Autotrain compatible Base model:axcxept/ezo-llama-3... Base model:finetune:axcxept/ez... Conversational Dataset:hachiml/hachi-alpaca En Endpoints compatible Instruct Ja Llama Region:us Safetensors Sft Sharded Tensorflow Trl Unsloth
Model Card on HF 🤗: https://huggingface.co/Sakalti/Llama3.2-3B-Uranus-1
Llama3.2 3B Uranus 1 Benchmarks
MMLU Pro: 23.27
GPQA: 6.26
MUSR: 6.92
BBH: 21.42
IFEval: 53.35 vs 88 (so35)-39.4%
MATH Lvl 5: 14.73
LLME Score: 0.33034
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)
Llama3.2 3B Uranus 1 Parameters and Internals
| LLM Name | Llama3.2 3B Uranus 1 |
| Repository 🤗 | https://huggingface.co/Sakalti/Llama3.2-3B-Uranus-1 |
| Base Model(s) | |
| Model Size | 3b |
| Required VRAM | 6.5 GB |
| Updated | 2025-01-21 |
| Maintainer | Sakalti |
| Model Type | llama |
| Instruction-Based | Yes |
| Model Files | |
| Supported Languages | en ja |
| Model Architecture | LlamaForCausalLM |
| License | llama3.2 |
| Context Length | 131072 |
| Model Max Length | 131072 |
| Transformers Version | 4.47.1 |
| Tokenizer Class | PreTrainedTokenizerFast |
| Padding Token | <|finetune_right_pad_id|> |
| Vocabulary Size | 128256 |
| Torch Data Type | float16 |
Best Alternatives to Llama3.2 3B Uranus 1
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Llama 3.2 3B Instruct | 128K / 6.5 GB | 1405328 | 905 |
| Omni Reasoner3 Merged | 128K / 6.4 GB | 47 | 7 |
| Orca Mini V9 5 3B Instruct | 128K / 6.5 GB | 399 | 6 |
| Llama 3.2 3B RP DeepThink | 128K / 7.2 GB | 371 | 2 |
| Llama 3.2 3B Instruct | 128K / 6.5 GB | 536930 | 2 |
| Smol Llama 3.2 3B | 128K / 7.2 GB | 267 | 0 |
| Orca Mini V9 6 3B Instruct | 128K / 6.5 GB | 62 | 4 |
| Codepy Deepthink 3B | 128K / 6.5 GB | 232 | 8 |
| Llama 3.2 3B Instruct | 128K / 6.4 GB | 85633 | 44 |
| Orca Mini V9 7 3B Instruct | 128K / 6.5 GB | 227 | 3 |
Note: green Score (e.g. "73.2") means that the model is better than Sakalti/Llama3.2-3B-Uranus-1 .
Rank the Llama3.2 3B Uranus 1 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? 41727 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227