bruhzair commited on
Commit
421605b
·
verified ·
1 Parent(s): 0f06576

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 +47 -0
  3. chat_template.jinja +7 -0
  4. config.json +35 -0
  5. mergekit_config.yml +15 -0
  6. model-00001-of-00062.safetensors +3 -0
  7. model-00002-of-00062.safetensors +3 -0
  8. model-00003-of-00062.safetensors +3 -0
  9. model-00004-of-00062.safetensors +3 -0
  10. model-00005-of-00062.safetensors +3 -0
  11. model-00006-of-00062.safetensors +3 -0
  12. model-00007-of-00062.safetensors +3 -0
  13. model-00008-of-00062.safetensors +3 -0
  14. model-00009-of-00062.safetensors +3 -0
  15. model-00010-of-00062.safetensors +3 -0
  16. model-00011-of-00062.safetensors +3 -0
  17. model-00012-of-00062.safetensors +3 -0
  18. model-00013-of-00062.safetensors +3 -0
  19. model-00014-of-00062.safetensors +3 -0
  20. model-00015-of-00062.safetensors +3 -0
  21. model-00016-of-00062.safetensors +3 -0
  22. model-00017-of-00062.safetensors +3 -0
  23. model-00018-of-00062.safetensors +3 -0
  24. model-00019-of-00062.safetensors +3 -0
  25. model-00020-of-00062.safetensors +3 -0
  26. model-00021-of-00062.safetensors +3 -0
  27. model-00022-of-00062.safetensors +3 -0
  28. model-00023-of-00062.safetensors +3 -0
  29. model-00024-of-00062.safetensors +3 -0
  30. model-00025-of-00062.safetensors +3 -0
  31. model-00026-of-00062.safetensors +3 -0
  32. model-00027-of-00062.safetensors +3 -0
  33. model-00028-of-00062.safetensors +3 -0
  34. model-00029-of-00062.safetensors +3 -0
  35. model-00030-of-00062.safetensors +3 -0
  36. model-00031-of-00062.safetensors +3 -0
  37. model-00032-of-00062.safetensors +3 -0
  38. model-00033-of-00062.safetensors +3 -0
  39. model-00034-of-00062.safetensors +3 -0
  40. model-00035-of-00062.safetensors +3 -0
  41. model-00036-of-00062.safetensors +3 -0
  42. model-00037-of-00062.safetensors +3 -0
  43. model-00038-of-00062.safetensors +3 -0
  44. model-00039-of-00062.safetensors +3 -0
  45. model-00040-of-00062.safetensors +3 -0
  46. model-00041-of-00062.safetensors +3 -0
  47. model-00042-of-00062.safetensors +3 -0
  48. model-00043-of-00062.safetensors +3 -0
  49. model-00044-of-00062.safetensors +3 -0
  50. model-00045-of-00062.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 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: []
3
+ library_name: transformers
4
+ tags:
5
+ - mergekit
6
+ - merge
7
+
8
+ ---
9
+ # prototype-0.4x308
10
+
11
+ This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
12
+
13
+ ## Merge Details
14
+ ### Merge Method
15
+
16
+ This model was merged using the [SCE](https://arxiv.org/abs/2408.07990) merge method using /workspace/prototype-0.4x295 as a base.
17
+
18
+ ### Models Merged
19
+
20
+ The following models were included in the merge:
21
+ * /workspace/cache/models--TheDrummer--Fallen-Llama-3.3-70B-v1/snapshots/d46ef2629f1c3cd46789a55793c5ff0af60de3e8
22
+ * /workspace/cache/models--nbeerbower--Llama3.1-Gutenberg-Doppel-70B/snapshots/f083f3a89b8275e7e5329bb0668ada189f80b507
23
+ * /workspace/cache/models--Doctor-Shotgun--L3.3-70B-Magnum-Diamond/snapshots/a7dfb66b4469a4c9ca07ff28bccc73a44797e76c
24
+ * /workspace/cache/models--tdrussell--Llama-3-70B-Instruct-Storywriter/snapshots/19be2a7c6382a9150e126cf144e2b2964e700d3c
25
+ * /workspace/cache/models--Ppoyaa--MythoNemo-L3.1-70B-v1.0/snapshots/faaa4e992764eb4667b8f541dcf75ce8b7aaadcc
26
+
27
+ ### Configuration
28
+
29
+ The following YAML configuration was used to produce this model:
30
+
31
+ ```yaml
32
+ models:
33
+ - model: /workspace/cache/models--Doctor-Shotgun--L3.3-70B-Magnum-Diamond/snapshots/a7dfb66b4469a4c9ca07ff28bccc73a44797e76c
34
+ - model: /workspace/cache/models--nbeerbower--Llama3.1-Gutenberg-Doppel-70B/snapshots/f083f3a89b8275e7e5329bb0668ada189f80b507
35
+ - model: /workspace/cache/models--tdrussell--Llama-3-70B-Instruct-Storywriter/snapshots/19be2a7c6382a9150e126cf144e2b2964e700d3c
36
+ - model: /workspace/cache/models--Ppoyaa--MythoNemo-L3.1-70B-v1.0/snapshots/faaa4e992764eb4667b8f541dcf75ce8b7aaadcc
37
+ - model: /workspace/cache/models--TheDrummer--Fallen-Llama-3.3-70B-v1/snapshots/d46ef2629f1c3cd46789a55793c5ff0af60de3e8
38
+ base_model: /workspace/prototype-0.4x295
39
+ select_topk: 0.24
40
+ merge_method: sce
41
+ tokenizer:
42
+ source: base
43
+ chat_template: llama3
44
+ pad_to_multiple_of: 8
45
+ int8_mask: true
46
+ dtype: float32
47
+ ```
chat_template.jinja ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {% set loop_messages = messages %}
2
+ {% for message in loop_messages %}
3
+ {% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}
4
+ {% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}
5
+ {{ content }}
6
+ {% endfor %}
7
+ {% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}
config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "LlamaForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 128000,
8
+ "eos_token_id": 128001,
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": 80,
19
+ "num_key_value_heads": 8,
20
+ "pretraining_tp": 1,
21
+ "rms_norm_eps": 1e-05,
22
+ "rope_scaling": {
23
+ "factor": 8.0,
24
+ "high_freq_factor": 4.0,
25
+ "low_freq_factor": 1.0,
26
+ "original_max_position_embeddings": 8192,
27
+ "rope_type": "llama3"
28
+ },
29
+ "rope_theta": 500000.0,
30
+ "tie_word_embeddings": false,
31
+ "torch_dtype": "float32",
32
+ "transformers_version": "4.55.0",
33
+ "use_cache": true,
34
+ "vocab_size": 128256
35
+ }
mergekit_config.yml ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ models:
2
+ - model: /workspace/cache/models--Doctor-Shotgun--L3.3-70B-Magnum-Diamond/snapshots/a7dfb66b4469a4c9ca07ff28bccc73a44797e76c
3
+ - model: /workspace/cache/models--nbeerbower--Llama3.1-Gutenberg-Doppel-70B/snapshots/f083f3a89b8275e7e5329bb0668ada189f80b507
4
+ - model: /workspace/cache/models--tdrussell--Llama-3-70B-Instruct-Storywriter/snapshots/19be2a7c6382a9150e126cf144e2b2964e700d3c
5
+ - model: /workspace/cache/models--Ppoyaa--MythoNemo-L3.1-70B-v1.0/snapshots/faaa4e992764eb4667b8f541dcf75ce8b7aaadcc
6
+ - model: /workspace/cache/models--TheDrummer--Fallen-Llama-3.3-70B-v1/snapshots/d46ef2629f1c3cd46789a55793c5ff0af60de3e8
7
+ base_model: /workspace/prototype-0.4x295
8
+ select_topk: 0.24
9
+ merge_method: sce
10
+ tokenizer:
11
+ source: base
12
+ chat_template: llama3
13
+ pad_to_multiple_of: 8
14
+ int8_mask: true
15
+ dtype: float32
model-00001-of-00062.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5eee9390926e7aaaed531e6d6b8e7905a2138ca6d528907bdabe760ad2792926
3
+ size 4362175752
model-00002-of-00062.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a56d79c003f9b03fdebdc15a5a9d83aa9ad499a2d19f9074fb91730f749c7fc
3
+ size 4202692736
model-00003-of-00062.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cba32302c03a40e13e1556e990a0f556eef8b54c56331337c94d86e9c1f8c4e2
3
+ size 3154150216
model-00004-of-00062.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f52eef85314b056d774c1a298ac3b0b5643b38f5fd58528a79acf7f499ffebf4
3
+ size 4202692744
model-00005-of-00062.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:27ec7c98c8bd495e5bdc13b0be7a51cc721f564af71cc67a0cd61914fc654e09
3
+ size 4932634344
model-00006-of-00062.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e638811080a0a0aef0f426a4c15448c18fdb40830305f8d445143f6be94bfb0
3
+ size 4362142880
model-00007-of-00062.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:efa00d0251a7f253cddc6b3bf964ffbfce9be91c29d4712c1627b663c0885634
3
+ size 4932634344
model-00008-of-00062.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a7ce9f217d27de9d867c9b8920a7edd0b578d05c1b8052ae9d51956bc8c38716
3
+ size 4630611336
model-00009-of-00062.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2114eb228e3caf6bb96da6fe3db6854ec2acef44ce4ac71b9dbfbbf7d133b079
3
+ size 4362142888
model-00010-of-00062.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3fb74ef04ffcd644bb8ebcc6621dcfd368863bbdc4a4700ef60c81ecb50ac5b8
3
+ size 4362142880
model-00011-of-00062.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0443485c72e483e7fd508c95b021c180ef2e9efedbe1c247ea6d79473af1642f
3
+ size 4966188888
model-00012-of-00062.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6e644e5d3aa113461d9df5f1af92d96a26842a3df8758a17f9fe85ae23efc46b
3
+ size 4362142880
model-00013-of-00062.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c903cca0f050d6da84dad28008d9fdf97b943163d2b38ddf8d075e3a08ba36a4
3
+ size 4630644216
model-00014-of-00062.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:73805b79dac2cb09246c39f5069950b330c3e1c04daa4436b4fbca75f3031ea2
3
+ size 4630578456
model-00015-of-00062.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b5b11a26487b0c43bda3e59a18bd0a650bb034a19190381bf7a291db4d6a67c5
3
+ size 4630611336
model-00016-of-00062.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:671077ac910d739558d05ef6198eee7d93a86b603ad1ac775246e2cd496eea56
3
+ size 4362142880
model-00017-of-00062.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:97bfa9c910c6470fc77a65d1e6c51b8e69573be96cd4b88fecff8e8f90f14ab6
3
+ size 4966188888
model-00018-of-00062.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d15e1f7b384f39ff432c780ad243cb9de4d336724b9d28a6576aeed3e848ca24
3
+ size 4362142880
model-00019-of-00062.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:30c91ea1f37d3abcd8ebd9d73ed5450c0a69807d5eca05ce0cdfbf5c56afbfcd
3
+ size 4362142880
model-00020-of-00062.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2ed8f5e630051053d320fab8b53a300fa0a26e05d9af00ee39d3e43f7d66ed8e
3
+ size 4966188888
model-00021-of-00062.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ff468ee280b5d260d3acd65c8c25a4aedeab28a13f54eb3a13ad5624c5a6d8ac
3
+ size 4362142880
model-00022-of-00062.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d50202e7b87a618329e1dd1b2433530c0744d9b3632cdc47b4bf4c10a6bb1fd6
3
+ size 4362142872
model-00023-of-00062.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5e80832205ea6d9f17e6ede3af7cb544346dcdabb6893acfd198f68076c7a930
3
+ size 4932634344
model-00024-of-00062.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a08e5ff459e79011bbe0cfdc26bf0eb51a518081c6a1856023bcf00ad6da4fc
3
+ size 4362142880
model-00025-of-00062.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c98e64fa76633a0a8be58ecdaea79019a342a0d698d83b9703310c08d39e168
3
+ size 4932634344
model-00026-of-00062.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8e6039e34b26b6a4e197ad93a6bf4fb4c6fcbe6eae9347e30e0b299d463d8561
3
+ size 4362142880
model-00027-of-00062.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0555cf1c695903ac7f27a3e59296da63d8c5d7493f671dc0296ed70030ad8fd6
3
+ size 4630644224
model-00028-of-00062.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b447114f514d6fd5743abf2325ae7766541aea078065673fbb347f73d10c4cf7
3
+ size 4630578448
model-00029-of-00062.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:523f244e4b1a274a32fb429b703ffcee5072202963825f8bd959d01babbe9614
3
+ size 4630644224
model-00030-of-00062.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:63beb61995362731cd41b569dff8b22b0ca622b0875161af895f153e73dbaed3
3
+ size 4630578456
model-00031-of-00062.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:335c4c0b5df369ec31bd858d4dc031e6d3452f4e833d72a84137843516e857e8
3
+ size 4630644224
model-00032-of-00062.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:becec4ec8bf726dbf3dfccc16f43b3dee85958e8d25ec914d22470a31df3a853
3
+ size 4630578448
model-00033-of-00062.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c5c229ab0cff1c48fe592e8b7c301d93ab3467217a27bbff379ced029a413f9
3
+ size 4630644224
model-00034-of-00062.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:61a030070642a4146c47dfd406030e85ae7b1105215828ce6eec6b34983e2a4e
3
+ size 4362142880
model-00035-of-00062.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e6b888fc6c58bbb74b6078e6630395e15f73123412a35c93d1ddb65f76290375
3
+ size 4932601448
model-00036-of-00062.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:71e90bcb0e582ea30a2b544a40a38fb406eca6681ab181d664dda692c5926050
3
+ size 4362142880
model-00037-of-00062.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dfb18d9d5f4a1940a56b3435c60294ed5ccefa3701283206b0c375cb22cb46af
3
+ size 4664198768
model-00038-of-00062.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3d06d81c4ac1530de3d5fba08aaab4a4801616f7e45b9f4cf1dcb9d2287e1c52
3
+ size 4362142880
model-00039-of-00062.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6337e64ddc77ffb534011926dfda8d646e3518ced8dc75f59e9a42ab6727eaf1
3
+ size 4932601456
model-00040-of-00062.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a60b62e7d1a3c4fcad17120eeee46f84ebaf6a3bc4fb59fbb378e71b7c54708
3
+ size 4362142880
model-00041-of-00062.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:00574e1b2f07ffa7f7dd23e64f074b842100dc747ef36086dad177da5568f411
3
+ size 4664165888
model-00042-of-00062.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f62ae55e7bedc902629adba2eae3012154fd59b015c6a5d84a6be9dfed211438
3
+ size 4664165880
model-00043-of-00062.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:98a885325052b232f3d18ef0570bd2b104f73420b4b5606741c8da4fa24b9858
3
+ size 4362142880
model-00044-of-00062.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:efb81e34805c7cc5f3d03ab0a24d731f71ca55efdb564c89f905420d87d52120
3
+ size 4932634344
model-00045-of-00062.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d7b97444f235a3e015cb0b403627553dad878fbd4ac82c03e0494f70ceaf344c
3
+ size 4362142880