Thebloke

177 indexed models

177 matching models

TheBloke/law-chat-AWQ

vertexAI/publishers/hf-thebloke/models/law-chat-awq@001

Input modalities
text
Output modalities
text

TheBloke/Llama-2-13B-AWQ

azureFoundry/HuggingFace/thebloke-llama-2-13b-awq@1

`TheBloke/Llama-2-13B-AWQ` powered by Text Generation Inference (TGI) - [Example Notebook](https://aka.ms/hugging-face-text-generation-streaming-online-endpoint) - [Original Model Card](https://huggingface.co/TheBloke/Llama-2-13B-AWQ) - [Text Generation Inference Documentation](

Input modalities
text
Output modalities
text

TheBloke/Llama-2-13B-chat-AWQ

azureFoundry/HuggingFace/thebloke-llama-2-13b-chat-awq@1

`TheBloke/Llama-2-13B-chat-AWQ` powered by Text Generation Inference (TGI) - [Example Notebook](https://aka.ms/hugging-face-text-generation-streaming-online-endpoint) - [Original Model Card](https://huggingface.co/TheBloke/Llama-2-13B-chat-AWQ) - [Text Generation Inference Docum

Input modalities
text
Output modalities
text

TheBloke/Llama-2-13B-fp16

huggingface/TheBloke/Llama-2-13B-fp16

Input modalities
text
Output modalities
text

Benchmarks

  • Open Ko-LLM Leaderboard: 34.866%
  • Open LLM Leaderboard v1: 53.666%

TheBloke/Llama-2-13B-GPTQ

azureFoundry/HuggingFace/thebloke-llama-2-13b-gptq@1

`TheBloke/Llama-2-13B-GPTQ` powered by Text Generation Inference (TGI) - [Example Notebook](https://aka.ms/hugging-face-text-generation-streaming-online-endpoint) - [Original Model Card](https://huggingface.co/TheBloke/Llama-2-13B-GPTQ) - [Text Generation Inference Documentation

Input modalities
text
Output modalities
text

Benchmarks

  • Open LLM Leaderboard v1: 53.264%

TheBloke/Llama-2-70B-Chat-AWQ

azureFoundry/HuggingFace/thebloke-llama-2-70b-chat-awq@1

`TheBloke/Llama-2-70B-Chat-AWQ` powered by Text Generation Inference (TGI) - [Example Notebook](https://aka.ms/hugging-face-text-generation-streaming-online-endpoint) - [Original Model Card](https://huggingface.co/TheBloke/Llama-2-70B-Chat-AWQ) - [Text Generation Inference Docum

Input modalities
text
Output modalities
text

TheBloke/Llama-2-70B-Chat-GPTQ

vertexAI/publishers/hf-thebloke/models/llama-2-70b-chat-gptq@001

Input modalities
text
Output modalities
text

Benchmarks

  • Open LLM Leaderboard v1: 59.752%

TheBloke/Llama-2-70B-fp16

huggingface/TheBloke/Llama-2-70B-fp16

Input modalities
text
Output modalities
text

Benchmarks

  • Open LLM Leaderboard v1: 64.519%

TheBloke/Llama-2-70B-GPTQ

azureFoundry/HuggingFace/thebloke-llama-2-70b-gptq@1

`TheBloke/Llama-2-70B-GPTQ` powered by Text Generation Inference (TGI) - [Example Notebook](https://aka.ms/hugging-face-text-generation-streaming-online-endpoint) - [Original Model Card](https://huggingface.co/TheBloke/Llama-2-70B-GPTQ) - [Text Generation Inference Documentation

Input modalities
text
Output modalities
text

TheBloke/Llama2-70B-OASST-SFT-v10-GPTQ

azureFoundry/HuggingFace/thebloke-llama2-70b-oasst-sft-v10-gptq@1

`TheBloke/Llama2-70B-OASST-SFT-v10-GPTQ` powered by Text Generation Inference (TGI) - [Example Notebook](https://aka.ms/hugging-face-text-generation-streaming-online-endpoint) - [Original Model Card](https://huggingface.co/TheBloke/Llama2-70B-OASST-SFT-v10-GPTQ) - [Text Generati

Input modalities
text
Output modalities
text

TheBloke/Llama-2-7B-Chat-AWQ

vertexAI/publishers/hf-thebloke/models/llama-2-7b-chat-awq@001

Input modalities
text
Output modalities
text

Benchmarks

  • Open LLM Leaderboard v1: 29.139%

TheBloke/Llama-2-7B-fp16

azureFoundry/HuggingFace/thebloke-llama-2-7b-fp16@1

`TheBloke/Llama-2-7B-fp16` powered by Text Generation Inference (TGI) - [Example Notebook](https://aka.ms/hugging-face-text-generation-streaming-online-endpoint) - [Original Model Card](https://huggingface.co/TheBloke/Llama-2-7B-fp16) - [Text Generation Inference Documentation](

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