LLM EXPLORER 60,828 MODELS INDEXED

Bielik 7B Instruct V0.1 by speakleash

By speakleash · 3228 downloads
HF Repo ↗ Copy URL

Bielik 7B Instruct V0.1 is an open-source language model by speakleash. Features: 7b LLM, VRAM: 14.4GB, Context: 4K, License: cc-by-nc-4.0, Fine-Tuned, Instruction-Based, LLM Explorer Score: 0.17, Arc: 47.4, HellaSwag: 68.8, MMLU: 49.3, GSM8K: 30.3.

  Arxiv:2005.01643   Arxiv:2006.09092   Arxiv:2309.11235   Arxiv:2410.18565   Conversational   Deploy:azure   Endpoints compatible   Finetuned   Instruct   Mistral   Pl   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/speakleash/Bielik-7B-Instruct-v0.1 

Bielik 7B Instruct V0.1 Parameters and Internals

Model Type 
causal decoder-only
Additional Notes 
No moderation mechanisms; potential for lewd, false, biased outputs
Supported Languages 
Polish (fluent)
Training Details 
Data Sources:
OpenHermes-2.5, orca-math-word-problems-200k
Methodology:
Instruction fine-tuning
Context Length:
4096
Hardware Used:
Athena supercomputer, Helios supercomputer
Model Architecture:
Architecture similar to LLaMA and Mistral
Input Output 
Input Format:
[INST] and [/INST] tokens
Accepted Modalities:
text
LLM NameBielik 7B Instruct V0.1
Repository 🤗https://huggingface.co/speakleash/Bielik-7B-Instruct-v0.1 
Model Size7b
Required VRAM14.4 GB
Updated2026-08-04
Maintainerspeakleash
Model Typemistral
Instruction-BasedYes
Model Files  4.9 GB: 1-of-3   5.0 GB: 2-of-3   4.5 GB: 3-of-3
Supported Languagespl
Model ArchitectureMistralForCausalLM
Licensecc-by-nc-4.0
Context Length4096
Model Max Length4096
Transformers Version4.38.2
Tokenizer ClassLlamaTokenizer
Vocabulary Size32000
Torch Data Typebfloat16

Best Alternatives to Bielik 7B Instruct V0.1

Best Alternatives
Context / RAM
Downloads
Likes
...Nemo Instruct 2407 Abliterated1000K / 24.5 GB22020
SpydazWeb AI HumanAI RP512K / 14.4 GB161
SpydazWeb AI HumanAI 002512K / 14.4 GB181
...daz Web AI ChatML 512K Project512K / 14.5 GB120
... Summarize 64K QLoRANET Merged128K / 4.1 GB100
...1 Summarize 64K LoRANET Merged128K / 14.4 GB100
Mistral 7B Instruct V0.232K / 14.4 GB11153373184
Mistral 7B Instruct V0.132K / 14.4 GB2536291846
Mistral 7B Instruct V0.232K / 14.4 GB13380
Copywriting Llm32K / 4.1 GB1221
Note: green Score (e.g. "73.2") means that the model is better than speakleash/Bielik-7B-Instruct-v0.1.