Geko3 is an open-source language model by dahalotto. Features: 2.5b LLM, VRAM: 5.1GB, Context: 8K, License: apache-2.0, LLM Explorer Score: 0.14.
Autotrain compatible Conversational Endpoints compatible Gemma Region:us Safetensors Sharded Tensorflow
Model Card on HF 🤗: https://huggingface.co/dahalotto/geko3
Geko3 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)
Geko3 Parameters and Internals
| LLM Name | Geko3 |
| Repository 🤗 | https://huggingface.co/dahalotto/geko3 |
| Model Size | 2.5b |
| Required VRAM | 5.1 GB |
| Updated | 2024-11-28 |
| Maintainer | dahalotto |
| Model Type | gemma |
| Model Files | |
| Model Architecture | GemmaForCausalLM |
| License | apache-2.0 |
| Context Length | 8192 |
| Model Max Length | 8192 |
| Transformers Version | 4.41.2 |
| Tokenizer Class | GemmaTokenizer |
| Padding Token | <pad> |
| Vocabulary Size | 256000 |
| Torch Data Type | float16 |
Best Alternatives to Geko3
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| M3 Sft It DPO | 8K / 10 GB | 158 | 0 |
| Gemma Ko V01 | 8K / 5.1 GB | 7 | 0 |
| M3 Sft Orca It Base | 8K / 10 GB | 11 | 0 |
| M3 Sft Orca It Base | 8K / 10 GB | 5 | 0 |
| Orca Gemma It DPO | 8K / 10 GB | 5 | 0 |
| Gemma EPFL | 8K / 10 GB | 5 | 0 |
| M3 Sft Gemma It | 8K / 10 GB | 9 | 0 |
| M3 Sft Gemma | 8K / 10 GB | 7 | 0 |
| M3 Sft It DPO | 8K / 10 GB | 6 | 0 |
| M3 Sft DPO | 8K / 10 GB | 5 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than dahalotto/geko3 .
Rank the Geko3 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? 54120 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