Base model:finetune:speakleash... Base model:speakleash/bielik-1... Conversational En Instruct Medit-merge Mistral Pl Region:us Safetensors Sharded Tensorflow
Model Card on HF 🤗: https://huggingface.co/meditsolutions/MSH-v1-Bielik-v2.3-Instruct-MedIT-merge
MSH V1 Bielik V2.3 Instruct MedIT Merge Benchmarks
MMLU Pro: 27.78
GPQA: 12.75
MUSR: 13.84
BBH: 38.02
IFEval: 58.14 vs 88 (so35)-33.9%
MATH Lvl 5: 13.75
LLME Score: 0.36961
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 V1 Bielik V2.3 Instruct MedIT Merge Parameters and Internals
| LLM Name | MSH V1 Bielik V2.3 Instruct MedIT Merge |
| Repository 🤗 | https://huggingface.co/meditsolutions/MSH-v1-Bielik-v2.3-Instruct-MedIT-merge |
| Base Model(s) | |
| Model Size | 11b |
| Required VRAM | 22.3 GB |
| Updated | 2024-12-22 |
| 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 | 4.46.0 |
| Tokenizer Class | LlamaTokenizer |
| Padding Token | </s> |
| Vocabulary Size | 32128 |
| Torch Data Type | bfloat16 |
Best Alternatives to MSH V1 Bielik V2.3 Instruct MedIT Merge
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| ...elik V2.3 Instruct Llama Prune | 32K / 15.4 GB | 2145 | 0 |
| Mistral 11B Instruct V0.1 | 32K / 42.9 GB | 81 | 0 |
| ...Alpha Mistral 7B Instruct V0.1 | 32K / 14.5 GB | 24 | 1 |
| ...Mistral 7B Instruct V0.2 Slerp | 32K / 14.4 GB | 28 | 1 |
| ...Mistral 7B Instruct V0.2 Slerp | 32K / 14.4 GB | 30 | 2 |
| Mistral 11B Instruct V0.2 | 32K / 21.4 GB | 6 | 3 |
| Bielik 11B V2.2 Instruct FP8 | 32K / 11.4 GB | 493 | 3 |
| Bielik 11B V2.2 Instruct W8A8 | 32K / 11.5 GB | 309 | 3 |
| ... 11B V2.2 Instruct Quanto 8bit | 32K / 12 GB | 24 | 3 |
| ... 11B V2.2 Instruct EXL2 4.5bit | 32K / 6.5 GB | 33 | 3 |
Rank the MSH V1 Bielik V2.3 Instruct MedIT Merge 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? 40066 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241217