Instructions to use webbigdata/C3TR-Adapter with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use webbigdata/C3TR-Adapter with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("unsloth/gemma-2-9b-it-bnb-4bit") model = PeftModel.from_pretrained(base_model, "webbigdata/C3TR-Adapter") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -73,9 +73,7 @@ def trans(my_str):
|
|
| 73 |
|
| 74 |
# Translation
|
| 75 |
generated_ids = model.generate(input_ids=input_ids,
|
| 76 |
-
|
| 77 |
-
use_cache=True,
|
| 78 |
-
prompt_lookup_num_tokens=10
|
| 79 |
)
|
| 80 |
full_outputs = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)
|
| 81 |
return full_outputs[0].split("### Answer:\n")[-1].strip()
|
|
|
|
| 73 |
|
| 74 |
# Translation
|
| 75 |
generated_ids = model.generate(input_ids=input_ids,
|
| 76 |
+
max_new_tokens=800, use_cache=True
|
|
|
|
|
|
|
| 77 |
)
|
| 78 |
full_outputs = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)
|
| 79 |
return full_outputs[0].split("### Answer:\n")[-1].strip()
|