Speakleash

12 indexed models

12 matching models

speakleash/Bielik-11B-v2

vertexAI/publishers/hf-speakleash/models/bielik-11b-v2@001

Input modalities
text
Output modalities
text

Benchmarks

  • Open LLM Leaderboard v2: 15.989%

speakleash/Bielik-11B-v2.0-Instruct

azureFoundry/HuggingFace/speakleash-bielik-11b-v2.0-instruct@1

`speakleash/Bielik-11B-v2.0-Instruct` powered by Text Generation Inference (TGI) - [Example Notebook](https://aka.ms/hugging-face-text-generation-streaming-online-endpoint) - [Original Model Card](https://huggingface.co/speakleash/Bielik-11B-v2.0-Instruct) - [Text Generation Inf

Input modalities
text
Output modalities
text

Benchmarks

  • Open LLM Leaderboard v2: 24.661%

speakleash/Bielik-11B-v2.1-Instruct

azureFoundry/HuggingFace/speakleash-bielik-11b-v2.1-instruct@6

`speakleash/Bielik-11B-v2.1-Instruct` powered by Text Generation Inference (TGI) - [Example Notebook](https://aka.ms/hugging-face-text-generation-streaming-online-endpoint) - [Original Model Card](https://huggingface.co/speakleash/Bielik-11B-v2.1-Instruct) - [Text Generation Inf

Input modalities
text
Output modalities
text

Benchmarks

  • Open LLM Leaderboard v2: 27.197%

speakleash/Bielik-11B-v2.2-Instruct-Quanto-8bit

azureFoundry/HuggingFace/speakleash-bielik-11b-v2.2-instruct-quanto-8bit@1

`speakleash/Bielik-11B-v2.2-Instruct-Quanto-8bit` powered by Text Generation Inference (TGI) - [Example Notebook](https://aka.ms/hugging-face-text-generation-streaming-online-endpoint) - [Original Model Card](https://huggingface.co/speakleash/Bielik-11B-v2.2-Instruct-Quanto-8bit

Input modalities
text
Output modalities
text

speakleash/Bielik-11B-v2.3-Instruct

azureFoundry/HuggingFace/speakleash-bielik-11b-v2-3-instruct@1

`speakleash/Bielik-11B-v2.3-Instruct` powered by Text Generation Inference (TGI) - [Example Notebook](https://aka.ms/hugging-face-text-generation-streaming-online-endpoint) - [Original Model Card](https://huggingface.co/speakleash/Bielik-11B-v2.3-Instruct) ### Send Request You

Input modalities
text
Output modalities
text

Benchmarks

  • BFCL: 21.9%
  • Open LLM Leaderboard v2: 28.331%

speakleash/Bielik-11B-v2.3-Instruct-FP8

azureFoundry/HuggingFace/speakleash-bielik-11b-v2.3-instruct-fp8@1

`speakleash/Bielik-11B-v2.3-Instruct-FP8` powered by Text Generation Inference (TGI) - [Example Notebook](https://aka.ms/hugging-face-text-generation-streaming-online-endpoint) - [Original Model Card](https://huggingface.co/speakleash/Bielik-11B-v2.3-Instruct-FP8) - [Text Genera

Input modalities
text
Output modalities
text

speakleash/Bielik-11B-v2.6-Instruct-GGUF

azureFoundry/HuggingFace/speakleash-bielik-11b-v2.6-instruct-gguf@1

`speakleash/Bielik-11B-v2.6-Instruct-GGUF` powered by vLLM - [Original Model Card](https://huggingface.co/speakleash/Bielik-11B-v2.6-Instruct-GGUF) - [vLLM Documentation](https://docs.vllm.ai) ## Chat Completions API ### Send Request You can use cURL or any REST Client to sen

Input modalities
text
Output modalities
text

speakleash/Bielik-11B-v3.0-Instruct

azureFoundry/HuggingFace/speakleash-bielik-11b-v3.0-instruct@1

**Gated Model Access Required** `speakleash/Bielik-11B-v3.0-Instruct` requires special access approval from the authors through Hugging Face. To use this model, you must: 1. Request access through the [model page on Hugging Face](https://huggingface.co/speakleash/Bielik-11B-v3.

Input modalities
text
Output modalities
text

speakleash/Bielik-4.5B-v3.0-Instruct

azureFoundry/HuggingFace/speakleash-bielik-4.5b-v3.0-instruct@1

**Gated Model Access Required** `speakleash/Bielik-4.5B-v3.0-Instruct` requires special access approval from the authors through Hugging Face. To use this model, you must: 1. Request access through the [model page on Hugging Face](https://huggingface.co/speakleash/Bielik-4.5B-v

Input modalities
text
Output modalities
text

speakleash/Bielik-7B-Instruct-v0.1

vertexAI/publishers/hf-speakleash/models/bielik-7b-instruct-v0.1@001

Input modalities
text
Output modalities
text

Benchmarks

  • Open LLM Leaderboard v1: 51.256%

speakleash/Bielik-7B-v0.1

vertexAI/publishers/hf-speakleash/models/bielik-7b-v0.1@001

Input modalities
text
Output modalities
text

Benchmarks

  • Open LLM Leaderboard v1: 50.007%

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