agentlans commited on
Commit
97acbab
·
1 Parent(s): ba0ec1f

Add model files

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 +58 -3
  3. config.json +40 -0
  4. mergekit_config.yml +22 -0
  5. model-00001-of-00291.safetensors +3 -0
  6. model-00002-of-00291.safetensors +3 -0
  7. model-00003-of-00291.safetensors +3 -0
  8. model-00004-of-00291.safetensors +3 -0
  9. model-00005-of-00291.safetensors +3 -0
  10. model-00006-of-00291.safetensors +3 -0
  11. model-00007-of-00291.safetensors +3 -0
  12. model-00008-of-00291.safetensors +3 -0
  13. model-00009-of-00291.safetensors +3 -0
  14. model-00010-of-00291.safetensors +3 -0
  15. model-00011-of-00291.safetensors +3 -0
  16. model-00012-of-00291.safetensors +3 -0
  17. model-00013-of-00291.safetensors +3 -0
  18. model-00014-of-00291.safetensors +3 -0
  19. model-00015-of-00291.safetensors +3 -0
  20. model-00016-of-00291.safetensors +3 -0
  21. model-00017-of-00291.safetensors +3 -0
  22. model-00018-of-00291.safetensors +3 -0
  23. model-00019-of-00291.safetensors +3 -0
  24. model-00020-of-00291.safetensors +3 -0
  25. model-00021-of-00291.safetensors +3 -0
  26. model-00022-of-00291.safetensors +3 -0
  27. model-00023-of-00291.safetensors +3 -0
  28. model-00024-of-00291.safetensors +3 -0
  29. model-00025-of-00291.safetensors +3 -0
  30. model-00026-of-00291.safetensors +3 -0
  31. model-00027-of-00291.safetensors +3 -0
  32. model-00028-of-00291.safetensors +3 -0
  33. model-00029-of-00291.safetensors +3 -0
  34. model-00030-of-00291.safetensors +3 -0
  35. model-00031-of-00291.safetensors +3 -0
  36. model-00032-of-00291.safetensors +3 -0
  37. model-00033-of-00291.safetensors +3 -0
  38. model-00034-of-00291.safetensors +3 -0
  39. model-00035-of-00291.safetensors +3 -0
  40. model-00036-of-00291.safetensors +3 -0
  41. model-00037-of-00291.safetensors +3 -0
  42. model-00038-of-00291.safetensors +3 -0
  43. model-00039-of-00291.safetensors +3 -0
  44. model-00040-of-00291.safetensors +3 -0
  45. model-00041-of-00291.safetensors +3 -0
  46. model-00042-of-00291.safetensors +3 -0
  47. model-00043-of-00291.safetensors +3 -0
  48. model-00044-of-00291.safetensors +3 -0
  49. model-00045-of-00291.safetensors +3 -0
  50. model-00046-of-00291.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 CHANGED
@@ -1,3 +1,58 @@
1
- ---
2
- license: llama3.1
3
- ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: llama3.1
3
+ base_model:
4
+ - DreadPoor/LemonP-8B-Model_Stock
5
+ - Youlln/1PARAMMYL-8B-ModelStock
6
+ - jaspionjader/f-2-8b
7
+ - Etherll/SuperHermes
8
+ - meta-llama/Llama-3.1-8B-Instruct
9
+ tags:
10
+ - merge
11
+ - mergekit
12
+ ---
13
+ # Llama 3.1 Daredevilish Instruct
14
+
15
+ - This model is an experimental Llama 3.1-based merge, inspired by the approach used in [mlabonne/Daredevil-8B](https://huggingface.co/mlabonne/Daredevil-8B).
16
+ - It combines top-performing Llama 3.1 8B models on the MMLU-Pro benchmark from the [Open LLM Leaderboard](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/) as of January 21, 2025.
17
+ - Its straightforward language makes it accessible and potentially valuable for everyday use.
18
+
19
+ ## Model Details
20
+
21
+ - **Architecture:** Llama 3.1 (8.03B parameters)
22
+ - **Training:** Merged from top MMLU-Pro models without additional finetuning
23
+ - **Release Date:** January 21, 2025
24
+
25
+ ## Merge Configuration
26
+
27
+ The model was created using [mergekit](https://github.com/arcee-ai/mergekit) with the following merge configuration:
28
+
29
+ ```yaml
30
+ models:
31
+ - model: DreadPoor/LemonP-8B-Model_Stock
32
+ parameters:
33
+ density: 0.6
34
+ weight: 0.16
35
+ - model: Youlln/1PARAMMYL-8B-ModelStock
36
+ parameters:
37
+ density: 0.6
38
+ weight: 0.13
39
+ - model: jaspionjader/f-2-8b
40
+ parameters:
41
+ density: 0.6
42
+ weight: 0.10
43
+ - model: Etherll/SuperHermes
44
+ parameters:
45
+ density: 0.6
46
+ weight: 0.08
47
+ merge_method: dare_ties
48
+ base_model: meta-llama/Llama-3.1-8B-Instruct
49
+ dtype: bfloat16
50
+ ```
51
+
52
+ ## Usage and Limitations
53
+
54
+ This experimental model is designed for research and development purposes. Users should be aware of potential biases and limitations inherent in language models. Always validate outputs and use the model responsibly.
55
+
56
+ ## Future Work
57
+
58
+ Further evaluation and fine-tuning may be necessary to optimize performance across various tasks. Researchers are encouraged to build upon this experimental merge to advance the capabilities of Llama-based models.
config.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/drive2/Meta-Llama-3.1-8B-Instruct",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 128000,
9
+ "eos_token_id": [
10
+ 128001,
11
+ 128008,
12
+ 128009
13
+ ],
14
+ "head_dim": 128,
15
+ "hidden_act": "silu",
16
+ "hidden_size": 4096,
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 14336,
19
+ "max_position_embeddings": 131072,
20
+ "mlp_bias": false,
21
+ "model_type": "llama",
22
+ "num_attention_heads": 32,
23
+ "num_hidden_layers": 32,
24
+ "num_key_value_heads": 8,
25
+ "pretraining_tp": 1,
26
+ "rms_norm_eps": 1e-05,
27
+ "rope_scaling": {
28
+ "factor": 8.0,
29
+ "high_freq_factor": 4.0,
30
+ "low_freq_factor": 1.0,
31
+ "original_max_position_embeddings": 8192,
32
+ "rope_type": "llama3"
33
+ },
34
+ "rope_theta": 500000.0,
35
+ "tie_word_embeddings": false,
36
+ "torch_dtype": "bfloat16",
37
+ "transformers_version": "4.47.1",
38
+ "use_cache": true,
39
+ "vocab_size": 128256
40
+ }
mergekit_config.yml ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ models:
2
+ # - model: /drive2/Meta-Llama-3.1-8B
3
+ # No parameters necessary for base model
4
+ - model: /drive2/LemonP-8B-Model_Stock
5
+ parameters:
6
+ density: 0.6
7
+ weight: 0.16
8
+ - model: /drive2/1PARAMMYL-8B-ModelStock
9
+ parameters:
10
+ density: 0.6
11
+ weight: 0.13
12
+ - model: /drive2/f-2-8b
13
+ parameters:
14
+ density: 0.6
15
+ weight: 0.10
16
+ - model: /drive2/SuperHermes
17
+ parameters:
18
+ density: 0.6
19
+ weight: 0.08
20
+ merge_method: dare_ties
21
+ base_model: /drive2/Meta-Llama-3.1-8B-Instruct
22
+ dtype: bfloat16
model-00001-of-00291.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:48bcd693c6e6ba2fa8d26200f2b80f1a0f65a863479c1502ee5e9403dd9553fb
3
+ size 1050673280
model-00002-of-00291.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f41791c0e751f682ddc620a262083dcbe684c163ceac5c583098ecc38401c613
3
+ size 1050673296
model-00003-of-00291.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6bb91a6330845a9c7fdb0570aa0dfc8f8c8aa68427fef55247082b71e35257c2
3
+ size 8328
model-00004-of-00291.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:231e77f796993d9cc04317ad9e7e0c826df8224cad5da33a73099558097c8369
3
+ size 117440664
model-00005-of-00291.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:144593b3aa70643e6732f0f8378fd4597435599c4bfb755b2d8a13215738b8f4
3
+ size 117440664
model-00006-of-00291.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bdaca8672cc52abc09be8d5a3e3be903f9ebbcc5ac0a0429725dab8e6370bcb3
3
+ size 117440656
model-00007-of-00291.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:31468fe56201d4918e1854e082658554455e5453ffc78091310231defdf2fb45
3
+ size 8344
model-00008-of-00291.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:463c5b13e60e4658b97425aec0cb72b8a640bc651fc9e174cd7f320730fe3d0d
3
+ size 8388760
model-00009-of-00291.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:78982d67f377cfc198387ab90d0a05a6789935ce509d11446a660d256a43e7c2
3
+ size 33554584
model-00010-of-00291.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc472e81510b41ad041670e17f07acac8ca6ecceac5e9be6d9e84d81bf75f263
3
+ size 33554584
model-00011-of-00291.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e82f3e4f818ab38b23b0a26bff290b069f42899c1753ec7055591b61ff892cce
3
+ size 8388760
model-00012-of-00291.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c8fac3a2ab956248a1ddc1de0b7869675cf7cdcfc1821d726ff8f6e5eb75e673
3
+ size 8328
model-00013-of-00291.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:466ba7ce15863a25ec7cf01b58fcd8c6e8e48f953bcdb64440413421e545c0be
3
+ size 117440664
model-00014-of-00291.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d785e16910941c837b434fb6b6fe349fbaa65fd8bf948dfe2153953b5f0fcbf9
3
+ size 117440664
model-00015-of-00291.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f79d17fe35dc5ec02c9f41d0cae3101040cb916d547f171703a57dd0c7c1c5f1
3
+ size 117440656
model-00016-of-00291.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e170a9942aed3f44c58945558253326ffcad46ae79e7c89be3061189d5cb716e
3
+ size 8344
model-00017-of-00291.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8ce06b6468ca959a74b41a277c3dbce70b0b1775dd81c955f9d05ff11000b143
3
+ size 8388760
model-00018-of-00291.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f4d9b6cc7cb910849c6bd99ed69fc8d1468380fef3ea7fc08b125ce1eb7bca1
3
+ size 33554584
model-00019-of-00291.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1fb2cb39c66909dc270db4691a55d693831330e0c02d0d252a1ee5dc2f8b95a8
3
+ size 33554584
model-00020-of-00291.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e6e77fca9e726657484df5e4bb2812bc75d5062315a0e0503886b8c00cd6961b
3
+ size 8388760
model-00021-of-00291.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:89fb1f275e36ef798ef1220e31e113fa863af4155f86cb1b0871acbf97eb7e24
3
+ size 8336
model-00022-of-00291.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ee06121da4ccc6e23f00484cc6676c0ce313f7373d97ce6b0a4bf73511c11057
3
+ size 117440664
model-00023-of-00291.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4629434a1801f24b117b4ba6f9a47de14590fe3dae65aeddff4261136556455f
3
+ size 117440664
model-00024-of-00291.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a944ea73a4a51fe81f1a185ba09e7819222af55ab78bf2b28e0edf8596b895b3
3
+ size 117440656
model-00025-of-00291.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:83581d5be00c2d98c8b0be17f8f83852928db7bbd554702bbd7798c4449d651d
3
+ size 8344
model-00026-of-00291.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e6424680bca87917378783d6fe22fb456fe7846d09529734ceeb32008f491bc
3
+ size 8388760
model-00027-of-00291.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:55d61d15b1b4993a5a0693252eddf3b3bf21b3f352865f047640c13185a031d5
3
+ size 33554584
model-00028-of-00291.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aafcfc8b47f287b06aad4d5162e7321648b132c260354fb3460a86475225226c
3
+ size 33554584
model-00029-of-00291.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6c2c15b79770d5633b8017e1efb30495750409edd84b8529c4d71bd383f18f27
3
+ size 8388760
model-00030-of-00291.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3dfeec97632f16871cc35c1bc95cb6c0c91ddd582fdc536fdcfa57f1bd5390bf
3
+ size 8336
model-00031-of-00291.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f2f4b87151b60360b4cb37ae58769bcaedcba5c8c1da4da28234131b9ace076
3
+ size 117440664
model-00032-of-00291.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fdf3b322b060cd31bf7055921a10b44bd10723e810e33849d31c8c4ed76bd720
3
+ size 117440664
model-00033-of-00291.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dec93cc333797619ea16d528f862be9c0bea84e6702ef0ef75da9c650d776ae4
3
+ size 117440656
model-00034-of-00291.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:463f3215e847f98ee6b1cefa3c1040a2e2e1b68e01ea666b0520e7bf01539a6a
3
+ size 8344
model-00035-of-00291.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:64d862bd58379dde9c786fd59f2250d5f02078bf9b48da4ffe3b5a7269f9c9b2
3
+ size 8388760
model-00036-of-00291.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:23686920633d566bf1e312e833ad7751b9cf61dcdaafdf3d6a662c21ab903484
3
+ size 33554584
model-00037-of-00291.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:88e2a6cd87ec1088687cff1d8c364a59b7d0287ecf054c2bb926fc86e7c17770
3
+ size 33554584
model-00038-of-00291.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f8c2694d63e7f463634d6d68f5e6e193f5401040ca68c7adaad974ed3a81f120
3
+ size 8388760
model-00039-of-00291.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4f8ba6390eab0203b5935f4d7700a9c7662edf9e949c16f8af2d022883823abe
3
+ size 8336
model-00040-of-00291.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:30d49b274125ea38b59e391c0b6f1149ac1f21cf64ba3aeaf766f2a8c0dca50d
3
+ size 117440664
model-00041-of-00291.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:78cfc3cc8ef0ae1483b891cf822de3b7046d8431ba55ce88dbfa9d565178a5e7
3
+ size 117440664
model-00042-of-00291.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:921009efaf516e3488e25b99e9ce3954bbc8038f23a14328da5a0c40b6cf105b
3
+ size 117440656
model-00043-of-00291.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4f8387d5b43c5514ff090e22f43d288392bbcea63024c53e42c920b8b175990b
3
+ size 8344
model-00044-of-00291.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b364cb23ba0ae839ad7fbea311b568e7f7aece30cefcf546e3396ba06986994f
3
+ size 8388760
model-00045-of-00291.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fc503bee2ee380b90650b47decbc63f7e36a9f17cbf1c1ee7fc087eccc382a4d
3
+ size 33554584
model-00046-of-00291.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:176a4da73626f8de0482a2745c6f4396485875bc731d27fcdbf6914e8c43a185
3
+ size 33554584