Hugging Face's logo

Sakalti
/
ultiima-125B

Text Generation
Transformers
Safetensors
qwen2
mergekit
Merge
conversational
text-generation-inference
Model card Files Community
Sakalti commited on
Commit
3c1a805
·
verified ·
1 Parent(s): c7848e9

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 +53 -0
  3. added_tokens.json +24 -0
  4. config.json +29 -0
  5. mergekit_config.yml +24 -0
  6. merges.txt +0 -0
  7. model-00001-of-00052.safetensors +3 -0
  8. model-00002-of-00052.safetensors +3 -0
  9. model-00003-of-00052.safetensors +3 -0
  10. model-00004-of-00052.safetensors +3 -0
  11. model-00005-of-00052.safetensors +3 -0
  12. model-00006-of-00052.safetensors +3 -0
  13. model-00007-of-00052.safetensors +3 -0
  14. model-00008-of-00052.safetensors +3 -0
  15. model-00009-of-00052.safetensors +3 -0
  16. model-00010-of-00052.safetensors +3 -0
  17. model-00011-of-00052.safetensors +3 -0
  18. model-00012-of-00052.safetensors +3 -0
  19. model-00013-of-00052.safetensors +3 -0
  20. model-00014-of-00052.safetensors +3 -0
  21. model-00015-of-00052.safetensors +3 -0
  22. model-00016-of-00052.safetensors +3 -0
  23. model-00017-of-00052.safetensors +3 -0
  24. model-00018-of-00052.safetensors +3 -0
  25. model-00019-of-00052.safetensors +3 -0
  26. model-00020-of-00052.safetensors +3 -0
  27. model-00021-of-00052.safetensors +3 -0
  28. model-00022-of-00052.safetensors +3 -0
  29. model-00023-of-00052.safetensors +3 -0
  30. model-00024-of-00052.safetensors +3 -0
  31. model-00025-of-00052.safetensors +3 -0
  32. model-00026-of-00052.safetensors +3 -0
  33. model-00027-of-00052.safetensors +3 -0
  34. model-00028-of-00052.safetensors +3 -0
  35. model-00029-of-00052.safetensors +3 -0
  36. model-00030-of-00052.safetensors +3 -0
  37. model-00031-of-00052.safetensors +3 -0
  38. model-00032-of-00052.safetensors +3 -0
  39. model-00033-of-00052.safetensors +3 -0
  40. model-00034-of-00052.safetensors +3 -0
  41. model-00035-of-00052.safetensors +3 -0
  42. model-00036-of-00052.safetensors +3 -0
  43. model-00037-of-00052.safetensors +3 -0
  44. model-00038-of-00052.safetensors +3 -0
  45. model-00039-of-00052.safetensors +3 -0
  46. model-00040-of-00052.safetensors +3 -0
  47. model-00041-of-00052.safetensors +3 -0
  48. model-00042-of-00052.safetensors +3 -0
  49. model-00043-of-00052.safetensors +3 -0
  50. model-00044-of-00052.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 +1,53 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model:
3
+ - Sakalti/ultiima-72B
4
+ library_name: transformers
5
+ tags:
6
+ - mergekit
7
+ - merge
8
+
9
+ ---
10
+ # merge
11
+
12
+ This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
13
+
14
+ ## Merge Details
15
+ ### Merge Method
16
+
17
+ This model was merged using the passthrough merge method.
18
+
19
+ ### Models Merged
20
+
21
+ The following models were included in the merge:
22
+ * [Sakalti/ultiima-72B](https://huggingface.co/Sakalti/ultiima-72B)
23
+
24
+ ### Configuration
25
+
26
+ The following YAML configuration was used to produce this model:
27
+
28
+ ```yaml
29
+ slices:
30
+ - sources:
31
+ - layer_range: [0, 20]
32
+ model: Sakalti/ultiima-72B
33
+ - sources:
34
+ - layer_range: [10, 30]
35
+ model: Sakalti/ultiima-72B
36
+ - sources:
37
+ - layer_range: [20, 40]
38
+ model: Sakalti/ultiima-72B
39
+ - sources:
40
+ - layer_range: [30, 50]
41
+ model: Sakalti/ultiima-72B
42
+ - sources:
43
+ - layer_range: [40, 60]
44
+ model: Sakalti/ultiima-72B
45
+ - sources:
46
+ - layer_range: [50, 70]
47
+ model: Sakalti/ultiima-72B
48
+ - sources:
49
+ - layer_range: [60, 80]
50
+ model: Sakalti/ultiima-72B
51
+ dtype: float16
52
+ merge_method: passthrough
53
+ ```
added_tokens.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</tool_call>": 151658,
3
+ "<tool_call>": 151657,
4
+ "<|box_end|>": 151649,
5
+ "<|box_start|>": 151648,
6
+ "<|endoftext|>": 151643,
7
+ "<|file_sep|>": 151664,
8
+ "<|fim_middle|>": 151660,
9
+ "<|fim_pad|>": 151662,
10
+ "<|fim_prefix|>": 151659,
11
+ "<|fim_suffix|>": 151661,
12
+ "<|im_end|>": 151645,
13
+ "<|im_start|>": 151644,
14
+ "<|image_pad|>": 151655,
15
+ "<|object_ref_end|>": 151647,
16
+ "<|object_ref_start|>": 151646,
17
+ "<|quad_end|>": 151651,
18
+ "<|quad_start|>": 151650,
19
+ "<|repo_name|>": 151663,
20
+ "<|video_pad|>": 151656,
21
+ "<|vision_end|>": 151653,
22
+ "<|vision_pad|>": 151654,
23
+ "<|vision_start|>": 151652
24
+ }
config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "Sakalti/ultiima-72B",
3
+ "architectures": [
4
+ "Qwen2ForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 151643,
8
+ "eos_token_id": 151643,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 8192,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 29568,
13
+ "max_position_embeddings": 131072,
14
+ "max_window_layers": 80,
15
+ "model_type": "qwen2",
16
+ "num_attention_heads": 64,
17
+ "num_hidden_layers": 140,
18
+ "num_key_value_heads": 8,
19
+ "rms_norm_eps": 1e-05,
20
+ "rope_scaling": null,
21
+ "rope_theta": 1000000.0,
22
+ "sliding_window": null,
23
+ "tie_word_embeddings": false,
24
+ "torch_dtype": "float16",
25
+ "transformers_version": "4.46.2",
26
+ "use_cache": true,
27
+ "use_sliding_window": false,
28
+ "vocab_size": 152064
29
+ }
mergekit_config.yml ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ slices:
2
+ - sources:
3
+ - layer_range: [0, 20]
4
+ model: Sakalti/ultiima-72B
5
+ - sources:
6
+ - layer_range: [10, 30]
7
+ model: Sakalti/ultiima-72B
8
+ - sources:
9
+ - layer_range: [20, 40]
10
+ model: Sakalti/ultiima-72B
11
+ - sources:
12
+ - layer_range: [30, 50]
13
+ model: Sakalti/ultiima-72B
14
+ - sources:
15
+ - layer_range: [40, 60]
16
+ model: Sakalti/ultiima-72B
17
+ - sources:
18
+ - layer_range: [50, 70]
19
+ model: Sakalti/ultiima-72B
20
+ - sources:
21
+ - layer_range: [60, 80]
22
+ model: Sakalti/ultiima-72B
23
+ dtype: float16
24
+ merge_method: passthrough
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model-00001-of-00052.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd22346776e2d6fff5cb31e89ee0082fd776cd2c0cb0de6b04a4ab02adda284f
3
+ size 4982849880
model-00002-of-00052.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bcc782c210b90e079907a929dbf3ea7cb7f36c57b144222ab260d662512ce631
3
+ size 4964084872
model-00003-of-00052.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d9cf1eda74b2dead6c312833f8ff0d21f55685fb98be4b1935957a1e96ab62df
3
+ size 4997660376
model-00004-of-00052.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb3a0fce5eb2678b7178232ad0dd0de09c3ca586e76d29fbea5f80330da3ec2f
3
+ size 4565680272
model-00005-of-00052.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a0c0362578c772097222513b19c6189bad61fccc00c1ba7e9bdb6ae14eef3fd
3
+ size 4964068400
model-00006-of-00052.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6774147f2132e8c096088768691010a88918802e55f43376c9bf7b1fe5282528
3
+ size 4915904664
model-00007-of-00052.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ece9414019480d2403107c32cc477495175e205cb3e98ddabd30b9d334aeb4de
3
+ size 4647435984
model-00008-of-00052.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:23c892c02b8762b159909e0505fd5ab81727e79fbcc33a79402cf1ff132a6930
3
+ size 4964068392
model-00009-of-00052.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6cd0431beafbb540a57afdb8537c447a3a30f268b16d2e7f519223fce85772b8
3
+ size 4599255760
model-00010-of-00052.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f74b6829e4904497877e9d180aa997facd00c33b1ef345a39a20320ba67f2eb
3
+ size 4964101384
model-00011-of-00052.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7369d5f464cb6c31c40aba945ae6a837a88ccbf44e3475426d373303c1807b02
3
+ size 4781653832
model-00012-of-00052.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:50d8e9c758c8bb46390bfb1897302e66b261ae23cff8649d9ee722f89b0cd89d
3
+ size 4964068392
model-00013-of-00052.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:20942faa2e4b76281c23331f094ba3ea97ad53cc4a8214ec820ad2ceb9d6a402
3
+ size 4599272256
model-00014-of-00052.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:392ec48f4dfcba547d27dc222cfe33c924ad0df50794a332c6ee2820244777df
3
+ size 4964068400
model-00015-of-00052.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f6fb8a355936abdbaf58246930864928e988800311c58dca3c446639a86b31ae
3
+ size 4997660376
model-00016-of-00052.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c0387e07ebe55217fa6c7643105572ae940c0a6307be4fedbce50bf2bba2098
3
+ size 4565680272
model-00017-of-00052.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:374ea11e9fed5a7629c55299eaf1b3d1cf67f2c1aee4779368d09f77180211bd
3
+ size 4781670312
model-00018-of-00052.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:605d2368f87bf664641873bd5c021679fa906eee9e5ddaff9dd23efa7027bcaa
3
+ size 4964068400
model-00019-of-00052.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:56be02b2b7395af19590cd46b82b67b1b1db200ccb9c11c10ddce77bffb0e8b4
3
+ size 4997660376
model-00020-of-00052.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a5a2a57b8984c644d5fbf2080a8e89e7e0dabdf2636ebfd012898dd66ee899d1
3
+ size 4565680272
model-00021-of-00052.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de501c6285dcdc6b15691683723b41301eaad38f8e0cd2da581d3d9288e1a9da
3
+ size 4964068400
model-00022-of-00052.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fad71c72ebc0406d4cec13f1b62f750e05d350e1c6c607f1d1ec22802f142c71
3
+ size 4915904664
model-00023-of-00052.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ee8f71d4e6819a9d9ab9d2a72f6e71d181d086a71b31846a9a7b822d3801a62
3
+ size 4647435984
model-00024-of-00052.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:86787689bb3d84e3fae3e756edfcd4668d322d135d0ea698c67fdc5538ea8f4d
3
+ size 4964068392
model-00025-of-00052.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:da4b5f5bbae1072bacb2d8b7356c0923c65c8756003ba927ab64b95f3f4a48bd
3
+ size 4781670312
model-00026-of-00052.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:423fccce17ff75d3b164ddfdf43605c97e55da8958cd96d5a07e50f9fa7be6f8
3
+ size 4915904664
model-00027-of-00052.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ea7e56c885dfb5902fcf753f2537b8528ed6a0936019ae0b08418c96f2079985
3
+ size 4647435984
model-00028-of-00052.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:702bc369614756a46d602d906a57dc29db4318c2ef028a26e5fe8e25515bfaba
3
+ size 4964068392
model-00029-of-00052.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a9c90a20a9a4bd2f64e894fe52ceaec8bff9ce83d895980a14b0cf6a10cae77f
3
+ size 4599272256
model-00030-of-00052.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed8d38472225121b18549ef2ff42d0675332f381f889c37e1431f02bc5ed0947
3
+ size 4964068400
model-00031-of-00052.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c13e892215a8cc8e0bd705621534de41df4317a6d10f166e093a90268cb899b
3
+ size 4997660376
model-00032-of-00052.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d384c6f40ff62301db119b59413a3504f0c92c59059adff403feaf72886432ff
3
+ size 4565663768
model-00033-of-00052.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b94060691d74fa8249a3b5c99cb2fad667749d6e4d676e01c32d0dea088fc86f
3
+ size 4781686824
model-00034-of-00052.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1f35823b0783be1e052b249178488ecd09f8860ed1982b07f73386013cf471c3
3
+ size 4964068416
model-00035-of-00052.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a5de762c4e26fd5258b6e80d1bc2c173c064571ef839be4f5dc6b0395dfa381
3
+ size 4997660384
model-00036-of-00052.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:90ad5b0f14d54801404019a21c57df3401566628b29399ca095090a78bce232e
3
+ size 4565680296
model-00037-of-00052.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b6c2ba8662d91d8d1aaed8d3cdd80ad872fbf8657d79234e06b3a3284b1e80f9
3
+ size 4964068408
model-00038-of-00052.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7c6b0c6e795122e31f7a997cfdca8a2dc597253f4f5aeb40dc1e984787bffcec
3
+ size 4915904688
model-00039-of-00052.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ea183443efe649a5cc96d6f21e644909f5e5a966521528df02f16ec0c4040a4
3
+ size 4647435984
model-00040-of-00052.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:25e0b75862d3417df87fac6325d9dbefe0d4eeab8cc78ecb09998033256ba635
3
+ size 4781670328
model-00041-of-00052.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b2779ea20a3b4c18d28740837f006c04d2a6a0a77a05e4ef0f267e56bdce0fbe
3
+ size 4964068424
model-00042-of-00052.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:73d18c34a40676e708e8408a089961f57562fb6e447ed0e832fdee56558d6ac0
3
+ size 4915904704
model-00043-of-00052.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc718ab3949b05fd1af8502d7ef7991404f096cb05c4782e3f80db6c1434e44a
3
+ size 4647436016
model-00044-of-00052.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d5797504cf740f912473b7966919f4a91dd0b30857211d99463dcd219c6a71e0
3
+ size 4964068416