Bielik 11B V2.2 Instruct W8A8 by speakleash

 ยป  All LLMs  ยป  speakleash  ยป  Bielik 11B V2.2 Instruct W8A8   URL Share it on

  8-bit   8bit   Autotrain compatible Base model:finetune:speakleash... Base model:speakleash/bielik-1...   Conversational   Finetuned   Gguf   Instruct   Mistral   Pl   Quantized   Region:us   Safetensors   Sharded   Tensorflow

Bielik 11B V2.2 Instruct W8A8 Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Bielik 11B V2.2 Instruct W8A8 (speakleash/Bielik-11B-v2.2-Instruct-W8A8)

Bielik 11B V2.2 Instruct W8A8 Parameters and Internals

Model Type 
causal decoder-only
Supported Languages 
Polish (native)
Training Details 
Context Length:
4096
Input Output 
Accepted Modalities:
text
Output Format:
text
LLM NameBielik 11B V2.2 Instruct W8A8
Repository ๐Ÿค—https://huggingface.co/speakleash/Bielik-11B-v2.2-Instruct-W8A8 
Base Model(s)  speakleash/Bielik-11B-v2.2-Instruct   speakleash/Bielik-11B-v2.2-Instruct
Model Size11b
Required VRAM11.5 GB
Updated2024-12-22
Maintainerspeakleash
Model Typemistral
Instruction-BasedYes
Model Files  5.0 GB: 1-of-3   5.0 GB: 2-of-3   1.5 GB: 3-of-3
Supported Languagespl
Quantization Type8bit
Model ArchitectureMistralForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.44.2
Tokenizer ClassLlamaTokenizer
Padding Token</s>
Vocabulary Size32128
Torch Data Typebfloat16

Best Alternatives to Bielik 11B V2.2 Instruct W8A8

Best Alternatives
Context / RAM
Downloads
Likes
Bielik 11B V2.2 Instruct FP832K / 11.4 GB4933
... 11B V2.2 Instruct Quanto 8bit32K / 12 GB243
...elik V2.3 Instruct MedIT Merge32K / 22.3 GB19121
...elik V2.3 Instruct Llama Prune32K / 15.4 GB21450
... 11B V2.2 Instruct EXL2 4.5bit32K / 6.5 GB333
...B V2.2 Instruct HQQ 4bit 128gs32K / 6.2 GB263
...B V2.2 Instruct HQQ 8bit 128gs32K / 11.7 GB173
Mistral 11B Instruct V0.132K / 42.9 GB810
...Alpha Mistral 7B Instruct V0.132K / 14.5 GB241
...Mistral 7B Instruct V0.2 Slerp32K / 14.4 GB281
Note: green Score (e.g. "73.2") means that the model is better than speakleash/Bielik-11B-v2.2-Instruct-W8A8.

Rank the Bielik 11B V2.2 Instruct W8A8 Capabilities

๐Ÿ†˜ Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! ๐ŸŒŸ

Instruction Following and Task Automation  
Factuality and Completeness of Knowledge  
Censorship and Alignment  
Data Analysis and Insight Generation  
Text Generation  
Text Summarization and Feature Extraction  
Code Generation  
Multi-Language Support and Translation  

What open-source LLMs or SLMs are you in search of? 40123 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241217