Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,20 @@
|
|
| 1 |
---
|
| 2 |
license: openrail
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
license: openrail
|
| 3 |
+
model-index:
|
| 4 |
+
- name: SantaCoder
|
| 5 |
+
results:
|
| 6 |
+
- task:
|
| 7 |
+
type: text-generation
|
| 8 |
+
dataset:
|
| 9 |
+
type: nuprl/MultiPL-E
|
| 10 |
+
name: MultiPL HumanEval (Lua)
|
| 11 |
+
metrics:
|
| 12 |
+
- name: pass@1
|
| 13 |
+
type: pass@1
|
| 14 |
+
value: 0.09
|
| 15 |
+
verified: false
|
| 16 |
---
|
| 17 |
+
|
| 18 |
+
This model is a fine-tuned [SantaCoder](https://huggingface.co/bigcode/santacoder), which is
|
| 19 |
+
fine-tuned on a subset of the Lua code found on [The Stack](https://huggingface.co/datasets/bigcode/the-stack-dedup).
|
| 20 |
+
We used [this script](https://github.com/loubnabnl/santacoder-finetuning) for fine-tuning.
|