Instructions to use gradientdegen/task-12-Megatron-7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use gradientdegen/task-12-Megatron-7B with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2.5-7B-Instruct") model = PeftModel.from_pretrained(base_model, "gradientdegen/task-12-Megatron-7B") - Notebooks
- Google Colab
- Kaggle
Upload folder using huggingface_hub
Browse files- adapter_config.json +5 -5
- adapter_model.safetensors +1 -1
adapter_config.json
CHANGED
|
@@ -3,13 +3,13 @@
|
|
| 3 |
"peft_type": "LORA",
|
| 4 |
"use_rslora": false,
|
| 5 |
"target_modules": [
|
| 6 |
-
"up_proj",
|
| 7 |
-
"gate_proj",
|
| 8 |
-
"k_proj",
|
| 9 |
"v_proj",
|
| 10 |
"down_proj",
|
| 11 |
-
"
|
| 12 |
-
"
|
|
|
|
|
|
|
|
|
|
| 13 |
],
|
| 14 |
"task_type": "CAUSAL_LM",
|
| 15 |
"r": 128,
|
|
|
|
| 3 |
"peft_type": "LORA",
|
| 4 |
"use_rslora": false,
|
| 5 |
"target_modules": [
|
|
|
|
|
|
|
|
|
|
| 6 |
"v_proj",
|
| 7 |
"down_proj",
|
| 8 |
+
"k_proj",
|
| 9 |
+
"gate_proj",
|
| 10 |
+
"o_proj",
|
| 11 |
+
"up_proj",
|
| 12 |
+
"q_proj"
|
| 13 |
],
|
| 14 |
"task_type": "CAUSAL_LM",
|
| 15 |
"r": 128,
|
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1736241568
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ba74813d8d062726299d9ebc1aba007d83cc0b55498ad20eb48047fb56b2a124
|
| 3 |
size 1736241568
|