Nm Testing

11 indexed models

11 matching models

nm-testing/DeepSeek-R1-Distill-Llama-70B-FP8-dynamic

azureFoundry/HuggingFace/nm-testing-deepseek-r1-distill-llama-70b-fp8-dynamic@1

`nm-testing/DeepSeek-R1-Distill-Llama-70B-FP8-dynamic` powered by Text Generation Inference (TGI) - [Example Notebook](https://aka.ms/hugging-face-text-generation-streaming-online-endpoint) - [Original Model Card](https://huggingface.co/nm-testing/DeepSeek-R1-Distill-Llama-70B-F

Input modalities
text
Output modalities
text

nm-testing/llama7b-one-shot-2_4-w4a16-marlin24-t

azureFoundry/HuggingFace/nm-testing-llama7b-one-shot-2-4-w4a16-marlin24-t@1

`nm-testing/llama7b-one-shot-2_4-w4a16-marlin24-t` powered by Text Generation Inference (TGI) - [Example Notebook](https://aka.ms/hugging-face-text-generation-streaming-online-endpoint) - [Original Model Card](https://huggingface.co/nm-testing/llama7b-one-shot-2_4-w4a16-marlin24

Input modalities
text
Output modalities
text

nm-testing/Meta-Llama-3-8B-FP8-compressed-tensors-test

azureFoundry/HuggingFace/nm-testing-meta-llama-3-8b-fp8-compressed-tensors-test@1

`nm-testing/Meta-Llama-3-8B-FP8-compressed-tensors-test` powered by Text Generation Inference (TGI) - [Example Notebook](https://aka.ms/hugging-face-text-generation-streaming-online-endpoint) - [Original Model Card](https://huggingface.co/nm-testing/Meta-Llama-3-8B-FP8-compresse

Input modalities
text
Output modalities
text

nm-testing/Meta-Llama-3-8B-Instruct-nonuniform-test

azureFoundry/HuggingFace/nm-testing-meta-llama-3-8b-instruct-nonuniform-test@1

`nm-testing/Meta-Llama-3-8B-Instruct-nonuniform-test` powered by Text Generation Inference (TGI) - [Example Notebook](https://aka.ms/hugging-face-text-generation-streaming-online-endpoint) - [Original Model Card](https://huggingface.co/nm-testing/Meta-Llama-3-8B-Instruct-nonunif

Input modalities
text
Output modalities
text

nm-testing/Meta-Llama-3-8B-Instruct-W8A8-FP8-Channelwise-compressed-tensors

azureFoundry/HuggingFace/nm-testing-meta-llama-3-8b-instruct-w8a8-fp8-channelwise-compressed-tensors@1

`nm-testing/Meta-Llama-3-8B-Instruct-W8A8-FP8-Channelwise-compressed-tensors` powered by Text Generation Inference (TGI) - [Example Notebook](https://aka.ms/hugging-face-text-generation-streaming-online-endpoint) - [Original Model Card](https://huggingface.co/nm-testing/Meta-Lla

Input modalities
text
Output modalities
text

nm-testing/Qwen2-1.5B-Instruct-FP8W8

azureFoundry/HuggingFace/nm-testing-qwen2-1.5b-instruct-fp8w8@1

`nm-testing/Qwen2-1.5B-Instruct-FP8W8` powered by Text Generation Inference (TGI) - [Example Notebook](https://aka.ms/hugging-face-text-generation-streaming-online-endpoint) - [Original Model Card](https://huggingface.co/nm-testing/Qwen2-1.5B-Instruct-FP8W8) - [Text Generation I

Input modalities
text
Output modalities
text

nm-testing/TinyLlama-1.1B-compressed-tensors-kv-cache-scheme

azureFoundry/HuggingFace/nm-testing-tinyllama-1.1b-compressed-tensors-kv-cache-scheme@1

`nm-testing/TinyLlama-1.1B-compressed-tensors-kv-cache-scheme` powered by Text Generation Inference (TGI) - [Example Notebook](https://aka.ms/hugging-face-text-generation-streaming-online-endpoint) - [Original Model Card](https://huggingface.co/nm-testing/TinyLlama-1.1B-compress

Input modalities
text
Output modalities
text

nm-testing/tinyllama-oneshot-w8a8-channel-dynamic-token-v2

azureFoundry/HuggingFace/nm-testing-tinyllama-oneshot-w8a8-channel-dynamic-token-v2@1

`nm-testing/tinyllama-oneshot-w8a8-channel-dynamic-token-v2` powered by Text Generation Inference (TGI) - [Example Notebook](https://aka.ms/hugging-face-text-generation-streaming-online-endpoint) - [Original Model Card](https://huggingface.co/nm-testing/tinyllama-oneshot-w8a8-ch

Input modalities
text
Output modalities
text

nm-testing/tinyllama-oneshot-w8a8-dynamic-token-v2

azureFoundry/HuggingFace/nm-testing-tinyllama-oneshot-w8a8-dynamic-token-v2@1

`nm-testing/tinyllama-oneshot-w8a8-dynamic-token-v2` powered by Text Generation Inference (TGI) - [Example Notebook](https://aka.ms/hugging-face-text-generation-streaming-online-endpoint) - [Original Model Card](https://huggingface.co/nm-testing/tinyllama-oneshot-w8a8-dynamic-to

Input modalities
text
Output modalities
text

nm-testing/tinyllama-oneshot-w8a8-dynamic-token-v2-asym

azureFoundry/HuggingFace/nm-testing-tinyllama-oneshot-w8a8-dynamic-token-v2-asym@1

`nm-testing/tinyllama-oneshot-w8a8-dynamic-token-v2-asym` powered by Text Generation Inference (TGI) - [Example Notebook](https://aka.ms/hugging-face-text-generation-streaming-online-endpoint) - [Original Model Card](https://huggingface.co/nm-testing/tinyllama-oneshot-w8a8-dynam

Input modalities
text
Output modalities
text

nm-testing/tinyllama-oneshot-w8-channel-a8-tensor

azureFoundry/HuggingFace/nm-testing-tinyllama-oneshot-w8-channel-a8-tensor@1

`nm-testing/tinyllama-oneshot-w8-channel-a8-tensor` powered by Text Generation Inference (TGI) - [Example Notebook](https://aka.ms/hugging-face-text-generation-streaming-online-endpoint) - [Original Model Card](https://huggingface.co/nm-testing/tinyllama-oneshot-w8-channel-a8-te

Input modalities
text
Output modalities
text

Models

Loading
EVIDENCE / COMPARISON

Benchmarks

Explore every benchmark

Loading

These charts contain model-linked results. The charts above also include unlinked source profiles. Compare scores within each evaluation. Model quality, usage, transparency and system performance measure different things.

Install TensorTrace