Create README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
metrics:
|
| 3 |
+
- code_eval
|
| 4 |
+
library_name: transformers
|
| 5 |
+
tags:
|
| 6 |
+
- code
|
| 7 |
+
model-index:
|
| 8 |
+
- name: Tiny-StarCoder-Py
|
| 9 |
+
results:
|
| 10 |
+
- task:
|
| 11 |
+
type: text-generation
|
| 12 |
+
dataset:
|
| 13 |
+
type: openai_humaneval
|
| 14 |
+
name: HumanEval
|
| 15 |
+
metrics:
|
| 16 |
+
- name: pass@1
|
| 17 |
+
type: pass@1
|
| 18 |
+
value: 7.84%
|
| 19 |
+
verified: false
|
| 20 |
+
---
|
| 21 |
+
159M model with the same architecture and tokenizer as StarCoder (8k context length) pre-trained on 100B tokens of Python from StarCoderData (~6 epochs)
|
| 22 |
+
|
| 23 |
+
Full training arguments + loss at: https://wandb.ai/loubnabnl/tiny_starcoder/runs/qogbxkgy/overview?workspace=user-loubnabnl
|
| 24 |
+
|
| 25 |
+
Pass@1: 7.84%
|