Instructions to use cragtmp/domain0529 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use cragtmp/domain0529 with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("/data1/chenjiazun/LLM/Llama-3.2-11B-Vision-Instruct") model = PeftModel.from_pretrained(base_model, "cragtmp/domain0529") - Notebooks
- Google Colab
- Kaggle
chen commited on
Upload folder using huggingface_hub
Browse files- adapter_config.json +1 -1
adapter_config.json
CHANGED
|
@@ -22,7 +22,7 @@
|
|
| 22 |
"r": 8,
|
| 23 |
"rank_pattern": {},
|
| 24 |
"revision": null,
|
| 25 |
-
"target_modules": "(?:.*?(?:vision|image|visual|patch|language|text).*?(?:self_attn|attention|attn|mlp|feed_forward|ffn|dense).*?(?:q_proj|k_proj|v_proj|o_proj|fc1|fc2|gate_proj|up_proj|down_proj)
|
| 26 |
"task_type": "CAUSAL_LM",
|
| 27 |
"use_dora": false,
|
| 28 |
"use_rslora": false
|
|
|
|
| 22 |
"r": 8,
|
| 23 |
"rank_pattern": {},
|
| 24 |
"revision": null,
|
| 25 |
+
"target_modules": "(?:.*?(?:vision|image|visual|patch|language|text).*?(?:self_attn|attention|attn|mlp|feed_forward|ffn|dense).*?(?:q_proj|k_proj|v_proj|o_proj|fc1|fc2|gate_proj|up_proj|down_proj))|(?:\\bmodel\\.layers\\.[\\d]{1,}\\.(?:self_attn|attention|attn|mlp|feed_forward|ffn|dense)\\.(?:q_proj|k_proj|v_proj|o_proj|fc1|fc2|gate_proj|up_proj|down_proj))",
|
| 26 |
"task_type": "CAUSAL_LM",
|
| 27 |
"use_dora": false,
|
| 28 |
"use_rslora": false
|