Nemotron in vLLM
Collection
Nemotron models that have been converted and/or quantized to work well in vLLM
•
7 items
•
Updated
Nemotron-4-340B-Base-hf-FP8
Converted and quantized checkpoint of nvidia/Nemotron-4-340B-Base. Specifically it was produced from the v1.2 .nemo checkpoint on NGC.
This runs in vLLM with this PR: https://github.com/vllm-project/vllm/pull/6611
Evaluations
All the below evaluations were run with lm-eval==0.4.3 on 8xA100 GPUs.
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,gpu_memory_utilization=0.6 --tasks truthfulqa_mc2 --num_fewshot 0 --batch_size 16
vllm (pretrained=/home/mgoin/code/Nemotron-4-340B-Base-hf-FP8,tensor_parallel_size=8,distributed_executor_backend=ray,max_model_len=4096,gpu_memory_utilization=0.6), gen_kwargs: (None), limit: None, num_fewshot: 0, batch_size: 16
| Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr|
|--------------|------:|------|-----:|------|---|-----:|---|-----:|
|truthfulqa_mc2| 2|none | 0|acc |↑ |0.4869|± |0.0142|
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,gpu_memory_utilization=0.6 --tasks winogrande --num_fewshot 5 --batch_size 16
vllm (pretrained=/home/mgoin/code/Nemotron-4-340B-Base-hf-FP8,tensor_parallel_size=8,distributed_executor_backend=ray,max_model_len=4096,gpu_memory_utilization=0.6), gen_kwargs: (None), limit: None, num_fewshot: 5, batch_size: 16
| Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr|
|----------|------:|------|-----:|------|---|-----:|---|-----:|
|winogrande| 1|none | 5|acc |↑ |0.8887|± |0.0088|
The original paper evals for reference:
The Minitron paper has more evals as well:
- Downloads last month
- 5
Inference API (serverless) has been turned off for this model.