Hugging Face's logo

softwareweaver
/
Twilight-Large-123B

Text Generation
Transformers
Safetensors
mistral
mergekit
Merge
conversational
text-generation-inference
Model card Files
xet
 Community
4
softwareweaver commited on
Commit
a4b7051
·
verified ·
1 Parent(s): 49b219a

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. README.md +48 -0
  2. config.json +27 -0
  3. mergekit_config.yml +16 -0
  4. model-00001-of-00051.safetensors +3 -0
  5. model-00002-of-00051.safetensors +3 -0
  6. model-00003-of-00051.safetensors +3 -0
  7. model-00004-of-00051.safetensors +3 -0
  8. model-00005-of-00051.safetensors +3 -0
  9. model-00006-of-00051.safetensors +3 -0
  10. model-00007-of-00051.safetensors +3 -0
  11. model-00008-of-00051.safetensors +3 -0
  12. model-00009-of-00051.safetensors +3 -0
  13. model-00010-of-00051.safetensors +3 -0
  14. model-00011-of-00051.safetensors +3 -0
  15. model-00012-of-00051.safetensors +3 -0
  16. model-00013-of-00051.safetensors +3 -0
  17. model-00014-of-00051.safetensors +3 -0
  18. model-00015-of-00051.safetensors +3 -0
  19. model-00016-of-00051.safetensors +3 -0
  20. model-00017-of-00051.safetensors +3 -0
  21. model-00018-of-00051.safetensors +3 -0
  22. model-00019-of-00051.safetensors +3 -0
  23. model-00020-of-00051.safetensors +3 -0
  24. model-00021-of-00051.safetensors +3 -0
  25. model-00022-of-00051.safetensors +3 -0
  26. model-00023-of-00051.safetensors +3 -0
  27. model-00024-of-00051.safetensors +3 -0
  28. model-00025-of-00051.safetensors +3 -0
  29. model-00026-of-00051.safetensors +3 -0
  30. model-00027-of-00051.safetensors +3 -0
  31. model-00028-of-00051.safetensors +3 -0
  32. model-00029-of-00051.safetensors +3 -0
  33. model-00030-of-00051.safetensors +3 -0
  34. model-00031-of-00051.safetensors +3 -0
  35. model-00032-of-00051.safetensors +3 -0
  36. model-00033-of-00051.safetensors +3 -0
  37. model-00034-of-00051.safetensors +3 -0
  38. model-00035-of-00051.safetensors +3 -0
  39. model-00036-of-00051.safetensors +3 -0
  40. model-00037-of-00051.safetensors +3 -0
  41. model-00038-of-00051.safetensors +3 -0
  42. model-00039-of-00051.safetensors +3 -0
  43. model-00040-of-00051.safetensors +3 -0
  44. model-00041-of-00051.safetensors +3 -0
  45. model-00042-of-00051.safetensors +3 -0
  46. model-00043-of-00051.safetensors +3 -0
  47. model-00044-of-00051.safetensors +3 -0
  48. model-00045-of-00051.safetensors +3 -0
  49. model-00046-of-00051.safetensors +3 -0
  50. model-00047-of-00051.safetensors +3 -0
README.md ADDED
@@ -0,0 +1,48 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model:
3
+ - schnapper79/lumikabra-123B_v0.4
4
+ - mistralai/Mistral-Large-Instruct-2407
5
+ - TheDrummer/Behemoth-123B-v1
6
+ library_name: transformers
7
+ tags:
8
+ - mergekit
9
+ - merge
10
+
11
+ ---
12
+ # Twilight-Large
13
+
14
+ This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
15
+
16
+ ## Merge Details
17
+ ### Merge Method
18
+
19
+ This model was merged using the della_linear merge method using [mistralai/Mistral-Large-Instruct-2407](https://huggingface.co/mistralai/Mistral-Large-Instruct-2407) as a base.
20
+
21
+ ### Models Merged
22
+
23
+ The following models were included in the merge:
24
+ * [schnapper79/lumikabra-123B_v0.4](https://huggingface.co/schnapper79/lumikabra-123B_v0.4)
25
+ * [TheDrummer/Behemoth-123B-v1](https://huggingface.co/TheDrummer/Behemoth-123B-v1)
26
+
27
+ ### Configuration
28
+
29
+ The following YAML configuration was used to produce this model:
30
+
31
+ ```yaml
32
+ models:
33
+ - model: TheDrummer/Behemoth-123B-v1
34
+ parameters:
35
+ weight: 0.25
36
+ density: 0.9
37
+ - model: schnapper79/lumikabra-123B_v0.4
38
+ parameters:
39
+ weight: 0.3
40
+ density: 0.9
41
+ merge_method: della_linear
42
+ base_model: mistralai/Mistral-Large-Instruct-2407
43
+ parameters:
44
+ epsilon: 0.05
45
+ lambda: 1
46
+ int8_mask: true
47
+ dtype: bfloat16
48
+ ```
config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "softwareweaver/Twilight-Large-123B",
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": 12288,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 28672,
14
+ "max_position_embeddings": 131072,
15
+ "model_type": "mistral",
16
+ "num_attention_heads": 96,
17
+ "num_hidden_layers": 88,
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": "4.45.2",
25
+ "use_cache": true,
26
+ "vocab_size": 32768
27
+ }
mergekit_config.yml ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ models:
2
+ - model: TheDrummer/Behemoth-123B-v1
3
+ parameters:
4
+ weight: 0.25
5
+ density: 0.9
6
+ - model: schnapper79/lumikabra-123B_v0.4
7
+ parameters:
8
+ weight: 0.3
9
+ density: 0.9
10
+ merge_method: della_linear
11
+ base_model: mistralai/Mistral-Large-Instruct-2407
12
+ parameters:
13
+ epsilon: 0.05
14
+ lambda: 1
15
+ int8_mask: true
16
+ dtype: bfloat16
model-00001-of-00051.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:28ea143453695b72170d67935ed31741b16d2367a7a2e2f5e85b98af712bd4d8
3
+ size 4378928504
model-00002-of-00051.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:77c768041acdad2ef31ed8e094b44786d953737460975ba643e98c39731558be
3
+ size 4907411088
model-00003-of-00051.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8c65331712512eb118dbc66c6a02da45811ca1b19c2aca656b1d3de2273559b3
3
+ size 4806747904
model-00004-of-00051.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c38ee620deeeb46835b592529f41dc087b3ac81b64321ea745fac98f23a711f1
3
+ size 4831938544
model-00005-of-00051.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9cc0cfc46df3006b2320ad9b015b2cefb55473e725f80e4ae498de1f1df88849
3
+ size 4831938552
model-00006-of-00051.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cddfe2c102927819db4a0aa35daef91fa0a4179de1ee8feb5960fab69a07dee3
3
+ size 4907411096
model-00007-of-00051.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e8f6b5b919f8654919304f3ce9035e0dcd998f17d32775f35bc55663444c3c90
3
+ size 4806747904
model-00008-of-00051.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2e64efba4ce27b36cba3326a9ae5e505938a285429cbcaa9fb62dcd50308231b
3
+ size 4831938536
model-00009-of-00051.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4704f16235e2a80d4015dcef4d6d35ef259d9119f1f1c4c0fe6aae4d8b4a73bd
3
+ size 4831938552
model-00010-of-00051.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f969781903501540d025bedb48a2efd0db8b2b6bb73a2b62acfd01acee3005ad
3
+ size 4907411096
model-00011-of-00051.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8c36c756142279bf657d98e86b69e3689304b7ea8625154383f940ddb91e6cd4
3
+ size 4806747904
model-00012-of-00051.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c81e216652582cf94d9d0d2b9cf1172adefaa058c829e9bc92a0ba177a4654ec
3
+ size 4831938544
model-00013-of-00051.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:54107339276c7d24c3d1f3d41fa88f76707465f7ea8e000d590b0872bb111c84
3
+ size 4831938552
model-00014-of-00051.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cec73e14a3f484d567f1ff805017e49e4740cf70a92936fa184b670922c7a51f
3
+ size 4907411088
model-00015-of-00051.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8447e857c5958b69e618b84d384530ac82d0a800800dbbb48302665678d35363
3
+ size 4806747904
model-00016-of-00051.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:60d50b15af8a8cdeb91bbc129eb669e335328637988376e51da338390316e16c
3
+ size 4831938544
model-00017-of-00051.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:60789cc0cd833e6ad7d024f9bea98b241a6dfbfa710c4e251ecc511726cfcdab
3
+ size 4831938552
model-00018-of-00051.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eca79d132710d11cf6115665f4c5739b5aada236d2a1a1aee1461dfcdc938e23
3
+ size 4907411096
model-00019-of-00051.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de28b2cff39039f5006efa1af98fa9e4a1991fdde12bbcb7ab49388649163dea
3
+ size 4806747904
model-00020-of-00051.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:779558a95efee9c7420a302cc29ab41499c4a8c454359dee0ba5f49b9918c7c2
3
+ size 4831938544
model-00021-of-00051.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d4b24e0974f83785c7df1a27be9d50b865c707505aa4ba687a57998897fc1345
3
+ size 4831938544
model-00022-of-00051.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:499209a97d3bdf943527558161f6c98f91e0a75b9213f2c71aa2b950405bf8aa
3
+ size 4907411096
model-00023-of-00051.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b147eb673020d53ee7c72853d898461f5885ab58bdb6439703514ce3f26dcb4e
3
+ size 4806747904
model-00024-of-00051.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f897612bff8ac53ab864c805d540446a9f18f5bd402feb89d33b589dfb8477a2
3
+ size 4831938544
model-00025-of-00051.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b51f8ffda01f70fb27b1601990fbf7eac770dc92ecfd985308c68111dd31cf8a
3
+ size 4831938552
model-00026-of-00051.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:681df3346e5fd4cdab849816a9fea4e2215394e80a343bd477fced3876353e06
3
+ size 4907411096
model-00027-of-00051.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2c93b3ac18a2691c767644ac58862356958ed5fb04e66ddf6438654c0bcdace8
3
+ size 4806747896
model-00028-of-00051.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3379768bb5896ac37138a88e3dfa54046f4d98e5ea5154d053d5a8de9daaff4a
3
+ size 4831938544
model-00029-of-00051.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f2244ccc7ee12f8b1201995fe5a3e2cfd6d694ae4f799704d703d2a472b4ab09
3
+ size 4831938552
model-00030-of-00051.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e930bdc6438e7024fb50dc773291c64639e148b4e2c0ba0fce68deed79e5c805
3
+ size 4907411096
model-00031-of-00051.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3f537670b9969002ad24bb0d10f8205c476711b30311a8bcf7adda4312a7d999
3
+ size 4806747904
model-00032-of-00051.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:541ea9f2af4e940e0a9608dc6a197dd0bd36faf7e581112c07a74287b5ab7096
3
+ size 4831938544
model-00033-of-00051.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4244b93ba61d2f48e7772c22f4561e2f9bae40aba1991882632ec9bb8539903a
3
+ size 4831938544
model-00034-of-00051.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2ff558ffa6ae651c2aa2a4b37f8663580d7b2c89d7d657c84ca722710c6ee12e
3
+ size 4907411096
model-00035-of-00051.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:78765f1600064b06d9cbe45b26fe2f948a6a965c13d9f5b2542476f5e383e577
3
+ size 4806747904
model-00036-of-00051.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a2b43b3af5fde9361394704398cf9ff64a8e82bb05e3b4dc2fc91fdcf98ef05
3
+ size 4831938544
model-00037-of-00051.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:51cba72b7f430135484c5cd8f0c4b350439050d4261542cc881dc29d9e4a162e
3
+ size 4831938552
model-00038-of-00051.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cee23eb5be848da0b49f556c7e73a6e3517ca97f7a077b6c536a85f164e1878b
3
+ size 4907411096
model-00039-of-00051.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:475f2411279fa07c78d1af68247e571cbc15d6c08aa02d97526bdcdb678093ae
3
+ size 4806747904
model-00040-of-00051.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ba26d3a9715c045f3a89ac064f956f1a9ce4eb59e6b91eed500e528642ece08a
3
+ size 4831938544
model-00041-of-00051.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2de7e37f210b4151fff8dc3ee287a902495b3e818667319078617efa7cd53581
3
+ size 4831938552
model-00042-of-00051.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:941890c4749e708d62ef1916035af9c14366851ba15f7bf9d17829f376a5e2db
3
+ size 4907411096
model-00043-of-00051.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0faff725f849752b22f13078561142135342c16daa000173910efb454d00b047
3
+ size 4806747904
model-00044-of-00051.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e12e5be33fcf62b5ebb82f29ae7caa3fb47da46f5830f145acaf9ec1a2fe839c
3
+ size 4831938544
model-00045-of-00051.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:02f667d30acd3cdb1c0af928f5d7e9a2ae7a17a941f3201ec2ac8aedd795d552
3
+ size 4831938552
model-00046-of-00051.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e5a909baa133cf95f9a78909680ec1d455ae3ae8ce69dccae7885e7d710fcea1
3
+ size 4907411088
model-00047-of-00051.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e9770d36074c1fcabfeb23b1698f0d503b66727902f547d188f580f949701ce3
3
+ size 4806747904