CuriousCat29 commited on
Commit
a297199
·
verified ·
1 Parent(s): 923c987

Upload folder using huggingface_hub

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. .gitattributes +1 -0
  2. README.md +57 -0
  3. config.json +37 -0
  4. mergekit_config.yml +26 -0
  5. model-00001-of-00050.safetensors +3 -0
  6. model-00002-of-00050.safetensors +3 -0
  7. model-00003-of-00050.safetensors +3 -0
  8. model-00004-of-00050.safetensors +3 -0
  9. model-00005-of-00050.safetensors +3 -0
  10. model-00006-of-00050.safetensors +3 -0
  11. model-00007-of-00050.safetensors +3 -0
  12. model-00008-of-00050.safetensors +3 -0
  13. model-00009-of-00050.safetensors +3 -0
  14. model-00010-of-00050.safetensors +3 -0
  15. model-00011-of-00050.safetensors +3 -0
  16. model-00012-of-00050.safetensors +3 -0
  17. model-00013-of-00050.safetensors +3 -0
  18. model-00014-of-00050.safetensors +3 -0
  19. model-00015-of-00050.safetensors +3 -0
  20. model-00016-of-00050.safetensors +3 -0
  21. model-00017-of-00050.safetensors +3 -0
  22. model-00018-of-00050.safetensors +3 -0
  23. model-00019-of-00050.safetensors +3 -0
  24. model-00020-of-00050.safetensors +3 -0
  25. model-00021-of-00050.safetensors +3 -0
  26. model-00022-of-00050.safetensors +3 -0
  27. model-00023-of-00050.safetensors +3 -0
  28. model-00024-of-00050.safetensors +3 -0
  29. model-00025-of-00050.safetensors +3 -0
  30. model-00026-of-00050.safetensors +3 -0
  31. model-00027-of-00050.safetensors +3 -0
  32. model-00028-of-00050.safetensors +3 -0
  33. model-00029-of-00050.safetensors +3 -0
  34. model-00030-of-00050.safetensors +3 -0
  35. model-00031-of-00050.safetensors +3 -0
  36. model-00032-of-00050.safetensors +3 -0
  37. model-00033-of-00050.safetensors +3 -0
  38. model-00034-of-00050.safetensors +3 -0
  39. model-00035-of-00050.safetensors +3 -0
  40. model-00036-of-00050.safetensors +3 -0
  41. model-00037-of-00050.safetensors +3 -0
  42. model-00038-of-00050.safetensors +3 -0
  43. model-00039-of-00050.safetensors +3 -0
  44. model-00040-of-00050.safetensors +3 -0
  45. model-00041-of-00050.safetensors +3 -0
  46. model-00042-of-00050.safetensors +3 -0
  47. model-00043-of-00050.safetensors +3 -0
  48. model-00044-of-00050.safetensors +3 -0
  49. model-00045-of-00050.safetensors +3 -0
  50. model-00046-of-00050.safetensors +3 -0
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model:
3
+ - TheDrummer/Fallen-Llama-3.3-70B-v1
4
+ - TheDrummer/Anubis-70B-v1.1
5
+ library_name: transformers
6
+ tags:
7
+ - mergekit
8
+ - merge
9
+
10
+ ---
11
+ # merged
12
+
13
+ This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
14
+
15
+ ## Merge Details
16
+ ### Merge Method
17
+
18
+ This model was merged using the Passthrough merge method.
19
+
20
+ ### Models Merged
21
+
22
+ The following models were included in the merge:
23
+ * [TheDrummer/Fallen-Llama-3.3-70B-v1](https://huggingface.co/TheDrummer/Fallen-Llama-3.3-70B-v1)
24
+ * [TheDrummer/Anubis-70B-v1.1](https://huggingface.co/TheDrummer/Anubis-70B-v1.1)
25
+
26
+ ### Configuration
27
+
28
+ The following YAML configuration was used to produce this model:
29
+
30
+ ```yaml
31
+ dtype: bfloat16
32
+ merge_method: passthrough
33
+ modules:
34
+ default:
35
+ slices:
36
+ - sources:
37
+ - layer_range: [0, 20]
38
+ model: TheDrummer/Fallen-Llama-3.3-70B-v1
39
+ - sources:
40
+ - layer_range: [10, 30]
41
+ model: TheDrummer/Anubis-70B-v1.1
42
+ - sources:
43
+ - layer_range: [20, 40]
44
+ model: TheDrummer/Fallen-Llama-3.3-70B-v1
45
+ - sources:
46
+ - layer_range: [30, 50]
47
+ model: TheDrummer/Anubis-70B-v1.1
48
+ - sources:
49
+ - layer_range: [40, 60]
50
+ model: TheDrummer/Fallen-Llama-3.3-70B-v1
51
+ - sources:
52
+ - layer_range: [50, 70]
53
+ model: TheDrummer/Anubis-70B-v1.1
54
+ - sources:
55
+ - layer_range: [60, 80]
56
+ model: TheDrummer/Fallen-Llama-3.3-70B-v1
57
+ ```
config.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "LlamaForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 128000,
8
+ "eos_token_id": 128009,
9
+ "head_dim": 128,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 8192,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 28672,
14
+ "max_position_embeddings": 131072,
15
+ "mlp_bias": false,
16
+ "model_type": "llama",
17
+ "num_attention_heads": 64,
18
+ "num_hidden_layers": 140,
19
+ "num_key_value_heads": 8,
20
+ "pad_token_id": 128004,
21
+ "pretraining_tp": 1,
22
+ "rms_norm_eps": 1e-05,
23
+ "rope_scaling": {
24
+ "factor": 8.0,
25
+ "high_freq_factor": 4.0,
26
+ "low_freq_factor": 1.0,
27
+ "original_max_position_embeddings": 8192,
28
+ "rope_type": "llama3"
29
+ },
30
+ "rope_theta": 500000.0,
31
+ "tie_word_embeddings": false,
32
+ "torch_dtype": "bfloat16",
33
+ "transformers_version": "4.53.0",
34
+ "unsloth_fixed": true,
35
+ "use_cache": true,
36
+ "vocab_size": 128256
37
+ }
mergekit_config.yml ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ dtype: bfloat16
2
+ merge_method: passthrough
3
+ modules:
4
+ default:
5
+ slices:
6
+ - sources:
7
+ - layer_range: [0, 20]
8
+ model: TheDrummer/Fallen-Llama-3.3-70B-v1
9
+ - sources:
10
+ - layer_range: [10, 30]
11
+ model: TheDrummer/Anubis-70B-v1.1
12
+ - sources:
13
+ - layer_range: [20, 40]
14
+ model: TheDrummer/Fallen-Llama-3.3-70B-v1
15
+ - sources:
16
+ - layer_range: [30, 50]
17
+ model: TheDrummer/Anubis-70B-v1.1
18
+ - sources:
19
+ - layer_range: [40, 60]
20
+ model: TheDrummer/Fallen-Llama-3.3-70B-v1
21
+ - sources:
22
+ - layer_range: [50, 70]
23
+ model: TheDrummer/Anubis-70B-v1.1
24
+ - sources:
25
+ - layer_range: [60, 80]
26
+ model: TheDrummer/Fallen-Llama-3.3-70B-v1
model-00001-of-00050.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:985f23c68602f9dcd77c92f0049127d865c0e4fb02dfac529b08310ef06e9e0f
3
+ size 4672471504
model-00002-of-00050.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de725e47f4911b7c48a44f5db5db49e7baf352e44677b68b48eb48fc04dfa8e5
3
+ size 4831922704
model-00003-of-00050.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4eb0981794a8403d93a5023278cd26a08ba575412d5925c6a8d65e5a17af65de
3
+ size 4966190768
model-00004-of-00050.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6c528be5011b3997f30da7b2d25d0ab6168a17681ab0f810b1309d3496012612
3
+ size 4831906224
model-00005-of-00050.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:285e0605f8980650129696c4905dc66018eca29010ebe0c296466c93d669bbc3
3
+ size 4999711736
model-00006-of-00050.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dabedb7f3e252464808efd8fb36023f170da4bee62e1e0bc22c4cfa5acaef701
3
+ size 4798385256
model-00007-of-00050.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:728ce4ac75bf7393e45be7dd47ad2e1f580a297d53f426ca3e13980f269ae8ec
3
+ size 4831906216
model-00008-of-00050.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:04916d293b57e4af5d24374668990e0ad7eaeddab073f5c1214356d36ebd4972
3
+ size 4966190760
model-00009-of-00050.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:afacdaa7d5e8f0209c36d55794472709d513090887b152b0350293e2a9fd550e
3
+ size 4664167408
model-00010-of-00050.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e3ad3f415ec0e3b995c655f2135d95077d7cf47e179024128753b2eeefdae433
3
+ size 4831906224
model-00011-of-00050.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a7f0cade435532c93288376b5884c3cb5f082059f2ec29f691a6b5bdeb0cf3c
3
+ size 4999711736
model-00012-of-00050.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dd6b5291a19c1c9083d3d49bd5231cc0ff44122da0dad3f74e1ff2f76ec32cd0
3
+ size 4798385256
model-00013-of-00050.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a319a4bdc35ea54d2fb9c2dd3fc94d474bc6b71274b5cadf51d677253b11041d
3
+ size 4831906216
model-00014-of-00050.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac9a4fbb4d473486024229f2b3d69fa4deab2c5fb30065d0cd9e670ecdffcbc3
3
+ size 4966190760
model-00015-of-00050.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9fa4dc2769e51b4e3a7a0fe9730599d3690228755cd2f41fad3b66746c730fab
3
+ size 4831906224
model-00016-of-00050.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b6b963b1c8cd99537caa1121b10ab872e4b55af6f9492ff6f4d719d3dff7c02d
3
+ size 4966174264
model-00017-of-00050.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c17b19a1ceea4a64908cb93f2bc78cf697e9c9ad9cf2311f2e135c380025006
3
+ size 4966140568
model-00018-of-00050.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:81f47c08b4660fcf85ee1ab8ea96424f64e3a973c7cd3d4bc2484af466279210
3
+ size 4999711720
model-00019-of-00050.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:450435f03c77beed2ee69b886e8ea1c4f210964bbb1c6c81164fbbd51cc2bf0b
3
+ size 4999711736
model-00020-of-00050.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:223dfe65b4b331f4ede1bfababeec94d433a92622d3b2e44fe834f52e6541b70
3
+ size 4798385256
model-00021-of-00050.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cef032507772dfb151e32dfe1c5bc1ea1366989dc4952041af35d9b19118c000
3
+ size 4831906216
model-00022-of-00050.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:523f75fc6d2e9ef435e7211a97876aa98662215bb4e8976ef78fdaab7c96449c
3
+ size 4966190760
model-00023-of-00050.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7c98e858ab0c0e4b17a0970f278cf05a1eb14a461abd841a33b2fe2226e8aec1
3
+ size 4831906224
model-00024-of-00050.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6e645212096018dccc52f7d5e23c49c951594e61efe318443da149d9064ee5d1
3
+ size 4664167400
model-00025-of-00050.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0db08959bf00a0c3d0c570c4f76d58ac956d7fb31b4ae887d952aa3d60604e7c
3
+ size 4999711736
model-00026-of-00050.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8943f952696d81a9cf57c18eb27eb59022f02675c7a5b5b7da7e91a7cc3b0d1c
3
+ size 4798385256
model-00027-of-00050.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:babd197aa69c47b0d35d42c6eabb85c6a410b7b40b77cee5aa36459f277bdf50
3
+ size 4831906216
model-00028-of-00050.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2b1768e27aa1c3aef9886b184e089eb00ac8f423b6b392c332a8d50d55c42ce2
3
+ size 4966190760
model-00029-of-00050.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd12360291b2dcf232443ea7212b069f578150c1dffe5f6c72257ac603d6c660
3
+ size 4831906224
model-00030-of-00050.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c334d44e18a4d487db08fab9d61e5f50a1661d4faf92b9f61f2fbfac7ef092b
3
+ size 4966190768
model-00031-of-00050.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:27043f88d02e6fe8859d4812b3fdee07f8825d13eb97bdd593801655e3399fc9
3
+ size 4982901392
model-00032-of-00050.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f6ac6a3e305e69b9aa74318208cf7af8adcf491b0fdeccb4f8b8ed4c50fff489
3
+ size 4982934392
model-00033-of-00050.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:69481293e11e10269ccd81b4c92456831585a08ac3d0d9b84511c55e4fd6232f
3
+ size 4999711752
model-00034-of-00050.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c3594a4255ee42a52c9cf9f13c5223a7a0ee5f89dd14c92101775ffb0a9edf50
3
+ size 4798385264
model-00035-of-00050.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:30b479f66b39ee74c17d44dd392d5561876778513351a5eb3d4c7aa0287c591d
3
+ size 4831906232
model-00036-of-00050.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d37a4dd1f0331ec5a61e1b0e9a863be8c052dec6287eefe025ae986f7e68651f
3
+ size 4966190784
model-00037-of-00050.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d6fc3e03b9e13f4b8fce2b717243a9b390d6a7a93146c5b5f53128d21f56a5fb
3
+ size 4831906232
model-00038-of-00050.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c36c55b238e098703c7d0590fb655f08a092fa2e92f8d5e0b52cbfa20bf776a
3
+ size 4966174288
model-00039-of-00050.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed9feda3c21b52b3209a3cc0ea367a39d33293a39972eef6a21bc17474aadb2d
3
+ size 4966140568
model-00040-of-00050.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:832923249841f57835488d7d84f87c727c820c19b4881abeebe45f1475538e68
3
+ size 4999711752
model-00041-of-00050.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:30fec90f1bd1c13735b612487f2adb677fe957f91aafcdcf42e3c7b61793028b
3
+ size 4999711760
model-00042-of-00050.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b5f90c3f51807eccfd7ff42075979b1daab67c2f3d88f7b0d3cafc498096de57
3
+ size 4798385280
model-00043-of-00050.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:07ce048380bf33f5ea5855415e3eb9cf91768b92ca6379e8d3283026777a2314
3
+ size 4831906240
model-00044-of-00050.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:00a5a5df8b45fa1663e81980e1970bc1032cd5860ef39043413bdbbe9e57675c
3
+ size 4966190792
model-00045-of-00050.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:09fcf2b21ae011c7968d5ed4ed28fd3c08be585287bef1fe5f407f1cea64897e
3
+ size 4831906240
model-00046-of-00050.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a3610f7675f9e9f7ab48aac392224d60a53721618ef5d9a41cb535176a767f2f
3
+ size 4966174288