Model Card on HF 🤗: https://huggingface.co/CYFRAGOVPL/Llama-PLLuM-8B-base
Llama PLLuM 8B Base Benchmarks
MMLU Pro: 19.52
GPQA: 4.7
MUSR: 10.06
BBH: 20.22
IFEval: 28.99 vs 88 (so35)-67.1%
MATH Lvl 5: 3.63
LLME Score: 0.32873
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)
Llama PLLuM 8B Base Parameters and Internals
| LLM Name | Llama PLLuM 8B Base |
| Repository 🤗 | https://huggingface.co/CYFRAGOVPL/Llama-PLLuM-8B-base |
| Model Size | 8b |
| Required VRAM | 16.1 GB |
| Updated | 2025-03-21 |
| Maintainer | CYFRAGOVPL |
| Model Type | llama |
| Model Files | |
| Supported Languages | pl |
| Model Architecture | LlamaForCausalLM |
| License | llama3.1 |
| Context Length | 131072 |
| Model Max Length | 131072 |
| Transformers Version | 4.47.0.dev0 |
| Tokenizer Class | PreTrainedTokenizerFast |
| Vocabulary Size | 128256 |
| Torch Data Type | bfloat16 |
Best Alternatives to Llama PLLuM 8B Base
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| ...a 3 8B Instruct Gradient 1048K | 1024K / 16.1 GB | 5022 | 682 |
| A8 | 1024K / 16.1 GB | 371 | 0 |
| A18 | 1024K / 16.1 GB | 272 | 0 |
| A12 | 1024K / 16.1 GB | 256 | 0 |
| B5 | 1024K / 16.1 GB | 147 | 0 |
| A15 | 1024K / 16.1 GB | 160 | 0 |
| A5 | 1024K / 16.1 GB | 150 | 0 |
| A16 | 1024K / 16.1 GB | 172 | 0 |
| A13 | 1024K / 16.1 GB | 236 | 0 |
| A17 | 1024K / 16.1 GB | 168 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than CYFRAGOVPL/Llama-PLLuM-8B-base .
Rank the Llama PLLuM 8B Base 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? 45354 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227