Hugging Face's logo

DavidAU
/
MN-18.5B-Celeste-V1.9-Story-Wizard-ED1-Instruct

Text Generation
Transformers
Safetensors
mistral
mergekit
Merge
conversational
text-generation-inference
Inference Endpoints
Model card Files Community
DavidAU commited on
Commit
dbcc390
•
1 Parent(s): ac016d2

Upload folder using huggingface_hub

Browse files
Files changed (45) hide show
  1. https:/huggingface.co/DavidAU/MN-18.5B-Celeste-V1.9-Story-Wizard-ED1-Instruct/tree/main/README.md +77 -0
  2. https:/huggingface.co/DavidAU/MN-18.5B-Celeste-V1.9-Story-Wizard-ED1-Instruct/tree/main/config.json +27 -0
  3. https:/huggingface.co/DavidAU/MN-18.5B-Celeste-V1.9-Story-Wizard-ED1-Instruct/tree/main/mergekit_config.yml +46 -0
  4. https:/huggingface.co/DavidAU/MN-18.5B-Celeste-V1.9-Story-Wizard-ED1-Instruct/tree/main/model-00001-of-00038.safetensors +3 -0
  5. https:/huggingface.co/DavidAU/MN-18.5B-Celeste-V1.9-Story-Wizard-ED1-Instruct/tree/main/model-00002-of-00038.safetensors +3 -0
  6. https:/huggingface.co/DavidAU/MN-18.5B-Celeste-V1.9-Story-Wizard-ED1-Instruct/tree/main/model-00003-of-00038.safetensors +3 -0
  7. https:/huggingface.co/DavidAU/MN-18.5B-Celeste-V1.9-Story-Wizard-ED1-Instruct/tree/main/model-00004-of-00038.safetensors +3 -0
  8. https:/huggingface.co/DavidAU/MN-18.5B-Celeste-V1.9-Story-Wizard-ED1-Instruct/tree/main/model-00005-of-00038.safetensors +3 -0
  9. https:/huggingface.co/DavidAU/MN-18.5B-Celeste-V1.9-Story-Wizard-ED1-Instruct/tree/main/model-00006-of-00038.safetensors +3 -0
  10. https:/huggingface.co/DavidAU/MN-18.5B-Celeste-V1.9-Story-Wizard-ED1-Instruct/tree/main/model-00007-of-00038.safetensors +3 -0
  11. https:/huggingface.co/DavidAU/MN-18.5B-Celeste-V1.9-Story-Wizard-ED1-Instruct/tree/main/model-00008-of-00038.safetensors +3 -0
  12. https:/huggingface.co/DavidAU/MN-18.5B-Celeste-V1.9-Story-Wizard-ED1-Instruct/tree/main/model-00009-of-00038.safetensors +3 -0
  13. https:/huggingface.co/DavidAU/MN-18.5B-Celeste-V1.9-Story-Wizard-ED1-Instruct/tree/main/model-00010-of-00038.safetensors +3 -0
  14. https:/huggingface.co/DavidAU/MN-18.5B-Celeste-V1.9-Story-Wizard-ED1-Instruct/tree/main/model-00011-of-00038.safetensors +3 -0
  15. https:/huggingface.co/DavidAU/MN-18.5B-Celeste-V1.9-Story-Wizard-ED1-Instruct/tree/main/model-00012-of-00038.safetensors +3 -0
  16. https:/huggingface.co/DavidAU/MN-18.5B-Celeste-V1.9-Story-Wizard-ED1-Instruct/tree/main/model-00013-of-00038.safetensors +3 -0
  17. https:/huggingface.co/DavidAU/MN-18.5B-Celeste-V1.9-Story-Wizard-ED1-Instruct/tree/main/model-00014-of-00038.safetensors +3 -0
  18. https:/huggingface.co/DavidAU/MN-18.5B-Celeste-V1.9-Story-Wizard-ED1-Instruct/tree/main/model-00015-of-00038.safetensors +3 -0
  19. https:/huggingface.co/DavidAU/MN-18.5B-Celeste-V1.9-Story-Wizard-ED1-Instruct/tree/main/model-00016-of-00038.safetensors +3 -0
  20. https:/huggingface.co/DavidAU/MN-18.5B-Celeste-V1.9-Story-Wizard-ED1-Instruct/tree/main/model-00017-of-00038.safetensors +3 -0
  21. https:/huggingface.co/DavidAU/MN-18.5B-Celeste-V1.9-Story-Wizard-ED1-Instruct/tree/main/model-00018-of-00038.safetensors +3 -0
  22. https:/huggingface.co/DavidAU/MN-18.5B-Celeste-V1.9-Story-Wizard-ED1-Instruct/tree/main/model-00019-of-00038.safetensors +3 -0
  23. https:/huggingface.co/DavidAU/MN-18.5B-Celeste-V1.9-Story-Wizard-ED1-Instruct/tree/main/model-00020-of-00038.safetensors +3 -0
  24. https:/huggingface.co/DavidAU/MN-18.5B-Celeste-V1.9-Story-Wizard-ED1-Instruct/tree/main/model-00021-of-00038.safetensors +3 -0
  25. https:/huggingface.co/DavidAU/MN-18.5B-Celeste-V1.9-Story-Wizard-ED1-Instruct/tree/main/model-00022-of-00038.safetensors +3 -0
  26. https:/huggingface.co/DavidAU/MN-18.5B-Celeste-V1.9-Story-Wizard-ED1-Instruct/tree/main/model-00023-of-00038.safetensors +3 -0
  27. https:/huggingface.co/DavidAU/MN-18.5B-Celeste-V1.9-Story-Wizard-ED1-Instruct/tree/main/model-00024-of-00038.safetensors +3 -0
  28. https:/huggingface.co/DavidAU/MN-18.5B-Celeste-V1.9-Story-Wizard-ED1-Instruct/tree/main/model-00025-of-00038.safetensors +3 -0
  29. https:/huggingface.co/DavidAU/MN-18.5B-Celeste-V1.9-Story-Wizard-ED1-Instruct/tree/main/model-00026-of-00038.safetensors +3 -0
  30. https:/huggingface.co/DavidAU/MN-18.5B-Celeste-V1.9-Story-Wizard-ED1-Instruct/tree/main/model-00027-of-00038.safetensors +3 -0
  31. https:/huggingface.co/DavidAU/MN-18.5B-Celeste-V1.9-Story-Wizard-ED1-Instruct/tree/main/model-00028-of-00038.safetensors +3 -0
  32. https:/huggingface.co/DavidAU/MN-18.5B-Celeste-V1.9-Story-Wizard-ED1-Instruct/tree/main/model-00029-of-00038.safetensors +3 -0
  33. https:/huggingface.co/DavidAU/MN-18.5B-Celeste-V1.9-Story-Wizard-ED1-Instruct/tree/main/model-00030-of-00038.safetensors +3 -0
  34. https:/huggingface.co/DavidAU/MN-18.5B-Celeste-V1.9-Story-Wizard-ED1-Instruct/tree/main/model-00031-of-00038.safetensors +3 -0
  35. https:/huggingface.co/DavidAU/MN-18.5B-Celeste-V1.9-Story-Wizard-ED1-Instruct/tree/main/model-00032-of-00038.safetensors +3 -0
  36. https:/huggingface.co/DavidAU/MN-18.5B-Celeste-V1.9-Story-Wizard-ED1-Instruct/tree/main/model-00033-of-00038.safetensors +3 -0
  37. https:/huggingface.co/DavidAU/MN-18.5B-Celeste-V1.9-Story-Wizard-ED1-Instruct/tree/main/model-00034-of-00038.safetensors +3 -0
  38. https:/huggingface.co/DavidAU/MN-18.5B-Celeste-V1.9-Story-Wizard-ED1-Instruct/tree/main/model-00035-of-00038.safetensors +3 -0
  39. https:/huggingface.co/DavidAU/MN-18.5B-Celeste-V1.9-Story-Wizard-ED1-Instruct/tree/main/model-00036-of-00038.safetensors +3 -0
  40. https:/huggingface.co/DavidAU/MN-18.5B-Celeste-V1.9-Story-Wizard-ED1-Instruct/tree/main/model-00037-of-00038.safetensors +3 -0
  41. https:/huggingface.co/DavidAU/MN-18.5B-Celeste-V1.9-Story-Wizard-ED1-Instruct/tree/main/model-00038-of-00038.safetensors +3 -0
  42. https:/huggingface.co/DavidAU/MN-18.5B-Celeste-V1.9-Story-Wizard-ED1-Instruct/tree/main/model.safetensors.index.json +1 -0
  43. https:/huggingface.co/DavidAU/MN-18.5B-Celeste-V1.9-Story-Wizard-ED1-Instruct/tree/main/special_tokens_map.json +23 -0
  44. https:/huggingface.co/DavidAU/MN-18.5B-Celeste-V1.9-Story-Wizard-ED1-Instruct/tree/main/tokenizer.json +0 -0
  45. https:/huggingface.co/DavidAU/MN-18.5B-Celeste-V1.9-Story-Wizard-ED1-Instruct/tree/main/tokenizer_config.json +0 -0
https:/huggingface.co/DavidAU/MN-18.5B-Celeste-V1.9-Story-Wizard-ED1-Instruct/tree/main/README.md ADDED
@@ -0,0 +1,77 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: []
3
+ library_name: transformers
4
+ tags:
5
+ - mergekit
6
+ - merge
7
+
8
+ ---
9
+ # MN-12B-Celeste-V1.9-Instruct
10
+
11
+ This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
12
+
13
+ ## Merge Details
14
+ ### Merge Method
15
+
16
+ This model was merged using the passthrough merge method.
17
+
18
+ ### Models Merged
19
+
20
+ The following models were included in the merge:
21
+ * g:/11b/Mistral-Nemo-Instruct-2407-12B
22
+ * G:/11B/MN-12B-Celeste-V1.9
23
+
24
+ ### Configuration
25
+
26
+ The following YAML configuration was used to produce this model:
27
+
28
+ ```yaml
29
+ # SMB with instruct to help performance.
30
+
31
+ slices:
32
+ - sources:
33
+ - model: g:/11b/Mistral-Nemo-Instruct-2407-12B
34
+ layer_range: [0, 14]
35
+ - sources:
36
+ - model: G:/11B/MN-12B-Celeste-V1.9
37
+ layer_range: [8, 24]
38
+ parameters:
39
+ scale:
40
+ - filter: o_proj
41
+ value: 1
42
+ - filter: down_proj
43
+ value: 1
44
+ - value: 1
45
+ - sources:
46
+ - model: g:/11b/Mistral-Nemo-Instruct-2407-12B
47
+ layer_range: [14, 22]
48
+ parameters:
49
+ scale:
50
+ - filter: o_proj
51
+ value: .5
52
+ - filter: down_proj
53
+ value: .5
54
+ - value: 1
55
+ - sources:
56
+ - model: g:/11b/Mistral-Nemo-Instruct-2407-12B
57
+ layer_range: [22, 31]
58
+ parameters:
59
+ scale:
60
+ - filter: o_proj
61
+ value: .75
62
+ - filter: down_proj
63
+ value: .75
64
+ - value: 1
65
+ - sources:
66
+ - model: G:/11B/MN-12B-Celeste-V1.9
67
+ layer_range: [24, 40]
68
+ parameters:
69
+ scale:
70
+ - filter: o_proj
71
+ value: 1
72
+ - filter: down_proj
73
+ value: 1
74
+ - value: 1
75
+ merge_method: passthrough
76
+ dtype: bfloat16
77
+ ```
https:/huggingface.co/DavidAU/MN-18.5B-Celeste-V1.9-Story-Wizard-ED1-Instruct/tree/main/config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "g:/11b/Mistral-Nemo-Instruct-2407-12B",
3
+ "architectures": [
4
+ "MistralForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 1,
8
+ "eos_token_id": 2,
9
+ "head_dim": 128,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 5120,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 14336,
14
+ "max_position_embeddings": 1024000,
15
+ "model_type": "mistral",
16
+ "num_attention_heads": 32,
17
+ "num_hidden_layers": 63,
18
+ "num_key_value_heads": 8,
19
+ "rms_norm_eps": 1e-05,
20
+ "rope_theta": 1000000.0,
21
+ "sliding_window": null,
22
+ "tie_word_embeddings": false,
23
+ "torch_dtype": "bfloat16",
24
+ "transformers_version": "4.43.3",
25
+ "use_cache": true,
26
+ "vocab_size": 131072
27
+ }
https:/huggingface.co/DavidAU/MN-18.5B-Celeste-V1.9-Story-Wizard-ED1-Instruct/tree/main/mergekit_config.yml ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ slices:
2
+ - sources:
3
+ - model: g:/11b/Mistral-Nemo-Instruct-2407-12B
4
+ layer_range: [0, 14]
5
+ - sources:
6
+ - model: G:/11B/MN-12B-Celeste-V1.9
7
+ layer_range: [8, 24]
8
+ parameters:
9
+ scale:
10
+ - filter: o_proj
11
+ value: 1
12
+ - filter: down_proj
13
+ value: 1
14
+ - value: 1
15
+ - sources:
16
+ - model: g:/11b/Mistral-Nemo-Instruct-2407-12B
17
+ layer_range: [14, 22]
18
+ parameters:
19
+ scale:
20
+ - filter: o_proj
21
+ value: .5
22
+ - filter: down_proj
23
+ value: .5
24
+ - value: 1
25
+ - sources:
26
+ - model: g:/11b/Mistral-Nemo-Instruct-2407-12B
27
+ layer_range: [22, 31]
28
+ parameters:
29
+ scale:
30
+ - filter: o_proj
31
+ value: .75
32
+ - filter: down_proj
33
+ value: .75
34
+ - value: 1
35
+ - sources:
36
+ - model: G:/11B/MN-12B-Celeste-V1.9
37
+ layer_range: [24, 40]
38
+ parameters:
39
+ scale:
40
+ - filter: o_proj
41
+ value: 1
42
+ - filter: down_proj
43
+ value: 1
44
+ - value: 1
45
+ merge_method: passthrough
46
+ dtype: bfloat16
https:/huggingface.co/DavidAU/MN-18.5B-Celeste-V1.9-Story-Wizard-ED1-Instruct/tree/main/model-00001-of-00038.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3fe33f77d2258863517dcc1e1955790fb876486fc079102fab3e08c3b3b2989f
3
+ size 1342177408
https:/huggingface.co/DavidAU/MN-18.5B-Celeste-V1.9-Story-Wizard-ED1-Instruct/tree/main/model-00002-of-00038.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:99ee43a228c5ca850b13d0bf13d6dc85a7b6aa597a404b017dfb3774a928ad23
3
+ size 1342177424
https:/huggingface.co/DavidAU/MN-18.5B-Celeste-V1.9-Story-Wizard-ED1-Instruct/tree/main/model-00003-of-00038.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e7b5f5aca8092e0ac4b789cadc2c4d9a9cd228b2c0700ffa6ccb2058d505a3ef
3
+ size 996189888
https:/huggingface.co/DavidAU/MN-18.5B-Celeste-V1.9-Story-Wizard-ED1-Instruct/tree/main/model-00004-of-00038.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:76b23e13f35e47bd4ce9fdebed3a74b483a716f312ef79d1c0a6772345d529e7
3
+ size 996189904
https:/huggingface.co/DavidAU/MN-18.5B-Celeste-V1.9-Story-Wizard-ED1-Instruct/tree/main/model-00005-of-00038.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f13728b5de870f0e7c584d1dd4c5a46538f1799400112dbf0ecfd1ed66294694
3
+ size 922768872
https:/huggingface.co/DavidAU/MN-18.5B-Celeste-V1.9-Story-Wizard-ED1-Instruct/tree/main/model-00006-of-00038.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d716686378c0b21e4b6664e1610b5b1507571b19a99458717ce55e260e67818
3
+ size 943761352
https:/huggingface.co/DavidAU/MN-18.5B-Celeste-V1.9-Story-Wizard-ED1-Instruct/tree/main/model-00007-of-00038.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e6d3c1f910941aca15b564f3b75fbc1fdaa18a473209a2251a1aa0bfca48efdd
3
+ size 943761344
https:/huggingface.co/DavidAU/MN-18.5B-Celeste-V1.9-Story-Wizard-ED1-Instruct/tree/main/model-00008-of-00038.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:27949165f3b13684b85f08f2dcb82550bf107ed10881e6b2e77f58f3643312db
3
+ size 943761344
https:/huggingface.co/DavidAU/MN-18.5B-Celeste-V1.9-Story-Wizard-ED1-Instruct/tree/main/model-00009-of-00038.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4fafebf6e0446aa697f42576af9ce4fcda6dda25c005c630e5720571a5c80ce0
3
+ size 943761344
https:/huggingface.co/DavidAU/MN-18.5B-Celeste-V1.9-Story-Wizard-ED1-Instruct/tree/main/model-00010-of-00038.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d4050400534c021342a8baeefd0a7940002e0acb83a808e50d201d85a6ac030d
3
+ size 943761344
https:/huggingface.co/DavidAU/MN-18.5B-Celeste-V1.9-Story-Wizard-ED1-Instruct/tree/main/model-00011-of-00038.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a6a970d4f538443f62d21b5c17e221a6b279a54fb71eb1d18602c7a4f4faaa60
3
+ size 985683336
https:/huggingface.co/DavidAU/MN-18.5B-Celeste-V1.9-Story-Wizard-ED1-Instruct/tree/main/model-00012-of-00038.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd47e0d50c15780a2d839eb39ec6c080935f9c4c31cf96c9d8a279c63aa6575d
3
+ size 996189904
https:/huggingface.co/DavidAU/MN-18.5B-Celeste-V1.9-Story-Wizard-ED1-Instruct/tree/main/model-00013-of-00038.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a22dba0f6c30ea6d93ce7a0253b503f0242f47740314ad5a1872cc20e2d93865
3
+ size 933254752
https:/huggingface.co/DavidAU/MN-18.5B-Celeste-V1.9-Story-Wizard-ED1-Instruct/tree/main/model-00014-of-00038.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3022f389c12109166c9fb3db21e2d6fc13ff853af548f52a397334e4e9d4c7a1
3
+ size 943761352
https:/huggingface.co/DavidAU/MN-18.5B-Celeste-V1.9-Story-Wizard-ED1-Instruct/tree/main/model-00015-of-00038.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e5e2b55ec6e88c423e539078f69034453634e751e1d28628c98dd283294db22
3
+ size 996190368
https:/huggingface.co/DavidAU/MN-18.5B-Celeste-V1.9-Story-Wizard-ED1-Instruct/tree/main/model-00016-of-00038.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5ea003524357a82c3f748329800bf40d88b8075e90e33615b5067e956691b4c8
3
+ size 996189904
https:/huggingface.co/DavidAU/MN-18.5B-Celeste-V1.9-Story-Wizard-ED1-Instruct/tree/main/model-00017-of-00038.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ab12a771d4756f2873e0f86e55fef0cd5891e801be1ecc2a15a3a0478e6ba1bf
3
+ size 880825712
https:/huggingface.co/DavidAU/MN-18.5B-Celeste-V1.9-Story-Wizard-ED1-Instruct/tree/main/model-00018-of-00038.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:afe6e664116c6619621cccbd230e26813b3670a8e00263d516ebe115956c1665
3
+ size 943761352
https:/huggingface.co/DavidAU/MN-18.5B-Celeste-V1.9-Story-Wizard-ED1-Instruct/tree/main/model-00019-of-00038.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:795b6487a358db5382af0a62eb84ebe6911b4d5788d5bf25efb95b301534acdd
3
+ size 943761344
https:/huggingface.co/DavidAU/MN-18.5B-Celeste-V1.9-Story-Wizard-ED1-Instruct/tree/main/model-00020-of-00038.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2fda237489fb3a327e9ae387b5cb59b267108f4a8061b631c0a0a530ff374dc0
3
+ size 943761344
https:/huggingface.co/DavidAU/MN-18.5B-Celeste-V1.9-Story-Wizard-ED1-Instruct/tree/main/model-00021-of-00038.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:117941cb47a90a4de444bbc9340e3d50d80733afbf207c12dd5f701170f721d7
3
+ size 943761344
https:/huggingface.co/DavidAU/MN-18.5B-Celeste-V1.9-Story-Wizard-ED1-Instruct/tree/main/model-00022-of-00038.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:56443f22dfc148f04bcb73fbed7ad7ed547f989d3c761e4e2ccca9ae3aa20239
3
+ size 943761344
https:/huggingface.co/DavidAU/MN-18.5B-Celeste-V1.9-Story-Wizard-ED1-Instruct/tree/main/model-00023-of-00038.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c6ca8613c5a08bb414a9ffbf0c3509358e444531655064c3fe2ffda52963c7d
3
+ size 985683336
https:/huggingface.co/DavidAU/MN-18.5B-Celeste-V1.9-Story-Wizard-ED1-Instruct/tree/main/model-00024-of-00038.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:73d1db1bea3661fd354864214b392e1fafea75b7b7ec4fe728c575326d1787c4
3
+ size 996189904
https:/huggingface.co/DavidAU/MN-18.5B-Celeste-V1.9-Story-Wizard-ED1-Instruct/tree/main/model-00025-of-00038.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8641fc84a1b9824f0842fe96f4c7a4e09f4984e55ace69a053b4c8822af03c8d
3
+ size 933254752
https:/huggingface.co/DavidAU/MN-18.5B-Celeste-V1.9-Story-Wizard-ED1-Instruct/tree/main/model-00026-of-00038.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:55220fef195c04013d981f8846da86254e3a1426d35605b32553db92e7960cb5
3
+ size 943761352
https:/huggingface.co/DavidAU/MN-18.5B-Celeste-V1.9-Story-Wizard-ED1-Instruct/tree/main/model-00027-of-00038.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:faa0d424cae33224f10acf4bed222e6cedb2916ab46ca3ae857d1af0e07c18ff
3
+ size 996190368
https:/huggingface.co/DavidAU/MN-18.5B-Celeste-V1.9-Story-Wizard-ED1-Instruct/tree/main/model-00028-of-00038.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:762bbfeceb25c4404d6f80dd787d8265f1e755ac29f70bc3354a3a985127974e
3
+ size 996189904
https:/huggingface.co/DavidAU/MN-18.5B-Celeste-V1.9-Story-Wizard-ED1-Instruct/tree/main/model-00029-of-00038.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3a152294c7d5bbf493dc84ecee44eed202da0638ea51c9437f4d20776532d84a
3
+ size 985694144
https:/huggingface.co/DavidAU/MN-18.5B-Celeste-V1.9-Story-Wizard-ED1-Instruct/tree/main/model-00030-of-00038.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1b40e0c8d36e8efced0a396b5e4888a22b230e8e790db459da8e00543734027e
3
+ size 943761344
https:/huggingface.co/DavidAU/MN-18.5B-Celeste-V1.9-Story-Wizard-ED1-Instruct/tree/main/model-00031-of-00038.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ab5360e7b843e2c900ec3f0a5e12f618c221b9f213fa3b6969be99092c2bed15
3
+ size 943761344
https:/huggingface.co/DavidAU/MN-18.5B-Celeste-V1.9-Story-Wizard-ED1-Instruct/tree/main/model-00032-of-00038.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1f41bb1e0e9ce1a6f58bb33d4f89cc1add277b73f8f4b7e77928fc3d4a663ad4
3
+ size 996179560
https:/huggingface.co/DavidAU/MN-18.5B-Celeste-V1.9-Story-Wizard-ED1-Instruct/tree/main/model-00033-of-00038.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ecc63b69e844a5d152bd2419c03180807d0b3126ecf1f2ab0d8f5cd56c18b4d
3
+ size 933265104
https:/huggingface.co/DavidAU/MN-18.5B-Celeste-V1.9-Story-Wizard-ED1-Instruct/tree/main/model-00034-of-00038.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:18bf2da6035b53cf861d14c1c154b148729a307b45d404e5bb98e1e098eac96a
3
+ size 943761328
https:/huggingface.co/DavidAU/MN-18.5B-Celeste-V1.9-Story-Wizard-ED1-Instruct/tree/main/model-00035-of-00038.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:13c1175e2a332f9be37a667de25d7d5f56a06b9dbd805c385a13f78df7416dca
3
+ size 943761328
https:/huggingface.co/DavidAU/MN-18.5B-Celeste-V1.9-Story-Wizard-ED1-Instruct/tree/main/model-00036-of-00038.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ff77e667b90c4887f64e275ce0cd950ece64d3625233a7fcc05c8ba5be99cd85
3
+ size 985693664
https:/huggingface.co/DavidAU/MN-18.5B-Celeste-V1.9-Story-Wizard-ED1-Instruct/tree/main/model-00037-of-00038.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2693ed3f5eda97bd3a7111e04f22d691d3f59b0b8c808c20ed64df9ce372d483
3
+ size 943761336
https:/huggingface.co/DavidAU/MN-18.5B-Celeste-V1.9-Story-Wizard-ED1-Instruct/tree/main/model-00038-of-00038.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a9e5e3ce3b44306d912fc98b123526b56572937a7da7aa2102b0b53e1e330e9a
3
+ size 796950216
https:/huggingface.co/DavidAU/MN-18.5B-Celeste-V1.9-Story-Wizard-ED1-Instruct/tree/main/model.safetensors.index.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"metadata": {"mergekit_version": "0.0.4.4", "total_size": 37037004800}, "weight_map": {"lm_head.weight": "model-00001-of-00038.safetensors", "model.embed_tokens.weight": "model-00002-of-00038.safetensors", "model.layers.0.input_layernorm.weight": "model-00003-of-00038.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00003-of-00038.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00003-of-00038.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00003-of-00038.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00003-of-00038.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00003-of-00038.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00003-of-00038.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00003-of-00038.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00003-of-00038.safetensors", "model.layers.1.input_layernorm.weight": "model-00003-of-00038.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00003-of-00038.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00003-of-00038.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00003-of-00038.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00003-of-00038.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00003-of-00038.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00004-of-00038.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00004-of-00038.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00004-of-00038.safetensors", "model.layers.16.input_layernorm.weight": "model-00004-of-00038.safetensors", "model.layers.10.input_layernorm.weight": "model-00004-of-00038.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00004-of-00038.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00004-of-00038.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00004-of-00038.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00004-of-00038.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00004-of-00038.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00004-of-00038.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00038.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00004-of-00038.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00038.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00004-of-00038.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00005-of-00038.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00005-of-00038.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00005-of-00038.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00005-of-00038.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00005-of-00038.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00005-of-00038.safetensors", "model.layers.17.input_layernorm.weight": "model-00005-of-00038.safetensors", "model.layers.11.input_layernorm.weight": "model-00005-of-00038.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00005-of-00038.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00005-of-00038.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00005-of-00038.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00005-of-00038.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00005-of-00038.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00006-of-00038.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00006-of-00038.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00006-of-00038.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00006-of-00038.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00006-of-00038.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00006-of-00038.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00006-of-00038.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00006-of-00038.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00006-of-00038.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00006-of-00038.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00006-of-00038.safetensors", "model.layers.18.input_layernorm.weight": "model-00006-of-00038.safetensors", "model.layers.12.input_layernorm.weight": "model-00006-of-00038.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00006-of-00038.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00006-of-00038.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00006-of-00038.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00006-of-00038.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00007-of-00038.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00007-of-00038.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00007-of-00038.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00007-of-00038.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00007-of-00038.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00007-of-00038.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00007-of-00038.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00007-of-00038.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00007-of-00038.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00007-of-00038.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00007-of-00038.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00007-of-00038.safetensors", "model.layers.19.input_layernorm.weight": "model-00007-of-00038.safetensors", "model.layers.13.input_layernorm.weight": "model-00007-of-00038.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00007-of-00038.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00007-of-00038.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00007-of-00038.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00008-of-00038.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00008-of-00038.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00008-of-00038.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00008-of-00038.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00008-of-00038.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00008-of-00038.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00008-of-00038.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00008-of-00038.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00008-of-00038.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00008-of-00038.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00008-of-00038.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00008-of-00038.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00008-of-00038.safetensors", "model.layers.30.input_layernorm.weight": "model-00008-of-00038.safetensors", "model.layers.20.input_layernorm.weight": "model-00008-of-00038.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00008-of-00038.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00008-of-00038.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00009-of-00038.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00009-of-00038.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00009-of-00038.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00009-of-00038.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00009-of-00038.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00009-of-00038.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00009-of-00038.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00009-of-00038.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00009-of-00038.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00009-of-00038.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00009-of-00038.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00009-of-00038.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00009-of-00038.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00009-of-00038.safetensors", "model.layers.31.input_layernorm.weight": "model-00009-of-00038.safetensors", "model.layers.21.input_layernorm.weight": "model-00009-of-00038.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00009-of-00038.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00010-of-00038.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00010-of-00038.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00010-of-00038.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00010-of-00038.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00010-of-00038.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00010-of-00038.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00010-of-00038.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00010-of-00038.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00010-of-00038.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00010-of-00038.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00010-of-00038.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00010-of-00038.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00010-of-00038.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00010-of-00038.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00010-of-00038.safetensors", "model.layers.32.input_layernorm.weight": "model-00010-of-00038.safetensors", "model.layers.22.input_layernorm.weight": "model-00010-of-00038.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00011-of-00038.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00011-of-00038.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00011-of-00038.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00011-of-00038.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00011-of-00038.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00011-of-00038.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00011-of-00038.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00011-of-00038.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00011-of-00038.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00011-of-00038.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00011-of-00038.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00011-of-00038.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00012-of-00038.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00012-of-00038.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00012-of-00038.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00012-of-00038.safetensors", "model.layers.33.input_layernorm.weight": "model-00012-of-00038.safetensors", "model.layers.23.input_layernorm.weight": "model-00012-of-00038.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00012-of-00038.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00012-of-00038.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00012-of-00038.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00012-of-00038.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00012-of-00038.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00012-of-00038.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00012-of-00038.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00012-of-00038.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00012-of-00038.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00013-of-00038.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00013-of-00038.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00013-of-00038.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00013-of-00038.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00013-of-00038.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00013-of-00038.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00013-of-00038.safetensors", "model.layers.34.input_layernorm.weight": "model-00013-of-00038.safetensors", "model.layers.24.input_layernorm.weight": "model-00013-of-00038.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00013-of-00038.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00013-of-00038.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00013-of-00038.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00013-of-00038.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00013-of-00038.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00014-of-00038.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00014-of-00038.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00014-of-00038.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00014-of-00038.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00014-of-00038.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00014-of-00038.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00014-of-00038.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00014-of-00038.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00014-of-00038.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00014-of-00038.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00014-of-00038.safetensors", "model.layers.35.input_layernorm.weight": "model-00014-of-00038.safetensors", "model.layers.25.input_layernorm.weight": "model-00014-of-00038.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00014-of-00038.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00014-of-00038.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00014-of-00038.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00014-of-00038.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00015-of-00038.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00015-of-00038.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00015-of-00038.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00015-of-00038.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00015-of-00038.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00015-of-00038.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00015-of-00038.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00015-of-00038.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00015-of-00038.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00015-of-00038.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00015-of-00038.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00015-of-00038.safetensors", "model.layers.2.input_layernorm.weight": "model-00015-of-00038.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00015-of-00038.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00015-of-00038.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00015-of-00038.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00015-of-00038.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00015-of-00038.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00015-of-00038.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00016-of-00038.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00016-of-00038.safetensors", "model.layers.36.input_layernorm.weight": "model-00016-of-00038.safetensors", "model.layers.26.input_layernorm.weight": "model-00016-of-00038.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00016-of-00038.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00016-of-00038.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00016-of-00038.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00016-of-00038.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00016-of-00038.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00016-of-00038.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00016-of-00038.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00016-of-00038.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00016-of-00038.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00016-of-00038.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00016-of-00038.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00017-of-00038.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00017-of-00038.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00017-of-00038.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00017-of-00038.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00017-of-00038.safetensors", "model.layers.37.input_layernorm.weight": "model-00017-of-00038.safetensors", "model.layers.27.input_layernorm.weight": "model-00017-of-00038.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00017-of-00038.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00017-of-00038.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00017-of-00038.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00017-of-00038.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00017-of-00038.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00018-of-00038.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00018-of-00038.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00018-of-00038.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00018-of-00038.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00018-of-00038.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00018-of-00038.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00018-of-00038.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00018-of-00038.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00018-of-00038.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00018-of-00038.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00018-of-00038.safetensors", "model.layers.38.input_layernorm.weight": "model-00018-of-00038.safetensors", "model.layers.28.input_layernorm.weight": "model-00018-of-00038.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00018-of-00038.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00018-of-00038.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00018-of-00038.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00018-of-00038.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00019-of-00038.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00019-of-00038.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00019-of-00038.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00019-of-00038.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00019-of-00038.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00019-of-00038.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00019-of-00038.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00019-of-00038.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00019-of-00038.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00019-of-00038.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00019-of-00038.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00019-of-00038.safetensors", "model.layers.39.input_layernorm.weight": "model-00019-of-00038.safetensors", "model.layers.29.input_layernorm.weight": "model-00019-of-00038.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00019-of-00038.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00019-of-00038.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00019-of-00038.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00020-of-00038.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00020-of-00038.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00020-of-00038.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00020-of-00038.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00020-of-00038.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00020-of-00038.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00020-of-00038.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00020-of-00038.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00020-of-00038.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00020-of-00038.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00020-of-00038.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00020-of-00038.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00020-of-00038.safetensors", "model.layers.47.input_layernorm.weight": "model-00020-of-00038.safetensors", "model.layers.40.input_layernorm.weight": "model-00020-of-00038.safetensors", "model.layers.47.mlp.down_proj.weight": "model-00020-of-00038.safetensors", "model.layers.40.mlp.down_proj.weight": "model-00020-of-00038.safetensors", "model.layers.47.mlp.gate_proj.weight": "model-00021-of-00038.safetensors", "model.layers.40.mlp.gate_proj.weight": "model-00021-of-00038.safetensors", "model.layers.47.mlp.up_proj.weight": "model-00021-of-00038.safetensors", "model.layers.40.mlp.up_proj.weight": "model-00021-of-00038.safetensors", "model.layers.47.post_attention_layernorm.weight": "model-00021-of-00038.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00021-of-00038.safetensors", "model.layers.47.self_attn.k_proj.weight": "model-00021-of-00038.safetensors", "model.layers.40.self_attn.k_proj.weight": "model-00021-of-00038.safetensors", "model.layers.47.self_attn.o_proj.weight": "model-00021-of-00038.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00021-of-00038.safetensors", "model.layers.47.self_attn.q_proj.weight": "model-00021-of-00038.safetensors", "model.layers.40.self_attn.q_proj.weight": "model-00021-of-00038.safetensors", "model.layers.47.self_attn.v_proj.weight": "model-00021-of-00038.safetensors", "model.layers.40.self_attn.v_proj.weight": "model-00021-of-00038.safetensors", "model.layers.48.input_layernorm.weight": "model-00021-of-00038.safetensors", "model.layers.41.input_layernorm.weight": "model-00021-of-00038.safetensors", "model.layers.48.mlp.down_proj.weight": "model-00021-of-00038.safetensors", "model.layers.41.mlp.down_proj.weight": "model-00022-of-00038.safetensors", "model.layers.48.mlp.gate_proj.weight": "model-00022-of-00038.safetensors", "model.layers.41.mlp.gate_proj.weight": "model-00022-of-00038.safetensors", "model.layers.48.mlp.up_proj.weight": "model-00022-of-00038.safetensors", "model.layers.41.mlp.up_proj.weight": "model-00022-of-00038.safetensors", "model.layers.48.post_attention_layernorm.weight": "model-00022-of-00038.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00022-of-00038.safetensors", "model.layers.48.self_attn.k_proj.weight": "model-00022-of-00038.safetensors", "model.layers.41.self_attn.k_proj.weight": "model-00022-of-00038.safetensors", "model.layers.48.self_attn.o_proj.weight": "model-00022-of-00038.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00022-of-00038.safetensors", "model.layers.48.self_attn.q_proj.weight": "model-00022-of-00038.safetensors", "model.layers.41.self_attn.q_proj.weight": "model-00022-of-00038.safetensors", "model.layers.48.self_attn.v_proj.weight": "model-00022-of-00038.safetensors", "model.layers.41.self_attn.v_proj.weight": "model-00022-of-00038.safetensors", "model.layers.49.input_layernorm.weight": "model-00022-of-00038.safetensors", "model.layers.42.input_layernorm.weight": "model-00022-of-00038.safetensors", "model.layers.49.mlp.down_proj.weight": "model-00023-of-00038.safetensors", "model.layers.42.mlp.down_proj.weight": "model-00023-of-00038.safetensors", "model.layers.49.mlp.gate_proj.weight": "model-00023-of-00038.safetensors", "model.layers.42.mlp.gate_proj.weight": "model-00023-of-00038.safetensors", "model.layers.49.mlp.up_proj.weight": "model-00023-of-00038.safetensors", "model.layers.42.mlp.up_proj.weight": "model-00023-of-00038.safetensors", "model.layers.49.post_attention_layernorm.weight": "model-00023-of-00038.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00023-of-00038.safetensors", "model.layers.49.self_attn.k_proj.weight": "model-00023-of-00038.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00023-of-00038.safetensors", "model.layers.49.self_attn.o_proj.weight": "model-00023-of-00038.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00023-of-00038.safetensors", "model.layers.49.self_attn.q_proj.weight": "model-00024-of-00038.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00024-of-00038.safetensors", "model.layers.49.self_attn.v_proj.weight": "model-00024-of-00038.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00024-of-00038.safetensors", "model.layers.50.input_layernorm.weight": "model-00024-of-00038.safetensors", "model.layers.43.input_layernorm.weight": "model-00024-of-00038.safetensors", "model.layers.50.mlp.down_proj.weight": "model-00024-of-00038.safetensors", "model.layers.43.mlp.down_proj.weight": "model-00024-of-00038.safetensors", "model.layers.50.mlp.gate_proj.weight": "model-00024-of-00038.safetensors", "model.layers.43.mlp.gate_proj.weight": "model-00024-of-00038.safetensors", "model.layers.50.mlp.up_proj.weight": "model-00024-of-00038.safetensors", "model.layers.43.mlp.up_proj.weight": "model-00024-of-00038.safetensors", "model.layers.50.post_attention_layernorm.weight": "model-00024-of-00038.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00024-of-00038.safetensors", "model.layers.50.self_attn.k_proj.weight": "model-00024-of-00038.safetensors", "model.layers.43.self_attn.k_proj.weight": "model-00025-of-00038.safetensors", "model.layers.50.self_attn.o_proj.weight": "model-00025-of-00038.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00025-of-00038.safetensors", "model.layers.50.self_attn.q_proj.weight": "model-00025-of-00038.safetensors", "model.layers.43.self_attn.q_proj.weight": "model-00025-of-00038.safetensors", "model.layers.50.self_attn.v_proj.weight": "model-00025-of-00038.safetensors", "model.layers.43.self_attn.v_proj.weight": "model-00025-of-00038.safetensors", "model.layers.51.input_layernorm.weight": "model-00025-of-00038.safetensors", "model.layers.44.input_layernorm.weight": "model-00025-of-00038.safetensors", "model.layers.51.mlp.down_proj.weight": "model-00025-of-00038.safetensors", "model.layers.44.mlp.down_proj.weight": "model-00025-of-00038.safetensors", "model.layers.51.mlp.gate_proj.weight": "model-00025-of-00038.safetensors", "model.layers.44.mlp.gate_proj.weight": "model-00025-of-00038.safetensors", "model.layers.51.mlp.up_proj.weight": "model-00025-of-00038.safetensors", "model.layers.44.mlp.up_proj.weight": "model-00026-of-00038.safetensors", "model.layers.51.post_attention_layernorm.weight": "model-00026-of-00038.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00026-of-00038.safetensors", "model.layers.51.self_attn.k_proj.weight": "model-00026-of-00038.safetensors", "model.layers.44.self_attn.k_proj.weight": "model-00026-of-00038.safetensors", "model.layers.51.self_attn.o_proj.weight": "model-00026-of-00038.safetensors", "model.layers.44.self_attn.o_proj.weight": "model-00026-of-00038.safetensors", "model.layers.51.self_attn.q_proj.weight": "model-00026-of-00038.safetensors", "model.layers.44.self_attn.q_proj.weight": "model-00026-of-00038.safetensors", "model.layers.51.self_attn.v_proj.weight": "model-00026-of-00038.safetensors", "model.layers.44.self_attn.v_proj.weight": "model-00026-of-00038.safetensors", "model.layers.52.input_layernorm.weight": "model-00026-of-00038.safetensors", "model.layers.45.input_layernorm.weight": "model-00026-of-00038.safetensors", "model.layers.52.mlp.down_proj.weight": "model-00026-of-00038.safetensors", "model.layers.45.mlp.down_proj.weight": "model-00026-of-00038.safetensors", "model.layers.52.mlp.gate_proj.weight": "model-00026-of-00038.safetensors", "model.layers.45.mlp.gate_proj.weight": "model-00026-of-00038.safetensors", "model.layers.52.mlp.up_proj.weight": "model-00027-of-00038.safetensors", "model.layers.45.mlp.up_proj.weight": "model-00027-of-00038.safetensors", "model.layers.52.post_attention_layernorm.weight": "model-00027-of-00038.safetensors", "model.layers.45.post_attention_layernorm.weight": "model-00027-of-00038.safetensors", "model.layers.52.self_attn.k_proj.weight": "model-00027-of-00038.safetensors", "model.layers.45.self_attn.k_proj.weight": "model-00027-of-00038.safetensors", "model.layers.52.self_attn.o_proj.weight": "model-00027-of-00038.safetensors", "model.layers.45.self_attn.o_proj.weight": "model-00027-of-00038.safetensors", "model.layers.52.self_attn.q_proj.weight": "model-00027-of-00038.safetensors", "model.layers.45.self_attn.q_proj.weight": "model-00027-of-00038.safetensors", "model.layers.52.self_attn.v_proj.weight": "model-00027-of-00038.safetensors", "model.layers.45.self_attn.v_proj.weight": "model-00027-of-00038.safetensors", "model.layers.3.input_layernorm.weight": "model-00027-of-00038.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00027-of-00038.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00027-of-00038.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00027-of-00038.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00027-of-00038.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00027-of-00038.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00027-of-00038.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00028-of-00038.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00028-of-00038.safetensors", "model.layers.53.input_layernorm.weight": "model-00028-of-00038.safetensors", "model.layers.46.input_layernorm.weight": "model-00028-of-00038.safetensors", "model.layers.53.mlp.down_proj.weight": "model-00028-of-00038.safetensors", "model.layers.46.mlp.down_proj.weight": "model-00028-of-00038.safetensors", "model.layers.53.mlp.gate_proj.weight": "model-00028-of-00038.safetensors", "model.layers.46.mlp.gate_proj.weight": "model-00028-of-00038.safetensors", "model.layers.53.mlp.up_proj.weight": "model-00028-of-00038.safetensors", "model.layers.46.mlp.up_proj.weight": "model-00028-of-00038.safetensors", "model.layers.53.post_attention_layernorm.weight": "model-00028-of-00038.safetensors", "model.layers.46.post_attention_layernorm.weight": "model-00028-of-00038.safetensors", "model.layers.53.self_attn.k_proj.weight": "model-00028-of-00038.safetensors", "model.layers.46.self_attn.k_proj.weight": "model-00028-of-00038.safetensors", "model.layers.53.self_attn.o_proj.weight": "model-00028-of-00038.safetensors", "model.layers.46.self_attn.o_proj.weight": "model-00029-of-00038.safetensors", "model.layers.53.self_attn.q_proj.weight": "model-00029-of-00038.safetensors", "model.layers.46.self_attn.q_proj.weight": "model-00029-of-00038.safetensors", "model.layers.53.self_attn.v_proj.weight": "model-00029-of-00038.safetensors", "model.layers.46.self_attn.v_proj.weight": "model-00029-of-00038.safetensors", "model.layers.54.input_layernorm.weight": "model-00029-of-00038.safetensors", "model.layers.54.mlp.down_proj.weight": "model-00029-of-00038.safetensors", "model.layers.54.mlp.gate_proj.weight": "model-00029-of-00038.safetensors", "model.layers.54.mlp.up_proj.weight": "model-00029-of-00038.safetensors", "model.layers.54.post_attention_layernorm.weight": "model-00029-of-00038.safetensors", "model.layers.54.self_attn.k_proj.weight": "model-00029-of-00038.safetensors", "model.layers.54.self_attn.o_proj.weight": "model-00029-of-00038.safetensors", "model.layers.54.self_attn.q_proj.weight": "model-00029-of-00038.safetensors", "model.layers.54.self_attn.v_proj.weight": "model-00029-of-00038.safetensors", "model.layers.55.input_layernorm.weight": "model-00029-of-00038.safetensors", "model.layers.55.mlp.down_proj.weight": "model-00029-of-00038.safetensors", "model.layers.55.mlp.gate_proj.weight": "model-00029-of-00038.safetensors", "model.layers.55.mlp.up_proj.weight": "model-00030-of-00038.safetensors", "model.layers.55.post_attention_layernorm.weight": "model-00030-of-00038.safetensors", "model.layers.55.self_attn.k_proj.weight": "model-00030-of-00038.safetensors", "model.layers.55.self_attn.o_proj.weight": "model-00030-of-00038.safetensors", "model.layers.55.self_attn.q_proj.weight": "model-00030-of-00038.safetensors", "model.layers.55.self_attn.v_proj.weight": "model-00030-of-00038.safetensors", "model.layers.56.input_layernorm.weight": "model-00030-of-00038.safetensors", "model.layers.56.mlp.down_proj.weight": "model-00030-of-00038.safetensors", "model.layers.56.mlp.gate_proj.weight": "model-00030-of-00038.safetensors", "model.layers.56.mlp.up_proj.weight": "model-00030-of-00038.safetensors", "model.layers.56.post_attention_layernorm.weight": "model-00030-of-00038.safetensors", "model.layers.56.self_attn.k_proj.weight": "model-00030-of-00038.safetensors", "model.layers.56.self_attn.o_proj.weight": "model-00030-of-00038.safetensors", "model.layers.56.self_attn.q_proj.weight": "model-00030-of-00038.safetensors", "model.layers.56.self_attn.v_proj.weight": "model-00030-of-00038.safetensors", "model.layers.57.input_layernorm.weight": "model-00030-of-00038.safetensors", "model.layers.57.mlp.down_proj.weight": "model-00030-of-00038.safetensors", "model.layers.57.mlp.gate_proj.weight": "model-00031-of-00038.safetensors", "model.layers.57.mlp.up_proj.weight": "model-00031-of-00038.safetensors", "model.layers.57.post_attention_layernorm.weight": "model-00031-of-00038.safetensors", "model.layers.57.self_attn.k_proj.weight": "model-00031-of-00038.safetensors", "model.layers.57.self_attn.o_proj.weight": "model-00031-of-00038.safetensors", "model.layers.57.self_attn.q_proj.weight": "model-00031-of-00038.safetensors", "model.layers.57.self_attn.v_proj.weight": "model-00031-of-00038.safetensors", "model.layers.58.input_layernorm.weight": "model-00031-of-00038.safetensors", "model.layers.58.mlp.down_proj.weight": "model-00031-of-00038.safetensors", "model.layers.58.mlp.gate_proj.weight": "model-00031-of-00038.safetensors", "model.layers.58.mlp.up_proj.weight": "model-00031-of-00038.safetensors", "model.layers.58.post_attention_layernorm.weight": "model-00031-of-00038.safetensors", "model.layers.58.self_attn.k_proj.weight": "model-00031-of-00038.safetensors", "model.layers.58.self_attn.o_proj.weight": "model-00031-of-00038.safetensors", "model.layers.58.self_attn.q_proj.weight": "model-00031-of-00038.safetensors", "model.layers.58.self_attn.v_proj.weight": "model-00031-of-00038.safetensors", "model.layers.59.input_layernorm.weight": "model-00031-of-00038.safetensors", "model.layers.59.mlp.down_proj.weight": "model-00032-of-00038.safetensors", "model.layers.59.mlp.gate_proj.weight": "model-00032-of-00038.safetensors", "model.layers.59.mlp.up_proj.weight": "model-00032-of-00038.safetensors", "model.layers.59.post_attention_layernorm.weight": "model-00032-of-00038.safetensors", "model.layers.59.self_attn.k_proj.weight": "model-00032-of-00038.safetensors", "model.layers.59.self_attn.o_proj.weight": "model-00032-of-00038.safetensors", "model.layers.59.self_attn.q_proj.weight": "model-00032-of-00038.safetensors", "model.layers.59.self_attn.v_proj.weight": "model-00032-of-00038.safetensors", "model.layers.60.input_layernorm.weight": "model-00032-of-00038.safetensors", "model.layers.60.mlp.down_proj.weight": "model-00032-of-00038.safetensors", "model.layers.60.mlp.gate_proj.weight": "model-00032-of-00038.safetensors", "model.layers.60.mlp.up_proj.weight": "model-00032-of-00038.safetensors", "model.layers.60.post_attention_layernorm.weight": "model-00032-of-00038.safetensors", "model.layers.60.self_attn.k_proj.weight": "model-00032-of-00038.safetensors", "model.layers.60.self_attn.o_proj.weight": "model-00033-of-00038.safetensors", "model.layers.60.self_attn.q_proj.weight": "model-00033-of-00038.safetensors", "model.layers.60.self_attn.v_proj.weight": "model-00033-of-00038.safetensors", "model.layers.61.input_layernorm.weight": "model-00033-of-00038.safetensors", "model.layers.61.mlp.down_proj.weight": "model-00033-of-00038.safetensors", "model.layers.61.mlp.gate_proj.weight": "model-00033-of-00038.safetensors", "model.layers.61.mlp.up_proj.weight": "model-00033-of-00038.safetensors", "model.layers.61.post_attention_layernorm.weight": "model-00033-of-00038.safetensors", "model.layers.61.self_attn.k_proj.weight": "model-00033-of-00038.safetensors", "model.layers.61.self_attn.o_proj.weight": "model-00033-of-00038.safetensors", "model.layers.61.self_attn.q_proj.weight": "model-00033-of-00038.safetensors", "model.layers.61.self_attn.v_proj.weight": "model-00033-of-00038.safetensors", "model.layers.62.input_layernorm.weight": "model-00033-of-00038.safetensors", "model.layers.62.mlp.down_proj.weight": "model-00033-of-00038.safetensors", "model.layers.62.mlp.gate_proj.weight": "model-00033-of-00038.safetensors", "model.layers.62.mlp.up_proj.weight": "model-00034-of-00038.safetensors", "model.layers.62.post_attention_layernorm.weight": "model-00034-of-00038.safetensors", "model.layers.62.self_attn.k_proj.weight": "model-00034-of-00038.safetensors", "model.layers.62.self_attn.o_proj.weight": "model-00034-of-00038.safetensors", "model.layers.62.self_attn.q_proj.weight": "model-00034-of-00038.safetensors", "model.layers.62.self_attn.v_proj.weight": "model-00034-of-00038.safetensors", "model.layers.4.input_layernorm.weight": "model-00034-of-00038.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00034-of-00038.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00034-of-00038.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00034-of-00038.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00034-of-00038.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00034-of-00038.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00034-of-00038.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00034-of-00038.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00034-of-00038.safetensors", "model.layers.5.input_layernorm.weight": "model-00034-of-00038.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00034-of-00038.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00035-of-00038.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00035-of-00038.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00035-of-00038.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00035-of-00038.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00035-of-00038.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00035-of-00038.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00035-of-00038.safetensors", "model.layers.6.input_layernorm.weight": "model-00035-of-00038.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00035-of-00038.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00035-of-00038.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00035-of-00038.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00035-of-00038.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00035-of-00038.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00035-of-00038.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00035-of-00038.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00035-of-00038.safetensors", "model.layers.7.input_layernorm.weight": "model-00035-of-00038.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00036-of-00038.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00036-of-00038.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00036-of-00038.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00036-of-00038.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00036-of-00038.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00036-of-00038.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00036-of-00038.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00036-of-00038.safetensors", "model.layers.14.input_layernorm.weight": "model-00036-of-00038.safetensors", "model.layers.8.input_layernorm.weight": "model-00036-of-00038.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00036-of-00038.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00036-of-00038.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00036-of-00038.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00037-of-00038.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00037-of-00038.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00037-of-00038.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00037-of-00038.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00037-of-00038.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00037-of-00038.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00037-of-00038.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00037-of-00038.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00037-of-00038.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00037-of-00038.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00037-of-00038.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00037-of-00038.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00037-of-00038.safetensors", "model.layers.15.input_layernorm.weight": "model-00037-of-00038.safetensors", "model.layers.9.input_layernorm.weight": "model-00037-of-00038.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00037-of-00038.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00037-of-00038.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00038-of-00038.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00038-of-00038.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00038-of-00038.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00038-of-00038.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00038-of-00038.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00038-of-00038.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00038-of-00038.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00038-of-00038.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00038-of-00038.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00038-of-00038.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00038-of-00038.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00038-of-00038.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00038-of-00038.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00038-of-00038.safetensors", "model.norm.weight": "model-00038-of-00038.safetensors"}}
https:/huggingface.co/DavidAU/MN-18.5B-Celeste-V1.9-Story-Wizard-ED1-Instruct/tree/main/special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "unk_token": {
17
+ "content": "<unk>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
https:/huggingface.co/DavidAU/MN-18.5B-Celeste-V1.9-Story-Wizard-ED1-Instruct/tree/main/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
https:/huggingface.co/DavidAU/MN-18.5B-Celeste-V1.9-Story-Wizard-ED1-Instruct/tree/main/tokenizer_config.json ADDED
The diff for this file is too large to render. See raw diff