Base model:finetune:meditsolut... Base model:meditsolutions/msh-... Conversational En Instruct Medit-lite Mistral Model-pruning Pl Region:us Safetensors Sharded Tensorflow
Model Card on HF 🤗: https://huggingface.co/meditsolutions/MSH-Lite-7B-v1-Bielik-v2.3-Instruct-Llama-Prune
MSH Lite 7B V1 Bielik V2.3 Instruct Llama Prune Benchmarks
MMLU Pro: 13.22
GPQA: 7.05
MUSR: 11.57
BBH: 16.14
IFEval: 36.55 vs 88 (so35)-58.5%
MATH Lvl 5: 2.64
LLME Score: 0.22909
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
What is the LLM Explorer Rank (Score)
MSH Lite 7B V1 Bielik V2.3 Instruct Llama Prune Parameters and Internals
| LLM Name | MSH Lite 7B V1 Bielik V2.3 Instruct Llama Prune |
| Repository 🤗 | https://huggingface.co/meditsolutions/MSH-Lite-7B-v1-Bielik-v2.3-Instruct-Llama-Prune |
| Base Model(s) | |
| Model Size | 11b |
| Required VRAM | 15.4 GB |
| Updated | 2025-09-23 |
| Maintainer | meditsolutions |
| Model Type | mistral |
| Instruction-Based | Yes |
| Model Files | |
| Supported Languages | pl en |
| Model Architecture | MistralForCausalLM |
| License | apache-2.0 |
| Context Length | 32768 |
| Model Max Length | 32768 |
| Transformers Version | 4.46.2 |
| Tokenizer Class | LlamaTokenizer |
| Padding Token | </s> |
| Vocabulary Size | 32128 |
| Torch Data Type | bfloat16 |
Best Alternatives to MSH Lite 7B V1 Bielik V2.3 Instruct Llama Prune
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| ...elik V2.3 Instruct MedIT Merge | 32K / 22.3 GB | 4 | 2 |
| Mistral 11B Instruct V0.1 | 32K / 42.9 GB | 6 | 0 |
| ...Alpha Mistral 7B Instruct V0.1 | 32K / 14.5 GB | 6 | 0 |
| ...Mistral 7B Instruct V0.2 Slerp | 32K / 14.4 GB | 5 | 1 |
| ...Mistral 7B Instruct V0.2 Slerp | 32K / 14.4 GB | 7 | 2 |
| Mistral 11B Instruct V0.2 | 32K / 21.4 GB | 6 | 3 |
| ... 11B V2.2 Instruct Quanto 8bit | 32K / 12 GB | 60 | 4 |
| Bielik 11B V2.2 Instruct FP8 | 32K / 11.4 GB | 53 | 3 |
| Bielik 11B V2.2 Instruct W8A8 | 32K / 11.5 GB | 31 | 3 |
| ... 11B V2.2 Instruct EXL2 4.5bit | 32K / 6.5 GB | 61 | 3 |
Note: green Score (e.g. "73.2") means that the model is better than meditsolutions/MSH-Lite-7B-v1-Bielik-v2.3-Instruct-Llama-Prune .
Rank the MSH Lite 7B V1 Bielik V2.3 Instruct Llama Prune Capabilities
🆘 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! 🌟
What open-source LLMs or SLMs are you in search of? 51543 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124