Text Generation
PEFT
Safetensors
qlora
tinyllama
cli
command-line
fine-tuning
low-resource
internship
fenrir
Instructions to use Harish2002/cli-lora-tinyllama with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use Harish2002/cli-lora-tinyllama with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("TinyLlama/TinyLlama-1.1B-Chat-v1.0") model = PeftModel.from_pretrained(base_model, "Harish2002/cli-lora-tinyllama") - Notebooks
- Google Colab
- Kaggle
Upload eval_results.json with huggingface_hub
Browse files- eval_results.json +10 -0
eval_results.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"model": "Harish2002/cli-lora-tinyllama",
|
| 3 |
+
"task": "CLI Question Answering",
|
| 4 |
+
"eval_samples": 20,
|
| 5 |
+
"metrics": {
|
| 6 |
+
"accuracy": 0.85,
|
| 7 |
+
"exact_match": 0.75
|
| 8 |
+
},
|
| 9 |
+
"notes": "Model evaluated manually on real CLI questions collected from Stack Overflow. Performance is acceptable for inference in CLI assistance tasks."
|
| 10 |
+
}
|