Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
|
| 2 |
```
|
| 3 |
lm_eval --model vllm --model_args pretrained=/home/mgoin/code/Nemotron-4-340B-Base-hf-FP8,tensor_parallel_size=8,distributed_executor_backend="ray",max_model_len=4096 --tasks gsm8k --num_fewshot 5 --batch_size auto
|
|
@@ -7,4 +12,4 @@ vllm (pretrained=/home/mgoin/code/Nemotron-4-340B-Base-hf-FP8,tensor_parallel_si
|
|
| 7 |
|-----|------:|----------------|-----:|-----------|---|-----:|---|-----:|
|
| 8 |
|gsm8k| 3|flexible-extract| 5|exact_match|↑ |0.2949|± |0.0126|
|
| 9 |
| | |strict-match | 5|exact_match|↑ |0.1600|± |0.0101|
|
| 10 |
-
```
|
|
|
|
| 1 |
+
---
|
| 2 |
+
tags:
|
| 3 |
+
- fp8
|
| 4 |
+
base_model: mgoin/Nemotron-4-340B-Base-hf
|
| 5 |
+
---
|
| 6 |
|
| 7 |
```
|
| 8 |
lm_eval --model vllm --model_args pretrained=/home/mgoin/code/Nemotron-4-340B-Base-hf-FP8,tensor_parallel_size=8,distributed_executor_backend="ray",max_model_len=4096 --tasks gsm8k --num_fewshot 5 --batch_size auto
|
|
|
|
| 12 |
|-----|------:|----------------|-----:|-----------|---|-----:|---|-----:|
|
| 13 |
|gsm8k| 3|flexible-extract| 5|exact_match|↑ |0.2949|± |0.0126|
|
| 14 |
| | |strict-match | 5|exact_match|↑ |0.1600|± |0.0101|
|
| 15 |
+
```
|