Create README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model:
|
| 3 |
+
- a-m-team/AM-Thinking-v1
|
| 4 |
+
---
|
| 5 |
+
vllm (pretrained=/root/autodl-tmp/AM-Thinking-v1,add_bos_token=true,max_model_len=5096,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|↑ |0.792|± |0.0257|
|
| 9 |
+
| | |strict-match | 5|exact_match|↑ |0.780|± |0.0263|
|
| 10 |
+
|
| 11 |
+
vllm (pretrained=/root/autodl-tmp/AM-Thinking-v1,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|↑ |0.798|± |0.0180|
|
| 15 |
+
| | |strict-match | 5|exact_match|↑ |0.786|± |0.0184|
|
| 16 |
+
|
| 17 |
+
vllm (pretrained=/root/autodl-tmp/AM-Thinking-v1,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 |↑ |0.8023|± |0.0131|
|
| 21 |
+
| - humanities | 2|none | |acc |↑ |0.8154|± |0.0276|
|
| 22 |
+
| - other | 2|none | |acc |↑ |0.8000|± |0.0276|
|
| 23 |
+
| - social sciences| 2|none | |acc |↑ |0.8556|± |0.0255|
|
| 24 |
+
| - stem | 2|none | |acc |↑ |0.7614|± |0.0237|
|
| 25 |
+
|
| 26 |
+
|
| 27 |
+
vllm (pretrained=/root/autodl-tmp/AM-Thinking-v1-awq,add_bos_token=true,max_model_len=5096,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|↑ |0.820|± |0.0243|
|
| 31 |
+
| | |strict-match | 5|exact_match|↑ |0.816|± |0.0246|
|
| 32 |
+
|
| 33 |
+
vllm (pretrained=/root/autodl-tmp/AM-Thinking-v1-awq,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|↑ |0.816|± |0.0173|
|
| 37 |
+
| | |strict-match | 5|exact_match|↑ |0.814|± |0.0174|
|
| 38 |
+
|
| 39 |
+
vllm (pretrained=/root/autodl-tmp/AM-Thinking-v1-awq,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 |↑ |0.7930|± |0.0132|
|
| 43 |
+
| - humanities | 2|none | |acc |↑ |0.8051|± |0.0278|
|
| 44 |
+
| - other | 2|none | |acc |↑ |0.7846|± |0.0277|
|
| 45 |
+
| - social sciences| 2|none | |acc |↑ |0.8444|± |0.0261|
|
| 46 |
+
| - stem | 2|none | |acc |↑ |0.7579|± |0.0242|
|