Instructions to use kulits/BrickNet-4B-SFT with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use kulits/BrickNet-4B-SFT with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3-4B") model = PeftModel.from_pretrained(base_model, "kulits/BrickNet-4B-SFT") - Notebooks
- Google Colab
- Kaggle
Initial upload
Browse files- README.md +8 -0
- adapter_config.json +19 -0
- adapter_model.safetensors +3 -0
README.md
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: peft
|
| 3 |
+
base_model: kulits/BrickNet-4B-PT
|
| 4 |
+
pipeline_tag: text-generation
|
| 5 |
+
tags:
|
| 6 |
+
- peft
|
| 7 |
+
- lora
|
| 8 |
+
---
|
adapter_config.json
ADDED
|
@@ -0,0 +1,19 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"inference_mode": true,
|
| 3 |
+
"task_type": "CAUSAL_LM",
|
| 4 |
+
"r": 32,
|
| 5 |
+
"lora_dropout": 0.0,
|
| 6 |
+
"base_model_name_or_path": "Qwen/Qwen3-4B",
|
| 7 |
+
"bias": "none",
|
| 8 |
+
"peft_type": "LORA",
|
| 9 |
+
"target_modules": [
|
| 10 |
+
"q_proj",
|
| 11 |
+
"k_proj",
|
| 12 |
+
"v_proj",
|
| 13 |
+
"o_proj",
|
| 14 |
+
"gate_proj",
|
| 15 |
+
"up_proj",
|
| 16 |
+
"down_proj"
|
| 17 |
+
],
|
| 18 |
+
"lora_alpha": 64
|
| 19 |
+
}
|
adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4dfcc9e6ad5620f4b0579c576030e0b19190ff0094fa446bb74631026e9b4439
|
| 3 |
+
size 132188360
|