bruhzair commited on
Commit
ba244ff
·
verified ·
1 Parent(s): bec3159

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-00063.safetensors +3 -0
  7. model-00002-of-00063.safetensors +3 -0
  8. model-00003-of-00063.safetensors +3 -0
  9. model-00004-of-00063.safetensors +3 -0
  10. model-00005-of-00063.safetensors +3 -0
  11. model-00006-of-00063.safetensors +3 -0
  12. model-00007-of-00063.safetensors +3 -0
  13. model-00008-of-00063.safetensors +3 -0
  14. model-00009-of-00063.safetensors +3 -0
  15. model-00010-of-00063.safetensors +3 -0
  16. model-00011-of-00063.safetensors +3 -0
  17. model-00012-of-00063.safetensors +3 -0
  18. model-00013-of-00063.safetensors +3 -0
  19. model-00014-of-00063.safetensors +3 -0
  20. model-00015-of-00063.safetensors +3 -0
  21. model-00016-of-00063.safetensors +3 -0
  22. model-00017-of-00063.safetensors +3 -0
  23. model-00018-of-00063.safetensors +3 -0
  24. model-00019-of-00063.safetensors +3 -0
  25. model-00020-of-00063.safetensors +3 -0
  26. model-00021-of-00063.safetensors +3 -0
  27. model-00022-of-00063.safetensors +3 -0
  28. model-00023-of-00063.safetensors +3 -0
  29. model-00024-of-00063.safetensors +3 -0
  30. model-00025-of-00063.safetensors +3 -0
  31. model-00026-of-00063.safetensors +3 -0
  32. model-00027-of-00063.safetensors +3 -0
  33. model-00028-of-00063.safetensors +3 -0
  34. model-00029-of-00063.safetensors +3 -0
  35. model-00030-of-00063.safetensors +3 -0
  36. model-00031-of-00063.safetensors +3 -0
  37. model-00032-of-00063.safetensors +3 -0
  38. model-00033-of-00063.safetensors +3 -0
  39. model-00034-of-00063.safetensors +3 -0
  40. model-00035-of-00063.safetensors +3 -0
  41. model-00036-of-00063.safetensors +3 -0
  42. model-00037-of-00063.safetensors +3 -0
  43. model-00038-of-00063.safetensors +3 -0
  44. model-00039-of-00063.safetensors +3 -0
  45. model-00040-of-00063.safetensors +3 -0
  46. model-00041-of-00063.safetensors +3 -0
  47. model-00042-of-00063.safetensors +3 -0
  48. model-00043-of-00063.safetensors +3 -0
  49. model-00044-of-00063.safetensors +3 -0
  50. model-00045-of-00063.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-0.4x301
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--EVA-UNIT-01--EVA-LLaMA-3.33-70B-v0.0/snapshots/501b61987a44172bf2d68365893fcd13081ad4db
24
+ * /workspace/cache/models--tdrussell--Llama-3-70B-Instruct-Storywriter/snapshots/19be2a7c6382a9150e126cf144e2b2964e700d3c
25
+ * /workspace/cache/models--Doctor-Shotgun--L3.3-70B-Magnum-Diamond/snapshots/a7dfb66b4469a4c9ca07ff28bccc73a44797e76c
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--EVA-UNIT-01--EVA-LLaMA-3.33-70B-v0.0/snapshots/501b61987a44172bf2d68365893fcd13081ad4db
37
+ - model: /workspace/cache/models--TheDrummer--Fallen-Llama-3.3-70B-v1/snapshots/d46ef2629f1c3cd46789a55793c5ff0af60de3e8
38
+ base_model: /workspace/prototype-0.4x295
39
+ select_topk: 0.26
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--EVA-UNIT-01--EVA-LLaMA-3.33-70B-v0.0/snapshots/501b61987a44172bf2d68365893fcd13081ad4db
6
+ - model: /workspace/cache/models--TheDrummer--Fallen-Llama-3.3-70B-v1/snapshots/d46ef2629f1c3cd46789a55793c5ff0af60de3e8
7
+ base_model: /workspace/prototype-0.4x295
8
+ select_topk: 0.26
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-00063.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4a9cdd1c2527c90f5ade40f371c0921d0b2f3d987b1ea29b7c0544017d7093d6
3
+ size 3120628536
model-00002-of-00063.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:705e7f52001d041d36cc7603d27d03b907e2125202aff0d92263eb74ed5776d8
3
+ size 4202692736
model-00003-of-00063.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5e0e937477681361bd0abcdb019bc5a288864415e21defa05397d0f92b3077e9
3
+ size 2214626000
model-00004-of-00063.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd5243ccf11f6158e3d01846e2e2967f70b3512d94b14a845e0ce215ff4b893f
3
+ size 4202692744
model-00005-of-00063.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e5e2dbcbdb43e2a1daacf6475c42dfdf5051b25f24fcf2fc948061b17e2cf360
3
+ size 4664198768
model-00006-of-00063.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:33656602d30d9c1b8e8c763a41f116a5973884672417232ff42641ffddb03ff5
3
+ size 4899014032
model-00007-of-00063.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b92e9ce302ef3c91bf67c64061be6e76b9f2d31c7e7611262f401044fb679f6f
3
+ size 4362208640
model-00008-of-00063.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:083fd63c705737191da0fd177c5a303c51a443841f015d4b8daebc124a4a8846
3
+ size 4630578456
model-00009-of-00063.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:74453318e9d31a12b4ee2134a14b51229d1159cd694826aec9b9888aa89ac869
3
+ size 4664133000
model-00010-of-00063.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a733f9d2deb891acf5b66fb8033729f6818e9754d9f48879748b3f464ea7c211
3
+ size 4395763192
model-00011-of-00063.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fea5ce9a97441bbe048a621b9d3a5db67dece44b076eb00596df7c0d4acfa99e
3
+ size 4362142880
model-00012-of-00063.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:80b88b32905122027069f805d0c90fd2794e8b61e2a72927017b0a5bc5cd641e
3
+ size 4932601456
model-00013-of-00063.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b41e829792b0658b41f8929dc3c6612729c584120b828459d8d2a2d1df455415
3
+ size 4362142880
model-00014-of-00063.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:350d3c7d7864a7c2214db8ebdb4cd2b0ce6f0e814266bdca21ccc02f8a69841d
3
+ size 4664165888
model-00015-of-00063.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:88d6393e3c74a699162201fc521068297b09d881afe2fd0aa17e4d5a87a34856
3
+ size 4664165888
model-00016-of-00063.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:75f9f54a929f7ededfceacdec53dff88bac525fd5a5d7ca08c1a5ce26e981b68
3
+ size 4362142880
model-00017-of-00063.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f24b7e1b4a6b94d029a0b523e47ad29601d0db4ade9d7a610070d3049d1ff246
3
+ size 4932634344
model-00018-of-00063.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d509395b4309c8147dee07b7b441200a3ac8a31df6b36845d804ca2e513458b
3
+ size 4362142880
model-00019-of-00063.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c882a4ea191f7dacb8a23c13182d1b0579d43874967a595b59cf46cb6aff5edf
3
+ size 4630644224
model-00020-of-00063.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f24fc3dbe69b9a5cb0f1d75b0909d8e4e48d2115ebe835299ceb4e6d0e7d3bd9
3
+ size 4630578448
model-00021-of-00063.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:89a0d04419f55e13b4a1629ca35e885370cb68aef322546f96ddb4dd7d12804e
3
+ size 4630611336
model-00022-of-00063.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f8847091aa873d4cee8636434d232ea47b8d457489fe22323b8d51cabec363dd
3
+ size 4362142880
model-00023-of-00063.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4df90214ef38deee07b4f96c328bb0056c810ab6f6ec5c3bd4b6c404ed3e1cb2
3
+ size 4966188888
model-00024-of-00063.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dab50b9432eb47786154a616b53106aafa4f0237a5af0ebaac51fa831bf1eb52
3
+ size 4362142880
model-00025-of-00063.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2266da7e7ecb2ecb61b403a0b5d25b88cffae257c18dc52074d4d752e3e30b46
3
+ size 4362142880
model-00026-of-00063.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:efbefa823d75704c4f9942415680d22d085a4a6b51674bdabd25f698436c27d7
3
+ size 4932634344
model-00027-of-00063.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1da309ea96b930948ce5a6d1402b202559960f03d88e604fb2680d788e6bfb4f
3
+ size 4362142880
model-00028-of-00063.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c43f63de34275c0ec11b0631bd3ff226bdc82011745ca47af069357c24ff9ab5
3
+ size 4932634336
model-00029-of-00063.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:22ada06dfe82efb97b384c28772abe582186153103b24d4b60cb4d10547c9e72
3
+ size 4630578456
model-00030-of-00063.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ee6a3d3640d833e5d9e24ec2ab0efeb7545776bbc056b49c70b2bf3ba93b624e
3
+ size 4362175760
model-00031-of-00063.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0666fde2d846b30ead90bc7d144ce4699b473c801f8bce0caf30951fd53e856a
3
+ size 4395730312
model-00032-of-00063.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cefddb4ec6b2516311a15848d0b16e708017723e0db333ebd238c9c919dac4e6
3
+ size 4932568576
model-00033-of-00063.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:75a229361e74dea1aa3515461116292e8f19faaa4a7a9391ed2fb74cf2bf1797
3
+ size 4362175760
model-00034-of-00063.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:64d0bef19915717045ff4c1fec5d0212ec657fe1d4209c143e7a43bc00cb9f11
3
+ size 4362142880
model-00035-of-00063.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:285d12b6a48847f9658aeb35cc176700206b6f0663e09a2e147e725c2f220192
3
+ size 4966188888
model-00036-of-00063.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:47ec2a9b0da04748341eb18ae3688b158bee54d2af2dc72e85add63dee6e6145
3
+ size 4362142880
model-00037-of-00063.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8340a8a9138a2c98fe91ac02edbe67a30e83c061c0c13b9a3c609b289b435551
3
+ size 4362142872
model-00038-of-00063.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe49ca5ecb5b66e815f6bc8e01446a8d7cfb5dc3a390e438252a7a75a0141080
3
+ size 4932634344
model-00039-of-00063.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:961b6329abc26f95ad76410b968e6c9857df637bda3a0fade0a30b20c3c05ac1
3
+ size 4362142880
model-00040-of-00063.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e146ba5e26a8dc02e698587dff58b99d36f6b70b64c1f632cca9a9e8db544edc
3
+ size 4932634344
model-00041-of-00063.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f9ae0353cb8672b6b6a83d04bc9dbd48b3345a8e8f3ff5230f7fc124e731e264
3
+ size 4362142880
model-00042-of-00063.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ada9f79dfb6ecd2a14f7dd50ff61d356bbb385073c7cc264d0d152efc22d7d7c
3
+ size 4630644224
model-00043-of-00063.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d28c32ac60052dd2b2538969d016c1f51d76f8b3a0eacb8213dd612d78ac93e3
3
+ size 4630578456
model-00044-of-00063.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:816696f546bd07c492f2451ccb3a4f9d207cf3ff8bf17afe4245b7db3d3a6ca6
3
+ size 4630644224
model-00045-of-00063.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:325866d6ae708dc5c917c62ee527c0ec184a265a17b08d4f83ef6d3ec718548b
3
+ size 4362142880