nm-testing
/

Meta-Llama-3-8B-Instruct-FP8-K-V

Text Generation

text-generation-inference

Inference Endpoints

compressed-tensors

Model card Files Files and versions Community

mgoin commited on Aug 28

Commit

3b8f267

•

1 Parent(s): 87e14e9

Update README.md

Files changed (1) hide show

README.md +4 -8

README.md CHANGED Viewed

@@ -2,15 +2,11 @@
 ```
-vllm (pretrained=neuralmagic/Meta-Llama-3-8B-Instruct-FP8-KV,tensor_parallel_size=1,kv_cache_dtype=fp8,distributed_executor_backend=ray), gen_kwargs: (None), limit: None, num_fewshot: None, batch_size: auto
-|Tasks|Version|     Filter     |n-shot|  Metric   |   |Value |   |Stderr|
-|-----|------:|----------------|-----:|-----------|---|-----:|---|-----:|
-|gsm8k|      3|flexible-extract|     5|exact_match|↑  |0.7400|±  |0.0121|
-|     |       |strict-match    |     5|exact_match|↑  |0.7415|±  |0.0121|
-vllm (pretrained=nm-testing/Meta-Llama-3-8B-Instruct-FP8-K-V,tensor_parallel_size=1,kv_cache_dtype=fp8,distributed_executor_backend=ray), gen_kwargs: (None), limit: None, num_fewshot: None, batch_size: auto
 |Tasks|Version|     Filter     |n-shot|  Metric   |   |Value |   |Stderr|
 |-----|------:|----------------|-----:|-----------|---|-----:|---|-----:|
-|gsm8k|      3|flexible-extract|     5|exact_match|↑  |0.7354|±  |0.0122|
-|     |       |strict-match    |     5|exact_match|↑  |0.7369|±  |0.0121|
 ```

 ```
+lm_eval --model vllm --model_args pretrained=nm-testing/Meta-Llama-3-8B-Instruct-FP8-K-V,kv_cache_dtype=fp8,add_bos_token=True --tasks gsm8k --num_fewshot 5 --batch_size auto
+vllm (pretrained=nm-testing/Meta-Llama-3-8B-Instruct-FP8-K-V,kv_cache_dtype=fp8,add_bos_token=True), gen_kwargs: (None), limit: None, num_fewshot: 5, batch_size: auto
 |Tasks|Version|     Filter     |n-shot|  Metric   |   |Value |   |Stderr|
 |-----|------:|----------------|-----:|-----------|---|-----:|---|-----:|
+|gsm8k|      3|flexible-extract|     5|exact_match|↑  |0.7748|±  |0.0115|
+|     |       |strict-match    |     5|exact_match|↑  |0.7763|±  |0.0115|
 ```