Instructions to use quin210/qwen3-4b-sft-dpo-grpo with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use quin210/qwen3-4b-sft-dpo-grpo with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("quin210/qwen3-4b-sft-dpo-grpo", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Upload Qwen3ForCausalLM
Browse files- adapter_config.json +5 -5
- generation_config.json +13 -0
adapter_config.json
CHANGED
|
@@ -29,13 +29,13 @@
|
|
| 29 |
"rank_pattern": {},
|
| 30 |
"revision": null,
|
| 31 |
"target_modules": [
|
| 32 |
-
"
|
| 33 |
-
"k_proj",
|
| 34 |
"o_proj",
|
| 35 |
-
"
|
| 36 |
"v_proj",
|
| 37 |
-
"
|
| 38 |
-
"
|
|
|
|
| 39 |
],
|
| 40 |
"target_parameters": null,
|
| 41 |
"task_type": "CAUSAL_LM",
|
|
|
|
| 29 |
"rank_pattern": {},
|
| 30 |
"revision": null,
|
| 31 |
"target_modules": [
|
| 32 |
+
"down_proj",
|
|
|
|
| 33 |
"o_proj",
|
| 34 |
+
"gate_proj",
|
| 35 |
"v_proj",
|
| 36 |
+
"up_proj",
|
| 37 |
+
"q_proj",
|
| 38 |
+
"k_proj"
|
| 39 |
],
|
| 40 |
"target_parameters": null,
|
| 41 |
"task_type": "CAUSAL_LM",
|
generation_config.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 151643,
|
| 3 |
+
"do_sample": true,
|
| 4 |
+
"eos_token_id": [
|
| 5 |
+
151645,
|
| 6 |
+
151643
|
| 7 |
+
],
|
| 8 |
+
"pad_token_id": 151643,
|
| 9 |
+
"temperature": 0.6,
|
| 10 |
+
"top_k": 20,
|
| 11 |
+
"top_p": 0.95,
|
| 12 |
+
"transformers_version": "5.0.0"
|
| 13 |
+
}
|