Update README.md
Browse files
README.md
CHANGED
|
@@ -5,6 +5,7 @@ base_model:
|
|
| 5 |
---
|
| 6 |
|
| 7 |
The model is derived from Llama-2-7b-hf through pruning using LLM-Streamline **(Streamlining Redundant Layers to Compress Large Language Models, ICLR 2025 Spotlight)**. The entire training process required only 0.06B tokens.
|
|
|
|
| 8 |
Below are the results of the evaluation using lm-eval:
|
| 9 |
| | arc_c | arc_e | boolq | hellaswag | openbookqa | rte | winogrande | Avg |
|
| 10 |
|--------------|-------|-------|-------|-----------|------------|------|------------|------|
|
|
|
|
| 5 |
---
|
| 6 |
|
| 7 |
The model is derived from Llama-2-7b-hf through pruning using LLM-Streamline **(Streamlining Redundant Layers to Compress Large Language Models, ICLR 2025 Spotlight)**. The entire training process required only 0.06B tokens.
|
| 8 |
+
|
| 9 |
Below are the results of the evaluation using lm-eval:
|
| 10 |
| | arc_c | arc_e | boolq | hellaswag | openbookqa | rte | winogrande | Avg |
|
| 11 |
|--------------|-------|-------|-------|-----------|------------|------|------------|------|
|