Create README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model:
|
| 3 |
+
- SicariusSicariiStuff/Impish_Magic_24B
|
| 4 |
+
---
|
| 5 |
+
vllm (pretrained=/root/autodl-tmp/Impish_Magic_24B,add_bos_token=true,max_model_len=3096,dtype=bfloat16,trust_remote_code=true,gpu_memory_utilization=0.8), 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|↑ |0.908|± |0.0183|
|
| 9 |
+
| | |strict-match | 5|exact_match|↑ |0.904|± |0.0187|
|
| 10 |
+
|
| 11 |
+
vllm (pretrained=/root/autodl-tmp/Impish_Magic_24B,add_bos_token=true,max_model_len=3048,dtype=bfloat16,trust_remote_code=true,gpu_memory_utilization=0.9), gen_kwargs: (None), limit: None, num_fewshot: None, batch_size: auto
|
| 12 |
+
| Groups |Version|Filter|n-shot|Metric| |Value | |Stderr|
|
| 13 |
+
|------------------|------:|------|------|------|---|-----:|---|-----:|
|
| 14 |
+
|mmlu | 2|none | |acc |↑ |0.7545|± |0.0034|
|
| 15 |
+
| - humanities | 2|none | |acc |↑ |0.6782|± |0.0064|
|
| 16 |
+
| - other | 2|none | |acc |↑ |0.8169|± |0.0067|
|
| 17 |
+
| - social sciences| 2|none | |acc |↑ |0.8469|± |0.0064|
|
| 18 |
+
| - stem | 2|none | |acc |↑ |0.7168|± |0.0077|
|
| 19 |
+
|
| 20 |
+
|
| 21 |
+
vllm (pretrained=/root/autodl-tmp/90-512-2048-9999999,add_bos_token=true,max_model_len=3096,dtype=bfloat16,trust_remote_code=true,gpu_memory_utilization=0.8), gen_kwargs: (None), limit: 250.0, num_fewshot: 5, batch_size: auto
|
| 22 |
+
|Tasks|Version| Filter |n-shot| Metric | |Value| |Stderr|
|
| 23 |
+
|-----|------:|----------------|-----:|-----------|---|----:|---|-----:|
|
| 24 |
+
|gsm8k| 3|flexible-extract| 5|exact_match|↑ |0.908|± |0.0183|
|
| 25 |
+
| | |strict-match | 5|exact_match|↑ |0.908|± |0.0183|
|
| 26 |
+
|
| 27 |
+
vllm (pretrained=/root/autodl-tmp/90-512-2048-9999999,add_bos_token=true,max_model_len=3048,dtype=bfloat16,trust_remote_code=true,gpu_memory_utilization=0.9), gen_kwargs: (None), limit: None, num_fewshot: None, batch_size: auto
|
| 28 |
+
| Groups |Version|Filter|n-shot|Metric| |Value | |Stderr|
|
| 29 |
+
|------------------|------:|------|------|------|---|-----:|---|-----:|
|
| 30 |
+
|mmlu | 2|none | |acc |↑ |0.7527|± |0.0034|
|
| 31 |
+
| - humanities | 2|none | |acc |↑ |0.6810|± |0.0064|
|
| 32 |
+
| - other | 2|none | |acc |↑ |0.8072|± |0.0068|
|
| 33 |
+
| - social sciences| 2|none | |acc |↑ |0.8463|± |0.0064|
|
| 34 |
+
| - stem | 2|none | |acc |↑ |0.7146|± |0.0077|
|