Update README.md
Browse files
README.md
CHANGED
|
@@ -31,7 +31,7 @@ metrics:
|
|
| 31 |
|
| 32 |
# Llama-3.2-1B-Instruct-ORPO
|
| 33 |
|
| 34 |
-
[Evaluation](#evaluation) [Environmental Inpact](#environmental-impact)
|
| 35 |
|
| 36 |
## Model Details
|
| 37 |
|
|
@@ -51,6 +51,9 @@ This model is optimized for general-purpose language tasks.
|
|
| 51 |
|
| 52 |
|
| 53 |
We used the [Eulether](https://github.com/EleutherAI/lm-evaluation-harness) test harness to evaluate the finetuned model.
|
|
|
|
|
|
|
|
|
|
| 54 |
|
| 55 |
| Tasks |Version|Filter|n-shot| Metric | |Value | |Stderr|
|
| 56 |
|---------|------:|------|-----:|--------|---|-----:|---|-----:|
|
|
|
|
| 31 |
|
| 32 |
# Llama-3.2-1B-Instruct-ORPO
|
| 33 |
|
| 34 |
+
[Evaluation](#evaluation) [Environmental Inpact](#environmental-impact)
|
| 35 |
|
| 36 |
## Model Details
|
| 37 |
|
|
|
|
| 51 |
|
| 52 |
|
| 53 |
We used the [Eulether](https://github.com/EleutherAI/lm-evaluation-harness) test harness to evaluate the finetuned model.
|
| 54 |
+
The table below presents a summary of the evaluation performed.
|
| 55 |
+
|
| 56 |
+
For a more granular evaluation on `MMLU`, please see Section [MMLU](#mmlu).
|
| 57 |
|
| 58 |
| Tasks |Version|Filter|n-shot| Metric | |Value | |Stderr|
|
| 59 |
|---------|------:|------|-----:|--------|---|-----:|---|-----:|
|