CuriousCat29 commited on
Commit
163f026
·
verified ·
1 Parent(s): a4db723

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 +55 -0
  3. config.json +40 -0
  4. mergekit_config.yml +24 -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 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model:
3
+ - Doctor-Shotgun/L3.3-70B-Magnum-v4-SE
4
+ - TheDrummer/Anubis-70B-v1
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
+ * [Doctor-Shotgun/L3.3-70B-Magnum-v4-SE](https://huggingface.co/Doctor-Shotgun/L3.3-70B-Magnum-v4-SE)
24
+ * [TheDrummer/Anubis-70B-v1](https://huggingface.co/TheDrummer/Anubis-70B-v1)
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
+ slices:
34
+ - sources:
35
+ - layer_range: [0, 20]
36
+ model: Doctor-Shotgun/L3.3-70B-Magnum-v4-SE
37
+ - sources:
38
+ - layer_range: [10, 30]
39
+ model: TheDrummer/Anubis-70B-v1
40
+ - sources:
41
+ - layer_range: [20, 40]
42
+ model: Doctor-Shotgun/L3.3-70B-Magnum-v4-SE
43
+ - sources:
44
+ - layer_range: [30, 50]
45
+ model: TheDrummer/Anubis-70B-v1
46
+ - sources:
47
+ - layer_range: [40, 60]
48
+ model: Doctor-Shotgun/L3.3-70B-Magnum-v4-SE
49
+ - sources:
50
+ - layer_range: [50, 70]
51
+ model: TheDrummer/Anubis-70B-v1
52
+ - sources:
53
+ - layer_range: [60, 80]
54
+ model: Doctor-Shotgun/L3.3-70B-Magnum-v4-SE
55
+ ```
config.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "Doctor-Shotgun/L3.3-70B-Magnum-v4-SE",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 128000,
9
+ "eos_token_id": [
10
+ 128001,
11
+ 128008,
12
+ 128009
13
+ ],
14
+ "head_dim": 128,
15
+ "hidden_act": "silu",
16
+ "hidden_size": 8192,
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 28672,
19
+ "max_position_embeddings": 131072,
20
+ "mlp_bias": false,
21
+ "model_type": "llama",
22
+ "num_attention_heads": 64,
23
+ "num_hidden_layers": 140,
24
+ "num_key_value_heads": 8,
25
+ "pretraining_tp": 1,
26
+ "rms_norm_eps": 1e-05,
27
+ "rope_scaling": {
28
+ "factor": 8.0,
29
+ "high_freq_factor": 4.0,
30
+ "low_freq_factor": 1.0,
31
+ "original_max_position_embeddings": 8192,
32
+ "rope_type": "llama3"
33
+ },
34
+ "rope_theta": 500000.0,
35
+ "tie_word_embeddings": false,
36
+ "torch_dtype": "bfloat16",
37
+ "transformers_version": "4.48.1",
38
+ "use_cache": true,
39
+ "vocab_size": 128256
40
+ }
mergekit_config.yml ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ dtype: bfloat16
2
+ merge_method: passthrough
3
+ slices:
4
+ - sources:
5
+ - layer_range: [0, 20]
6
+ model: Doctor-Shotgun/L3.3-70B-Magnum-v4-SE
7
+ - sources:
8
+ - layer_range: [10, 30]
9
+ model: TheDrummer/Anubis-70B-v1
10
+ - sources:
11
+ - layer_range: [20, 40]
12
+ model: Doctor-Shotgun/L3.3-70B-Magnum-v4-SE
13
+ - sources:
14
+ - layer_range: [30, 50]
15
+ model: TheDrummer/Anubis-70B-v1
16
+ - sources:
17
+ - layer_range: [40, 60]
18
+ model: Doctor-Shotgun/L3.3-70B-Magnum-v4-SE
19
+ - sources:
20
+ - layer_range: [50, 70]
21
+ model: TheDrummer/Anubis-70B-v1
22
+ - sources:
23
+ - layer_range: [60, 80]
24
+ model: Doctor-Shotgun/L3.3-70B-Magnum-v4-SE
model-00001-of-00050.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:947df7ef185036ad0e010fb47c3b8e86311f3bcab77af70efa2adeb9cfcbfdc0
3
+ size 4672471504
model-00002-of-00050.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:83c0a00b186e397a7a54b0ca8ea52d5762b6bd69deb3768cac37bcefe981e791
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:d0b92f69294175ff65a63e0e671fe9c3baee9fabf781cf673b21ebed9f39c68b
3
+ size 4966190768
model-00004-of-00050.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:087742d636cdf0304655627741579209efda03283e71dbe2e49afe4bf7148e5d
3
+ size 4831906224
model-00005-of-00050.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1225420e943793fc14cee4ae4f22e6671cab446e4b1f7debdf958ec8fb816ba1
3
+ size 4999711744
model-00006-of-00050.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d04a994249dffdcfcde5541d4c71d34d484fea57b542f8159f64f9b8fbb7f1bf
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:c8ff0e271f4cc62263846622354b18474c3f08f042e31c07bacd78d99c6894e3
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:ad258575793a41d7b01678d31db1d1a8590bd0dbc37b59efd43c796c8a3b2074
3
+ size 4966190768
model-00009-of-00050.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3d73c5d2126763087f2952884bfd011a818da4269ca9fe276ced7539c8285f03
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:ed957bfb179a096f5c37453605682529ffaca7b9c068474ddd3b46fee8f9df5d
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:b3bfaf322344f50cee931843a64136e4a51838027a9dd049d6661c9ba3143b1d
3
+ size 4999711744
model-00012-of-00050.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f59fadda32f257d78a2278b77b017c96b427caabb2c40250ac86dbc4d99cae6
3
+ size 4798385256
model-00013-of-00050.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:721b3c707e8e09dfccbc5872c9cea2a23501b56353525a2ca67023d22086199b
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:accf4c6c92894fa99261eee19730dcc436e1caac00bc2c34be64ed1fe0cbe69e
3
+ size 4966190768
model-00015-of-00050.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e37594df8f0454e775592d490f7444b277df0610333d13661c619b9f94be9dc6
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:eec472ff9a6de29673f1d6158ce2ddc81311796add7d4aab2a783e9cbb8d20a2
3
+ size 4966174264
model-00017-of-00050.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4d8e5ee6299a8c23e05db053d4413eb946d9454b6c5eb7965e2d9ab42fef42ff
3
+ size 4966140568
model-00018-of-00050.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ecd35e8621e51411b0f8e83e5e76fe2d99fb1f43fdb5892abf913536deba28a
3
+ size 4999711728
model-00019-of-00050.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:69acd545f71123fe0acd4c6c3da31eec034421df4eda320cc62f04116ef63e3a
3
+ size 4999711744
model-00020-of-00050.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3fcb70af8009d1cd718dfea24ff5691616c1fb5830d246efec7fca1a0050d42f
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:bbdf38a6d5861f9082db7398e5fd56b1ba5f6b13a313caeeb83265e607387661
3
+ size 4831906216
model-00022-of-00050.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:44284de4524a8be58d13468c44acdeaf834ae1525789a0c681a9b2be22670a42
3
+ size 4966190768
model-00023-of-00050.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d46207f1aa58bf36a454f464ba467a78b43ed326a2582b47c02ba9f1e5b0f823
3
+ size 4831906224
model-00024-of-00050.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:82e3ff5352f8dd317fa30b92abe976a9ee3ba0f846c90d184e6f5098d2842f83
3
+ size 4664167400
model-00025-of-00050.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2ac25a25d61237d0ed5c813a1dc70d12e0a39fbfa4fe4a6d2770f5af7548a1dd
3
+ size 4999711744
model-00026-of-00050.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:126b8cb332adc5f9ccea863753db4222dd95b5e0f70eb0a9f5d4ea68fe6e61f9
3
+ size 4798385256
model-00027-of-00050.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:264a9e52f85248dabdc1e886204c36b2035b5e13a8d48ba14844b5bd58df753c
3
+ size 4831906216
model-00028-of-00050.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e21fdb2b9314c7363691e9f22116385fddc80cc507f16e11d9d0dc6cc275cff
3
+ size 4966190768
model-00029-of-00050.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5aed730d172f30e2b0630f48158e1f70d9366236b7f9bd5419873e057f9c93b6
3
+ size 4831906224
model-00030-of-00050.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:24c7f1c14247c8244e48c2571e9d2df6ddd24c594cc31b931521566a4d0c8a87
3
+ size 4966190768
model-00031-of-00050.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:51f1428a9a93d6715620bd2efa2fe383cce799cea3cc435c8aa6bc0c32920eef
3
+ size 4982901392
model-00032-of-00050.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6c9e51fb13056063197f408a925454d8aa58d752424341a5fd634873b0669da0
3
+ size 4982934400
model-00033-of-00050.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6379d56234917f35c2f9cd54193b823bc776e34ca26344de79c8e53adab10675
3
+ size 4999711744
model-00034-of-00050.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fbda5fdbf5c8383f4000d8c9b7acaef097aebea37ee829e29207680a9c907c84
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:dc8fb0b3bdba1a80e50cce5d5e5317799ea97fcb7368bc196d33ffe6b5a52729
3
+ size 4831906232
model-00036-of-00050.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4781a3a468293d11df208f8f7f961dc1f363179e3c917a268979e96ce6da8007
3
+ size 4966190776
model-00037-of-00050.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9915548194d50cd631ee8b10c5c85a147e52759da474b70bf127a800e0c07124
3
+ size 4831906232
model-00038-of-00050.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:24e926d465858cd9b00d5cd91f247eb37a005f1b2fd6afddbc9d45bd637dc8d1
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:f554706dd7dc6aba9bc123d1b9954fe3b9d71de428112a46a79e9bf52db581e9
3
+ size 4966140568
model-00040-of-00050.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:583369d25eabe9cdd25bfc054a783a48faf0b0544a044f45c8564caaa7586212
3
+ size 4999711752
model-00041-of-00050.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:07238f91387bc7c383fc0432a5f76e03c5e2493a4ca6a10be93fc5fb6d12897a
3
+ size 4999711768
model-00042-of-00050.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3235f00739cce630dfca9fac921598469a3a499b5365e0c845ae66932c3f8769
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:db8a94f1ad9132d1d42966d754fb04acf1a15d81f35cad558b1c1c25f364410d
3
+ size 4831906240
model-00044-of-00050.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7bb77fc538585d228dcdfc7eef1e0a733369308ff5802696c3fd756bb5aaeeef
3
+ size 4966190800
model-00045-of-00050.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e5af3c011795d9ef2f70cd5b13851c53f30e55656ea9707109d7aa7113d6f762
3
+ size 4831906248
model-00046-of-00050.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e199de54f0d09f5503144b938e7695fdad811f7215deeacc17cc2e127ca74746
3
+ size 4966174288