bruhzair commited on
Commit
68eb04b
·
verified ·
1 Parent(s): d2ab988

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-0.4x300
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--ArliAI--Llama-3.3-70B-ArliAI-RPMax-v2/snapshots/3a47eabeb5861db09dad26fcf0fb0d57114e40d3
22
+ * /workspace/cache/models--ReadyArt--L3.3-The-Omega-Directive-70B-Unslop-v2.1/snapshots/61e03f3fe59b3b22b7e9e17e9bbe807f434da16d
23
+ * /workspace/cache/models--TheDrummer--Fallen-Llama-3.3-70B-v1/snapshots/d46ef2629f1c3cd46789a55793c5ff0af60de3e8
24
+ * /workspace/cache/models--Sao10K--L3.3-70B-Euryale-v2.3/snapshots/e5737724a37ae00926e95acf663ca73d430dc8ad
25
+ * /workspace/cache/models--Delta-Vector--Shimamura-70B/snapshots/1106f197a3ea1424512c30a8576bd718313b57c3
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--Delta-Vector--Shimamura-70B/snapshots/1106f197a3ea1424512c30a8576bd718313b57c3
34
+ - model: /workspace/cache/models--ArliAI--Llama-3.3-70B-ArliAI-RPMax-v2/snapshots/3a47eabeb5861db09dad26fcf0fb0d57114e40d3
35
+ - model: /workspace/cache/models--Sao10K--L3.3-70B-Euryale-v2.3/snapshots/e5737724a37ae00926e95acf663ca73d430dc8ad
36
+ - model: /workspace/cache/models--ReadyArt--L3.3-The-Omega-Directive-70B-Unslop-v2.1/snapshots/61e03f3fe59b3b22b7e9e17e9bbe807f434da16d
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--Delta-Vector--Shimamura-70B/snapshots/1106f197a3ea1424512c30a8576bd718313b57c3
3
+ - model: /workspace/cache/models--ArliAI--Llama-3.3-70B-ArliAI-RPMax-v2/snapshots/3a47eabeb5861db09dad26fcf0fb0d57114e40d3
4
+ - model: /workspace/cache/models--Sao10K--L3.3-70B-Euryale-v2.3/snapshots/e5737724a37ae00926e95acf663ca73d430dc8ad
5
+ - model: /workspace/cache/models--ReadyArt--L3.3-The-Omega-Directive-70B-Unslop-v2.1/snapshots/61e03f3fe59b3b22b7e9e17e9bbe807f434da16d
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-00063.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a0639a75d99ef1d3364d5de3fc7b6d0ad7f9cb14a97035668ee4bd8f033ffc89
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:c15ed9ab7622425a6c4a1d8c661f1cd823257f307b72a794ab9f4afe6d742ab1
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:b90786831276ee55736c2e4798efbe5dc45b77548cb50331b45564fca81470c6
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:bfa4cc03572a0cf1963366f3e02136ecfed1535579a13c752f4834ee9de580ca
3
+ size 4202692744
model-00005-of-00063.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:315bd2c38c9bfd5735e428dda47133195eebccf158cff8cdc8a7eb0d52994ce5
3
+ size 4664198768
model-00006-of-00063.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:359f2a16a9c6dac390a8d7992e4138a05391891f94c8cce68261c5b5b48cda0d
3
+ size 4630578456
model-00007-of-00063.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d26b421fb56b3fda90f359620552a335ac7bfc5deaf983b7dc0c275b42b50950
3
+ size 4630644224
model-00008-of-00063.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:627cb116d763bd911f2463dcb4ab52622e88e3e79085d06db53a34e6e0af5b16
3
+ size 4630578456
model-00009-of-00063.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8406233469e7df9e20947bd24421d879c70b9c3f8db59483eef0d3029f6f8cb2
3
+ size 4630611336
model-00010-of-00063.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c08bf5913e631fbe5c6bc92240eb19f063d8fa98e92d92907288c32b92e0d97b
3
+ size 4362142880
model-00011-of-00063.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:76b441f4728f2e046ad241aeb29e9368ed7ae8956ff6fc47d02602ba7f0b7ad2
3
+ size 4966188888
model-00012-of-00063.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d7ad5e27e0bb6af7ebf0c0f8d6dd275ecaeaaeca67ecdf5be9aab77f28e41d93
3
+ size 4362142880
model-00013-of-00063.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f18cbd396cf5d55880a7fd25a1d3f3f3d202dc6db5c68ce05ca812a3b4136654
3
+ size 4362142872
model-00014-of-00063.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d6739dc9a1c5220f6f2b5e6bf99a25bb87d457b6d0b09b1fc5cc9eda0b22e13
3
+ size 4932634336
model-00015-of-00063.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e6ec8949f234c17dcb5c62721393b99097792a75821a57d8424de5ec743204c
3
+ size 4664165880
model-00016-of-00063.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a30d68ff702af3087d5b4d1c84696349a28a9d1d3b3ef78a5be97b091dc86c4f
3
+ size 4362142880
model-00017-of-00063.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:264c277ef9b30e3cf718720c06e5da655acc895d02c87fd1ea27303011288d5b
3
+ size 4362175768
model-00018-of-00063.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f3752779ba217cdc697bde97616f7ab58cf0687ac1bcc6df6d9b66fce1432b8b
3
+ size 4932601456
model-00019-of-00063.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d1178fad5e79ae7bc8d1473b1857c6120202676a42c72645ca403185088dc5cf
3
+ size 4362142880
model-00020-of-00063.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c47e014a91524c840bc45e8cd4f3a32c45f78b359d2fda6aed4a006fda2d9055
3
+ size 4932634336
model-00021-of-00063.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1212645ecd974c9942ed1c42f2fbcd12939bcb4fc42b32225ea0cc92e931605b
3
+ size 4362142880
model-00022-of-00063.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc1ee738d9016aff2a1644a196f39d38f760ccea2b52ed21c424a85d84457bfc
3
+ size 4630644224
model-00023-of-00063.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cfd82ede3b8e53e78a7682a7e0d611fb96de58fa6f442516f09d4a5bb23950a3
3
+ size 4630578448
model-00024-of-00063.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f32c7f5f183bfb23c76e01e8e13592044a94a5bb570520f01ce9ea3aaf41b0fb
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:e5afb18d1a0555c5303f4ec161f74526e7e52454ca349249979ffcce4dfcfee3
3
+ size 4966188896
model-00026-of-00063.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f5ceb9dd5351b55e82fd961672300eee6c5146d644e6ae17f6617dba9d42e556
3
+ size 4362142880
model-00027-of-00063.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ccba1a13edbcb8c35efddf2b9d0deb2cc40fdc1e2a5741318d1f05563bd0ad3
3
+ size 4630611344
model-00028-of-00063.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b44f5ca39f1c2c17fadd40e53fee3fe594a0f6c8a66de6b1b49019f5a12c67dc
3
+ size 4664165880
model-00029-of-00063.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bae02625906c8d7029f9d21fc708c4952b5c6cfbdea6517dac42b454303d0df7
3
+ size 4362142880
model-00030-of-00063.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:07152bc8b6df0e2febc2a9919d961d553ce174b9d843bf7b99cadc580be97418
3
+ size 4932634344
model-00031-of-00063.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:82d098024fde3cd2540550252a84d9a10bced650b4e25cb94ab197359af75fba
3
+ size 4362142880
model-00032-of-00063.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6d19a8c919945fba8c0b80e5779edfeece37263aee525be09dea703f5dd73806
3
+ size 4630644224
model-00033-of-00063.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9aec426d03afe964418e3261b8736fc247f73ec94d2e798b2882f254b057e060
3
+ size 4630578456
model-00034-of-00063.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d65b15d6f82750ed95a84957e91f3ee12097ed195b696421ed88ed9f1d4e3a30
3
+ size 4630644224
model-00035-of-00063.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:df961a15a0e4626b6f3cab229ebd1e0dcf026248253c147a5bdfe3aeea744d7a
3
+ size 4630578456
model-00036-of-00063.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c417403f74dadca920025830590e778c67279e3f8ba154365ec89d22dd1792ae
3
+ size 4362142880
model-00037-of-00063.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0112d1def731c51dd56b5c4f255590da4c5636bde35077f8ad11f2650aec0eab
3
+ size 4966188896
model-00038-of-00063.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:498d0dce41041fd5124333aba3a203810ee9880d23210855bc85ea5482314509
3
+ size 4362142880
model-00039-of-00063.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a0d1c0fb14867151ea564019e0e439882ea6fe91737b14af99a90eb5eb138267
3
+ size 4630644224
model-00040-of-00063.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5be6bd8061307a86a11a80644547b83da2d87cef349cad76db23d2ea855d7d96
3
+ size 4630578456
model-00041-of-00063.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:04ee29e2d41d73be98962eef6ce35cc3c02325d8e4e9b8add117702524492d23
3
+ size 4630644224
model-00042-of-00063.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd2b8bbbf70a78997dff92b09b0b4c5db727e83acf243fe7c5aa1249b22c656a
3
+ size 4630578448
model-00043-of-00063.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0eaa4b407ceb8d442294a0370f4d2c16fe4b50b179c334bd47591ada20ac98c3
3
+ size 4630644216
model-00044-of-00063.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fb22283b94e2c0927d947f205eac578f0f3973826acf3f49064522dfa5193867
3
+ size 4630578456
model-00045-of-00063.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:398bb11c9efe5118e3cebc19836c2c607ad4a097953809a4530c9b2e3a6171b1
3
+ size 4630644224