Commit
•
32699c5
1
Parent(s):
5628b57
Update README.md
Browse files
README.md
CHANGED
|
@@ -17,7 +17,10 @@ tags:
|
|
| 17 |
- code llama
|
| 18 |
---
|
| 19 |
|
| 20 |
-
# **Phind-CodeLlama-34B-v1
|
|
|
|
|
|
|
|
|
|
| 21 |
We've fine-tuned CodeLlama-34B and CodeLlama-34B-Python on an internal Phind dataset that achieve 67.6% and 69.5% pass@1 on HumanEval, respectively. GPT-4 achieves 67%. We've applied OpenAI's decontamination methodology to our dataset to ensure result validity.
|
| 22 |
|
| 23 |
More details can be found on our [blog post](https://www.phind.com/blog/code-llama-beats-gpt4).
|
|
|
|
| 17 |
- code llama
|
| 18 |
---
|
| 19 |
|
| 20 |
+
# NOTE: We've now launched **Phind-CodeLlama-34B-v2**, which acheives **73.8% pass@1** on HumanEval. It is instruction-tuned and much easier to use than this v1 model.
|
| 21 |
+
# Check out Phind-CodeLlama-34B-v2 [here](https://huggingface.co/Phind/Phind-CodeLlama-34B-v2).
|
| 22 |
+
|
| 23 |
+
## **Phind-CodeLlama-34B-v1**
|
| 24 |
We've fine-tuned CodeLlama-34B and CodeLlama-34B-Python on an internal Phind dataset that achieve 67.6% and 69.5% pass@1 on HumanEval, respectively. GPT-4 achieves 67%. We've applied OpenAI's decontamination methodology to our dataset to ensure result validity.
|
| 25 |
|
| 26 |
More details can be found on our [blog post](https://www.phind.com/blog/code-llama-beats-gpt4).
|