Upload folder using huggingface_hub
Browse files- README.md +3 -0
- light/adapter_config.json +41 -0
- light/adapters.safetensors +3 -0
- smart/adapter_config.json +41 -0
- smart/adapters.safetensors +3 -0
README.md
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# LC-350M LoRA adapters for LiquidAI/LFM2.5-350M-MLX-4bit
|
| 2 |
+
Base: LiquidAI/LFM2.5-350M-MLX-4bit
|
| 3 |
+
See https://github.com/vasanthsreeram/lc-350m
|
light/adapter_config.json
ADDED
|
@@ -0,0 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"adapter_path": "/Users/vas/Documents/macwispr/bench/polish_finetune/adapters/lfm350-polish-teacher",
|
| 3 |
+
"batch_size": 2,
|
| 4 |
+
"clear_cache_threshold": 0,
|
| 5 |
+
"config": null,
|
| 6 |
+
"data": "/Users/vas/Documents/macwispr/bench/polish_finetune/data",
|
| 7 |
+
"fine_tune_type": "lora",
|
| 8 |
+
"grad_accumulation_steps": 1,
|
| 9 |
+
"grad_checkpoint": false,
|
| 10 |
+
"iters": 800,
|
| 11 |
+
"learning_rate": 1e-05,
|
| 12 |
+
"lora_parameters": {
|
| 13 |
+
"rank": 8,
|
| 14 |
+
"dropout": 0.0,
|
| 15 |
+
"scale": 20.0
|
| 16 |
+
},
|
| 17 |
+
"lr_schedule": null,
|
| 18 |
+
"mask_prompt": true,
|
| 19 |
+
"max_seq_length": 512,
|
| 20 |
+
"model": "LiquidAI/LFM2.5-350M-MLX-4bit",
|
| 21 |
+
"num_layers": 8,
|
| 22 |
+
"optimizer": "adam",
|
| 23 |
+
"optimizer_config": {
|
| 24 |
+
"adam": {},
|
| 25 |
+
"adamw": {},
|
| 26 |
+
"muon": {},
|
| 27 |
+
"sgd": {},
|
| 28 |
+
"adafactor": {}
|
| 29 |
+
},
|
| 30 |
+
"project_name": null,
|
| 31 |
+
"report_to": null,
|
| 32 |
+
"resume_adapter_file": null,
|
| 33 |
+
"save_every": 100,
|
| 34 |
+
"seed": 42,
|
| 35 |
+
"steps_per_eval": 50,
|
| 36 |
+
"steps_per_report": 10,
|
| 37 |
+
"test": false,
|
| 38 |
+
"test_batches": 500,
|
| 39 |
+
"train": true,
|
| 40 |
+
"val_batches": 25
|
| 41 |
+
}
|
light/adapters.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:48da6ac57b1e654bacf54030127c893d9663ce5f7d974314e30f38bc4e7896b3
|
| 3 |
+
size 6039553
|
smart/adapter_config.json
ADDED
|
@@ -0,0 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"adapter_path": "polish_finetune/adapters/lfm350-smart-course",
|
| 3 |
+
"batch_size": 2,
|
| 4 |
+
"clear_cache_threshold": 0,
|
| 5 |
+
"config": null,
|
| 6 |
+
"data": "polish_finetune/data/smart",
|
| 7 |
+
"fine_tune_type": "lora",
|
| 8 |
+
"grad_accumulation_steps": 1,
|
| 9 |
+
"grad_checkpoint": false,
|
| 10 |
+
"iters": 600,
|
| 11 |
+
"learning_rate": 1e-05,
|
| 12 |
+
"lora_parameters": {
|
| 13 |
+
"rank": 8,
|
| 14 |
+
"dropout": 0.0,
|
| 15 |
+
"scale": 20.0
|
| 16 |
+
},
|
| 17 |
+
"lr_schedule": null,
|
| 18 |
+
"mask_prompt": true,
|
| 19 |
+
"max_seq_length": 512,
|
| 20 |
+
"model": "LiquidAI/LFM2.5-350M-MLX-4bit",
|
| 21 |
+
"num_layers": 8,
|
| 22 |
+
"optimizer": "adam",
|
| 23 |
+
"optimizer_config": {
|
| 24 |
+
"adam": {},
|
| 25 |
+
"adamw": {},
|
| 26 |
+
"muon": {},
|
| 27 |
+
"sgd": {},
|
| 28 |
+
"adafactor": {}
|
| 29 |
+
},
|
| 30 |
+
"project_name": null,
|
| 31 |
+
"report_to": null,
|
| 32 |
+
"resume_adapter_file": null,
|
| 33 |
+
"save_every": 100,
|
| 34 |
+
"seed": 42,
|
| 35 |
+
"steps_per_eval": 50,
|
| 36 |
+
"steps_per_report": 10,
|
| 37 |
+
"test": false,
|
| 38 |
+
"test_batches": 500,
|
| 39 |
+
"train": true,
|
| 40 |
+
"val_batches": 25
|
| 41 |
+
}
|
smart/adapters.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2c07d6f72e72c0a445213133ecbdb29cc1bd678a00ae7772959237155bd6bd42
|
| 3 |
+
size 6039553
|