Update README.md
Browse files
README.md
CHANGED
@@ -9,6 +9,7 @@ vllm (pretrained=/root/autodl-tmp/phi-4-abliterated,add_bos_token=true,tensor_pa
|
|
9 |
|-----|------:|----------------|-----:|-----------|---|----:|---|-----:|
|
10 |
|gsm8k| 3|flexible-extract| 5|exact_match|↑ |0.932|± | 0.016|
|
11 |
| | |strict-match | 5|exact_match|↑ |0.932|± | 0.016|
|
|
|
12 |
vllm (pretrained=/root/autodl-tmp/phi-4-abliterated,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
|
13 |
|Tasks|Version| Filter |n-shot| Metric | |Value| |Stderr|
|
14 |
|-----|------:|----------------|-----:|-----------|---|----:|---|-----:|
|
@@ -21,6 +22,7 @@ vllm (pretrained=/root/autodl-tmp/phi-4-abliterated-85,add_bos_token=true,tensor
|
|
21 |
|-----|------:|----------------|-----:|-----------|---|----:|---|-----:|
|
22 |
|gsm8k| 3|flexible-extract| 5|exact_match|↑ | 0.92|± |0.0172|
|
23 |
| | |strict-match | 5|exact_match|↑ | 0.92|± |0.0172|
|
|
|
24 |
vllm (pretrained=/root/autodl-tmp/phi-4-abliterated-85,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 |
|-----|------:|----------------|-----:|-----------|---|----:|---|-----:|
|
@@ -33,6 +35,7 @@ vllm (pretrained=/root/autodl-tmp/phi-4-abliterated-8625,add_bos_token=true,tens
|
|
33 |
|-----|------:|----------------|-----:|-----------|---|----:|---|-----:|
|
34 |
|gsm8k| 3|flexible-extract| 5|exact_match|↑ |0.932|± | 0.016|
|
35 |
| | |strict-match | 5|exact_match|↑ |0.932|± | 0.016|
|
|
|
36 |
vllm (pretrained=/root/autodl-tmp/phi-4-abliterated-8625,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
|
37 |
|Tasks|Version| Filter |n-shot| Metric | |Value| |Stderr|
|
38 |
|-----|------:|----------------|-----:|-----------|---|----:|---|-----:|
|
@@ -45,6 +48,7 @@ vllm (pretrained=/root/autodl-tmp/phi-4-abliterated-875,add_bos_token=true,tenso
|
|
45 |
|-----|------:|----------------|-----:|-----------|---|----:|---|-----:|
|
46 |
|gsm8k| 3|flexible-extract| 5|exact_match|↑ |0.924|± |0.0168|
|
47 |
| | |strict-match | 5|exact_match|↑ |0.924|± |0.0168|
|
|
|
48 |
vllm (pretrained=/root/autodl-tmp/phi-4-abliterated-875,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
|
49 |
|Tasks|Version| Filter |n-shot| Metric | |Value| |Stderr|
|
50 |
|-----|------:|----------------|-----:|-----------|---|----:|---|-----:|
|
|
|
9 |
|-----|------:|----------------|-----:|-----------|---|----:|---|-----:|
|
10 |
|gsm8k| 3|flexible-extract| 5|exact_match|↑ |0.932|± | 0.016|
|
11 |
| | |strict-match | 5|exact_match|↑ |0.932|± | 0.016|
|
12 |
+
|
13 |
vllm (pretrained=/root/autodl-tmp/phi-4-abliterated,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
|
14 |
|Tasks|Version| Filter |n-shot| Metric | |Value| |Stderr|
|
15 |
|-----|------:|----------------|-----:|-----------|---|----:|---|-----:|
|
|
|
22 |
|-----|------:|----------------|-----:|-----------|---|----:|---|-----:|
|
23 |
|gsm8k| 3|flexible-extract| 5|exact_match|↑ | 0.92|± |0.0172|
|
24 |
| | |strict-match | 5|exact_match|↑ | 0.92|± |0.0172|
|
25 |
+
|
26 |
vllm (pretrained=/root/autodl-tmp/phi-4-abliterated-85,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
|
27 |
|Tasks|Version| Filter |n-shot| Metric | |Value| |Stderr|
|
28 |
|-----|------:|----------------|-----:|-----------|---|----:|---|-----:|
|
|
|
35 |
|-----|------:|----------------|-----:|-----------|---|----:|---|-----:|
|
36 |
|gsm8k| 3|flexible-extract| 5|exact_match|↑ |0.932|± | 0.016|
|
37 |
| | |strict-match | 5|exact_match|↑ |0.932|± | 0.016|
|
38 |
+
|
39 |
vllm (pretrained=/root/autodl-tmp/phi-4-abliterated-8625,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
|
40 |
|Tasks|Version| Filter |n-shot| Metric | |Value| |Stderr|
|
41 |
|-----|------:|----------------|-----:|-----------|---|----:|---|-----:|
|
|
|
48 |
|-----|------:|----------------|-----:|-----------|---|----:|---|-----:|
|
49 |
|gsm8k| 3|flexible-extract| 5|exact_match|↑ |0.924|± |0.0168|
|
50 |
| | |strict-match | 5|exact_match|↑ |0.924|± |0.0168|
|
51 |
+
|
52 |
vllm (pretrained=/root/autodl-tmp/phi-4-abliterated-875,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
|
53 |
|Tasks|Version| Filter |n-shot| Metric | |Value| |Stderr|
|
54 |
|-----|------:|----------------|-----:|-----------|---|----:|---|-----:|
|