Gemma 2B Sft Preview is an open-source language model by pansophic. Features: 2b LLM, VRAM: 5GB, Context: 8K, License: other, Instruction-Based, Code Generating, HF Score: 54.8, LLM Explorer Score: 0.15, Arc: 52.3, HellaSwag: 73.6, MMLU: 45.8, TruthfulQA: 51.3, WinoGrande: 67, GSM8K: 38.6.
Autotrain compatible Base model:finetune:google/gem... Base model:google/gemma-2b Chatml Codegen Dataset:glaiveai/glaive-code-a... Dataset:huggingfaceh4/ultracha... Dataset:ise-uiuc/magicoder-evo... Dataset:ise-uiuc/magicoder-oss... Dataset:ldjnr/capybara Dataset:m-a-p/code-feedback Dataset:meta-math/metamathqa Dataset:migtissera/tess-coder-... Dataset:teknium/openhermes-2.5 En Endpoints compatible Gemma Instruct Model-index Region:us Safetensors
Model Card on HF 🤗: https://huggingface.co/pansophic/gemma-2b-sft-preview
Gemma 2B Sft Preview Benchmarks
ARC: 52.3 vs 96.7 (so35)-45.9%
HellaSwag: 73.6 vs 95.3 (gpt4)-22.8%
MMLU: 45.83 vs 88.3 (so35)-48.1%
TruthfulQA: 51.3 vs 59 (gpt4)-13.1%
WinoGrande: 67.01 vs 87.5 (gpt4)-23.4%
GSM8K: 38.59 vs 96.4 (so35)-60%
LLME Score: 0.14604
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)
Gemma 2B Sft Preview Parameters and Internals
| Model Type |
| |
| Additional Notes |
|
| LLM Name | Gemma 2B Sft Preview |
| Repository 🤗 | https://huggingface.co/pansophic/gemma-2b-sft-preview |
| Base Model(s) | |
| Model Size | 2b |
| Required VRAM | 5 GB |
| Updated | 2025-09-23 |
| Maintainer | pansophic |
| Model Type | gemma |
| Instruction-Based | Yes |
| Model Files | |
| Supported Languages | en |
| Generates Code | Yes |
| Model Architecture | GemmaForCausalLM |
| License | other |
| Context Length | 8192 |
| Model Max Length | 8192 |
| Transformers Version | 4.38.0.dev0 |
| Tokenizer Class | GemmaTokenizer |
| Padding Token | <|pad|> |
| Vocabulary Size | 256004 |
| Torch Data Type | bfloat16 |
Best Alternatives to Gemma 2B Sft Preview
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Datagemma 2B | 8K / 5.1 GB | 5 | 0 |
Rank the Gemma 2B Sft Preview 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? 52721 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