ size 4865559776
model-00015-of-00039.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:13ef86d39add83dbcdf300c0448e9a2ee8246a1ad3bdd9e8e3bb341638921371
3
+ size 4865559784
model-00016-of-00039.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:71eded5f7a349ab4a66f83b2a9ab77f6c6767d360c2b75f722b0237dd0fc7a4d
3
+ size 4865559784
model-00017-of-00039.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f5eef6d29f8061563402e527fde8359e3fad74e50d8ee78de2ff5f9796c6961f
3
+ size 4865559784
model-00018-of-00039.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:15f5f1225e4841611d6f5ceea5da1a5b69484df9d1bfa804f91c05042cc8cddd
3
+ size 4865559784
model-00019-of-00039.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1eb9e5c93feface5461f7194ccd66cc63ad4cf7ca50dbd5b63681b00bd88ad5c
3
+ size 4932504152
model-00020-of-00039.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e311542c2ebb157b39e73758d7b644dbe04b8926acb09eb29d2f013e97e5ab0f
3
+ size 4865559776
model-00021-of-00039.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f9ceeea5131dacee77322d06293c56c814224387ca5b6b560dc071d1dab459b
3
+ size 4865559784
model-00022-of-00039.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:150b2cf8bcc027d3e9f6a946264a2d13efe64bd3b24739f9b4e3f1e4a6ff8345
3
+ size 4865559784
model-00023-of-00039.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4147d76cc65fd750e5b775b60cd8b60cfeb3d41ae44b0bf9a6dc1297eb721da0
3
+ size 4865559784
model-00024-of-00039.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5fe1ae625cf30c07c3eed8cdd19e3edb3beb7a10999f5d9c6d734ed7a682da47
3
+ size 4865559784
model-00025-of-00039.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:207cd91c1650e70306bfdfdb58a3eb7b636d7d61b74ab3038686ff74ea3a4bbb
3
+ size 4932504152
model-00026-of-00039.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9b1ca9aaf3c88a2e6f0b0a11b31fd0aa761f865fb1e1c50de3232113f997c785
3
+ size 4865559776
model-00027-of-00039.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e568ca9d171e8e302679e34176a343bfe27eb6f8bdfb8d69cc09853864d902dc
3
+ size 4865559784
model-00028-of-00039.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8df7de6838c572bdddf3e70d2a0c9266269b9c2020eb44797aac9f319fae27bd
3
+ size 4865559784
model-00029-of-00039.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de4c5eaefdd7156782ad45dad517035cd814d4daeb9afa3674e23946cf3e0df5
3
+ size 4865559784
model-00030-of-00039.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:70510aec73235a412d7c42cd4c19f1f5ada150b0cf9953a2465c7294e9eaf73a
3
+ size 4865559784
model-00031-of-00039.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:09b97ae7038037667956f1a359fe6eaf74ddbe2ec50ab20e70ab0519aebff7fe
3
+ size 4932504152
model-00032-of-00039.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d0b08da8eaec5ed6640c2e05fce9d5f4e76a004c5e84002ca269f94e9601e79
3
+ size 4865559776
model-00033-of-00039.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e328241a5126a29ce27f4e7ad20f2d09854633452fc72d21df963a8ff5bca25e
3
+ size 4865559784
model-00034-of-00039.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b291edfe4d48e6cef331492539aab839ecdedb2419a255d8a10c977ff42493f3
3
+ size 4865559784
model-00035-of-00039.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e07563ccdf4c8e1f80fa557efb14a7d9cbbe8b7f1e53fbdbadcc7438fbd9602b
3
+ size 4865559784
model-00036-of-00039.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:baa59705218927aa284e5e9c11d58951c6729c916b87a7bc7c74e0919710dbc6
3
+ size 4865559784
model-00037-of-00039.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8726275c4b3436bde44241925971f8c3f52cd128fafb3cc305ac061f37440329
3
+ size 4999646120
model-00038-of-00039.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eadc145e5299405da6da1bd412907a99f4ede3bd06d9d8dcdf830bdd51d7483b
3
+ size 4798417824
model-00039-of-00039.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f1a8f6120c9a07d06db7cc85657dc42c07eb3465b2668c73e54054fc1c5c7f0
3
+ size 939574072
model.safetensors.index.json ADDED
@@ -0,0 +1,1001 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 186286882816
4
+ },
5
+ "weight_map": {
6
+ "embed_tokens.weight": "model-00001-of-00039.safetensors",
7
+ "layers.0.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00039.safetensors",
8
+ "layers.0.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00039.safetensors",
9
+ "layers.0.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00039.safetensors",
10
+ "layers.0.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00039.safetensors",
11
+ "layers.0.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00039.safetensors",
12
+ "layers.0.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00039.safetensors",
13
+ "layers.0.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00039.safetensors",
14
+ "layers.0.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00039.safetensors",
15
+ "layers.0.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00039.safetensors",
16
+ "layers.0.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00039.safetensors",
17
+ "layers.0.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00039.safetensors",
18
+ "layers.0.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00039.safetensors",
19
+ "layers.0.block_sparse_moe.experts.4.w1.weight": "model-00001-of-00039.safetensors",
20
+ "layers.0.block_sparse_moe.experts.4.w2.weight": "model-00001-of-00039.safetensors",
21
+ "layers.0.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00039.safetensors",
22
+ "layers.0.block_sparse_moe.experts.5.w1.weight": "model-00001-of-00039.safetensors",
23
+ "layers.0.block_sparse_moe.experts.5.w2.weight": "model-00001-of-00039.safetensors",
24
+ "layers.0.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00039.safetensors",
25
+ "layers.0.block_sparse_moe.experts.6.w1.weight": "model-00002-of-00039.safetensors",
26
+ "layers.0.block_sparse_moe.experts.6.w2.weight": "model-00002-of-00039.safetensors",
27
+ "layers.0.block_sparse_moe.experts.6.w3.weight": "model-00002-of-00039.safetensors",
28
+ "layers.0.block_sparse_moe.experts.7.w1.weight": "model-00002-of-00039.safetensors",
29
+ "layers.0.block_sparse_moe.experts.7.w2.weight": "model-00002-of-00039.safetensors",
30
+ "layers.0.block_sparse_moe.experts.7.w3.weight": "model-00002-of-00039.safetensors",
31
+ "layers.0.block_sparse_moe.gate.weight": "model-00001-of-00039.safetensors",
32
+ "layers.0.input_layernorm.weight": "model-00002-of-00039.safetensors",
33
+ "layers.0.post_attention_layernorm.weight": "model-00002-of-00039.safetensors",
34
+ "layers.0.self_attn.k_proj.weight": "model-00001-of-00039.safetensors",
35
+ "layers.0.self_attn.o_proj.weight": "model-00001-of-00039.safetensors",
36
+ "layers.0.self_attn.q_proj.weight": "model-00001-of-00039.safetensors",
37
+ "layers.0.self_attn.v_proj.weight": "model-00001-of-00039.safetensors",
38
+ "layers.1.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00039.safetensors",
39
+ "layers.1.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00039.safetensors",
40
+ "layers.1.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00039.safetensors",
41
+ "layers.1.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00039.safetensors",
42
+ "layers.1.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00039.safetensors",
43
+ "layers.1.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00039.safetensors",
44
+ "layers.1.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00039.safetensors",
45
+ "layers.1.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00039.safetensors",
46
+ "layers.1.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00039.safetensors",
47
+ "layers.1.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00039.safetensors",
48
+ "layers.1.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00039.safetensors",
49
+ "layers.1.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00039.safetensors",
50
+ "layers.1.block_sparse_moe.experts.4.w1.weight": "model-00002-of-00039.safetensors",
51
+ "layers.1.block_sparse_moe.experts.4.w2.weight": "model-00002-of-00039.safetensors",
52
+ "layers.1.block_sparse_moe.experts.4.w3.weight": "model-00003-of-00039.safetensors",
53
+ "layers.1.block_sparse_moe.experts.5.w1.weight": "model-00003-of-00039.safetensors",
54
+ "layers.1.block_sparse_moe.experts.5.w2.weight": "model-00003-of-00039.safetensors",
55
+ "layers.1.block_sparse_moe.experts.5.w3.weight": "model-00003-of-00039.safetensors",
56
+ "layers.1.block_sparse_moe.experts.6.w1.weight": "model-00003-of-00039.safetensors",
57
+ "layers.1.block_sparse_moe.experts.6.w2.weight": "model-00003-of-00039.safetensors",
58
+ "layers.1.block_sparse_moe.experts.6.w3.weight": "model-00003-of-00039.safetensors",
59
+ "layers.1.block_sparse_moe.experts.7.w1.weight": "model-00003-of-00039.safetensors",
60
+ "layers.1.block_sparse_moe.experts.7.w2.weight": "model-00003-of-00039.safetensors",
61
+ "layers.1.block_sparse_moe.experts.7.w3.weight": "model-00003-of-00039.safetensors",
62
+ "layers.1.block_sparse_moe.gate.weight": "model-00002-of-00039.safetensors",
63
+ "layers.1.input_layernorm.weight": "model-00003-of-00039.safetensors",
64
+ "layers.1.post_attention_layernorm.weight": "model-00003-of-00039.safetensors",
65
+ "layers.1.self_attn.k_proj.weight": "model-00002-of-00039.safetensors",
66
+ "layers.1.self_attn.o_proj.weight": "model-00002-of-00039.safetensors",
67
+ "layers.1.self_attn.q_proj.weight": "model-00002-of-00039.safetensors",
68
+ "layers.1.self_attn.v_proj.weight": "model-00002-of-00039.safetensors",
69
+ "layers.10.block_sparse_moe.experts.0.w1.weight": "model-00013-of-00039.safetensors",
70
+ "layers.10.block_sparse_moe.experts.0.w2.weight": "model-00013-of-00039.safetensors",
71
+ "layers.10.block_sparse_moe.experts.0.w3.weight": "model-00013-of-00039.safetensors",
72
+ "layers.10.block_sparse_moe.experts.1.w1.weight": "model-00013-of-00039.safetensors",
73
+ "layers.10.block_sparse_moe.experts.1.w2.weight": "model-00013-of-00039.safetensors",
74
+ "layers.10.block_sparse_moe.experts.1.w3.weight": "model-00013-of-00039.safetensors",
75
+ "layers.10.block_sparse_moe.experts.2.w1.weight": "model-00013-of-00039.safetensors",
76
+ "layers.10.block_sparse_moe.experts.2.w2.weight": "model-00013-of-00039.safetensors",
77
+ "layers.10.block_sparse_moe.experts.2.w3.weight": "model-00013-of-00039.safetensors",
78
+ "layers.10.block_sparse_moe.experts.3.w1.weight": "model-00013-of-00039.safetensors",
79
+ "layers.10.block_sparse_moe.experts.3.w2.weight": "model-00013-of-00039.safetensors",
80
+ "layers.10.block_sparse_moe.experts.3.w3.weight": "model-00013-of-00039.safetensors",
81
+ "layers.10.block_sparse_moe.experts.4.w1.weight": "model-00013-of-00039.safetensors",
82
+ "layers.10.block_sparse_moe.experts.4.w2.weight": "model-00013-of-00039.safetensors",
83
+ "layers.10.block_sparse_moe.experts.4.w3.weight": "model-00013-of-00039.safetensors",
84
+ "layers.10.block_sparse_moe.experts.5.w1.weight": "model-00013-of-00039.safetensors",
85
+ "layers.10.block_sparse_moe.experts.5.w2.weight": "model-00013-of-00039.safetensors",
86
+ "layers.10.block_sparse_moe.experts.5.w3.weight": "model-00013-of-00039.safetensors",
87
+ "layers.10.block_sparse_moe.experts.6.w1.weight": "model-00013-of-00039.safetensors",
88
+ "layers.10.block_sparse_moe.experts.6.w2.weight": "model-00013-of-00039.safetensors",
89
+ "layers.10.block_sparse_moe.experts.6.w3.weight": "model-00014-of-00039.safetensors",
90
+ "layers.10.block_sparse_moe.experts.7.w1.weight": "model-00014-of-00039.safetensors",
91
+ "layers.10.block_sparse_moe.experts.7.w2.weight": "model-00014-of-00039.safetensors",
92
+ "layers.10.block_sparse_moe.experts.7.w3.weight": "model-00014-of-00039.safetensors",
93
+ "layers.10.block_sparse_moe.gate.weight": "model-00013-of-00039.safetensors",
94
+ "layers.10.input_layernorm.weight": "model-00014-of-00039.safetensors",
95
+ "layers.10.post_attention_layernorm.weight": "model-00014-of-00039.safetensors",
96
+ "layers.10.self_attn.k_proj.weight": "model-00013-of-00039.safetensors",
97
+ "layers.10.self_attn.o_proj.weight": "model-00013-of-00039.safetensors",
98
+ "layers.10.self_attn.q_proj.weight": "model-00012-of-00039.safetensors",
99
+ "layers.10.self_attn.v_proj.weight": "model-00013-of-00039.safetensors",
100
+ "layers.11.block_sparse_moe.experts.0.w1.weight": "model-00014-of-00039.safetensors",
101
+ "layers.11.block_sparse_moe.experts.0.w2.weight": "model-00014-of-00039.safetensors",
102
+ "layers.11.block_sparse_moe.experts.0.w3.weight": "model-00014-of-00039.safetensors",
103
+ "layers.11.block_sparse_moe.experts.1.w1.weight": "model-00014-of-00039.safetensors",
104
+ "layers.11.block_sparse_moe.experts.1.w2.weight": "model-00014-of-00039.safetensors",
105
+ "layers.11.block_sparse_moe.experts.1.w3.weight": "model-00014-of-00039.safetensors",
106
+ "layers.11.block_sparse_moe.experts.2.w1.weight": "model-00014-of-00039.safetensors",
107
+ "layers.11.block_sparse_moe.experts.2.w2.weight": "model-00014-of-00039.safetensors",
108
+ "layers.11.block_sparse_moe.experts.2.w3.weight": "model-00014-of-00039.safetensors",
109
+ "layers.11.block_sparse_moe.experts.3.w1.weight": "model-00014-of-00039.safetensors",
110
+ "layers.11.block_sparse_moe.experts.3.w2.weight": "model-00014-of-00039.safetensors",
111
+ "layers.11.block_sparse_moe.experts.3.w3.weight": "model-00014-of-00039.safetensors",
112
+ "layers.11.block_sparse_moe.experts.4.w1.weight": "model-00014-of-00039.safetensors",
113
+ "layers.11.block_sparse_moe.experts.4.w2.weight": "model-00014-of-00039.safetensors",
114
+ "layers.11.block_sparse_moe.experts.4.w3.weight": "model-00014-of-00039.safetensors",
115
+ "layers.11.block_sparse_moe.experts.5.w1.weight": "model-00014-of-00039.safetensors",
116
+ "layers.11.block_sparse_moe.experts.5.w2.weight": "model-00015-of-00039.safetensors",
117
+ "layers.11.block_sparse_moe.experts.5.w3.weight": "model-00015-of-00039.safetensors",
118
+ "layers.11.block_sparse_moe.experts.6.w1.weight": "model-00015-of-00039.safetensors",
119
+ "layers.11.block_sparse_moe.experts.6.w2.weight": "model-00015-of-00039.safetensors",
120
+ "layers.11.block_sparse_moe.experts.6.w3.weight": "model-00015-of-00039.safetensors",
121
+ "layers.11.block_sparse_moe.experts.7.w1.weight": "model-00015-of-00039.safetensors",
122
+ "layers.11.block_sparse_moe.experts.7.w2.weight": "model-00015-of-00039.safetensors",
123
+ "layers.11.block_sparse_moe.experts.7.w3.weight": "model-00015-of-00039.safetensors",
124
+ "layers.11.block_sparse_moe.gate.weight": "model-00014-of-00039.safetensors",
125
+ "layers.11.input_layernorm.weight": "model-00015-of-00039.safetensors",
126
+ "layers.11.post_attention_layernorm.weight": "model-00015-of-00039.safetensors",
127
+ "layers.11.self_attn.k_proj.weight": "model-00014-of-00039.safetensors",
128
+ "layers.11.self_attn.o_proj.weight": "model-00014-of-00039.safetensors",
129
+ "layers.11.self_attn.q_proj.weight": "model-00014-of-00039.safetensors",
130
+ "layers.11.self_attn.v_proj.weight": "model-00014-of-00039.safetensors",
131
+ "layers.12.block_sparse_moe.experts.0.w1.weight": "model-00015-of-00039.safetensors",
132
+ "layers.12.block_sparse_moe.experts.0.w2.weight": "model-00015-of-00039.safetensors",
133
+ "layers.12.block_sparse_moe.experts.0.w3.weight": "model-00015-of-00039.safetensors",
134
+ "layers.12.block_sparse_moe.experts.1.w1.weight": "model-00015-of-00039.safetensors",
135
+ "layers.12.block_sparse_moe.experts.1.w2.weight": "model-00015-of-00039.safetensors",
136
+ "layers.12.block_sparse_moe.experts.1.w3.weight": "model-00015-of-00039.safetensors",
137
+ "layers.12.block_sparse_moe.experts.2.w1.weight": "model-00015-of-00039.safetensors",
138
+ "layers.12.block_sparse_moe.experts.2.w2.weight": "model-00015-of-00039.safetensors",
139
+ "layers.12.block_sparse_moe.experts.2.w3.weight": "model-00015-of-00039.safetensors",
140
+ "layers.12.block_sparse_moe.experts.3.w1.weight": "model-00015-of-00039.safetensors",
141
+ "layers.12.block_sparse_moe.experts.3.w2.weight": "model-00015-of-00039.safetensors",
142
+ "layers.12.block_sparse_moe.experts.3.w3.weight": "model-00015-of-00039.safetensors",
143
+ "layers.12.block_sparse_moe.experts.4.w1.weight": "model-00016-of-00039.safetensors",
144
+ "layers.12.block_sparse_moe.experts.4.w2.weight": "model-00016-of-00039.safetensors",
145
+ "layers.12.block_sparse_moe.experts.4.w3.weight": "model-00016-of-00039.safetensors",
146
+ "layers.12.block_sparse_moe.experts.5.w1.weight": "model-00016-of-00039.safetensors",
147
+ "layers.12.block_sparse_moe.experts.5.w2.weight": "model-00016-of-00039.safetensors",
148
+ "layers.12.block_sparse_moe.experts.5.w3.weight": "model-00016-of-00039.safetensors",
149
+ "layers.12.block_sparse_moe.experts.6.w1.weight": "model-00016-of-00039.safetensors",
150
+ "layers.12.block_sparse_moe.experts.6.w2.weight": "model-00016-of-00039.safetensors",
151
+ "layers.12.block_sparse_moe.experts.6.w3.weight": "model-00016-of-00039.safetensors",
152
+ "layers.12.block_sparse_moe.experts.7.w1.weight": "model-00016-of-00039.safetensors",
153
+ "layers.12.block_sparse_moe.experts.7.w2.weight": "model-00016-of-00039.safetensors",
154
+ "layers.12.block_sparse_moe.experts.7.w3.weight": "model-00016-of-00039.safetensors",
155
+ "layers.12.block_sparse_moe.gate.weight": "model-00015-of-00039.safetensors",
156
+ "layers.12.input_layernorm.weight": "model-00016-of-00039.safetensors",
157
+ "layers.12.post_attention_layernorm.weight": "model-00016-of-00039.safetensors",
158
+ "layers.12.self_attn.k_proj.weight": "model-00015-of-00039.safetensors",
159
+ "layers.12.self_attn.o_proj.weight": "model-00015-of-00039.safetensors",
160
+ "layers.12.self_attn.q_proj.weight": "model-00015-of-00039.safetensors",
161
+ "layers.12.self_attn.v_proj.weight": "model-00015-of-00039.safetensors",
162
+ "layers.13.block_sparse_moe.experts.0.w1.weight": "model-00016-of-00039.safetensors",
163
+ "layers.13.block_sparse_moe.experts.0.w2.weight": "model-00016-of-00039.safetensors",
164
+ "layers.13.block_sparse_moe.experts.0.w3.weight": "model-00016-of-00039.safetensors",
165
+ "layers.13.block_sparse_moe.experts.1.w1.weight": "model-00016-of-00039.safetensors",
166
+ "layers.13.block_sparse_moe.experts.1.w2.weight": "model-00016-of-00039.safetensors",
167
+ "layers.13.block_sparse_moe.experts.1.w3.weight": "model-00016-of-00039.safetensors",
168
+ "layers.13.block_sparse_moe.experts.2.w1.weight": "model-00016-of-00039.safetensors",
169
+ "layers.13.block_sparse_moe.experts.2.w2.weight": "model-00016-of-00039.safetensors",
170
+ "layers.13.block_sparse_moe.experts.2.w3.weight": "model-00017-of-00039.safetensors",
171
+ "layers.13.block_sparse_moe.experts.3.w1.weight": "model-00017-of-00039.safetensors",
172
+ "layers.13.block_sparse_moe.experts.3.w2.weight": "model-00017-of-00039.safetensors",
173
+ "layers.13.block_sparse_moe.experts.3.w3.weight": "model-00017-of-00039.safetensors",
174
+ "layers.13.block_sparse_moe.experts.4.w1.weight": "model-00017-of-00039.safetensors",
175
+ "layers.13.block_sparse_moe.experts.4.w2.weight": "model-00017-of-00039.safetensors",
176
+ "layers.13.block_sparse_moe.experts.4.w3.weight": "model-00017-of-00039.safetensors",
177
+ "layers.13.block_sparse_moe.experts.5.w1.weight": "model-00017-of-00039.safetensors",
178
+ "layers.13.block_sparse_moe.experts.5.w2.weight": "model-00017-of-00039.safetensors",
179
+ "layers.13.block_sparse_moe.experts.5.w3.weight": "model-00017-of-00039.safetensors",
180
+ "layers.13.block_sparse_moe.experts.6.w1.weight": "model-00017-of-00039.safetensors",
181
+ "layers.13.block_sparse_moe.experts.6.w2.weight": "model-00017-of-00039.safetensors",
182
+ "layers.13.block_sparse_moe.experts.6.w3.weight": "model-00017-of-00039.safetensors",
183
+ "layers.13.block_sparse_moe.experts.7.w1.weight": "model-00017-of-00039.safetensors",
184
+ "layers.13.block_sparse_moe.experts.7.w2.weight": "model-00017-of-00039.safetensors",
185
+ "layers.13.block_sparse_moe.experts.7.w3.weight": "model-00017-of-00039.safetensors",
186
+ "layers.13.block_sparse_moe.gate.weight": "model-00016-of-00039.safetensors",
187
+ "layers.13.input_layernorm.weight": "model-00017-of-00039.safetensors",
188
+ "layers.13.post_attention_layernorm.weight": "model-00017-of-00039.safetensors",
189
+ "layers.13.self_attn.k_proj.weight": "model-00016-of-00039.safetensors",
190
+ "layers.13.self_attn.o_proj.weight": "model-00016-of-00039.safetensors",
191
+ "layers.13.self_attn.q_proj.weight": "model-00016-of-00039.safetensors",
192
+ "layers.13.self_attn.v_proj.weight": "model-00016-of-00039.safetensors",
193
+ "layers.14.block_sparse_moe.experts.0.w1.weight": "model-00017-of-00039.safetensors",
194
+ "layers.14.block_sparse_moe.experts.0.w2.weight": "model-00017-of-00039.safetensors",
195
+ "layers.14.block_sparse_moe.experts.0.w3.weight": "model-00017-of-00039.safetensors",
196
+ "layers.14.block_sparse_moe.experts.1.w1.weight": "model-00017-of-00039.safetensors",
197
+ "layers.14.block_sparse_moe.experts.1.w2.weight": "model-00018-of-00039.safetensors",
198
+ "layers.14.block_sparse_moe.experts.1.w3.weight": "model-00018-of-00039.safetensors",
199
+ "layers.14.block_sparse_moe.experts.2.w1.weight": "model-00018-of-00039.safetensors",
200
+ "layers.14.block_sparse_moe.experts.2.w2.weight": "model-00018-of-00039.safetensors",
201
+ "layers.14.block_sparse_moe.experts.2.w3.weight": "model-00018-of-00039.safetensors",
202
+ "layers.14.block_sparse_moe.experts.3.w1.weight": "model-00018-of-00039.safetensors",
203
+ "layers.14.block_sparse_moe.experts.3.w2.weight": "model-00018-of-00039.safetensors",
204
+ "layers.14.block_sparse_moe.experts.3.w3.weight": "model-00018-of-00039.safetensors",
205
+ "layers.14.block_sparse_moe.experts.4.w1.weight": "model-00018-of-00039.safetensors",
206
+ "layers.14.block_sparse_moe.experts.4.w2.weight": "model-00018-of-00039.safetensors",
207
+ "layers.14.block_sparse_moe.experts.4.w3.weight": "model-00018-of-00039.safetensors",
208
+ "layers.14.block_sparse_moe.experts.5.w1.weight": "model-00018-of-00039.safetensors",
209
+ "layers.14.block_sparse_moe.experts.5.w2.weight": "model-00018-of-00039.safetensors",
210
+ "layers.14.block_sparse_moe.experts.5.w3.weight": "model-00018-of-00039.safetensors",
211
+ "layers.14.block_sparse_moe.experts.6.w1.weight": "model-00018-of-00039.safetensors",
212
+ "layers.14.block_sparse_moe.experts.6.w2.weight": "model-00018-of-00039.safetensors",
213
+ "layers.14.block_sparse_moe.experts.6.w3.weight": "model-00018-of-00039.safetensors",
214
+ "layers.14.block_sparse_moe.experts.7.w1.weight": "model-00018-of-00039.safetensors",
215
+ "layers.14.block_sparse_moe.experts.7.w2.weight": "model-00018-of-00039.safetensors",
216
+ "layers.14.block_sparse_moe.experts.7.w3.weight": "model-00018-of-00039.safetensors",
217
+ "layers.14.block_sparse_moe.gate.weight": "model-00017-of-00039.safetensors",
218
+ "layers.14.input_layernorm.weight": "model-00018-of-00039.safetensors",
219
+ "layers.14.post_attention_layernorm.weight": "model-00018-of-00039.safetensors",
220
+ "layers.14.self_attn.k_proj.weight": "model-00017-of-00039.safetensors",
221
+ "layers.14.self_attn.o_proj.weight": "model-00017-of-00039.safetensors",
222
+ "layers.14.self_attn.q_proj.weight": "model-00017-of-00039.safetensors",
223
+ "layers.14.self_attn.v_proj.weight": "model-00017-of-00039.safetensors",
224
+ "layers.15.block_sparse_moe.experts.0.w1.weight": "model-00019-of-00039.safetensors",
225
+ "layers.15.block_sparse_moe.experts.0.w2.weight": "model-00019-of-00039.safetensors",
226
+ "layers.15.block_sparse_moe.experts.0.w3.weight": "model-00019-of-00039.safetensors",
227
+ "layers.15.block_sparse_moe.experts.1.w1.weight": "model-00019-of-00039.safetensors",
228
+ "layers.15.block_sparse_moe.experts.1.w2.weight": "model-00019-of-00039.safetensors",
229
+ "layers.15.block_sparse_moe.experts.1.w3.weight": "model-00019-of-00039.safetensors",
230
+ "layers.15.block_sparse_moe.experts.2.w1.weight": "model-00019-of-00039.safetensors",
231
+ "layers.15.block_sparse_moe.experts.2.w2.weight": "model-00019-of-00039.safetensors",
232
+ "layers.15.block_sparse_moe.experts.2.w3.weight": "model-00019-of-00039.safetensors",
233
+ "layers.15.block_sparse_moe.experts.3.w1.weight": "model-00019-of-00039.safetensors",
234
+ "layers.15.block_sparse_moe.experts.3.w2.weight": "model-00019-of-00039.safetensors",
235
+ "layers.15.block_sparse_moe.experts.3.w3.weight": "model-00019-of-00039.safetensors",
236
+ "layers.15.block_sparse_moe.experts.4.w1.weight": "model-00019-of-00039.safetensors",
237
+ "layers.15.block_sparse_moe.experts.4.w2.weight": "model-00019-of-00039.safetensors",
238
+ "layers.15.block_sparse_moe.experts.4.w3.weight": "model-00019-of-00039.safetensors",
239
+ "layers.15.block_sparse_moe.experts.5.w1.weight": "model-00019-of-00039.safetensors",
240
+ "layers.15.block_sparse_moe.experts.5.w2.weight": "model-00019-of-00039.safetensors",
241
+ "layers.15.block_sparse_moe.experts.5.w3.weight": "model-00019-of-00039.safetensors",
242
+ "layers.15.block_sparse_moe.experts.6.w1.weight": "model-00019-of-00039.safetensors",
243
+ "layers.15.block_sparse_moe.experts.6.w2.weight": "model-00019-of-00039.safetensors",
244
+ "layers.15.block_sparse_moe.experts.6.w3.weight": "model-00019-of-00039.safetensors",
245
+ "layers.15.block_sparse_moe.experts.7.w1.weight": "model-00020-of-00039.safetensors",
246
+ "layers.15.block_sparse_moe.experts.7.w2.weight": "model-00020-of-00039.safetensors",
247
+ "layers.15.block_sparse_moe.experts.7.w3.weight": "model-00020-of-00039.safetensors",
248
+ "layers.15.block_sparse_moe.gate.weight": "model-00018-of-00039.safetensors",
249
+ "layers.15.input_layernorm.weight": "model-00020-of-00039.safetensors",
250
+ "layers.15.post_attention_layernorm.weight": "model-00020-of-00039.safetensors",
251
+ "layers.15.self_attn.k_proj.weight": "model-00018-of-00039.safetensors",
252
+ "layers.15.self_attn.o_proj.weight": "model-00018-of-00039.safetensors",
253
+ "layers.15.self_attn.q_proj.weight": "model-00018-of-00039.safetensors",
254
+ "layers.15.self_attn.v_proj.weight": "model-00018-of-00039.safetensors",
255
+ "layers.16.block_sparse_moe.experts.0.w1.weight": "model-00020-of-00039.safetensors",
256
+ "layers.16.block_sparse_moe.experts.0.w2.weight": "model-00020-of-00039.safetensors",
257
+ "layers.16.block_sparse_moe.experts.0.w3.weight": "model-00020-of-00039.safetensors",
258
+ "layers.16.block_sparse_moe.experts.1.w1.weight": "model-00020-of-00039.safetensors",
259
+ "layers.16.block_sparse_moe.experts.1.w2.weight": "model-00020-of-00039.safetensors",
260
+ "layers.16.block_sparse_moe.experts.1.w3.weight": "model-00020-of-00039.safetensors",
261
+ "layers.16.block_sparse_moe.experts.2.w1.weight": "model-00020-of-00039.safetensors",
262
+ "layers.16.block_sparse_moe.experts.2.w2.weight": "model-00020-of-00039.safetensors",
263
+ "layers.16.block_sparse_moe.experts.2.w3.weight": "model-00020-of-00039.safetensors",
264
+ "layers.16.block_sparse_moe.experts.3.w1.weight": "model-00020-of-00039.safetensors",
265
+ "layers.16.block_sparse_moe.experts.3.w2.weight": "model-00020-of-00039.safetensors",
266
+ "layers.16.block_sparse_moe.experts.3.w3.weight": "model-00020-of-00039.safetensors",
267
+ "layers.16.block_sparse_moe.experts.4.w1.weight": "model-00020-of-00039.safetensors",
268
+ "layers.16.block_sparse_moe.experts.4.w2.weight": "model-00020-of-00039.safetensors",
269
+ "layers.16.block_sparse_moe.experts.4.w3.weight": "model-00020-of-00039.safetensors",
270
+ "layers.16.block_sparse_moe.experts.5.w1.weight": "model-00020-of-00039.safetensors",
271
+ "layers.16.block_sparse_moe.experts.5.w2.weight": "model-00020-of-00039.safetensors",
272
+ "layers.16.block_sparse_moe.experts.5.w3.weight": "model-00021-of-00039.safetensors",
273
+ "layers.16.block_sparse_moe.experts.6.w1.weight": "model-00021-of-00039.safetensors",
274
+ "layers.16.block_sparse_moe.experts.6.w2.weight": "model-00021-of-00039.safetensors",
275
+ "layers.16.block_sparse_moe.experts.6.w3.weight": "model-00021-of-00039.safetensors",
276
+ "layers.16.block_sparse_moe.experts.7.w1.weight": "model-00021-of-00039.safetensors",
277
+ "layers.16.block_sparse_moe.experts.7.w2.weight": "model-00021-of-00039.safetensors",
278
+ "layers.16.block_sparse_moe.experts.7.w3.weight": "model-00021-of-00039.safetensors",
279
+ "layers.16.block_sparse_moe.gate.weight": "model-00020-of-00039.safetensors",
280
+ "layers.16.input_layernorm.weight": "model-00021-of-00039.safetensors",
281
+ "layers.16.post_attention_layernorm.weight": "model-00021-of-00039.safetensors",
282
+ "layers.16.self_attn.k_proj.weight": "model-00020-of-00039.safetensors",
283
+ "layers.16.self_attn.o_proj.weight": "model-00020-of-00039.safetensors",
284
+ "layers.16.self_attn.q_proj.weight": "model-00020-of-00039.safetensors",
285
+ "layers.16.self_attn.v_proj.weight": "model-00020-of-00039.safetensors",
286
+ "layers.17.block_sparse_moe.experts.0.w1.weight": "model-00021-of-00039.safetensors",
287
+ "layers.17.block_sparse_moe.experts.0.w2.weight": "model-00021-of-00039.safetensors",
288
+ "layers.17.block_sparse_moe.experts.0.w3.weight": "model-00021-of-00039.safetensors",
289
+ "layers.17.block_sparse_moe.experts.1.w1.weight": "model-00021-of-00039.safetensors",
290
+ "layers.17.block_sparse_moe.experts.1.w2.weight": "model-00021-of-00039.safetensors",
291
+ "layers.17.block_sparse_moe.experts.1.w3.weight": "model-00021-of-00039.safetensors",
292
+ "layers.17.block_sparse_moe.experts.2.w1.weight": "model-00021-of-00039.safetensors",
293
+ "layers.17.block_sparse_moe.experts.2.w2.weight": "model-00021-of-00039.safetensors",
294
+ "layers.17.block_sparse_moe.experts.2.w3.weight": "model-00021-of-00039.safetensors",
295
+ "layers.17.block_sparse_moe.experts.3.w1.weight": "model-00021-of-00039.safetensors",
296
+ "layers.17.block_sparse_moe.experts.3.w2.weight": "model-00021-of-00039.safetensors",
297
+ "layers.17.block_sparse_moe.experts.3.w3.weight": "model-00021-of-00039.safetensors",
298
+ "layers.17.block_sparse_moe.experts.4.w1.weight": "model-00021-of-00039.safetensors",
299
+ "layers.17.block_sparse_moe.experts.4.w2.weight": "model-00022-of-00039.safetensors",
300
+ "layers.17.block_sparse_moe.experts.4.w3.weight": "model-00022-of-00039.safetensors",
301
+ "layers.17.block_sparse_moe.experts.5.w1.weight": "model-00022-of-00039.safetensors",
302
+ "layers.17.block_sparse_moe.experts.5.w2.weight": "model-00022-of-00039.safetensors",
303
+ "layers.17.block_sparse_moe.experts.5.w3.weight": "model-00022-of-00039.safetensors",
304
+ "layers.17.block_sparse_moe.experts.6.w1.weight": "model-00022-of-00039.safetensors",
305
+ "layers.17.block_sparse_moe.experts.6.w2.weight": "model-00022-of-00039.safetensors",
306
+ "layers.17.block_sparse_moe.experts.6.w3.weight": "model-00022-of-00039.safetensors",
307
+ "layers.17.block_sparse_moe.experts.7.w1.weight": "model-00022-of-00039.safetensors",
308
+ "layers.17.block_sparse_moe.experts.7.w2.weight": "model-00022-of-00039.safetensors",
309
+ "layers.17.block_sparse_moe.experts.7.w3.weight": "model-00022-of-00039.safetensors",
310
+ "layers.17.block_sparse_moe.gate.weight": "model-00021-of-00039.safetensors",
311
+ "layers.17.input_layernorm.weight": "model-00022-of-00039.safetensors",
312
+ "layers.17.post_attention_layernorm.weight": "model-00022-of-00039.safetensors",
313
+ "layers.17.self_attn.k_proj.weight": "model-00021-of-00039.safetensors",
314
+ "layers.17.self_attn.o_proj.weight": "model-00021-of-00039.safetensors",
315
+ "layers.17.self_attn.q_proj.weight": "model-00021-of-00039.safetensors",
316
+ "layers.17.self_attn.v_proj.weight": "model-00021-of-00039.safetensors",
317
+ "layers.18.block_sparse_moe.experts.0.w1.weight": "model-00022-of-00039.safetensors",
318
+ "layers.18.block_sparse_moe.experts.0.w2.weight": "model-00022-of-00039.safetensors",
319
+ "layers.18.block_sparse_moe.experts.0.w3.weight": "model-00022-of-00039.safetensors",
320
+ "layers.18.block_sparse_moe.experts.1.w1.weight": "model-00022-of-00039.safetensors",
321
+ "layers.18.block_sparse_moe.experts.1.w2.weight": "model-00022-of-00039.safetensors",
322
+ "layers.18.block_sparse_moe.experts.1.w3.weight": "model-00022-of-00039.safetensors",
323
+ "layers.18.block_sparse_moe.experts.2.w1.weight": "model-00022-of-00039.safetensors",
324
+ "layers.18.block_sparse_moe.experts.2.w2.weight": "model-00022-of-00039.safetensors",
325
+ "layers.18.block_sparse_moe.experts.2.w3.weight": "model-00022-of-00039.safetensors",
326
+ "layers.18.block_sparse_moe.experts.3.w1.weight": "model-00023-of-00039.safetensors",
327
+ "layers.18.block_sparse_moe.experts.3.w2.weight": "model-00023-of-00039.safetensors",
328
+ "layers.18.block_sparse_moe.experts.3.w3.weight": "model-00023-of-00039.safetensors",
329
+ "layers.18.block_sparse_moe.experts.4.w1.weight": "model-00023-of-00039.safetensors",
330
+ "layers.18.block_sparse_moe.experts.4.w2.weight": "model-00023-of-00039.safetensors",
331
+ "layers.18.block_sparse_moe.experts.4.w3.weight": "model-00023-of-00039.safetensors",
332
+ "layers.18.block_sparse_moe.experts.5.w1.weight": "model-00023-of-00039.safetensors",
333
+ "layers.18.block_sparse_moe.experts.5.w2.weight": "model-00023-of-00039.safetensors",
334
+ "layers.18.block_sparse_moe.experts.5.w3.weight": "model-00023-of-00039.safetensors",
335
+ "layers.18.block_sparse_moe.experts.6.w1.weight": "model-00023-of-00039.safetensors",
336
+ "layers.18.block_sparse_moe.experts.6.w2.weight": "model-00023-of-00039.safetensors",
337
+ "layers.18.block_sparse_moe.experts.6.w3.weight": "model-00023-of-00039.safetensors",
338
+ "layers.18.block_sparse_moe.experts.7.w1.weight": "model-00023-of-00039.safetensors",
339
+ "layers.18.block_sparse_moe.experts.7.w2.weight": "model-00023-of-00039.safetensors",
340
+ "layers.18.block_sparse_moe.experts.7.w3.weight": "model-00023-of-00039.safetensors",
341
+ "layers.18.block_sparse_moe.gate.weight": "model-00022-of-00039.safetensors",
342
+ "layers.18.input_layernorm.weight": "model-00023-of-00039.safetensors",
343
+ "layers.18.post_attention_layernorm.weight": "model-00023-of-00039.safetensors",
344
+ "layers.18.self_attn.k_proj.weight": "model-00022-of-00039.safetensors",
345
+ "layers.18.self_attn.o_proj.weight": "model-00022-of-00039.safetensors",
346
+ "layers.18.self_attn.q_proj.weight": "model-00022-of-00039.safetensors",
347
+ "layers.18.self_attn.v_proj.weight": "model-00022-of-00039.safetensors",
348
+ "layers.19.block_sparse_moe.experts.0.w1.weight": "model-00023-of-00039.safetensors",
349
+ "layers.19.block_sparse_moe.experts.0.w2.weight": "model-00023-of-00039.safetensors",
350
+ "layers.19.block_sparse_moe.experts.0.w3.weight": "model-00023-of-00039.safetensors",
351
+ "layers.19.block_sparse_moe.experts.1.w1.weight": "model-00023-of-00039.safetensors",
352
+ "layers.19.block_sparse_moe.experts.1.w2.weight": "model-00023-of-00039.safetensors",
353
+ "layers.19.block_sparse_moe.experts.1.w3.weight": "model-00024-of-00039.safetensors",
354
+ "layers.19.block_sparse_moe.experts.2.w1.weight": "model-00024-of-00039.safetensors",
355
+ "layers.19.block_sparse_moe.experts.2.w2.weight": "model-00024-of-00039.safetensors",
356
+ "layers.19.block_sparse_moe.experts.2.w3.weight": "model-00024-of-00039.safetensors",
357
+ "layers.19.block_sparse_moe.experts.3.w1.weight": "model-00024-of-00039.safetensors",
358
+ "layers.19.block_sparse_moe.experts.3.w2.weight": "model-00024-of-00039.safetensors",
359
+ "layers.19.block_sparse_moe.experts.3.w3.weight": "model-00024-of-00039.safetensors",
360
+ "layers.19.block_sparse_moe.experts.4.w1.weight": "model-00024-of-00039.safetensors",
361
+ "layers.19.block_sparse_moe.experts.4.w2.weight": "model-00024-of-00039.safetensors",
362
+ "layers.19.block_sparse_moe.experts.4.w3.weight": "model-00024-of-00039.safetensors",
363
+ "layers.19.block_sparse_moe.experts.5.w1.weight": "model-00024-of-00039.safetensors",
364
+ "layers.19.block_sparse_moe.experts.5.w2.weight": "model-00024-of-00039.safetensors",
365
+ "layers.19.block_sparse_moe.experts.5.w3.weight": "model-00024-of-00039.safetensors",
366
+ "layers.19.block_sparse_moe.experts.6.w1.weight": "model-00024-of-00039.safetensors",
367
+ "layers.19.block_sparse_moe.experts.6.w2.weight": "model-00024-of-00039.safetensors",
368
+ "layers.19.block_sparse_moe.experts.6.w3.weight": "model-00024-of-00039.safetensors",
369
+ "layers.19.block_sparse_moe.experts.7.w1.weight": "model-00024-of-00039.safetensors",
370
+ "layers.19.block_sparse_moe.experts.7.w2.weight": "model-00024-of-00039.safetensors",
371
+ "layers.19.block_sparse_moe.experts.7.w3.weight": "model-00024-of-00039.safetensors",
372
+ "layers.19.block_sparse_moe.gate.weight": "model-00023-of-00039.safetensors",
373
+ "layers.19.input_layernorm.weight": "model-00024-of-00039.safetensors",
374
+ "layers.19.post_attention_layernorm.weight": "model-00024-of-00039.safetensors",
375
+ "layers.19.self_attn.k_proj.weight": "model-00023-of-00039.safetensors",
376
+ "layers.19.self_attn.o_proj.weight": "model-00023-of-00039.safetensors",
377
+ "layers.19.self_attn.q_proj.weight": "model-00023-of-00039.safetensors",
378
+ "layers.19.self_attn.v_proj.weight": "model-00023-of-00039.safetensors",
379
+ "layers.2.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00039.safetensors",
380
+ "layers.2.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00039.safetensors",
381
+ "layers.2.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00039.safetensors",
382
+ "layers.2.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00039.safetensors",
383
+ "layers.2.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00039.safetensors",
384
+ "layers.2.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00039.safetensors",
385
+ "layers.2.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00039.safetensors",
386
+ "layers.2.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00039.safetensors",
387
+ "layers.2.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00039.safetensors",
388
+ "layers.2.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00039.safetensors",
389
+ "layers.2.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00039.safetensors",
390
+ "layers.2.block_sparse_moe.experts.3.w3.weight": "model-00004-of-00039.safetensors",
391
+ "layers.2.block_sparse_moe.experts.4.w1.weight": "model-00004-of-00039.safetensors",
392
+ "layers.2.block_sparse_moe.experts.4.w2.weight": "model-00004-of-00039.safetensors",
393
+ "layers.2.block_sparse_moe.experts.4.w3.weight": "model-00004-of-00039.safetensors",
394
+ "layers.2.block_sparse_moe.experts.5.w1.weight": "model-00004-of-00039.safetensors",
395
+ "layers.2.block_sparse_moe.experts.5.w2.weight": "model-00004-of-00039.safetensors",
396
+ "layers.2.block_sparse_moe.experts.5.w3.weight": "model-00004-of-00039.safetensors",
397
+ "layers.2.block_sparse_moe.experts.6.w1.weight": "model-00004-of-00039.safetensors",
398
+ "layers.2.block_sparse_moe.experts.6.w2.weight": "model-00004-of-00039.safetensors",
399
+ "layers.2.block_sparse_moe.experts.6.w3.weight": "model-00004-of-00039.safetensors",
400
+ "layers.2.block_sparse_moe.experts.7.w1.weight": "model-00004-of-00039.safetensors",
401
+ "layers.2.block_sparse_moe.experts.7.w2.weight": "model-00004-of-00039.safetensors",
402
+ "layers.2.block_sparse_moe.experts.7.w3.weight": "model-00004-of-00039.safetensors",
403
+ "layers.2.block_sparse_moe.gate.weight": "model-00003-of-00039.safetensors",
404
+ "layers.2.input_layernorm.weight": "model-00004-of-00039.safetensors",
405
+ "layers.2.post_attention_layernorm.weight": "model-00004-of-00039.safetensors",
406
+ "layers.2.self_attn.k_proj.weight": "model-00003-of-00039.safetensors",
407
+ "layers.2.self_attn.o_proj.weight": "model-00003-of-00039.safetensors",
408
+ "layers.2.self_attn.q_proj.weight": "model-00003-of-00039.safetensors",
409
+ "layers.2.self_attn.v_proj.weight": "model-00003-of-00039.safetensors",
410
+ "layers.20.block_sparse_moe.experts.0.w1.weight": "model-00024-of-00039.safetensors",
411
+ "layers.20.block_sparse_moe.experts.0.w2.weight": "model-00025-of-00039.safetensors",
412
+ "layers.20.block_sparse_moe.experts.0.w3.weight": "model-00025-of-00039.safetensors",
413
+ "layers.20.block_sparse_moe.experts.1.w1.weight": "model-00025-of-00039.safetensors",
414
+ "layers.20.block_sparse_moe.experts.1.w2.weight": "model-00025-of-00039.safetensors",
415
+ "layers.20.block_sparse_moe.experts.1.w3.weight": "model-00025-of-00039.safetensors",
416
+ "layers.20.block_sparse_moe.experts.2.w1.weight": "model-00025-of-00039.safetensors",
417
+ "layers.20.block_sparse_moe.experts.2.w2.weight": "model-00025-of-00039.safetensors",
418
+ "layers.20.block_sparse_moe.experts.2.w3.weight": "model-00025-of-00039.safetensors",
419
+ "layers.20.block_sparse_moe.experts.3.w1.weight": "model-00025-of-00039.safetensors",
420
+ "layers.20.block_sparse_moe.experts.3.w2.weight": "model-00025-of-00039.safetensors",
421
+ "layers.20.block_sparse_moe.experts.3.w3.weight": "model-00025-of-00039.safetensors",
422
+ "layers.20.block_sparse_moe.experts.4.w1.weight": "model-00025-of-00039.safetensors",
423
+ "layers.20.block_sparse_moe.experts.4.w2.weight": "model-00025-of-00039.safetensors",
424
+ "layers.20.block_sparse_moe.experts.4.w3.weight": "model-00025-of-00039.safetensors",
425
+ "layers.20.block_sparse_moe.experts.5.w1.weight": "model-00025-of-00039.safetensors",
426
+ "layers.20.block_sparse_moe.experts.5.w2.weight": "model-00025-of-00039.safetensors",
427
+ "layers.20.block_sparse_moe.experts.5.w3.weight": "model-00025-of-00039.safetensors",
428
+ "layers.20.block_sparse_moe.experts.6.w1.weight": "model-00025-of-00039.safetensors",
429
+ "layers.20.block_sparse_moe.experts.6.w2.weight": "model-00025-of-00039.safetensors",
430
+ "layers.20.block_sparse_moe.experts.6.w3.weight": "model-00025-of-00039.safetensors",
431
+ "layers.20.block_sparse_moe.experts.7.w1.weight": "model-00025-of-00039.safetensors",
432
+ "layers.20.block_sparse_moe.experts.7.w2.weight": "model-00026-of-00039.safetensors",
433
+ "layers.20.block_sparse_moe.experts.7.w3.weight": "model-00026-of-00039.safetensors",
434
+ "layers.20.block_sparse_moe.gate.weight": "model-00024-of-00039.safetensors",
435
+ "layers.20.input_layernorm.weight": "model-00026-of-00039.safetensors",
436
+ "layers.20.post_attention_layernorm.weight": "model-00026-of-00039.safetensors",
437
+ "layers.20.self_attn.k_proj.weight": "model-00024-of-00039.safetensors",
438
+ "layers.20.self_attn.o_proj.weight": "model-00024-of-00039.safetensors",
439
+ "layers.20.self_attn.q_proj.weight": "model-00024-of-00039.safetensors",
440
+ "layers.20.self_attn.v_proj.weight": "model-00024-of-00039.safetensors",
441
+ "layers.21.block_sparse_moe.experts.0.w1.weight": "model-00026-of-00039.safetensors",
442
+ "layers.21.block_sparse_moe.experts.0.w2.weight": "model-00026-of-00039.safetensors",
443
+ "layers.21.block_sparse_moe.experts.0.w3.weight": "model-00026-of-00039.safetensors",
444
+ "layers.21.block_sparse_moe.experts.1.w1.weight": "model-00026-of-00039.safetensors",
445
+ "layers.21.block_sparse_moe.experts.1.w2.weight": "model-00026-of-00039.safetensors",
446
+ "layers.21.block_sparse_moe.experts.1.w3.weight": "model-00026-of-00039.safetensors",
447
+ "layers.21.block_sparse_moe.experts.2.w1.weight": "model-00026-of-00039.safetensors",
448
+ "layers.21.block_sparse_moe.experts.2.w2.weight": "model-00026-of-00039.safetensors",
449
+ "layers.21.block_sparse_moe.experts.2.w3.weight": "model-00026-of-00039.safetensors",
450
+ "layers.21.block_sparse_moe.experts.3.w1.weight": "model-00026-of-00039.safetensors",
451
+ "layers.21.block_sparse_moe.experts.3.w2.weight": "model-00026-of-00039.safetensors",
452
+ "layers.21.block_sparse_moe.experts.3.w3.weight": "model-00026-of-00039.safetensors",
453
+ "layers.21.block_sparse_moe.experts.4.w1.weight": "model-00026-of-00039.safetensors",
454
+ "layers.21.block_sparse_moe.experts.4.w2.weight": "model-00026-of-00039.safetensors",
455
+ "layers.21.block_sparse_moe.experts.4.w3.weight": "model-00026-of-00039.safetensors",
456
+ "layers.21.block_sparse_moe.experts.5.w1.weight": "model-00026-of-00039.safetensors",
457
+ "layers.21.block_sparse_moe.experts.5.w2.weight": "model-00026-of-00039.safetensors",
458
+ "layers.21.block_sparse_moe.experts.5.w3.weight": "model-00026-of-00039.safetensors",
459
+ "layers.21.block_sparse_moe.experts.6.w1.weight": "model-00027-of-00039.safetensors",
460
+ "layers.21.block_sparse_moe.experts.6.w2.weight": "model-00027-of-00039.safetensors",
461
+ "layers.21.block_sparse_moe.experts.6.w3.weight": "model-00027-of-00039.safetensors",
462
+ "layers.21.block_sparse_moe.experts.7.w1.weight": "model-00027-of-00039.safetensors",
463
+ "layers.21.block_sparse_moe.experts.7.w2.weight": "model-00027-of-00039.safetensors",
464
+ "layers.21.block_sparse_moe.experts.7.w3.weight": "model-00027-of-00039.safetensors",
465
+ "layers.21.block_sparse_moe.gate.weight": "model-00026-of-00039.safetensors",
466
+ "layers.21.input_layernorm.weight": "model-00027-of-00039.safetensors",
467
+ "layers.21.post_attention_layernorm.weight": "model-00027-of-00039.safetensors",
468
+ "layers.21.self_attn.k_proj.weight": "model-00026-of-00039.safetensors",
469
+ "layers.21.self_attn.o_proj.weight": "model-00026-of-00039.safetensors",
470
+ "layers.21.self_attn.q_proj.weight": "model-00026-of-00039.safetensors",
471
+ "layers.21.self_attn.v_proj.weight": "model-00026-of-00039.safetensors",
472
+ "layers.22.block_sparse_moe.experts.0.w1.weight": "model-00027-of-00039.safetensors",
473
+ "layers.22.block_sparse_moe.experts.0.w2.weight": "model-00027-of-00039.safetensors",
474
+ "layers.22.block_sparse_moe.experts.0.w3.weight": "model-00027-of-00039.safetensors",
475
+ "layers.22.block_sparse_moe.experts.1.w1.weight": "model-00027-of-00039.safetensors",
476
+ "layers.22.block_sparse_moe.experts.1.w2.weight": "model-00027-of-00039.safetensors",
477
+ "layers.22.block_sparse_moe.experts.1.w3.weight": "model-00027-of-00039.safetensors",
478
+ "layers.22.block_sparse_moe.experts.2.w1.weight": "model-00027-of-00039.safetensors",
479
+ "layers.22.block_sparse_moe.experts.2.w2.weight": "model-00027-of-00039.safetensors",
480
+ "layers.22.block_sparse_moe.experts.2.w3.weight": "model-00027-of-00039.safetensors",
481
+ "layers.22.block_sparse_moe.experts.3.w1.weight": "model-00027-of-00039.safetensors",
482
+ "layers.22.block_sparse_moe.experts.3.w2.weight": "model-00027-of-00039.safetensors",
483
+ "layers.22.block_sparse_moe.experts.3.w3.weight": "model-00027-of-00039.safetensors",
484
+ "layers.22.block_sparse_moe.experts.4.w1.weight": "model-00027-of-00039.safetensors",
485
+ "layers.22.block_sparse_moe.experts.4.w2.weight": "model-00027-of-00039.safetensors",
486
+ "layers.22.block_sparse_moe.experts.4.w3.weight": "model-00028-of-00039.safetensors",
487
+ "layers.22.block_sparse_moe.experts.5.w1.weight": "model-00028-of-00039.safetensors",
488
+ "layers.22.block_sparse_moe.experts.5.w2.weight": "model-00028-of-00039.safetensors",
489
+ "layers.22.block_sparse_moe.experts.5.w3.weight": "model-00028-of-00039.safetensors",
490
+ "layers.22.block_sparse_moe.experts.6.w1.weight": "model-00028-of-00039.safetensors",
491
+ "layers.22.block_sparse_moe.experts.6.w2.weight": "model-00028-of-00039.safetensors",
492
+ "layers.22.block_sparse_moe.experts.6.w3.weight": "model-00028-of-00039.safetensors",
493
+ "layers.22.block_sparse_moe.experts.7.w1.weight": "model-00028-of-00039.safetensors",
494
+ "layers.22.block_sparse_moe.experts.7.w2.weight": "model-00028-of-00039.safetensors",
495
+ "layers.22.block_sparse_moe.experts.7.w3.weight": "model-00028-of-00039.safetensors",
496
+ "layers.22.block_sparse_moe.gate.weight": "model-00027-of-00039.safetensors",
497
+ "layers.22.input_layernorm.weight": "model-00028-of-00039.safetensors",
498
+ "layers.22.post_attention_layernorm.weight": "model-00028-of-00039.safetensors",
499
+ "layers.22.self_attn.k_proj.weight": "model-00027-of-00039.safetensors",
500
+ "layers.22.self_attn.o_proj.weight": "model-00027-of-00039.safetensors",
501
+ "layers.22.self_attn.q_proj.weight": "model-00027-of-00039.safetensors",
502
+ "layers.22.self_attn.v_proj.weight": "model-00027-of-00039.safetensors",
503
+ "layers.23.block_sparse_moe.experts.0.w1.weight": "model-00028-of-00039.safetensors",
504
+ "layers.23.block_sparse_moe.experts.0.w2.weight": "model-00028-of-00039.safetensors",
505
+ "layers.23.block_sparse_moe.experts.0.w3.weight": "model-00028-of-00039.safetensors",
506
+ "layers.23.block_sparse_moe.experts.1.w1.weight": "model-00028-of-00039.safetensors",
507
+ "layers.23.block_sparse_moe.experts.1.w2.weight": "model-00028-of-00039.safetensors",
508
+ "layers.23.block_sparse_moe.experts.1.w3.weight": "model-00028-of-00039.safetensors",
509
+ "layers.23.block_sparse_moe.experts.2.w1.weight": "model-00028-of-00039.safetensors",
510
+ "layers.23.block_sparse_moe.experts.2.w2.weight": "model-00028-of-00039.safetensors",
511
+ "layers.23.block_sparse_moe.experts.2.w3.weight": "model-00028-of-00039.safetensors",
512
+ "layers.23.block_sparse_moe.experts.3.w1.weight": "model-00028-of-00039.safetensors",
513
+ "layers.23.block_sparse_moe.experts.3.w2.weight": "model-00029-of-00039.safetensors",
514
+ "layers.23.block_sparse_moe.experts.3.w3.weight": "model-00029-of-00039.safetensors",
515
+ "layers.23.block_sparse_moe.experts.4.w1.weight": "model-00029-of-00039.safetensors",
516
+ "layers.23.block_sparse_moe.experts.4.w2.weight": "model-00029-of-00039.safetensors",
517
+ "layers.23.block_sparse_moe.experts.4.w3.weight": "model-00029-of-00039.safetensors",
518
+ "layers.23.block_sparse_moe.experts.5.w1.weight": "model-00029-of-00039.safetensors",
519
+ "layers.23.block_sparse_moe.experts.5.w2.weight": "model-00029-of-00039.safetensors",
520
+ "layers.23.block_sparse_moe.experts.5.w3.weight": "model-00029-of-00039.safetensors",
521
+ "layers.23.block_sparse_moe.experts.6.w1.weight": "model-00029-of-00039.safetensors",
522
+ "layers.23.block_sparse_moe.experts.6.w2.weight": "model-00029-of-00039.safetensors",
523
+ "layers.23.block_sparse_moe.experts.6.w3.weight": "model-00029-of-00039.safetensors",
524
+ "layers.23.block_sparse_moe.experts.7.w1.weight": "model-00029-of-00039.safetensors",
525
+ "layers.23.block_sparse_moe.experts.7.w2.weight": "model-00029-of-00039.safetensors",
526
+ "layers.23.block_sparse_moe.experts.7.w3.weight": "model-00029-of-00039.safetensors",
527
+ "layers.23.block_sparse_moe.gate.weight": "model-00028-of-00039.safetensors",
528
+ "layers.23.input_layernorm.weight": "model-00029-of-00039.safetensors",
529
+ "layers.23.post_attention_layernorm.weight": "model-00029-of-00039.safetensors",
530
+ "layers.23.self_attn.k_proj.weight": "model-00028-of-00039.safetensors",
531
+ "layers.23.self_attn.o_proj.weight": "model-00028-of-00039.safetensors",
532
+ "layers.23.self_attn.q_proj.weight": "model-00028-of-00039.safetensors",
533
+ "layers.23.self_attn.v_proj.weight": "model-00028-of-00039.safetensors",
534
+ "layers.24.block_sparse_moe.experts.0.w1.weight": "model-00029-of-00039.safetensors",
535
+ "layers.24.block_sparse_moe.experts.0.w2.weight": "model-00029-of-00039.safetensors",
536
+ "layers.24.block_sparse_moe.experts.0.w3.weight": "model-00029-of-00039.safetensors",
537
+ "layers.24.block_sparse_moe.experts.1.w1.weight": "model-00029-of-00039.safetensors",
538
+ "layers.24.block_sparse_moe.experts.1.w2.weight": "model-00029-of-00039.safetensors",
539
+ "layers.24.block_sparse_moe.experts.1.w3.weight": "model-00029-of-00039.safetensors",
540
+ "layers.24.block_sparse_moe.experts.2.w1.weight": "model-00030-of-00039.safetensors",
541
+ "layers.24.block_sparse_moe.experts.2.w2.weight": "model-00030-of-00039.safetensors",
542
+ "layers.24.block_sparse_moe.experts.2.w3.weight": "model-00030-of-00039.safetensors",
543
+ "layers.24.block_sparse_moe.experts.3.w1.weight": "model-00030-of-00039.safetensors",
544
+ "layers.24.block_sparse_moe.experts.3.w2.weight": "model-00030-of-00039.safetensors",
545
+ "layers.24.block_sparse_moe.experts.3.w3.weight": "model-00030-of-00039.safetensors",
546
+ "layers.24.block_sparse_moe.experts.4.w1.weight": "model-00030-of-00039.safetensors",
547
+ "layers.24.block_sparse_moe.experts.4.w2.weight": "model-00030-of-00039.safetensors",
548
+ "layers.24.block_sparse_moe.experts.4.w3.weight": "model-00030-of-00039.safetensors",
549
+ "layers.24.block_sparse_moe.experts.5.w1.weight": "model-00030-of-00039.safetensors",
550
+ "layers.24.block_sparse_moe.experts.5.w2.weight": "model-00030-of-00039.safetensors",
551
+ "layers.24.block_sparse_moe.experts.5.w3.weight": "model-00030-of-00039.safetensors",
552
+ "layers.24.block_sparse_moe.experts.6.w1.weight": "model-00030-of-00039.safetensors",
553
+ "layers.24.block_sparse_moe.experts.6.w2.weight": "model-00030-of-00039.safetensors",
554
+ "layers.24.block_sparse_moe.experts.6.w3.weight": "model-00030-of-00039.safetensors",
555
+ "layers.24.block_sparse_moe.experts.7.w1.weight": "model-00030-of-00039.safetensors",
556
+ "layers.24.block_sparse_moe.experts.7.w2.weight": "model-00030-of-00039.safetensors",
557
+ "layers.24.block_sparse_moe.experts.7.w3.weight": "model-00030-of-00039.safetensors",
558
+ "layers.24.block_sparse_moe.gate.weight": "model-00029-of-00039.safetensors",
559
+ "layers.24.input_layernorm.weight": "model-00030-of-00039.safetensors",
560
+ "layers.24.post_attention_layernorm.weight": "model-00030-of-00039.safetensors",
561
+ "layers.24.self_attn.k_proj.weight": "model-00029-of-00039.safetensors",
562
+ "layers.24.self_attn.o_proj.weight": "model-00029-of-00039.safetensors",
563
+ "layers.24.self_attn.q_proj.weight": "model-00029-of-00039.safetensors",
564
+ "layers.24.self_attn.v_proj.weight": "model-00029-of-00039.safetensors",
565
+ "layers.25.block_sparse_moe.experts.0.w1.weight": "model-00030-of-00039.safetensors",
566
+ "layers.25.block_sparse_moe.experts.0.w2.weight": "model-00030-of-00039.safetensors",
567
+ "layers.25.block_sparse_moe.experts.0.w3.weight": "model-00031-of-00039.safetensors",
568
+ "layers.25.block_sparse_moe.experts.1.w1.weight": "model-00031-of-00039.safetensors",
569
+ "layers.25.block_sparse_moe.experts.1.w2.weight": "model-00031-of-00039.safetensors",
570
+ "layers.25.block_sparse_moe.experts.1.w3.weight": "model-00031-of-00039.safetensors",
571
+ "layers.25.block_sparse_moe.experts.2.w1.weight": "model-00031-of-00039.safetensors",
572
+ "layers.25.block_sparse_moe.experts.2.w2.weight": "model-00031-of-00039.safetensors",
573
+ "layers.25.block_sparse_moe.experts.2.w3.weight": "model-00031-of-00039.safetensors",
574
+ "layers.25.block_sparse_moe.experts.3.w1.weight": "model-00031-of-00039.safetensors",
575
+ "layers.25.block_sparse_moe.experts.3.w2.weight": "model-00031-of-00039.safetensors",
576
+ "layers.25.block_sparse_moe.experts.3.w3.weight": "model-00031-of-00039.safetensors",
577
+ "layers.25.block_sparse_moe.experts.4.w1.weight": "model-00031-of-00039.safetensors",
578
+ "layers.25.block_sparse_moe.experts.4.w2.weight": "model-00031-of-00039.safetensors",
579
+ "layers.25.block_sparse_moe.experts.4.w3.weight": "model-00031-of-00039.safetensors",
580
+ "layers.25.block_sparse_moe.experts.5.w1.weight": "model-00031-of-00039.safetensors",
581
+ "layers.25.block_sparse_moe.experts.5.w2.weight": "model-00031-of-00039.safetensors",
582
+ "layers.25.block_sparse_moe.experts.5.w3.weight": "model-00031-of-00039.safetensors",
583
+ "layers.25.block_sparse_moe.experts.6.w1.weight": "model-00031-of-00039.safetensors",
584
+ "layers.25.block_sparse_moe.experts.6.w2.weight": "model-00031-of-00039.safetensors",
585
+ "layers.25.block_sparse_moe.experts.6.w3.weight": "model-00031-of-00039.safetensors",
586
+ "layers.25.block_sparse_moe.experts.7.w1.weight": "model-00031-of-00039.safetensors",
587
+ "layers.25.block_sparse_moe.experts.7.w2.weight": "model-00031-of-00039.safetensors",
588
+ "layers.25.block_sparse_moe.experts.7.w3.weight": "model-00032-of-00039.safetensors",
589
+ "layers.25.block_sparse_moe.gate.weight": "model-00030-of-00039.safetensors",
590
+ "layers.25.input_layernorm.weight": "model-00032-of-00039.safetensors",
591
+ "layers.25.post_attention_layernorm.weight": "model-00032-of-00039.safetensors",
592
+ "layers.25.self_attn.k_proj.weight": "model-00030-of-00039.safetensors",
593
+ "layers.25.self_attn.o_proj.weight": "model-00030-of-00039.safetensors",
594
+ "layers.25.self_attn.q_proj.weight": "model-00030-of-00039.safetensors",
595
+ "layers.25.self_attn.v_proj.weight": "model-00030-of-00039.safetensors",
596
+ "layers.26.block_sparse_moe.experts.0.w1.weight": "model-00032-of-00039.safetensors",
597
+ "layers.26.block_sparse_moe.experts.0.w2.weight": "model-00032-of-00039.safetensors",
598
+ "layers.26.block_sparse_moe.experts.0.w3.weight": "model-00032-of-00039.safetensors",
599
+ "layers.26.block_sparse_moe.experts.1.w1.weight": "model-00032-of-00039.safetensors",
600
+ "layers.26.block_sparse_moe.experts.1.w2.weight": "model-00032-of-00039.safetensors",
601
+ "layers.26.block_sparse_moe.experts.1.w3.weight": "model-00032-of-00039.safetensors",
602
+ "layers.26.block_sparse_moe.experts.2.w1.weight": "model-00032-of-00039.safetensors",
603
+ "layers.26.block_sparse_moe.experts.2.w2.weight": "model-00032-of-00039.safetensors",
604
+ "layers.26.block_sparse_moe.experts.2.w3.weight": "model-00032-of-00039.safetensors",
605
+ "layers.26.block_sparse_moe.experts.3.w1.weight": "model-00032-of-00039.safetensors",
606
+ "layers.26.block_sparse_moe.experts.3.w2.weight": "model-00032-of-00039.safetensors",
607
+ "layers.26.block_sparse_moe.experts.3.w3.weight": "model-00032-of-00039.safetensors",
608
+ "layers.26.block_sparse_moe.experts.4.w1.weight": "model-00032-of-00039.safetensors",
609
+ "layers.26.block_sparse_moe.experts.4.w2.weight": "model-00032-of-00039.safetensors",
610
+ "layers.26.block_sparse_moe.experts.4.w3.weight": "model-00032-of-00039.safetensors",
611
+ "layers.26.block_sparse_moe.experts.5.w1.weight": "model-00032-of-00039.safetensors",
612
+ "layers.26.block_sparse_moe.experts.5.w2.weight": "model-00032-of-00039.safetensors",
613
+ "layers.26.block_sparse_moe.experts.5.w3.weight": "model-00032-of-00039.safetensors",
614
+ "layers.26.block_sparse_moe.experts.6.w1.weight": "model-00032-of-00039.safetensors",
615
+ "layers.26.block_sparse_moe.experts.6.w2.weight": "model-00033-of-00039.safetensors",
616
+ "layers.26.block_sparse_moe.experts.6.w3.weight": "model-00033-of-00039.safetensors",
617
+ "layers.26.block_sparse_moe.experts.7.w1.weight": "model-00033-of-00039.safetensors",
618
+ "layers.26.block_sparse_moe.experts.7.w2.weight": "model-00033-of-00039.safetensors",
619
+ "layers.26.block_sparse_moe.experts.7.w3.weight": "model-00033-of-00039.safetensors",
620
+ "layers.26.block_sparse_moe.gate.weight": "model-00032-of-00039.safetensors",
621
+ "layers.26.input_layernorm.weight": "model-00033-of-00039.safetensors",
622
+ "layers.26.post_attention_layernorm.weight": "model-00033-of-00039.safetensors",
623
+ "layers.26.self_attn.k_proj.weight": "model-00032-of-00039.safetensors",
624
+ "layers.26.self_attn.o_proj.weight": "model-00032-of-00039.safetensors",
625
+ "layers.26.self_attn.q_proj.weight": "model-00032-of-00039.safetensors",
626
+ "layers.26.self_attn.v_proj.weight": "model-00032-of-00039.safetensors",
627
+ "layers.27.block_sparse_moe.experts.0.w1.weight": "model-00033-of-00039.safetensors",
628
+ "layers.27.block_sparse_moe.experts.0.w2.weight": "model-00033-of-00039.safetensors",
629
+ "layers.27.block_sparse_moe.experts.0.w3.weight": "model-00033-of-00039.safetensors",
630
+ "layers.27.block_sparse_moe.experts.1.w1.weight": "model-00033-of-00039.safetensors",
631
+ "layers.27.block_sparse_moe.experts.1.w2.weight": "model-00033-of-00039.safetensors",
632
+ "layers.27.block_sparse_moe.experts.1.w3.weight": "model-00033-of-00039.safetensors",
633
+ "layers.27.block_sparse_moe.experts.2.w1.weight": "model-00033-of-00039.safetensors",
634
+ "layers.27.block_sparse_moe.experts.2.w2.weight": "model-00033-of-00039.safetensors",
635
+ "layers.27.block_sparse_moe.experts.2.w3.weight": "model-00033-of-00039.safetensors",
636
+ "layers.27.block_sparse_moe.experts.3.w1.weight": "model-00033-of-00039.safetensors",
637
+ "layers.27.block_sparse_moe.experts.3.w2.weight": "model-00033-of-00039.safetensors",
638
+ "layers.27.block_sparse_moe.experts.3.w3.weight": "model-00033-of-00039.safetensors",
639
+ "layers.27.block_sparse_moe.experts.4.w1.weight": "model-00033-of-00039.safetensors",
640
+ "layers.27.block_sparse_moe.experts.4.w2.weight": "model-00033-of-00039.safetensors",
641
+ "layers.27.block_sparse_moe.experts.4.w3.weight": "model-00033-of-00039.safetensors",
642
+ "layers.27.block_sparse_moe.experts.5.w1.weight": "model-00034-of-00039.safetensors",
643
+ "layers.27.block_sparse_moe.experts.5.w2.weight": "model-00034-of-00039.safetensors",
644
+ "layers.27.block_sparse_moe.experts.5.w3.weight": "model-00034-of-00039.safetensors",
645
+ "layers.27.block_sparse_moe.experts.6.w1.weight": "model-00034-of-00039.safetensors",
646
+ "layers.27.block_sparse_moe.experts.6.w2.weight": "model-00034-of-00039.safetensors",
647
+ "layers.27.block_sparse_moe.experts.6.w3.weight": "model-00034-of-00039.safetensors",
648
+ "layers.27.block_sparse_moe.experts.7.w1.weight": "model-00034-of-00039.safetensors",
649
+ "layers.27.block_sparse_moe.experts.7.w2.weight": "model-00034-of-00039.safetensors",
650
+ "layers.27.block_sparse_moe.experts.7.w3.weight": "model-00034-of-00039.safetensors",
651
+ "layers.27.block_sparse_moe.gate.weight": "model-00033-of-00039.safetensors",
652
+ "layers.27.input_layernorm.weight": "model-00034-of-00039.safetensors",
653
+ "layers.27.post_attention_layernorm.weight": "model-00034-of-00039.safetensors",
654
+ "layers.27.self_attn.k_proj.weight": "model-00033-of-00039.safetensors",
655
+ "layers.27.self_attn.o_proj.weight": "model-00033-of-00039.safetensors",
656
+ "layers.27.self_attn.q_proj.weight": "model-00033-of-00039.safetensors",
657
+ "layers.27.self_attn.v_proj.weight": "model-00033-of-00039.safetensors",
658
+ "layers.28.block_sparse_moe.experts.0.w1.weight": "model-00034-of-00039.safetensors",
659
+ "layers.28.block_sparse_moe.experts.0.w2.weight": "model-00034-of-00039.safetensors",
660
+ "layers.28.block_sparse_moe.experts.0.w3.weight": "model-00034-of-00039.safetensors",
661
+ "layers.28.block_sparse_moe.experts.1.w1.weight": "model-00034-of-00039.safetensors",
662
+ "layers.28.block_sparse_moe.experts.1.w2.weight": "model-00034-of-00039.safetensors",
663
+ "layers.28.block_sparse_moe.experts.1.w3.weight": "model-00034-of-00039.safetensors",
664
+ "layers.28.block_sparse_moe.experts.2.w1.weight": "model-00034-of-00039.safetensors",
665
+ "layers.28.block_sparse_moe.experts.2.w2.weight": "model-00034-of-00039.safetensors",
666
+ "layers.28.block_sparse_moe.experts.2.w3.weight": "model-00034-of-00039.safetensors",
667
+ "layers.28.block_sparse_moe.experts.3.w1.weight": "model-00034-of-00039.safetensors",
668
+ "layers.28.block_sparse_moe.experts.3.w2.weight": "model-00034-of-00039.safetensors",
669
+ "layers.28.block_sparse_moe.experts.3.w3.weight": "model-00035-of-00039.safetensors",
670
+ "layers.28.block_sparse_moe.experts.4.w1.weight": "model-00035-of-00039.safetensors",
671
+ "layers.28.block_sparse_moe.experts.4.w2.weight": "model-00035-of-00039.safetensors",
672
+ "layers.28.block_sparse_moe.experts.4.w3.weight": "model-00035-of-00039.safetensors",
673
+ "layers.28.block_sparse_moe.experts.5.w1.weight": "model-00035-of-00039.safetensors",
674
+ "layers.28.block_sparse_moe.experts.5.w2.weight": "model-00035-of-00039.safetensors",
675
+ "layers.28.block_sparse_moe.experts.5.w3.weight": "model-00035-of-00039.safetensors",
676
+ "layers.28.block_sparse_moe.experts.6.w1.weight": "model-00035-of-00039.safetensors",
677
+ "layers.28.block_sparse_moe.experts.6.w2.weight": "model-00035-of-00039.safetensors",
678
+ "layers.28.block_sparse_moe.experts.6.w3.weight": "model-00035-of-00039.safetensors",
679
+ "layers.28.block_sparse_moe.experts.7.w1.weight": "model-00035-of-00039.safetensors",
680
+ "layers.28.block_sparse_moe.experts.7.w2.weight": "model-00035-of-00039.safetensors",
681
+ "layers.28.block_sparse_moe.experts.7.w3.weight": "model-00035-of-00039.safetensors",
682
+ "layers.28.block_sparse_moe.gate.weight": "model-00034-of-00039.safetensors",
683
+ "layers.28.input_layernorm.weight": "model-00035-of-00039.safetensors",
684
+ "layers.28.post_attention_layernorm.weight": "model-00035-of-00039.safetensors",
685
+ "layers.28.self_attn.k_proj.weight": "model-00034-of-00039.safetensors",
686
+ "layers.28.self_attn.o_proj.weight": "model-00034-of-00039.safetensors",
687
+ "layers.28.self_attn.q_proj.weight": "model-00034-of-00039.safetensors",
688
+ "layers.28.self_attn.v_proj.weight": "model-00034-of-00039.safetensors",
689
+ "layers.29.block_sparse_moe.experts.0.w1.weight": "model-00035-of-00039.safetensors",
690
+ "layers.29.block_sparse_moe.experts.0.w2.weight": "model-00035-of-00039.safetensors",
691
+ "layers.29.block_sparse_moe.experts.0.w3.weight": "model-00035-of-00039.safetensors",
692
+ "layers.29.block_sparse_moe.experts.1.w1.weight": "model-00035-of-00039.safetensors",
693
+ "layers.29.block_sparse_moe.experts.1.w2.weight": "model-00035-of-00039.safetensors",
694
+ "layers.29.block_sparse_moe.experts.1.w3.weight": "model-00035-of-00039.safetensors",
695
+ "layers.29.block_sparse_moe.experts.2.w1.weight": "model-00035-of-00039.safetensors",
696
+ "layers.29.block_sparse_moe.experts.2.w2.weight": "model-00036-of-00039.safetensors",
697
+ "layers.29.block_sparse_moe.experts.2.w3.weight": "model-00036-of-00039.safetensors",
698
+ "layers.29.block_sparse_moe.experts.3.w1.weight": "model-00036-of-00039.safetensors",
699
+ "layers.29.block_sparse_moe.experts.3.w2.weight": "model-00036-of-00039.safetensors",
700
+ "layers.29.block_sparse_moe.experts.3.w3.weight": "model-00036-of-00039.safetensors",
701
+ "layers.29.block_sparse_moe.experts.4.w1.weight": "model-00036-of-00039.safetensors",
702
+ "layers.29.block_sparse_moe.experts.4.w2.weight": "model-00036-of-00039.safetensors",
703
+ "layers.29.block_sparse_moe.experts.4.w3.weight": "model-00036-of-00039.safetensors",
704
+ "layers.29.block_sparse_moe.experts.5.w1.weight": "model-00036-of-00039.safetensors",
705
+ "layers.29.block_sparse_moe.experts.5.w2.weight": "model-00036-of-00039.safetensors",
706
+ "layers.29.block_sparse_moe.experts.5.w3.weight": "model-00036-of-00039.safetensors",
707
+ "layers.29.block_sparse_moe.experts.6.w1.weight": "model-00036-of-00039.safetensors",
708
+ "layers.29.block_sparse_moe.experts.6.w2.weight": "model-00036-of-00039.safetensors",
709
+ "layers.29.block_sparse_moe.experts.6.w3.weight": "model-00036-of-00039.safetensors",
710
+ "layers.29.block_sparse_moe.experts.7.w1.weight": "model-00036-of-00039.safetensors",
711
+ "layers.29.block_sparse_moe.experts.7.w2.weight": "model-00036-of-00039.safetensors",
712
+ "layers.29.block_sparse_moe.experts.7.w3.weight": "model-00036-of-00039.safetensors",
713
+ "layers.29.block_sparse_moe.gate.weight": "model-00035-of-00039.safetensors",
714
+ "layers.29.input_layernorm.weight": "model-00036-of-00039.safetensors",
715
+ "layers.29.post_attention_layernorm.weight": "model-00036-of-00039.safetensors",
716
+ "layers.29.self_attn.k_proj.weight": "model-00035-of-00039.safetensors",
717
+ "layers.29.self_attn.o_proj.weight": "model-00035-of-00039.safetensors",
718
+ "layers.29.self_attn.q_proj.weight": "model-00035-of-00039.safetensors",
719
+ "layers.29.self_attn.v_proj.weight": "model-00035-of-00039.safetensors",
720
+ "layers.3.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00039.safetensors",
721
+ "layers.3.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00039.safetensors",
722
+ "layers.3.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00039.safetensors",
723
+ "layers.3.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00039.safetensors",
724
+ "layers.3.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00039.safetensors",
725
+ "layers.3.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00039.safetensors",
726
+ "layers.3.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00039.safetensors",
727
+ "layers.3.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00039.safetensors",
728
+ "layers.3.block_sparse_moe.experts.2.w3.weight": "model-00005-of-00039.safetensors",
729
+ "layers.3.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00039.safetensors",
730
+ "layers.3.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00039.safetensors",
731
+ "layers.3.block_sparse_moe.experts.3.w3.weight": "model-00005-of-00039.safetensors",
732
+ "layers.3.block_sparse_moe.experts.4.w1.weight": "model-00005-of-00039.safetensors",
733
+ "layers.3.block_sparse_moe.experts.4.w2.weight": "model-00005-of-00039.safetensors",
734
+ "layers.3.block_sparse_moe.experts.4.w3.weight": "model-00005-of-00039.safetensors",
735
+ "layers.3.block_sparse_moe.experts.5.w1.weight": "model-00005-of-00039.safetensors",
736
+ "layers.3.block_sparse_moe.experts.5.w2.weight": "model-00005-of-00039.safetensors",
737
+ "layers.3.block_sparse_moe.experts.5.w3.weight": "model-00005-of-00039.safetensors",
738
+ "layers.3.block_sparse_moe.experts.6.w1.weight": "model-00005-of-00039.safetensors",
739
+ "layers.3.block_sparse_moe.experts.6.w2.weight": "model-00005-of-00039.safetensors",
740
+ "layers.3.block_sparse_moe.experts.6.w3.weight": "model-00005-of-00039.safetensors",
741
+ "layers.3.block_sparse_moe.experts.7.w1.weight": "model-00005-of-00039.safetensors",
742
+ "layers.3.block_sparse_moe.experts.7.w2.weight": "model-00005-of-00039.safetensors",
743
+ "layers.3.block_sparse_moe.experts.7.w3.weight": "model-00005-of-00039.safetensors",
744
+ "layers.3.block_sparse_moe.gate.weight": "model-00004-of-00039.safetensors",
745
+ "layers.3.input_layernorm.weight": "model-00005-of-00039.safetensors",
746
+ "layers.3.post_attention_layernorm.weight": "model-00005-of-00039.safetensors",
747
+ "layers.3.self_attn.k_proj.weight": "model-00004-of-00039.safetensors",
748
+ "layers.3.self_attn.o_proj.weight": "model-00004-of-00039.safetensors",
749
+ "layers.3.self_attn.q_proj.weight": "model-00004-of-00039.safetensors",
750
+ "layers.3.self_attn.v_proj.weight": "model-00004-of-00039.safetensors",
751
+ "layers.30.block_sparse_moe.experts.0.w1.weight": "model-00036-of-00039.safetensors",
752
+ "layers.30.block_sparse_moe.experts.0.w2.weight": "model-00036-of-00039.safetensors",
753
+ "layers.30.block_sparse_moe.experts.0.w3.weight": "model-00036-of-00039.safetensors",
754
+ "layers.30.block_sparse_moe.experts.1.w1.weight": "model-00037-of-00039.safetensors",
755
+ "layers.30.block_sparse_moe.experts.1.w2.weight": "model-00037-of-00039.safetensors",
756
+ "layers.30.block_sparse_moe.experts.1.w3.weight": "model-00037-of-00039.safetensors",
757
+ "layers.30.block_sparse_moe.experts.2.w1.weight": "model-00037-of-00039.safetensors",
758
+ "layers.30.block_sparse_moe.experts.2.w2.weight": "model-00037-of-00039.safetensors",
759
+ "layers.30.block_sparse_moe.experts.2.w3.weight": "model-00037-of-00039.safetensors",
760
+ "layers.30.block_sparse_moe.experts.3.w1.weight": "model-00037-of-00039.safetensors",
761
+ "layers.30.block_sparse_moe.experts.3.w2.weight": "model-00037-of-00039.safetensors",
762
+ "layers.30.block_sparse_moe.experts.3.w3.weight": "model-00037-of-00039.safetensors",
763
+ "layers.30.block_sparse_moe.experts.4.w1.weight": "model-00037-of-00039.safetensors",
764
+ "layers.30.block_sparse_moe.experts.4.w2.weight": "model-00037-of-00039.safetensors",
765
+ "layers.30.block_sparse_moe.experts.4.w3.weight": "model-00037-of-00039.safetensors",
766
+ "layers.30.block_sparse_moe.experts.5.w1.weight": "model-00037-of-00039.safetensors",
767
+ "layers.30.block_sparse_moe.experts.5.w2.weight": "model-00037-of-00039.safetensors",
768
+ "layers.30.block_sparse_moe.experts.5.w3.weight": "model-00037-of-00039.safetensors",
769
+ "layers.30.block_sparse_moe.experts.6.w1.weight": "model-00037-of-00039.safetensors",
770
+ "layers.30.block_sparse_moe.experts.6.w2.weight": "model-00037-of-00039.safetensors",
771
+ "layers.30.block_sparse_moe.experts.6.w3.weight": "model-00037-of-00039.safetensors",
772
+ "layers.30.block_sparse_moe.experts.7.w1.weight": "model-00037-of-00039.safetensors",
773
+ "layers.30.block_sparse_moe.experts.7.w2.weight": "model-00037-of-00039.safetensors",
774
+ "layers.30.block_sparse_moe.experts.7.w3.weight": "model-00037-of-00039.safetensors",
775
+ "layers.30.block_sparse_moe.gate.weight": "model-00036-of-00039.safetensors",
776
+ "layers.30.input_layernorm.weight": "model-00037-of-00039.safetensors",
777
+ "layers.30.post_attention_layernorm.weight": "model-00037-of-00039.safetensors",
778
+ "layers.30.self_attn.k_proj.weight": "model-00036-of-00039.safetensors",
779
+ "layers.30.self_attn.o_proj.weight": "model-00036-of-00039.safetensors",
780
+ "layers.30.self_attn.q_proj.weight": "model-00036-of-00039.safetensors",
781
+ "layers.30.self_attn.v_proj.weight": "model-00036-of-00039.safetensors",
782
+ "layers.31.block_sparse_moe.experts.0.w1.weight": "model-00038-of-00039.safetensors",
783
+ "layers.31.block_sparse_moe.experts.0.w2.weight": "model-00038-of-00039.safetensors",
784
+ "layers.31.block_sparse_moe.experts.0.w3.weight": "model-00038-of-00039.safetensors",
785
+ "layers.31.block_sparse_moe.experts.1.w1.weight": "model-00038-of-00039.safetensors",
786
+ "layers.31.block_sparse_moe.experts.1.w2.weight": "model-00038-of-00039.safetensors",
787
+ "layers.31.block_sparse_moe.experts.1.w3.weight": "model-00038-of-00039.safetensors",
788
+ "layers.31.block_sparse_moe.experts.2.w1.weight": "model-00038-of-00039.safetensors",
789
+ "layers.31.block_sparse_moe.experts.2.w2.weight": "model-00038-of-00039.safetensors",
790
+ "layers.31.block_sparse_moe.experts.2.w3.weight": "model-00038-of-00039.safetensors",
791
+ "layers.31.block_sparse_moe.experts.3.w1.weight": "model-00038-of-00039.safetensors",
792
+ "layers.31.block_sparse_moe.experts.3.w2.weight": "model-00038-of-00039.safetensors",
793
+ "layers.31.block_sparse_moe.experts.3.w3.weight": "model-00038-of-00039.safetensors",
794
+ "layers.31.block_sparse_moe.experts.4.w1.weight": "model-00038-of-00039.safetensors",
795
+ "layers.31.block_sparse_moe.experts.4.w2.weight": "model-00038-of-00039.safetensors",
796
+ "layers.31.block_sparse_moe.experts.4.w3.weight": "model-00038-of-00039.safetensors",
797
+ "layers.31.block_sparse_moe.experts.5.w1.weight": "model-00038-of-00039.safetensors",
798
+ "layers.31.block_sparse_moe.experts.5.w2.weight": "model-00038-of-00039.safetensors",
799
+ "layers.31.block_sparse_moe.experts.5.w3.weight": "model-00038-of-00039.safetensors",
800
+ "layers.31.block_sparse_moe.experts.6.w1.weight": "model-00038-of-00039.safetensors",
801
+ "layers.31.block_sparse_moe.experts.6.w2.weight": "model-00038-of-00039.safetensors",
802
+ "layers.31.block_sparse_moe.experts.6.w3.weight": "model-00039-of-00039.safetensors",
803
+ "layers.31.block_sparse_moe.experts.7.w1.weight": "model-00039-of-00039.safetensors",
804
+ "layers.31.block_sparse_moe.experts.7.w2.weight": "model-00039-of-00039.safetensors",
805
+ "layers.31.block_sparse_moe.experts.7.w3.weight": "model-00039-of-00039.safetensors",
806
+ "layers.31.block_sparse_moe.gate.weight": "model-00038-of-00039.safetensors",
807
+ "layers.31.input_layernorm.weight": "model-00039-of-00039.safetensors",
808
+ "layers.31.post_attention_layernorm.weight": "model-00039-of-00039.safetensors",
809
+ "layers.31.self_attn.k_proj.weight": "model-00038-of-00039.safetensors",
810
+ "layers.31.self_attn.o_proj.weight": "model-00038-of-00039.safetensors",
811
+ "layers.31.self_attn.q_proj.weight": "model-00037-of-00039.safetensors",
812
+ "layers.31.self_attn.v_proj.weight": "model-00038-of-00039.safetensors",
813
+ "layers.4.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00039.safetensors",
814
+ "layers.4.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00039.safetensors",
815
+ "layers.4.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00039.safetensors",
816
+ "layers.4.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00039.safetensors",
817
+ "layers.4.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00039.safetensors",
818
+ "layers.4.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00039.safetensors",
819
+ "layers.4.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00039.safetensors",
820
+ "layers.4.block_sparse_moe.experts.2.w2.weight": "model-00006-of-00039.safetensors",
821
+ "layers.4.block_sparse_moe.experts.2.w3.weight": "model-00006-of-00039.safetensors",
822
+ "layers.4.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00039.safetensors",
823
+ "layers.4.block_sparse_moe.experts.3.w2.weight": "model-00006-of-00039.safetensors",
824
+ "layers.4.block_sparse_moe.experts.3.w3.weight": "model-00006-of-00039.safetensors",
825
+ "layers.4.block_sparse_moe.experts.4.w1.weight": "model-00006-of-00039.safetensors",
826
+ "layers.4.block_sparse_moe.experts.4.w2.weight": "model-00006-of-00039.safetensors",
827
+ "layers.4.block_sparse_moe.experts.4.w3.weight": "model-00006-of-00039.safetensors",
828
+ "layers.4.block_sparse_moe.experts.5.w1.weight": "model-00006-of-00039.safetensors",
829
+ "layers.4.block_sparse_moe.experts.5.w2.weight": "model-00006-of-00039.safetensors",
830
+ "layers.4.block_sparse_moe.experts.5.w3.weight": "model-00006-of-00039.safetensors",
831
+ "layers.4.block_sparse_moe.experts.6.w1.weight": "model-00006-of-00039.safetensors",
832
+ "layers.4.block_sparse_moe.experts.6.w2.weight": "model-00006-of-00039.safetensors",
833
+ "layers.4.block_sparse_moe.experts.6.w3.weight": "model-00006-of-00039.safetensors",
834
+ "layers.4.block_sparse_moe.experts.7.w1.weight": "model-00006-of-00039.safetensors",
835
+ "layers.4.block_sparse_moe.experts.7.w2.weight": "model-00006-of-00039.safetensors",
836
+ "layers.4.block_sparse_moe.experts.7.w3.weight": "model-00007-of-00039.safetensors",
837
+ "layers.4.block_sparse_moe.gate.weight": "model-00005-of-00039.safetensors",
838
+ "layers.4.input_layernorm.weight": "model-00007-of-00039.safetensors",
839
+ "layers.4.post_attention_layernorm.weight": "model-00007-of-00039.safetensors",
840
+ "layers.4.self_attn.k_proj.weight": "model-00005-of-00039.safetensors",
841
+ "layers.4.self_attn.o_proj.weight": "model-00005-of-00039.safetensors",
842
+ "layers.4.self_attn.q_proj.weight": "model-00005-of-00039.safetensors",
843
+ "layers.4.self_attn.v_proj.weight": "model-00005-of-00039.safetensors",
844
+ "layers.5.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00039.safetensors",
845
+ "layers.5.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00039.safetensors",
846
+ "layers.5.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00039.safetensors",
847
+ "layers.5.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00039.safetensors",
848
+ "layers.5.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00039.safetensors",
849
+ "layers.5.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00039.safetensors",
850
+ "layers.5.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00039.safetensors",
851
+ "layers.5.block_sparse_moe.experts.2.w2.weight": "model-00007-of-00039.safetensors",
852
+ "layers.5.block_sparse_moe.experts.2.w3.weight": "model-00007-of-00039.safetensors",
853
+ "layers.5.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00039.safetensors",
854
+ "layers.5.block_sparse_moe.experts.3.w2.weight": "model-00007-of-00039.safetensors",
855
+ "layers.5.block_sparse_moe.experts.3.w3.weight": "model-00007-of-00039.safetensors",
856
+ "layers.5.block_sparse_moe.experts.4.w1.weight": "model-00007-of-00039.safetensors",
857
+ "layers.5.block_sparse_moe.experts.4.w2.weight": "model-00007-of-00039.safetensors",
858
+ "layers.5.block_sparse_moe.experts.4.w3.weight": "model-00007-of-00039.safetensors",
859
+ "layers.5.block_sparse_moe.experts.5.w1.weight": "model-00007-of-00039.safetensors",
860
+ "layers.5.block_sparse_moe.experts.5.w2.weight": "model-00007-of-00039.safetensors",
861
+ "layers.5.block_sparse_moe.experts.5.w3.weight": "model-00007-of-00039.safetensors",
862
+ "layers.5.block_sparse_moe.experts.6.w1.weight": "model-00007-of-00039.safetensors",
863
+ "layers.5.block_sparse_moe.experts.6.w2.weight": "model-00008-of-00039.safetensors",
864
+ "layers.5.block_sparse_moe.experts.6.w3.weight": "model-00008-of-00039.safetensors",
865
+ "layers.5.block_sparse_moe.experts.7.w1.weight": "model-00008-of-00039.safetensors",
866
+ "layers.5.block_sparse_moe.experts.7.w2.weight": "model-00008-of-00039.safetensors",
867
+ "layers.5.block_sparse_moe.experts.7.w3.weight": "model-00008-of-00039.safetensors",
868
+ "layers.5.block_sparse_moe.gate.weight": "model-00007-of-00039.safetensors",
869
+ "layers.5.input_layernorm.weight": "model-00008-of-00039.safetensors",
870
+ "layers.5.post_attention_layernorm.weight": "model-00008-of-00039.safetensors",
871
+ "layers.5.self_attn.k_proj.weight": "model-00007-of-00039.safetensors",
872
+ "layers.5.self_attn.o_proj.weight": "model-00007-of-00039.safetensors",
873
+ "layers.5.self_attn.q_proj.weight": "model-00007-of-00039.safetensors",
874
+ "layers.5.self_attn.v_proj.weight": "model-00007-of-00039.safetensors",
875
+ "layers.6.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00039.safetensors",
876
+ "layers.6.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00039.safetensors",
877
+ "layers.6.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00039.safetensors",
878
+ "layers.6.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00039.safetensors",
879
+ "layers.6.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00039.safetensors",
880
+ "layers.6.block_sparse_moe.experts.1.w3.weight": "model-00008-of-00039.safetensors",
881
+ "layers.6.block_sparse_moe.experts.2.w1.weight": "model-00008-of-00039.safetensors",
882
+ "layers.6.block_sparse_moe.experts.2.w2.weight": "model-00008-of-00039.safetensors",
883
+ "layers.6.block_sparse_moe.experts.2.w3.weight": "model-00008-of-00039.safetensors",
884
+ "layers.6.block_sparse_moe.experts.3.w1.weight": "model-00008-of-00039.safetensors",
885
+ "layers.6.block_sparse_moe.experts.3.w2.weight": "model-00008-of-00039.safetensors",
886
+ "layers.6.block_sparse_moe.experts.3.w3.weight": "model-00008-of-00039.safetensors",
887
+ "layers.6.block_sparse_moe.experts.4.w1.weight": "model-00008-of-00039.safetensors",
888
+ "layers.6.block_sparse_moe.experts.4.w2.weight": "model-00008-of-00039.safetensors",
889
+ "layers.6.block_sparse_moe.experts.4.w3.weight": "model-00008-of-00039.safetensors",
890
+ "layers.6.block_sparse_moe.experts.5.w1.weight": "model-00009-of-00039.safetensors",
891
+ "layers.6.block_sparse_moe.experts.5.w2.weight": "model-00009-of-00039.safetensors",
892
+ "layers.6.block_sparse_moe.experts.5.w3.weight": "model-00009-of-00039.safetensors",
893
+ "layers.6.block_sparse_moe.experts.6.w1.weight": "model-00009-of-00039.safetensors",
894
+ "layers.6.block_sparse_moe.experts.6.w2.weight": "model-00009-of-00039.safetensors",
895
+ "layers.6.block_sparse_moe.experts.6.w3.weight": "model-00009-of-00039.safetensors",
896
+ "layers.6.block_sparse_moe.experts.7.w1.weight": "model-00009-of-00039.safetensors",
897
+ "layers.6.block_sparse_moe.experts.7.w2.weight": "model-00009-of-00039.safetensors",
898
+ "layers.6.block_sparse_moe.experts.7.w3.weight": "model-00009-of-00039.safetensors",
899
+ "layers.6.block_sparse_moe.gate.weight": "model-00008-of-00039.safetensors",
900
+ "layers.6.input_layernorm.weight": "model-00009-of-00039.safetensors",
901
+ "layers.6.post_attention_layernorm.weight": "model-00009-of-00039.safetensors",
902
+ "layers.6.self_attn.k_proj.weight": "model-00008-of-00039.safetensors",
903
+ "layers.6.self_attn.o_proj.weight": "model-00008-of-00039.safetensors",
904
+ "layers.6.self_attn.q_proj.weight": "model-00008-of-00039.safetensors",
905
+ "layers.6.self_attn.v_proj.weight": "model-00008-of-00039.safetensors",
906
+ "layers.7.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00039.safetensors",
907
+ "layers.7.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00039.safetensors",
908
+ "layers.7.block_sparse_moe.experts.0.w3.weight": "model-00009-of-00039.safetensors",
909
+ "layers.7.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00039.safetensors",
910
+ "layers.7.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00039.safetensors",
911
+ "layers.7.block_sparse_moe.experts.1.w3.weight": "model-00009-of-00039.safetensors",
912
+ "layers.7.block_sparse_moe.experts.2.w1.weight": "model-00009-of-00039.safetensors",
913
+ "layers.7.block_sparse_moe.experts.2.w2.weight": "model-00009-of-00039.safetensors",
914
+ "layers.7.block_sparse_moe.experts.2.w3.weight": "model-00009-of-00039.safetensors",
915
+ "layers.7.block_sparse_moe.experts.3.w1.weight": "model-00009-of-00039.safetensors",
916
+ "layers.7.block_sparse_moe.experts.3.w2.weight": "model-00009-of-00039.safetensors",
917
+ "layers.7.block_sparse_moe.experts.3.w3.weight": "model-00010-of-00039.safetensors",
918
+ "layers.7.block_sparse_moe.experts.4.w1.weight": "model-00010-of-00039.safetensors",
919
+ "layers.7.block_sparse_moe.experts.4.w2.weight": "model-00010-of-00039.safetensors",
920
+ "layers.7.block_sparse_moe.experts.4.w3.weight": "model-00010-of-00039.safetensors",
921
+ "layers.7.block_sparse_moe.experts.5.w1.weight": "model-00010-of-00039.safetensors",
922
+ "layers.7.block_sparse_moe.experts.5.w2.weight": "model-00010-of-00039.safetensors",
923
+ "layers.7.block_sparse_moe.experts.5.w3.weight": "model-00010-of-00039.safetensors",
924
+ "layers.7.block_sparse_moe.experts.6.w1.weight": "model-00010-of-00039.safetensors",
925
+ "layers.7.block_sparse_moe.experts.6.w2.weight": "model-00010-of-00039.safetensors",
926
+ "layers.7.block_sparse_moe.experts.6.w3.weight": "model-00010-of-00039.safetensors",
927
+ "layers.7.block_sparse_moe.experts.7.w1.weight": "model-00010-of-00039.safetensors",
928
+ "layers.7.block_sparse_moe.experts.7.w2.weight": "model-00010-of-00039.safetensors",
929
+ "layers.7.block_sparse_moe.experts.7.w3.weight": "model-00010-of-00039.safetensors",
930
+ "layers.7.block_sparse_moe.gate.weight": "model-00009-of-00039.safetensors",
931
+ "layers.7.input_layernorm.weight": "model-00010-of-00039.safetensors",
932
+ "layers.7.post_attention_layernorm.weight": "model-00010-of-00039.safetensors",
933
+ "layers.7.self_attn.k_proj.weight": "model-00009-of-00039.safetensors",
934
+ "layers.7.self_attn.o_proj.weight": "model-00009-of-00039.safetensors",
935
+ "layers.7.self_attn.q_proj.weight": "model-00009-of-00039.safetensors",
936
+ "layers.7.self_attn.v_proj.weight": "model-00009-of-00039.safetensors",
937
+ "layers.8.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00039.safetensors",
938
+ "layers.8.block_sparse_moe.experts.0.w2.weight": "model-00010-of-00039.safetensors",
939
+ "layers.8.block_sparse_moe.experts.0.w3.weight": "model-00010-of-00039.safetensors",
940
+ "layers.8.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00039.safetensors",
941
+ "layers.8.block_sparse_moe.experts.1.w2.weight": "model-00010-of-00039.safetensors",
942
+ "layers.8.block_sparse_moe.experts.1.w3.weight": "model-00010-of-00039.safetensors",
943
+ "layers.8.block_sparse_moe.experts.2.w1.weight": "model-00010-of-00039.safetensors",
944
+ "layers.8.block_sparse_moe.experts.2.w2.weight": "model-00011-of-00039.safetensors",
945
+ "layers.8.block_sparse_moe.experts.2.w3.weight": "model-00011-of-00039.safetensors",
946
+ "layers.8.block_sparse_moe.experts.3.w1.weight": "model-00011-of-00039.safetensors",
947
+ "layers.8.block_sparse_moe.experts.3.w2.weight": "model-00011-of-00039.safetensors",
948
+ "layers.8.block_sparse_moe.experts.3.w3.weight": "model-00011-of-00039.safetensors",
949
+ "layers.8.block_sparse_moe.experts.4.w1.weight": "model-00011-of-00039.safetensors",
950
+ "layers.8.block_sparse_moe.experts.4.w2.weight": "model-00011-of-00039.safetensors",
951
+ "layers.8.block_sparse_moe.experts.4.w3.weight": "model-00011-of-00039.safetensors",
952
+ "layers.8.block_sparse_moe.experts.5.w1.weight": "model-00011-of-00039.safetensors",
953
+ "layers.8.block_sparse_moe.experts.5.w2.weight": "model-00011-of-00039.safetensors",
954
+ "layers.8.block_sparse_moe.experts.5.w3.weight": "model-00011-of-00039.safetensors",
955
+ "layers.8.block_sparse_moe.experts.6.w1.weight": "model-00011-of-00039.safetensors",
956
+ "layers.8.block_sparse_moe.experts.6.w2.weight": "model-00011-of-00039.safetensors",
957
+ "layers.8.block_sparse_moe.experts.6.w3.weight": "model-00011-of-00039.safetensors",
958
+ "layers.8.block_sparse_moe.experts.7.w1.weight": "model-00011-of-00039.safetensors",
959
+ "layers.8.block_sparse_moe.experts.7.w2.weight": "model-00011-of-00039.safetensors",
960
+ "layers.8.block_sparse_moe.experts.7.w3.weight": "model-00011-of-00039.safetensors",
961
+ "layers.8.block_sparse_moe.gate.weight": "model-00010-of-00039.safetensors",
962
+ "layers.8.input_layernorm.weight": "model-00011-of-00039.safetensors",
963
+ "layers.8.post_attention_layernorm.weight": "model-00011-of-00039.safetensors",
964
+ "layers.8.self_attn.k_proj.weight": "model-00010-of-00039.safetensors",
965
+ "layers.8.self_attn.o_proj.weight": "model-00010-of-00039.safetensors",
966
+ "layers.8.self_attn.q_proj.weight": "model-00010-of-00039.safetensors",
967
+ "layers.8.self_attn.v_proj.weight": "model-00010-of-00039.safetensors",
968
+ "layers.9.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00039.safetensors",
969
+ "layers.9.block_sparse_moe.experts.0.w2.weight": "model-00011-of-00039.safetensors",
970
+ "layers.9.block_sparse_moe.experts.0.w3.weight": "model-00011-of-00039.safetensors",
971
+ "layers.9.block_sparse_moe.experts.1.w1.weight": "model-00012-of-00039.safetensors",
972
+ "layers.9.block_sparse_moe.experts.1.w2.weight": "model-00012-of-00039.safetensors",
973
+ "layers.9.block_sparse_moe.experts.1.w3.weight": "model-00012-of-00039.safetensors",
974
+ "layers.9.block_sparse_moe.experts.2.w1.weight": "model-00012-of-00039.safetensors",
975
+ "layers.9.block_sparse_moe.experts.2.w2.weight": "model-00012-of-00039.safetensors",
976
+ "layers.9.block_sparse_moe.experts.2.w3.weight": "model-00012-of-00039.safetensors",
977
+ "layers.9.block_sparse_moe.experts.3.w1.weight": "model-00012-of-00039.safetensors",
978
+ "layers.9.block_sparse_moe.experts.3.w2.weight": "model-00012-of-00039.safetensors",
979
+ "layers.9.block_sparse_moe.experts.3.w3.weight": "model-00012-of-00039.safetensors",
980
+ "layers.9.block_sparse_moe.experts.4.w1.weight": "model-00012-of-00039.safetensors",
981
+ "layers.9.block_sparse_moe.experts.4.w2.weight": "model-00012-of-00039.safetensors",
982
+ "layers.9.block_sparse_moe.experts.4.w3.weight": "model-00012-of-00039.safetensors",
983
+ "layers.9.block_sparse_moe.experts.5.w1.weight": "model-00012-of-00039.safetensors",
984
+ "layers.9.block_sparse_moe.experts.5.w2.weight": "model-00012-of-00039.safetensors",
985
+ "layers.9.block_sparse_moe.experts.5.w3.weight": "model-00012-of-00039.safetensors",
986
+ "layers.9.block_sparse_moe.experts.6.w1.weight": "model-00012-of-00039.safetensors",
987
+ "layers.9.block_sparse_moe.experts.6.w2.weight": "model-00012-of-00039.safetensors",
988
+ "layers.9.block_sparse_moe.experts.6.w3.weight": "model-00012-of-00039.safetensors",
989
+ "layers.9.block_sparse_moe.experts.7.w1.weight": "model-00012-of-00039.safetensors",
990
+ "layers.9.block_sparse_moe.experts.7.w2.weight": "model-00012-of-00039.safetensors",
991
+ "layers.9.block_sparse_moe.experts.7.w3.weight": "model-00012-of-00039.safetensors",
992
+ "layers.9.block_sparse_moe.gate.weight": "model-00011-of-00039.safetensors",
993
+ "layers.9.input_layernorm.weight": "model-00012-of-00039.safetensors",
994
+ "layers.9.post_attention_layernorm.weight": "model-00012-of-00039.safetensors",
995
+ "layers.9.self_attn.k_proj.weight": "model-00011-of-00039.safetensors",
996
+ "layers.9.self_attn.o_proj.weight": "model-00011-of-00039.safetensors",
997
+ "layers.9.self_attn.q_proj.weight": "model-00011-of-00039.safetensors",
998
+ "layers.9.self_attn.v_proj.weight": "model-00011-of-00039.safetensors",
999
+ "norm.weight": "model-00039-of-00039.safetensors"
1000
+ }
1001
+ }