Update README.md
Browse files
README.md
CHANGED
@@ -5,7 +5,12 @@ base_model: NousResearch/Llama-2-7b-hf
|
|
5 |
|
6 |
# Model Card for Model ID
|
7 |
|
8 |
-
|
|
|
|
|
|
|
|
|
|
|
9 |
|
10 |
|
11 |
|
@@ -23,7 +28,7 @@ base_model: NousResearch/Llama-2-7b-hf
|
|
23 |
- **Model type:** [More Information Needed]
|
24 |
- **Language(s) (NLP):** [More Information Needed]
|
25 |
- **License:** [More Information Needed]
|
26 |
-
- **Finetuned from model [optional]:**
|
27 |
|
28 |
### Model Sources [optional]
|
29 |
|
|
|
5 |
|
6 |
# Model Card for Model ID
|
7 |
|
8 |
+
The Llama 2-7b model has been fine-tuned for code generation task, in Python.
|
9 |
+
It has been trained on 300 samples from the https://huggingface.co/datasets/iamtarun/python_code_instructions_18k_alpaca dataset and
|
10 |
+
903 samples which have been generated synthetically using another LLM. The nature of the synthetic data is similar to the training dataset.
|
11 |
+
PEFT has been used to fine-tune the model.
|
12 |
+
Model performance has been evaluated using codeBLEU evaluation metric.
|
13 |
+
|
14 |
|
15 |
|
16 |
|
|
|
28 |
- **Model type:** [More Information Needed]
|
29 |
- **Language(s) (NLP):** [More Information Needed]
|
30 |
- **License:** [More Information Needed]
|
31 |
+
- **Finetuned from model [optional]:** https://huggingface.co/NousResearch/Llama-2-7b-chat-hf
|
32 |
|
33 |
### Model Sources [optional]
|
34 |
|