Hugging Face's logo

Aleph-Alpha
/
Pharia-1-LLM-7B-control-aligned

Text Generation
scaling
Model card Files Community
2
ArturBaranowskiAA commited on
Commit
10c9a0b
•
1 Parent(s): 694a2a9

Release Pharia-1-LLM-7B-control-aligned

Browse files
Files changed (32) hide show
  1. config.yml +44 -0
  2. model_state_layer_0_EmbeddingInput.pt +3 -0
  3. model_state_layer_10_TransformerLayer.pt +3 -0
  4. model_state_layer_11_TransformerLayer.pt +3 -0
  5. model_state_layer_12_TransformerLayer.pt +3 -0
  6. model_state_layer_13_TransformerLayer.pt +3 -0
  7. model_state_layer_14_TransformerLayer.pt +3 -0
  8. model_state_layer_15_TransformerLayer.pt +3 -0
  9. model_state_layer_16_TransformerLayer.pt +3 -0
  10. model_state_layer_17_TransformerLayer.pt +3 -0
  11. model_state_layer_18_TransformerLayer.pt +3 -0
  12. model_state_layer_19_TransformerLayer.pt +3 -0
  13. model_state_layer_1_TransformerLayer.pt +3 -0
  14. model_state_layer_20_TransformerLayer.pt +3 -0
  15. model_state_layer_21_TransformerLayer.pt +3 -0
  16. model_state_layer_22_TransformerLayer.pt +3 -0
  17. model_state_layer_23_TransformerLayer.pt +3 -0
  18. model_state_layer_24_TransformerLayer.pt +3 -0
  19. model_state_layer_25_TransformerLayer.pt +3 -0
  20. model_state_layer_26_TransformerLayer.pt +3 -0
  21. model_state_layer_27_TransformerLayer.pt +3 -0
  22. model_state_layer_28_LayerNormWrapper.pt +3 -0
  23. model_state_layer_29_TransformerLMHead.pt +3 -0
  24. model_state_layer_2_TransformerLayer.pt +3 -0
  25. model_state_layer_3_TransformerLayer.pt +3 -0
  26. model_state_layer_4_TransformerLayer.pt +3 -0
  27. model_state_layer_5_TransformerLayer.pt +3 -0
  28. model_state_layer_6_TransformerLayer.pt +3 -0
  29. model_state_layer_7_TransformerLayer.pt +3 -0
  30. model_state_layer_8_TransformerLayer.pt +3 -0
  31. model_state_layer_9_TransformerLayer.pt +3 -0
  32. vocab.json +0 -0
config.yml ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "luminous_architecture": {
3
+ "vocab_size": 128000,
4
+ "vocab_file": "vocab.json",
5
+ "hidden_size": 4608,
6
+ "num_layers": 27,
7
+ "num_attention_heads": 36,
8
+ "num_local_attention_heads": 0,
9
+ "local_attention_window_size": null,
10
+ "rotary_embedding_base": 1000000,
11
+ "rotary_percentage": 1.0,
12
+ "sequence_length": 8192,
13
+ "norm_type": "layernorm",
14
+ "relative_position_embedding_type": "rotary_complex",
15
+ "mlp_type": "default",
16
+ "mlp_factor": 4.0,
17
+ "attention_bias": true,
18
+ "attention_qkv_in_one": false,
19
+ "attention_num_kv_heads": 4,
20
+ "attention_use_matmul": false,
21
+ "mlp_bias": true,
22
+ "key_query_norm": false,
23
+ "weight_tying": false,
24
+ "masked_softmax": {
25
+ "kernel": "torch",
26
+ "softmax_in_fp32": true,
27
+ "scale": 1.0,
28
+ "deterministic_flash_attn_bwd": false
29
+ },
30
+ "layernorm": {
31
+ "optimization_type": "torch",
32
+ "layernorm_epsilon": 1e-05
33
+ },
34
+ "precision": "bfloat16",
35
+ "dropout_embedding": 0.0,
36
+ "dropout_attention_probs": 0.0,
37
+ "dropout_after_attention": 0.0,
38
+ "dropout_after_mlp": 0.0,
39
+ "finetunable_token_ids": [],
40
+ "image_encoder": false,
41
+ "dropout_image_encoder": 0.0,
42
+ "lora_config": null
43
+ }
44
+ }
model_state_layer_0_EmbeddingInput.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:944575547a8f40de0468abedfcb3a67e823ae2e6dee8cc9913ab7ce3139d2d11
3
+ size 1179649483
model_state_layer_10_TransformerLayer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3326b40056f8bef2f170ae36a395aa95df9d41919f1b55bc421aa28ba1672287
3
+ size 434219842
model_state_layer_11_TransformerLayer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0a2b27f899309f51a3a2e1babd385c0448fc2da2d07287ef9460bc412e1813eb
3
+ size 434219842
model_state_layer_12_TransformerLayer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3d492be6c62ac54151536f146f610eee326cbd5b44f47db3731e18ab6a28c9f7
3
+ size 434219842
model_state_layer_13_TransformerLayer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a0ab604522d1fcbbf1f0ea3cc584ff45274b1ec49ecd7cfa17ffceee9bc3c46e
3
+ size 434219842
model_state_layer_14_TransformerLayer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c0c5841264d139d63495512848a58e7dda74111c9a06fd448377ebae2153814a
3
+ size 434219842
model_state_layer_15_TransformerLayer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e99a49074e983328fed12365744432eef3faa7d436e25557398b94d543fab268
3
+ size 434219842
model_state_layer_16_TransformerLayer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9927876f812755e84fe23f0f04d490f830a1e570c46c645c278b317b64d273da
3
+ size 434219842
model_state_layer_17_TransformerLayer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6517aec4734c54a0ebe5c3a34db56b4fd0319c51699bc3581cb115906e6f5ddd
3
+ size 434219842
model_state_layer_18_TransformerLayer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:40b0b908e961b266089175de2c6b0e00fbd68c9e4af48eec174ffc4f4b0e9115
3
+ size 434219842
model_state_layer_19_TransformerLayer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e0acb652c0d858188e52bf0f3ab28e3839439608253773bb41cd7bfc222320b7
3
+ size 434219842
model_state_layer_1_TransformerLayer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:06e979172c717bf58e75173dfaca906a3f0dca58dc7540e5c8e707e912937574
3
+ size 434219822
model_state_layer_20_TransformerLayer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:21bc2ebcdcd23925278c52a5e3582f3e4827c14a9473dfa19850cde497d78e26
3
+ size 434219842
model_state_layer_21_TransformerLayer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e0afdf95ac6e5c49308375c318fec5212469398c6a92d76eff29aa42159f5b74
3
+ size 434219842
model_state_layer_22_TransformerLayer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b023d1ad0752422a30a49cb8914a909408b227490ffc572892aa0c43f120af1f
3
+ size 434219842
model_state_layer_23_TransformerLayer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:91f7a51afc64cd8514c28497b8f668a88b776aa826d5003b80aeb201ee0c6bde
3
+ size 434219842
model_state_layer_24_TransformerLayer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a9738644818fbe5822f06418c252b89d279efc7b809c845597250b287508ff2f
3
+ size 434219842
model_state_layer_25_TransformerLayer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec5831c9afcddadcc93f9f453a90eb454c991f7dc05d5702705d317bf2d887e2
3
+ size 434219842
model_state_layer_26_TransformerLayer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d62c3eed8d99092efea7d7cd6567a739a3448d71da827dce125609aeb47b62ba
3
+ size 434219842
model_state_layer_27_TransformerLayer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac7b9275de32430ba744d35510b0aa823e0ea988ca5239c55ae17a1fc08ea5c7
3
+ size 434219842
model_state_layer_28_LayerNormWrapper.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c43ee90f5370a66010b7aa690e4a1d855cfef85fe2627772ccc01f0a5e468d48
3
+ size 20172
model_state_layer_29_TransformerLMHead.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c0b5aa89e032b95749a0a11f931477d8605d5223160396e92dd8cae4abe12b63
3
+ size 1179649448
model_state_layer_2_TransformerLayer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:03c1d967b97a16bc4cf11130dca957daddd95608198b03d7a742090c574904b9
3
+ size 434219822
model_state_layer_3_TransformerLayer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:00110ff21e16c28d166ae7737f0eb9c3702348e9b09d34280908fd153c679fcc
3
+ size 434219822
model_state_layer_4_TransformerLayer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:976b2ce91395c252c00717e19e52143e045fec139ceb4c564fab2028e5c2cf99
3
+ size 434219822
model_state_layer_5_TransformerLayer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:46cdef8b748a158e47891a5934f089bb32d708fb7bf22bc262a0b336eade2aaa
3
+ size 434219822
model_state_layer_6_TransformerLayer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d1747434ad1a7f760b7ec0a33065d270368e903eec36698b714f425659969029
3
+ size 434219822
model_state_layer_7_TransformerLayer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6d333b2c506093cf6329c6430b76553868dc1c15c7bfaef5d4d1c878097f17ba
3
+ size 434219822
model_state_layer_8_TransformerLayer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d6e454bcb6cf09ea985c72317c9df9fc3a666e5fb7c95ec7363aeef325a23151
3
+ size 434219822
model_state_layer_9_TransformerLayer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2889738c8a166aa6048478c1513517237b7b18a8d863eb4686b644239a285ead
3
+ size 434219822
vocab.json ADDED
The diff for this file is too large to render. See raw diff