Merged Model Arxiv:2306.01708 Arxiv:2311.03099 Autotrain compatible Base model:bunnycore/llama-3.2... Base model:bunnycore/llama-3.2... Base model:bunnycore/smol-llam... Base model:prithivmlmods/llama... Conversational Endpoints compatible Llama Region:us Safetensors Sharded Tensorflow
Model Card on HF 🤗: https://huggingface.co/bunnycore/Llama-3.2-3B-Deep-Test
Llama 3.2 3B Deep Test Benchmarks
MMLU Pro: 23.92
GPQA: 1.9
MUSR: 2.56
BBH: 22.91
IFEval: 46.67 vs 88 (so35)-47%
MATH Lvl 5: 10.57
LLME Score: 0.32622
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 3.2 3B Deep Test Parameters and Internals
| LLM Name | Llama 3.2 3B Deep Test |
| Repository 🤗 | https://huggingface.co/bunnycore/Llama-3.2-3B-Deep-Test |
| Base Model(s) | |
| Merged Model | Yes |
| Model Size | 3b |
| Required VRAM | 7.2 GB |
| Updated | 2025-01-21 |
| Maintainer | bunnycore |
| Model Type | llama |
| Model Files | |
| Model Architecture | LlamaForCausalLM |
| Context Length | 131072 |
| Model Max Length | 131072 |
| Transformers Version | 4.46.2 |
| Tokenizer Class | PreTrainedTokenizerFast |
| Padding Token | <|eot_id|> |
| Vocabulary Size | 128256 |
| Torch Data Type | bfloat16 |
Best Alternatives to Llama 3.2 3B Deep Test
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Llama 3.2 3B Instruct | 128K / 6.5 GB | 1405328 | 905 |
| Llama 3.2 3B | 128K / 6.5 GB | 425944 | 464 |
| Hermes 3 Llama 3.2 3B | 128K / 6.5 GB | 18327 | 127 |
| Omni Reasoner3 Merged | 128K / 6.4 GB | 47 | 7 |
| Orca Mini V9 5 3B Instruct | 128K / 6.5 GB | 399 | 6 |
| Dolphin3.0 Llama3.2 3B | 128K / 6.5 GB | 4997 | 25 |
| Llama Deepsync 3B | 128K / 6.5 GB | 429 | 15 |
| Calme 3.1 Llamaloi 3B | 128K / 10.6 GB | 2794 | 1 |
| Llama 3.2 3B RP DeepThink | 128K / 7.2 GB | 371 | 2 |
| Llama 3.2 3B Instruct | 128K / 6.5 GB | 536930 | 2 |
Note: green Score (e.g. "73.2") means that the model is better than bunnycore/Llama-3.2-3B-Deep-Test .
Rank the Llama 3.2 3B Deep Test 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