Create README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model:
|
| 3 |
+
- Kaoeiri/Magnum-v4-Cydonia-v1.3-22B-2
|
| 4 |
+
---
|
| 5 |
+
vllm (pretrained=/root/autodl-tmp/Magnum-v4-Cydonia-v1.3-22B-2,add_bos_token=true,tensor_parallel_size=4,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|↑ |0.832|± |0.0237|
|
| 9 |
+
| | |strict-match | 5|exact_match|↑ |0.808|± |0.0250|
|
| 10 |
+
|
| 11 |
+
vllm (pretrained=/root/autodl-tmp/Magnum-v4-Cydonia-v1.3-22B-2,add_bos_token=true,tensor_parallel_size=4,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|↑ |0.846|± |0.0162|
|
| 15 |
+
| | |strict-match | 5|exact_match|↑ |0.814|± |0.0174|
|
| 16 |
+
|
| 17 |
+
|
| 18 |
+
vllm (pretrained=/root/autodl-tmp/Magnum-v4-Cydonia-v1.3-22B-2-89,add_bos_token=true,tensor_parallel_size=2,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|↑ |0.848|± |0.0228|
|
| 22 |
+
| | |strict-match | 5|exact_match|↑ |0.820|± |0.0243|
|
| 23 |
+
|
| 24 |
+
vllm (pretrained=/root/autodl-tmp/Magnum-v4-Cydonia-v1.3-22B-2-89,add_bos_token=true,tensor_parallel_size=2,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|↑ |0.850|± |0.0160|
|
| 28 |
+
| | |strict-match | 5|exact_match|↑ |0.812|± |0.0175|
|