Arxiv:2404.01744 Arxiv:2404.11459 Arxiv:2404.19296 Android Autotrain compatible Base model:finetune:google/gem... Base model:google/gemma-2b Conversational En Function calling Gemma On-device language model Region:us Safetensors Sharded Tensorflow
Octopus V2 Parameters and Internals
| LLM Name | Octopus V2 |
| Repository | Open on 🤗 |
| Base Model(s) | |
| Model Size | 2b |
| Required VRAM | 5.1 GB |
| Updated | 2024-07-27 |
| Maintainer | NexaAIDev |
| Model Type | gemma |
| Model Files | |
| Supported Languages | en |
| Model Architecture | GemmaForCausalLM |
| License | cc-by-nc-4.0 |
| Context Length | 8192 |
| Model Max Length | 8192 |
| Transformers Version | 4.39.0.dev0 |
| Tokenizer Class | GemmaTokenizer |
| Padding Token | <pad> |
| Vocabulary Size | 256022 |
| Torch Data Type | bfloat16 |
Quantized Models of the Octopus V2
Model |
Likes |
Downloads |
VRAM |
|---|---|---|---|
| Octopus V2 GGUF | 6 | 106 | 1 GB |
Best Alternatives to Octopus V2
Best Alternatives |
HF Rank |
Context/RAM |
Downloads |
Likes |
|---|---|---|---|---|
| Gemma 1.1 2B It | 0.4 | 8K / 5.1 GB | 54841 | 131 |
| Gemma 2B 10M | 0.3 | 8K / 10 GB | 308 | 212 |
| Codegemma 2B | 0.3 | 8K / 5.1 GB | 2688 | 63 |
| Gemma Ko 1.1 2B It | 0.3 | 8K / 5.1 GB | 2046 | 1 |
| EMO 2B | 0.3 | 8K / 5.1 GB | 3486 | 1 |
| Gemma 2B Ko V0 | 0.3 | 8K / 5 GB | 2030 | 0 |
| Gemma 2B Ko Dev Pbmt192 | 0.3 | 8K / 5 GB | 2557 | 1 |
| Gemma 2B Data Std | 0.3 | 8K / 5.1 GB | 2041 | 1 |
| Gemma 2B Orpo | 0.3 | 8K / 5.1 GB | 701 | 27 |
| Gemma Ko 2B | 0.3 | 8K / 5.1 GB | 6890 | 30 |
Note: green Score (e.g. "73.2") means that the model is better than NexaAIDev/Octopus-v2 .
Rank the Octopus V2 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? 34447 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024072501