Instructions to use coldcurrent/encinitas-gemma4-lora with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use coldcurrent/encinitas-gemma4-lora with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("google/gemma-4-26B-A4B-it") model = PeftModel.from_pretrained(base_model, "coldcurrent/encinitas-gemma4-lora") - Notebooks
- Google Colab
- Kaggle
Upload adapter_config.json with huggingface_hub
Browse files- adapter_config.json +23 -0
adapter_config.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"base_model_name_or_path": "google/gemma-4-26B-A4B-it",
|
| 3 |
+
"bias": "none",
|
| 4 |
+
"fan_in_fan_out": false,
|
| 5 |
+
"inference_mode": true,
|
| 6 |
+
"lora_alpha": 32,
|
| 7 |
+
"lora_dropout": 0.0,
|
| 8 |
+
"r": 16,
|
| 9 |
+
"target_modules": [
|
| 10 |
+
"base_layer",
|
| 11 |
+
"down_proj",
|
| 12 |
+
"experts",
|
| 13 |
+
"gate_proj",
|
| 14 |
+
"k_proj",
|
| 15 |
+
"o_proj",
|
| 16 |
+
"q_proj",
|
| 17 |
+
"up_proj",
|
| 18 |
+
"v_proj"
|
| 19 |
+
],
|
| 20 |
+
"task_type": "CAUSAL_LM",
|
| 21 |
+
"peft_type": "LORA",
|
| 22 |
+
"fw_lora_layout": "fused_peft_3d_v1"
|
| 23 |
+
}
|