Create README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,68 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model:
|
| 3 |
+
- shisa-ai/shisa-v2-unphi4-14b
|
| 4 |
+
---
|
| 5 |
+
vllm (pretrained=/root/autodl-tmp/shisa-v2-unphi4-14b,add_bos_token=true,max_model_len=3096,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|↑ |0.916|± |0.0176|
|
| 9 |
+
| | |strict-match | 5|exact_match|↑ |0.916|± |0.0176|
|
| 10 |
+
|
| 11 |
+
vllm (pretrained=/root/autodl-tmp/shisa-v2-unphi4-14b,add_bos_token=true,max_model_len=3096,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|↑ |0.928|± |0.0116|
|
| 15 |
+
| | |strict-match | 5|exact_match|↑ |0.928|± |0.0116|
|
| 16 |
+
|
| 17 |
+
vllm (pretrained=/root/autodl-tmp/shisa-v2-unphi4-14b,add_bos_token=true,max_model_len=3048,dtype=bfloat16), gen_kwargs: (None), limit: 15.0, num_fewshot: None, batch_size: 1
|
| 18 |
+
| Groups |Version|Filter|n-shot|Metric| |Value | |Stderr|
|
| 19 |
+
|------------------|------:|------|------|------|---|-----:|---|-----:|
|
| 20 |
+
|mmlu | 2|none | |acc |↑ |0.7708|± |0.0137|
|
| 21 |
+
| - humanities | 2|none | |acc |↑ |0.8205|± |0.0261|
|
| 22 |
+
| - other | 2|none | |acc |↑ |0.7590|± |0.0293|
|
| 23 |
+
| - social sciences| 2|none | |acc |↑ |0.8167|± |0.0280|
|
| 24 |
+
| - stem | 2|none | |acc |↑ |0.7158|± |0.0255|
|
| 25 |
+
|
| 26 |
+
|
| 27 |
+
vllm (pretrained=/root/autodl-tmp/shisa-v2-unphi-14b-W8A8-INT8,add_bos_token=true,max_model_len=3096,dtype=bfloat16), gen_kwargs: (None), limit: 250.0, num_fewshot: 5, batch_size: auto
|
| 28 |
+
|Tasks|Version| Filter |n-shot| Metric | |Value| |Stderr|
|
| 29 |
+
|-----|------:|----------------|-----:|-----------|---|----:|---|-----:|
|
| 30 |
+
|gsm8k| 3|flexible-extract| 5|exact_match|↑ |0.908|± |0.0183|
|
| 31 |
+
| | |strict-match | 5|exact_match|↑ |0.908|± |0.0183|
|
| 32 |
+
|
| 33 |
+
vllm (pretrained=/root/autodl-tmp/shisa-v2-unphi-14b-W8A8-INT8,add_bos_token=true,max_model_len=3096,dtype=bfloat16), gen_kwargs: (None), limit: 500.0, num_fewshot: 5, batch_size: auto
|
| 34 |
+
|Tasks|Version| Filter |n-shot| Metric | |Value| |Stderr|
|
| 35 |
+
|-----|------:|----------------|-----:|-----------|---|----:|---|-----:|
|
| 36 |
+
|gsm8k| 3|flexible-extract| 5|exact_match|↑ |0.916|± |0.0124|
|
| 37 |
+
| | |strict-match | 5|exact_match|↑ |0.916|± |0.0124|
|
| 38 |
+
|
| 39 |
+
vllm (pretrained=/root/autodl-tmp/shisa-v2-unphi-14b-W8A8-INT8,add_bos_token=true,max_model_len=3048,dtype=bfloat16), gen_kwargs: (None), limit: 15.0, num_fewshot: None, batch_size: 1
|
| 40 |
+
| Groups |Version|Filter|n-shot|Metric| |Value | |Stderr|
|
| 41 |
+
|------------------|------:|------|------|------|---|-----:|---|-----:|
|
| 42 |
+
|mmlu | 2|none | |acc |↑ |0.7673|± |0.0136|
|
| 43 |
+
| - humanities | 2|none | |acc |↑ |0.8205|± |0.0260|
|
| 44 |
+
| - other | 2|none | |acc |↑ |0.7590|± |0.0285|
|
| 45 |
+
| - social sciences| 2|none | |acc |↑ |0.8111|± |0.0286|
|
| 46 |
+
| - stem | 2|none | |acc |↑ |0.7088|± |0.0253|
|
| 47 |
+
|
| 48 |
+
|
| 49 |
+
vllm (pretrained=/root/autodl-tmp/8625-01-512,add_bos_token=true,max_model_len=3096,dtype=bfloat16), gen_kwargs: (None), limit: 250.0, num_fewshot: 5, batch_size: auto
|
| 50 |
+
|Tasks|Version| Filter |n-shot| Metric | |Value| |Stderr|
|
| 51 |
+
|-----|------:|----------------|-----:|-----------|---|----:|---|-----:|
|
| 52 |
+
|gsm8k| 3|flexible-extract| 5|exact_match|↑ |0.924|± |0.0168|
|
| 53 |
+
| | |strict-match | 5|exact_match|↑ |0.924|± |0.0168|
|
| 54 |
+
|
| 55 |
+
vllm (pretrained=/root/autodl-tmp/8625-01-512,add_bos_token=true,max_model_len=3096,dtype=bfloat16), gen_kwargs: (None), limit: 500.0, num_fewshot: 5, batch_size: auto
|
| 56 |
+
|Tasks|Version| Filter |n-shot| Metric | |Value| |Stderr|
|
| 57 |
+
|-----|------:|----------------|-----:|-----------|---|----:|---|-----:|
|
| 58 |
+
|gsm8k| 3|flexible-extract| 5|exact_match|↑ |0.928|± |0.0116|
|
| 59 |
+
| | |strict-match | 5|exact_match|↑ |0.928|± |0.0116|
|
| 60 |
+
|
| 61 |
+
vllm (pretrained=/root/autodl-tmp/8625-01-512,add_bos_token=true,max_model_len=3048,dtype=bfloat16), gen_kwargs: (None), limit: 15.0, num_fewshot: None, batch_size: 1
|
| 62 |
+
| Groups |Version|Filter|n-shot|Metric| |Value | |Stderr|
|
| 63 |
+
|------------------|------:|------|------|------|---|-----:|---|-----:|
|
| 64 |
+
|mmlu | 2|none | |acc |↑ |0.7708|± |0.0136|
|
| 65 |
+
| - humanities | 2|none | |acc |↑ |0.8103|± |0.0269|
|
| 66 |
+
| - other | 2|none | |acc |↑ |0.7692|± |0.0287|
|
| 67 |
+
| - social sciences| 2|none | |acc |↑ |0.8222|± |0.0278|
|
| 68 |
+
| - stem | 2|none | |acc |↑ |0.7123|± |0.0254|
|