bruhzair commited on
Commit
b2fc595
·
verified ·
1 Parent(s): 1c542b7

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 +39 -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-0.4x258
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-0.4x257 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--Sao10K--70B-L3.3-mhnnn-x1/snapshots/3fe1847bbe0dadf7306f3c4bf738f0547676177d
23
+ * /workspace/cache/models--TheDrummer--Anubis-70B-v1.1/snapshots/47ea1a3368e8d161b09acbc8c211ba4212e4b466
24
+ * /workspace/cache/models--Ppoyaa--MythoNemo-L3.1-70B-v1.0/snapshots/faaa4e992764eb4667b8f541dcf75ce8b7aaadcc
25
+ * /workspace/cache/models--Sao10K--L3.1-70B-Hanami-x1/snapshots/f054d970fe9119d0237ce97029e6f5b9fce630eb
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--Ppoyaa--MythoNemo-L3.1-70B-v1.0/snapshots/faaa4e992764eb4667b8f541dcf75ce8b7aaadcc
34
+ - model: /workspace/cache/models--Sao10K--70B-L3.3-mhnnn-x1/snapshots/3fe1847bbe0dadf7306f3c4bf738f0547676177d
35
+ - model: /workspace/cache/models--TheDrummer--Anubis-70B-v1.1/snapshots/47ea1a3368e8d161b09acbc8c211ba4212e4b466
36
+ - model: /workspace/cache/models--TheDrummer--Fallen-Llama-3.3-70B-v1/snapshots/d46ef2629f1c3cd46789a55793c5ff0af60de3e8
37
+ - model: /workspace/cache/models--Sao10K--L3.1-70B-Hanami-x1/snapshots/f054d970fe9119d0237ce97029e6f5b9fce630eb
38
+ base_model: /workspace/prototype-0.4x257
39
+ select_topk: 0.18
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 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "LlamaForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 128000,
8
+ "eos_token_id": [
9
+ 128001,
10
+ 128008,
11
+ 128009
12
+ ],
13
+ "head_dim": 128,
14
+ "hidden_act": "silu",
15
+ "hidden_size": 8192,
16
+ "initializer_range": 0.02,
17
+ "intermediate_size": 28672,
18
+ "max_position_embeddings": 131072,
19
+ "mlp_bias": false,
20
+ "model_type": "llama",
21
+ "num_attention_heads": 64,
22
+ "num_hidden_layers": 80,
23
+ "num_key_value_heads": 8,
24
+ "pretraining_tp": 1,
25
+ "rms_norm_eps": 1e-05,
26
+ "rope_scaling": {
27
+ "factor": 8.0,
28
+ "high_freq_factor": 4.0,
29
+ "low_freq_factor": 1.0,
30
+ "original_max_position_embeddings": 8192,
31
+ "rope_type": "llama3"
32
+ },
33
+ "rope_theta": 500000.0,
34
+ "tie_word_embeddings": false,
35
+ "torch_dtype": "float32",
36
+ "transformers_version": "4.53.2",
37
+ "use_cache": true,
38
+ "vocab_size": 128256
39
+ }
mergekit_config.yml ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ models:
2
+ - model: /workspace/cache/models--Ppoyaa--MythoNemo-L3.1-70B-v1.0/snapshots/faaa4e992764eb4667b8f541dcf75ce8b7aaadcc
3
+ - model: /workspace/cache/models--Sao10K--70B-L3.3-mhnnn-x1/snapshots/3fe1847bbe0dadf7306f3c4bf738f0547676177d
4
+ - model: /workspace/cache/models--TheDrummer--Anubis-70B-v1.1/snapshots/47ea1a3368e8d161b09acbc8c211ba4212e4b466
5
+ - model: /workspace/cache/models--TheDrummer--Fallen-Llama-3.3-70B-v1/snapshots/d46ef2629f1c3cd46789a55793c5ff0af60de3e8
6
+ - model: /workspace/cache/models--Sao10K--L3.1-70B-Hanami-x1/snapshots/f054d970fe9119d0237ce97029e6f5b9fce630eb
7
+ base_model: /workspace/prototype-0.4x257
8
+ select_topk: 0.18
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 sha256:7d2b787e1d49b3c32156b12ea1b7f534dafefa2f4525acb0aca448b3012e8941
3
+ size 4395763176
model-00002-of-00062.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e93ad0ed9245d93163bf6b798958d86632fd6782b6b6b482b2a6f57ddddff4c
3
+ size 4697720440
model-00003-of-00062.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b8341272d7349603c9d25039b9ee56611d80e63ab3c7f86bb29522ec9c29e5f0
3
+ size 4798317608
model-00004-of-00062.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d8ac55aacb5250854bfb47340f15b1d07f225775ba99664d9036587c81331c3c
3
+ size 838894184
model-00005-of-00062.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:742f9560920c765108c3b4d6bcec507f32a09b7de9232fc5dda729dd9e2895a6
3
+ size 4202725624
model-00006-of-00062.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8627ca7f68303794b776b60eceeb012f82f70f4111cfe28b4c4b486554134cbb
3
+ size 4429251984
model-00007-of-00062.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d428b14e80d182cdb0858d9c39632f2389f7f3843e063bd61def3af62fa3105a
3
+ size 4999676976
model-00008-of-00062.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4cbcef43a7cd4cec223c380d8dd9c8f25794ffd602249cb665185ffd326a7ee2
3
+ size 4840260432
model-00009-of-00062.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6c69c84c93ef01ef5cd5ea3a1fc15ad2225431983e21e6c31d063e9254745828
3
+ size 4328555448
model-00010-of-00062.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5ee5cf500a6a69a8ffc95ac06ee9bce418f1df111bbc9d9eb5135da90a52bde5
3
+ size 4630611344
model-00011-of-00062.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f0ef41b2fcf43a2af2abe70fbcb664e5438eaf6295e338f36418fb73a5dcbc7d
3
+ size 4395763192
model-00012-of-00062.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cf60f4a0cb8d36f1d2fe6396d87b9d7970522e589a7d23b11cf7574ef1fa4b9c
3
+ size 4630512688
model-00013-of-00062.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b2291e84755f48a2fa5b212b7f7dfc063523de7be901b5cccbd47ce38515bd58
3
+ size 4664198776
model-00014-of-00062.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:47b2ffa3eae71972a2feba99a813824206a5687d695f048ddea98e1a755c232c
3
+ size 4395763192
model-00015-of-00062.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e625aa02b54162e0a1cbe6dce1f593a6f35456ababbe3c76106d23c99b4b3124
3
+ size 4932568576
model-00016-of-00062.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6fc876ca9c7f5810fa106e67eac860c7632bb8bc4bfff20a2aad6770353c4251
3
+ size 4597056792
model-00017-of-00062.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b04549b222fe5b9691aa7811d2bcb0377097ace6f7d59316549bc1f7ff634dc0
3
+ size 4697753320
model-00018-of-00062.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8040e7514bba0b7c21380600fedfe50a3db4c85833cf50a39a150bbaea2dd91d
3
+ size 4999611208
model-00019-of-00062.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e216bb7dcf87e4201b4e689753da31bff058b75f37771ab1cda76e185ba0e84e
3
+ size 4664198768
model-00020-of-00062.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:39561fffe22cdf60133df7e53359a8cd5aac2e433d26fa1bd600d886c301c27f
3
+ size 4966188896
model-00021-of-00062.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:548836ff9936c0740244e9b7ab2da150cfecc6e487bd2f2fc1ab7095f6ce6c37
3
+ size 4664165896
model-00022-of-00062.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a3a22ec622fa7b1ec3cd61c94d7ac573cbfd7b26ae8df24ccffec6b196b9b647
3
+ size 4999644088
model-00023-of-00062.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:98bfb86f982e4d509d00046f3531c699642c2793da227aff5f724fda7649f9be
3
+ size 4966188896
model-00024-of-00062.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4c253d437d059d01632e6c14a254a25b3f2671747cb5e5bc0cd4d9cfe9c55e73
3
+ size 4697753320
model-00025-of-00062.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6af8bcf20795e2c2b1409b3f067e7cebefd1fe36f06be25c9497542825ffcdd8
3
+ size 4865393720
model-00026-of-00062.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8ad33d50ad899f2012173adffe4ce92e84e5ce72bf1b7ae67de5b61852b37d56
3
+ size 4127327624
model-00027-of-00062.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:362cce533de844683137b46f1fcef6fab1557381c77567aa3cc75f26bf988c9f
3
+ size 4697720440
model-00028-of-00062.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:12d46ab47da24848fd8118893a008a364a614d6e89f1f8d5b3bae18d944b9587
3
+ size 4899014024
model-00029-of-00062.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c1daea6038bb7ec3b80fc0a2d36ebcf30da1f8ee1dc44b5811e7e90918cc1d3a
3
+ size 4093740184
model-00030-of-00062.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e98d4ac5cbcc9480a19ab2e3bf1b7ca28b5f3df1155b020e1a501eb037a5325d
3
+ size 4697753320
model-00031-of-00062.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:297bd9d4cdc9743d6a6dbd818695fcb7eb16beb5dc3d678420d6de860fc09246
3
+ size 4596991032
model-00032-of-00062.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b130269198d36706b58cb76086ada28d6fff9a553b802ef3f38ac1a31bd15f4e
3
+ size 4664165880
model-00033-of-00062.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b5ba21daad932c797eba99ae45c2d18576a09a4e58f16e8b3db01c595a6b4b64
3
+ size 4395730320
model-00034-of-00062.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0a6a6a59f8e2aaa72821796421eec9c544648935874434bc63a112d79c8d9756
3
+ size 4899014024
model-00035-of-00062.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d0ad659a63e33521f9386f7bf813feef832d59356d658f9786cbaf7524b4fc27
3
+ size 4127294728
model-00036-of-00062.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:32c8ce14ea3c33684314d802c0362540a87a746c5e43edd3a25af12ed94eb166
3
+ size 4697753320
model-00037-of-00062.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b47d9237210708b54e7e58af9e1bebd90b7736e986e7cc07f689897aac729dd9
3
+ size 4831839168
model-00038-of-00062.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:174f0fb57d93eb23aca5652b50f318242bccf16e003b49580daba7728efa3505
3
+ size 4160882168
model-00039-of-00062.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b06deac98b2d3888175f729d97a11f5e8d0a32e2185793fc190be537d783108
3
+ size 4932634344
model-00040-of-00062.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c3c591e8e3a8556c706cc0d37266d0666546a3d1acbb0c54974543232fd592db
3
+ size 4362142888
model-00041-of-00062.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2f88543fe60e0186927ba8b07f1cf8fdafa351943434c58ab7de8a4bf787b84d
3
+ size 4630578456
model-00042-of-00062.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:49b9a96335b19c7d130dc05107901189da160598eea9fac15d8341066ec36266
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:e8af5b738a67551a2fe1d3ed388736710eab5e11df2a26f58c8e5649acaf53cd
3
+ size 4395730320
model-00044-of-00062.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:86c9ec296987608115efa00b5236c9e9892df4e8703296aeb40be29ac82f7119
3
+ size 4932568576
model-00045-of-00062.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b10703933d15b475103de6ff2a7d81ea7a474fa4b84631c5f79e92304f962923
3
+ size 4093740184