Upload model trained with Unsloth
Browse filesUpload model trained with Unsloth 2x faster
- adapter_config.json +47 -0
- adapter_model.safetensors +3 -0
adapter_config.json
ADDED
|
@@ -0,0 +1,47 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "mesolitica/Llama-3.2-3B-Malaysian-Reasoning",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"eva_config": null,
|
| 7 |
+
"exclude_modules": null,
|
| 8 |
+
"fan_in_fan_out": false,
|
| 9 |
+
"inference_mode": true,
|
| 10 |
+
"init_lora_weights": true,
|
| 11 |
+
"layer_replication": null,
|
| 12 |
+
"layers_pattern": null,
|
| 13 |
+
"layers_to_transform": [
|
| 14 |
+
11,
|
| 15 |
+
12,
|
| 16 |
+
13,
|
| 17 |
+
14,
|
| 18 |
+
15,
|
| 19 |
+
16,
|
| 20 |
+
17,
|
| 21 |
+
18,
|
| 22 |
+
19,
|
| 23 |
+
20,
|
| 24 |
+
21,
|
| 25 |
+
22,
|
| 26 |
+
23,
|
| 27 |
+
24,
|
| 28 |
+
25
|
| 29 |
+
],
|
| 30 |
+
"loftq_config": {},
|
| 31 |
+
"lora_alpha": 64,
|
| 32 |
+
"lora_bias": false,
|
| 33 |
+
"lora_dropout": 0,
|
| 34 |
+
"megatron_config": null,
|
| 35 |
+
"megatron_core": "megatron.core",
|
| 36 |
+
"modules_to_save": null,
|
| 37 |
+
"peft_type": "LORA",
|
| 38 |
+
"r": 819,
|
| 39 |
+
"rank_pattern": {},
|
| 40 |
+
"revision": null,
|
| 41 |
+
"target_modules": [
|
| 42 |
+
"gate_proj"
|
| 43 |
+
],
|
| 44 |
+
"task_type": "CAUSAL_LM",
|
| 45 |
+
"use_dora": false,
|
| 46 |
+
"use_rslora": true
|
| 47 |
+
}
|
adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3410d771b31830fe50a6f60f4a884f6a0eba8e50a9945299d3d1851b1bd7001f
|
| 3 |
+
size 553517032
|