Instructions to use yeok/Qwen3-8B-random_insertion-rl with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use yeok/Qwen3-8B-random_insertion-rl with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("yeok/Qwen3-8B-random_insertion-rl", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Unsloth Desktop
Epoch 0 (Trained with Unsloth)
Browse filesUpload model trained with Unsloth 2x faster
- adapter_config.json +2 -2
- adapter_model.safetensors +1 -1
adapter_config.json
CHANGED
|
@@ -29,12 +29,12 @@
|
|
| 29 |
"rank_pattern": {},
|
| 30 |
"revision": null,
|
| 31 |
"target_modules": [
|
|
|
|
| 32 |
"down_proj",
|
| 33 |
"v_proj",
|
| 34 |
-
"up_proj",
|
| 35 |
"q_proj",
|
| 36 |
-
"k_proj",
|
| 37 |
"o_proj",
|
|
|
|
| 38 |
"gate_proj"
|
| 39 |
],
|
| 40 |
"target_parameters": null,
|
|
|
|
| 29 |
"rank_pattern": {},
|
| 30 |
"revision": null,
|
| 31 |
"target_modules": [
|
| 32 |
+
"up_proj",
|
| 33 |
"down_proj",
|
| 34 |
"v_proj",
|
|
|
|
| 35 |
"q_proj",
|
|
|
|
| 36 |
"o_proj",
|
| 37 |
+
"k_proj",
|
| 38 |
"gate_proj"
|
| 39 |
],
|
| 40 |
"target_parameters": null,
|
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 349243752
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1fc4e42402cf95fe356d023cd2a085ac85787fbb0f1019f433b5cf89a1f44c71
|
| 3 |
size 349243752
|