Pangea 7B is an open-source language model by neulab. Features: 7b LLM, VRAM: 15.9GB, Context: 32K, License: apache-2.0, Instruction-Based, LLM Explorer Score: 0.18.
Arxiv:2410.16153 Am Ar Base model:finetune:qwen/qwen2... Base model:qwen/qwen2-7b-instr... Bg Bn Cs Dataset:neulab/pangeainstruct De El En Es Fa Fr Ga Hi Id Ig Instruct It Iw Ja Jv Ko Mn Ms Nl No Pl Pt Qwen2 Region:us Ro Ru Safetensors Sharded Si Su Sw Ta Te Tensorflow Th Tr Uk Ur Vi Zh
Model Card on HF 🤗: https://huggingface.co/neulab/Pangea-7B
Pangea 7B 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)
Pangea 7B Parameters and Internals
| LLM Name | Pangea 7B |
| Repository 🤗 | https://huggingface.co/neulab/Pangea-7B |
| Base Model(s) | |
| Model Size | 7b |
| Required VRAM | 15.9 GB |
| Updated | 2026-07-11 |
| Maintainer | neulab |
| Model Type | qwen2 |
| Instruction-Based | Yes |
| Model Files | |
| Supported Languages | am ar bg bn cs de el en es fa fr ga hi id ig it iw ja jv ko nl mn ms pl pt ro ru si su sw ta te th tr uk ur vi zh |
| Model Architecture | LlavaQwenForCausalLM |
| License | apache-2.0 |
| Context Length | 32768 |
| Model Max Length | 32768 |
| Transformers Version | 4.41.0 |
| Tokenizer Class | Qwen2Tokenizer |
| Padding Token | <|endoftext|> |
| Vocabulary Size | 152064 |
| Torch Data Type | bfloat16 |
| Errors | replace |
Best Alternatives to Pangea 7B
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| LongVA 7B | 218K / 15.9 GB | 865 | 15 |
| Llava Onevision Qwen2 7B Si | 32K / 16.1 GB | 71 | 12 |
Rank the Pangea 7B 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? 54990 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a