Update README.md
Browse files
README.md
CHANGED
|
@@ -2,6 +2,10 @@
|
|
| 2 |
base_model:
|
| 3 |
- IlyaGusev/saiga_nemo_12b
|
| 4 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5 |
vllm (pretrained=/root/autodl-tmp/saiga_nemo_12b,add_bos_token=true,tensor_parallel_size=2,max_model_len=2048), gen_kwargs: (None), limit: 250.0, num_fewshot: 5, batch_size: auto
|
| 6 |
|Tasks|Version| Filter |n-shot| Metric | |Value| |Stderr|
|
| 7 |
|-----|------:|----------------|-----:|-----------|---|----:|---|-----:|
|
|
|
|
| 2 |
base_model:
|
| 3 |
- IlyaGusev/saiga_nemo_12b
|
| 4 |
---
|
| 5 |
+
Consider using noneUsername/saiga_nemo_12b-W8A8-Dynamic-Per-Token-better. I tweaked the quantization parameters to get better results.
|
| 6 |
+
|
| 7 |
+
|
| 8 |
+
|
| 9 |
vllm (pretrained=/root/autodl-tmp/saiga_nemo_12b,add_bos_token=true,tensor_parallel_size=2,max_model_len=2048), gen_kwargs: (None), limit: 250.0, num_fewshot: 5, batch_size: auto
|
| 10 |
|Tasks|Version| Filter |n-shot| Metric | |Value| |Stderr|
|
| 11 |
|-----|------:|----------------|-----:|-----------|---|----:|---|-----:|
|