Create README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model:
|
| 3 |
+
- Sao10K/L3-8B-Stheno-v3.2
|
| 4 |
+
---
|
| 5 |
+
vllm (pretrained=/root/autodl-tmp/L3-8B-Stheno-v3.2,add_bos_token=true,max_model_len=2048,dtype=bfloat16), gen_kwargs: (None), limit: 250.0, num_fewshot: 5, batch_size: auto
|
| 6 |
+
|Tasks|Version| Filter |n-shot| Metric | |Value| |Stderr|
|
| 7 |
+
|-----|------:|----------------|-----:|-----------|---|----:|---|-----:|
|
| 8 |
+
|gsm8k| 3|flexible-extract| 5|exact_match|↑ |0.772|± |0.0266|
|
| 9 |
+
| | |strict-match | 5|exact_match|↑ |0.772|± |0.0266|
|
| 10 |
+
|
| 11 |
+
vllm (pretrained=/root/autodl-tmp/L3-8B-Stheno-v3.2,add_bos_token=true,max_model_len=2048,dtype=bfloat16), gen_kwargs: (None), limit: 500.0, num_fewshot: 5, batch_size: auto
|
| 12 |
+
|Tasks|Version| Filter |n-shot| Metric | |Value| |Stderr|
|
| 13 |
+
|-----|------:|----------------|-----:|-----------|---|----:|---|-----:|
|
| 14 |
+
|gsm8k| 3|flexible-extract| 5|exact_match|↑ |0.790|± |0.0182|
|
| 15 |
+
| | |strict-match | 5|exact_match|↑ |0.796|± |0.0180|
|
| 16 |
+
|
| 17 |
+
|
| 18 |
+
vllm (pretrained=/root/autodl-tmp/L3-8B-Stheno-v3.2-80,add_bos_token=true,max_model_len=2048,dtype=bfloat16), gen_kwargs: (None), limit: 250.0, num_fewshot: 5, batch_size: auto
|
| 19 |
+
|Tasks|Version| Filter |n-shot| Metric | |Value| |Stderr|
|
| 20 |
+
|-----|------:|----------------|-----:|-----------|---|----:|---|-----:|
|
| 21 |
+
|gsm8k| 3|flexible-extract| 5|exact_match|↑ |0.808|± | 0.025|
|
| 22 |
+
| | |strict-match | 5|exact_match|↑ |0.808|± | 0.025|
|
| 23 |
+
|
| 24 |
+
vllm (pretrained=/root/autodl-tmp/L3-8B-Stheno-v3.2-80,add_bos_token=true,max_model_len=2048,dtype=bfloat16), gen_kwargs: (None), limit: 500.0, num_fewshot: 5, batch_size: auto
|
| 25 |
+
|Tasks|Version| Filter |n-shot| Metric | |Value| |Stderr|
|
| 26 |
+
|-----|------:|----------------|-----:|-----------|---|----:|---|-----:|
|
| 27 |
+
|gsm8k| 3|flexible-extract| 5|exact_match|↑ |0.816|± |0.0173|
|
| 28 |
+
| | |strict-match | 5|exact_match|↑ |0.822|± |0.0171|
|