Update README.md
Browse files
README.md
CHANGED
|
@@ -39,4 +39,54 @@ vllm (pretrained=/root/autodl-tmp/phi-4-abliterated-869,add_bos_token=true,max_m
|
|
| 39 |
|Tasks|Version| Filter |n-shot| Metric | |Value| |Stderr|
|
| 40 |
|-----|------:|----------------|-----:|-----------|---|----:|---|-----:|
|
| 41 |
|gsm8k| 3|flexible-extract| 5|exact_match|↑ |0.918|± |0.0123|
|
| 42 |
-
| | |strict-match | 5|exact_match|↑ |0.916|± |0.0124|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 39 |
|Tasks|Version| Filter |n-shot| Metric | |Value| |Stderr|
|
| 40 |
|-----|------:|----------------|-----:|-----------|---|----:|---|-----:|
|
| 41 |
|gsm8k| 3|flexible-extract| 5|exact_match|↑ |0.918|± |0.0123|
|
| 42 |
+
| | |strict-match | 5|exact_match|↑ |0.916|± |0.0124|
|
| 43 |
+
|
| 44 |
+
|
| 45 |
+
|
| 46 |
+
|
| 47 |
+
|
| 48 |
+
|
| 49 |
+
|
| 50 |
+
|
| 51 |
+
vllm (pretrained=/root/autodl-tmp/phi-4,add_bos_token=true,max_model_len=2048), gen_kwargs: (None), limit: 250.0, num_fewshot: 5, batch_size: auto
|
| 52 |
+
|Tasks|Version| Filter |n-shot| Metric | |Value| |Stderr|
|
| 53 |
+
|-----|------:|----------------|-----:|-----------|---|----:|---|-----:|
|
| 54 |
+
|gsm8k| 3|flexible-extract| 5|exact_match|↑ |0.928|± |0.0164|
|
| 55 |
+
| | |strict-match | 5|exact_match|↑ |0.928|± |0.0164|
|
| 56 |
+
|
| 57 |
+
vllm (pretrained=/root/autodl-tmp/phi-4,add_bos_token=true,max_model_len=2048,dtype=bfloat16), gen_kwargs: (None), limit: 500.0, num_fewshot: 5, batch_size: auto
|
| 58 |
+
|Tasks|Version| Filter |n-shot| Metric | |Value| |Stderr|
|
| 59 |
+
|-----|------:|----------------|-----:|-----------|---|----:|---|-----:|
|
| 60 |
+
|gsm8k| 3|flexible-extract| 5|exact_match|↑ | 0.93|± |0.0114|
|
| 61 |
+
| | |strict-match | 5|exact_match|↑ | 0.93|± |0.0114|
|
| 62 |
+
|
| 63 |
+
vllm (pretrained=/root/autodl-tmp/phi-4,add_bos_token=true,max_model_len=800,dtype=bfloat16), gen_kwargs: (None), limit: 15.0, num_fewshot: None, batch_size: auto
|
| 64 |
+
| Groups |Version|Filter|n-shot|Metric| |Value | |Stderr|
|
| 65 |
+
|------------------|------:|------|------|------|---|-----:|---|-----:|
|
| 66 |
+
|mmlu | 2|none | |acc |↑ |0.7649|± |0.0137|
|
| 67 |
+
| - humanities | 2|none | |acc |↑ |0.8103|± |0.0256|
|
| 68 |
+
| - other | 2|none | |acc |↑ |0.7487|± |0.0287|
|
| 69 |
+
| - social sciences| 2|none | |acc |↑ |0.8167|± |0.0280|
|
| 70 |
+
| - stem | 2|none | |acc |↑ |0.7123|± |0.0260|
|
| 71 |
+
|
| 72 |
+
|
| 73 |
+
vllm (pretrained=/root/autodl-tmp/huihui-ai-phi-4-abliterated-W8A8,add_bos_token=true,max_model_len=2048), gen_kwargs: (None), limit: 250.0, num_fewshot: 5, batch_size: auto
|
| 74 |
+
|Tasks|Version| Filter |n-shot| Metric | |Value| |Stderr|
|
| 75 |
+
|-----|------:|----------------|-----:|-----------|---|----:|---|-----:|
|
| 76 |
+
|gsm8k| 3|flexible-extract| 5|exact_match|↑ |0.944|± |0.0146|
|
| 77 |
+
| | |strict-match | 5|exact_match|↑ |0.944|± |0.0146|
|
| 78 |
+
|
| 79 |
+
vllm (pretrained=/root/autodl-tmp/huihui-ai-phi-4-abliterated-W8A8,add_bos_token=true,max_model_len=2048,dtype=bfloat16), gen_kwargs: (None), limit: 500.0, num_fewshot: 5, batch_size: auto
|
| 80 |
+
|Tasks|Version| Filter |n-shot| Metric | |Value| |Stderr|
|
| 81 |
+
|-----|------:|----------------|-----:|-----------|---|----:|---|-----:|
|
| 82 |
+
|gsm8k| 3|flexible-extract| 5|exact_match|↑ |0.924|± |0.0119|
|
| 83 |
+
| | |strict-match | 5|exact_match|↑ |0.924|± |0.0119|
|
| 84 |
+
|
| 85 |
+
vllm (pretrained=/root/autodl-tmp/huihui-ai-phi-4-abliterated-W8A8,add_bos_token=true,max_model_len=800,dtype=bfloat16), gen_kwargs: (None), limit: 15.0, num_fewshot: None, batch_size: auto
|
| 86 |
+
| Groups |Version|Filter|n-shot|Metric| |Value | |Stderr|
|
| 87 |
+
|------------------|------:|------|------|------|---|-----:|---|-----:|
|
| 88 |
+
|mmlu | 2|none | |acc |↑ |0.7673|± |0.0136|
|
| 89 |
+
| - humanities | 2|none | |acc |↑ |0.8154|± |0.0256|
|
| 90 |
+
| - other | 2|none | |acc |↑ |0.7744|± |0.0285|
|
| 91 |
+
| - social sciences| 2|none | |acc |↑ |0.8278|± |0.0273|
|
| 92 |
+
| - stem | 2|none | |acc |↑ |0.6912|± |0.0263|
|