Hugging Face's logo

punsaisuwan
/
frankenmoe-python-typescript

MLX
lora
mixture-of-experts
code-generation
python
typescript
reasoning
streaming
Model card Files
xet
 Community
punsaisuwan commited on
Commit
2d2ceee
·
verified ·
1 Parent(s): 208d6e0

v2: Add Expert 3: Reasoning adapter weights

Browse files
Files changed (12) hide show
  1. adapters/expert-3-reasoning/0000100_adapters.safetensors +3 -0
  2. adapters/expert-3-reasoning/0000200_adapters.safetensors +3 -0
  3. adapters/expert-3-reasoning/0000300_adapters.safetensors +3 -0
  4. adapters/expert-3-reasoning/0000400_adapters.safetensors +3 -0
  5. adapters/expert-3-reasoning/0000500_adapters.safetensors +3 -0
  6. adapters/expert-3-reasoning/0000600_adapters.safetensors +3 -0
  7. adapters/expert-3-reasoning/0000700_adapters.safetensors +3 -0
  8. adapters/expert-3-reasoning/0000800_adapters.safetensors +3 -0
  9. adapters/expert-3-reasoning/0000900_adapters.safetensors +3 -0
  10. adapters/expert-3-reasoning/0001000_adapters.safetensors +3 -0
  11. adapters/expert-3-reasoning/adapter_config.json +40 -0
  12. adapters/expert-3-reasoning/adapters.safetensors +3 -0
adapters/expert-3-reasoning/0000100_adapters.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1b1a146927c2b65167ef6ac92bf5a3ba7b253b2ccd79df76c92a121bb29d1a3b
3
+ size 109359657
adapters/expert-3-reasoning/0000200_adapters.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a68736d8780678b399fdd3c40b6df68a314435636fc68a33354908a2b16ea349
3
+ size 109359657
adapters/expert-3-reasoning/0000300_adapters.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a9d88f5044c9c38c044847f086f4bfd9d33e7702fee8335d47ccc0b24d4912e0
3
+ size 109359657
adapters/expert-3-reasoning/0000400_adapters.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8312811178f2ac33caadd174f9c05bc25f371078e3a95a11e632f59464c7247f
3
+ size 109359657
adapters/expert-3-reasoning/0000500_adapters.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a9bf7f755487aae152dd171607ebaa70d198ffc3491e8a1f40e5d7f844501e38
3
+ size 109359657
adapters/expert-3-reasoning/0000600_adapters.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:317002399d7cc35097651ac57de34fcf9bd83b54a6a69ff24650682968401b25
3
+ size 109359657
adapters/expert-3-reasoning/0000700_adapters.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b8a58e48dd11d6f2e91e026619681b2f68ddf4fb8253a8f2c1204b519f990bee
3
+ size 109359657
adapters/expert-3-reasoning/0000800_adapters.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1fa1031d13be0985470686ef73b312cacef296a6d828d657a04c2448d6aa726c
3
+ size 109359657
adapters/expert-3-reasoning/0000900_adapters.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:294a65ac55cf4f08eddf336a3c523410be915910df6b31bc27ea4f86ff389709
3
+ size 109359657
adapters/expert-3-reasoning/0001000_adapters.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e956973ed7c14bc53675d8b60e32715f54bd8f24e84f6b9456ba7049903ee095
3
+ size 109359657
adapters/expert-3-reasoning/adapter_config.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "adapter_path": "./adapters/expert-3-reasoning",
3
+ "batch_size": 1,
4
+ "config": null,
5
+ "data": "data",
6
+ "fine_tune_type": "lora",
7
+ "grad_accumulation_steps": 1,
8
+ "grad_checkpoint": false,
9
+ "iters": 1000,
10
+ "learning_rate": 1e-05,
11
+ "lora_parameters": {
12
+ "rank": 8,
13
+ "dropout": 0.0,
14
+ "scale": 20.0
15
+ },
16
+ "lr_schedule": null,
17
+ "mask_prompt": true,
18
+ "max_seq_length": 4096,
19
+ "model": "./output-moe-mlx-4bit",
20
+ "num_layers": 16,
21
+ "optimizer": "adam",
22
+ "optimizer_config": {
23
+ "adam": {},
24
+ "adamw": {},
25
+ "muon": {},
26
+ "sgd": {},
27
+ "adafactor": {}
28
+ },
29
+ "project_name": null,
30
+ "report_to": null,
31
+ "resume_adapter_file": null,
32
+ "save_every": 100,
33
+ "seed": 0,
34
+ "steps_per_eval": 100,
35
+ "steps_per_report": 10,
36
+ "test": false,
37
+ "test_batches": 500,
38
+ "train": true,
39
+ "val_batches": 25
40
+ }
adapters/expert-3-reasoning/adapters.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e956973ed7c14bc53675d8b60e32715f54bd8f24e84f6b9456ba7049903ee095
3
+ size 109359657