Hugging Face's logo

wassemgtk
/
Tiny-ll

Text Generation
Transformers
Safetensors
llama
conversational
text-generation-inference
Inference Endpoints
Model card Files Community
wassemgtk commited on
Commit
a7a694f
•
1 Parent(s): 249f297

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 +72 -0
  2. config.json +28 -0
  3. mergekit_config.yml +42 -0
  4. model-00001-of-00046.safetensors +3 -0
  5. model-00002-of-00046.safetensors +3 -0
  6. model-00003-of-00046.safetensors +3 -0
  7. model-00004-of-00046.safetensors +3 -0
  8. model-00005-of-00046.safetensors +3 -0
  9. model-00006-of-00046.safetensors +3 -0
  10. model-00007-of-00046.safetensors +3 -0
  11. model-00008-of-00046.safetensors +3 -0
  12. model-00009-of-00046.safetensors +3 -0
  13. model-00010-of-00046.safetensors +3 -0
  14. model-00011-of-00046.safetensors +3 -0
  15. model-00012-of-00046.safetensors +3 -0
  16. model-00013-of-00046.safetensors +3 -0
  17. model-00014-of-00046.safetensors +3 -0
  18. model-00015-of-00046.safetensors +3 -0
  19. model-00016-of-00046.safetensors +3 -0
  20. model-00017-of-00046.safetensors +3 -0
  21. model-00018-of-00046.safetensors +3 -0
  22. model-00019-of-00046.safetensors +3 -0
  23. model-00020-of-00046.safetensors +3 -0
  24. model-00021-of-00046.safetensors +3 -0
  25. model-00022-of-00046.safetensors +3 -0
  26. model-00023-of-00046.safetensors +3 -0
  27. model-00024-of-00046.safetensors +3 -0
  28. model-00025-of-00046.safetensors +3 -0
  29. model-00026-of-00046.safetensors +3 -0
  30. model-00027-of-00046.safetensors +3 -0
  31. model-00028-of-00046.safetensors +3 -0
  32. model-00029-of-00046.safetensors +3 -0
  33. model-00030-of-00046.safetensors +3 -0
  34. model-00031-of-00046.safetensors +3 -0
  35. model-00032-of-00046.safetensors +3 -0
  36. model-00033-of-00046.safetensors +3 -0
  37. model-00034-of-00046.safetensors +3 -0
  38. model-00035-of-00046.safetensors +3 -0
  39. model-00036-of-00046.safetensors +3 -0
  40. model-00037-of-00046.safetensors +3 -0
  41. model-00038-of-00046.safetensors +3 -0
  42. model-00039-of-00046.safetensors +3 -0
  43. model-00040-of-00046.safetensors +3 -0
  44. model-00041-of-00046.safetensors +3 -0
  45. model-00042-of-00046.safetensors +3 -0
  46. model-00043-of-00046.safetensors +3 -0
  47. model-00044-of-00046.safetensors +3 -0
  48. model-00045-of-00046.safetensors +3 -0
  49. model-00046-of-00046.safetensors +3 -0
  50. model.safetensors.index.json +0 -0
README.md ADDED
@@ -0,0 +1,72 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model:
3
+ - mlabonne/Meta-Llama-3-225B-Instruct
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
+ * [mlabonne/Meta-Llama-3-225B-Instruct](https://huggingface.co/mlabonne/Meta-Llama-3-225B-Instruct)
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: mlabonne/Meta-Llama-3-225B-Instruct
33
+ - sources:
34
+ - layer_range: [10, 30]
35
+ model: mlabonne/Meta-Llama-3-225B-Instruct
36
+ - sources:
37
+ - layer_range: [20, 40]
38
+ model: mlabonne/Meta-Llama-3-225B-Instruct
39
+ - sources:
40
+ - layer_range: [30, 50]
41
+ model: mlabonne/Meta-Llama-3-225B-Instruct
42
+ - sources:
43
+ - layer_range: [40, 60]
44
+ model: mlabonne/Meta-Llama-3-225B-Instruct
45
+ - sources:
46
+ - layer_range: [50, 70]
47
+ model: mlabonne/Meta-Llama-3-225B-Instruct
48
+ - sources:
49
+ - layer_range: [60, 80]
50
+ model: mlabonne/Meta-Llama-3-225B-Instruct
51
+ - sources:
52
+ - layer_range: [70, 90]
53
+ model: mlabonne/Meta-Llama-3-225B-Instruct
54
+ - sources:
55
+ - layer_range: [80, 100]
56
+ model: mlabonne/Meta-Llama-3-225B-Instruct
57
+ - sources:
58
+ - layer_range: [90, 110]
59
+ model: mlabonne/Meta-Llama-3-225B-Instruct
60
+ - sources:
61
+ - layer_range: [100, 120]
62
+ model: mlabonne/Meta-Llama-3-225B-Instruct
63
+ - sources:
64
+ - layer_range: [110, 130]
65
+ model: mlabonne/Meta-Llama-3-225B-Instruct
66
+ - sources:
67
+ - layer_range: [120, 140]
68
+ model: mlabonne/Meta-Llama-3-225B-Instruct
69
+ merge_method: passthrough
70
+ dtype: float16
71
+
72
+ ```
config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "mlabonne/Meta-Llama-3-225B-Instruct",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 128000,
9
+ "eos_token_id": 128001,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 8192,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 28672,
14
+ "max_position_embeddings": 8192,
15
+ "model_type": "llama",
16
+ "num_attention_heads": 64,
17
+ "num_hidden_layers": 260,
18
+ "num_key_value_heads": 8,
19
+ "pretraining_tp": 1,
20
+ "rms_norm_eps": 1e-05,
21
+ "rope_scaling": null,
22
+ "rope_theta": 500000.0,
23
+ "tie_word_embeddings": false,
24
+ "torch_dtype": "float16",
25
+ "transformers_version": "4.39.3",
26
+ "use_cache": true,
27
+ "vocab_size": 128256
28
+ }
mergekit_config.yml ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ slices:
2
+ - sources:
3
+ - layer_range: [0, 20]
4
+ model: mlabonne/Meta-Llama-3-225B-Instruct
5
+ - sources:
6
+ - layer_range: [10, 30]
7
+ model: mlabonne/Meta-Llama-3-225B-Instruct
8
+ - sources:
9
+ - layer_range: [20, 40]
10
+ model: mlabonne/Meta-Llama-3-225B-Instruct
11
+ - sources:
12
+ - layer_range: [30, 50]
13
+ model: mlabonne/Meta-Llama-3-225B-Instruct
14
+ - sources:
15
+ - layer_range: [40, 60]
16
+ model: mlabonne/Meta-Llama-3-225B-Instruct
17
+ - sources:
18
+ - layer_range: [50, 70]
19
+ model: mlabonne/Meta-Llama-3-225B-Instruct
20
+ - sources:
21
+ - layer_range: [60, 80]
22
+ model: mlabonne/Meta-Llama-3-225B-Instruct
23
+ - sources:
24
+ - layer_range: [70, 90]
25
+ model: mlabonne/Meta-Llama-3-225B-Instruct
26
+ - sources:
27
+ - layer_range: [80, 100]
28
+ model: mlabonne/Meta-Llama-3-225B-Instruct
29
+ - sources:
30
+ - layer_range: [90, 110]
31
+ model: mlabonne/Meta-Llama-3-225B-Instruct
32
+ - sources:
33
+ - layer_range: [100, 120]
34
+ model: mlabonne/Meta-Llama-3-225B-Instruct
35
+ - sources:
36
+ - layer_range: [110, 130]
37
+ model: mlabonne/Meta-Llama-3-225B-Instruct
38
+ - sources:
39
+ - layer_range: [120, 140]
40
+ model: mlabonne/Meta-Llama-3-225B-Instruct
41
+ merge_method: passthrough
42
+ dtype: float16
model-00001-of-00046.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:039c0342bf3d58edfe3a54f08711262162840d8a0bf9e1e4aefd8c48ea381c39
3
+ size 9919646856
model-00002-of-00046.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7488579ab08f9da6578d528c5e586b3688192b3ac30ebe648f386da971fe1192
3
+ size 9852573384
model-00003-of-00046.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e136f19ed3dccf14a8215196f56fd533bd7b21eedc32dc2fa12f68298f41a76c
3
+ size 9798096896
model-00004-of-00046.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac8f9ab4b59dc46bef01155f883e1bdb6039ec0439c35131f0f2d9233bf07b55
3
+ size 9965868720
model-00005-of-00046.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:311c8d8824f22e8d84c9595d3c027e8fb3f21eae5d5fc1fa51ed91422261eb1e
3
+ size 9965868720
model-00006-of-00046.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a6f95e7dc27ed4e11515d24eaee855f013a732a55f34e0f13622c80895bbaa13
3
+ size 9999423392
model-00007-of-00046.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ff2108b3008b319d9781880115d562b0ed2282b8df2c07684fe6fe66a6b64b87
3
+ size 9999456376
model-00008-of-00046.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:581473c427880d79fd78eaf5aaf60c2896947ad7a313158eb0dc999eacb7eeb3
3
+ size 9932347744
model-00009-of-00046.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:289507f1f71f5fa2325b14c12f6bc4e598c798681b2047d86f326cc4c39592f4
3
+ size 9563216464
model-00010-of-00046.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f9da7448501f47657e8df595a7c647a081f16fcd7d33292f1d0026f1d66e786b
3
+ size 9798096912
model-00011-of-00046.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2e8c5ca22268c191ef7153ebe18cb82a29b99d845ce66738bdb33971d605c588
3
+ size 9965835736
model-00012-of-00046.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:df63103418f6d50d7bc2e2db3bedab8455f841c68bf282d144b56f461d7e2013
3
+ size 9965835728
model-00013-of-00046.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d38a79933a7870614dbfa8604a9c0f59067f7846092f4499888ffc9bc5440d6
3
+ size 9697400048
model-00014-of-00046.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c3239b0750463c3df61e8ae294c0cb46332858aa414380a9f3240d6a7fcea279
3
+ size 9999423384
model-00015-of-00046.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:70a291c6b2aca9140f93d44be2b65e1fb628d34c4b227f49a4ed0ba8f0fa7297
3
+ size 9965835728
model-00016-of-00046.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:53c129b2e939db26b56fd2393489e03d0cfa29586fa008d5e5fd5abd1e4271d6
3
+ size 9798129952
model-00017-of-00046.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2dc98e5dcc0402d18ddfc546727efc9a45651cfdcb588fafb4aa470102565f55
3
+ size 9697434328
model-00018-of-00046.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1dbf6b527978d611dc5fbb666fc9b2b7e4f54b9408fd433fe1f6fac4ce859790
3
+ size 9798096960
model-00019-of-00046.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2074b562aae9b6a58e8e4d44b9d0279841bc5d9c777112b3d512ac0874b3d51e
3
+ size 9965835768
model-00020-of-00046.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8c61648ee78eb88bde3f784dd92400db89602da4801b1096119a7673b3cd5061
3
+ size 9965835776
model-00021-of-00046.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6ae28a9cc477346ea2f17c0df7f73d2282e3dfd988f9446c19c4a4bcdbf5d1b5
3
+ size 9798129952
model-00022-of-00046.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:279fa5fb99828de77ecd902b2ff41a7eebe36547f20dc668e9ca513950c156fd
3
+ size 9965835768
model-00023-of-00046.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:74679fa5cd96d2cda2e7df235077d0431cb9d543feca63f77612e808e5dc7a9c
3
+ size 9932314776
model-00024-of-00046.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:510d68844b8366a98f2160346e89a28db368a82460c7f247aaffa9d3cfbb8a09
3
+ size 9798130664
model-00025-of-00046.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9cf2478c42f39a16252a730b0bea4cce3da9a9e28ef2289f647bc2353fe13c30
3
+ size 9798096968
model-00026-of-00046.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a967a1e0ee893e68530e3d4803353177d6f349e9efee48eb2692dff48276291
3
+ size 9798096968
model-00027-of-00046.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c099d2cf2bfd3b99f553e7f94619467f9e7b97bc3bcab31c9b442de16f00718a
3
+ size 9965835784
model-00028-of-00046.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1fd1bf4273bb7d1a2bed252ed39466d580ec1a0c42c9c5072c721a2e0234cd20
3
+ size 9965835784
model-00029-of-00046.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe14fb374e5638fca8926bb3ca5cda3aa33b11965c09d07c21c27dccfaab222c
3
+ size 9663845408
model-00030-of-00046.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:59ca34d8b46f8c8dba0ed9371211215b4527f0227ef3766e30b05331d43f8479
3
+ size 9932315520
model-00031-of-00046.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9dcdebece10edb037f9aecca84300e42a7a35fbccc569a86a38145c29bb808c8
3
+ size 9965868752
model-00032-of-00046.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:70ec27a6c135306ff139c04fff13f49aad1261885f84ee3112260475dd950984
3
+ size 9932347824
model-00033-of-00046.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e2425d0cfdc1a5d46ea357599c19e3b5fd9d0aa93273e112762ac6ef8ac06ad9
3
+ size 9798130656
model-00034-of-00046.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:99a29c4d3601445a5db650beb287e228e4a20123a40f5eb554b2eb3b760eca76
3
+ size 9999390456
model-00035-of-00046.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:47fd89b08423979e1e41e48de997bb7bce32c0b1532bf8b8a010ee0ae6f8a17d
3
+ size 9965835784
model-00036-of-00046.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9af83eea8f82607f28b1b6cec9d8b1025fb47846ed9a3668e0cdde02aaa03c91
3
+ size 9965835784
model-00037-of-00046.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:45d7988e594020b46ea1fca961ba9616b64dd9365fe499f5b6c4295ae789e77a
3
+ size 9932314088
model-00038-of-00046.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c3b1b705396aec9bd669d7d5e84d4adf06972e5102641378b94399b9f561cb12
3
+ size 9630325128
model-00039-of-00046.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6d96df25b6ab25fb85e2869dfca8765bb0f3e65639214d72e95047c3479ab2f8
3
+ size 9798096968
model-00040-of-00046.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bec3ba33c6d4f147d95a4853c0e37d9ff176c9673cf99a95c0dcb471d2a654df
3
+ size 9798096968
model-00041-of-00046.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:095e4b8f66a87690871e3f16f6442d275d99a0962f3f483c218b370a060f80ed
3
+ size 9798096968
model-00042-of-00046.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1b95fd558ed3a682d23fd4131c2a297b145c08cf055be97ee67daca9e3f16c19
3
+ size 9798080480
model-00043-of-00046.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0a88d9f954238921b2fb74511de7ccfcd9541e7c0efc998b890afe0edd763a05
3
+ size 9798063968
model-00044-of-00046.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:77036f6584e18623fe4a6e5bf1390a047e65f6fa29966c146f401104f0e7b438
3
+ size 9798080456
model-00045-of-00046.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:48656675642026bd23b73c20daeb15763f60fb18cbc72aeff6a79145cc110e41
3
+ size 9798080472
model-00046-of-00046.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:00483167cb543303c5f50d1b30fae01391264d358ddbb0b91e206e7aef665e63
3
+ size 5133929528
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff