Arxiv:2305.18290 Autotrain compatible Base model:finetune:lianghsun/... Base model:lianghsun/llama-3.2... Chat Conversational Dataset:davidlanz/taiwanchat Dataset:lianghsun/reasoning-ba... Dataset:lianghsun/tw-bar-exami... Dataset:lianghsun/tw-contract-... Dataset:lianghsun/tw-emergency... Dataset:lianghsun/tw-instruct Dataset:lianghsun/tw-judgment-... Dataset:lianghsun/tw-judgment-... Dataset:lianghsun/tw-law-artic... Dataset:lianghsun/tw-legal-nlp Dataset:lianghsun/tw-legal-syn... Dataset:lianghsun/tw-structure... Dataset:lianghsun/vulnerabilit... Dataset:minyichen/glaive toolc... Dataset:neural-bridge/rag-data... Dataset:rombodawg/everything i... Dataset:xzuyn/manythings-trans... De En Endpoints compatible Fr Instruct It Ja Ko Llama Llama3.2 Model-index Region:us Roc Safetensors Sharded Slm Taiwan Tensorflow Zh Zh-tw
Model Card on HF 🤗: https://huggingface.co/DavidLanz/Llama-3.2-Taiwan-3B-Instruct
Llama 3.2 Taiwan 3B Instruct Benchmarks
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 Taiwan 3B Instruct Parameters and Internals
| LLM Name | Llama 3.2 Taiwan 3B Instruct |
| Repository 🤗 | https://huggingface.co/DavidLanz/Llama-3.2-Taiwan-3B-Instruct |
| Base Model(s) | |
| Model Size | 3b |
| Required VRAM | 6.5 GB |
| Updated | 2025-07-29 |
| Maintainer | DavidLanz |
| Model Type | llama |
| Instruction-Based | Yes |
| Model Files | |
| Supported Languages | zh en it de fr ja ko |
| Model Architecture | LlamaForCausalLM |
| License | llama3.2 |
| Context Length | 131072 |
| Model Max Length | 131072 |
| Transformers Version | 4.48.3 |
| Tokenizer Class | PreTrainedTokenizerFast |
| Padding Token | <|finetune_right_pad_id|> |
| Vocabulary Size | 128256 |
| Torch Data Type | bfloat16 |
Best Alternatives to Llama 3.2 Taiwan 3B Instruct
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Llama 3.2 3B Instruct | 128K / 6.5 GB | 1911763 | 1628 |
| DeepSeek R1 Distill Llama 3B | 128K / 6.5 GB | 1644 | 15 |
| Llama 3.2 3B RP Toxic Fuse | 128K / 6.4 GB | 192 | 2 |
| Llama 3.2 3B Instruct | 128K / 6.5 GB | 159569 | 74 |
| Zeitgeist 3B V1 | 128K / 6.5 GB | 105 | 5 |
| ReasoningCore 3B T1 1 | 128K / 6.5 GB | 36 | 1 |
| ... 3.2 3B Math Instruct RE1 ORPO | 128K / 6.5 GB | 48 | 0 |
| Llama 3.2 3B ToxicKod | 128K / 6.4 GB | 3 | 2 |
| Orpheus 3B 0.1 Pretrained | 128K / 6.6 GB | 6731 | 1 |
| TwinLlama 3.2 3B Instruct | 128K / 6.5 GB | 46 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than DavidLanz/Llama-3.2-Taiwan-3B-Instruct .
Rank the Llama 3.2 Taiwan 3B Instruct 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? 50200 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124