FLOR 6.3B Xat is an open-source language model by xaviviro. Features: 6.3b LLM, VRAM: 12.5GB, License: apache-2.0, HF Score: 38.2, LLM Explorer Score: 0.15, Arc: 38.7, HellaSwag: 63.8, MMLU: 26.5, TruthfulQA: 38, WinoGrande: 62.4.
Base model:finetune:projecte-a... Base model:projecte-aina/flor-... Bloom Ca Catalan Chatml Dataset:xaviviro/oasst2 ca gpt En Endpoints compatible Es Finetuned Gpt4 Region:us Safetensors Sharded Tensorflow
Model Card on HF 🤗: https://huggingface.co/xaviviro/FLOR-6.3B-xat
FLOR 6.3B Xat Benchmarks
ARC: 38.65 vs 96.7 (so35)-60%
HellaSwag: 63.76 vs 95.3 (gpt4)-33.1%
MMLU: 26.54 vs 88.3 (so35)-69.9%
TruthfulQA: 37.96 vs 59 (gpt4)-35.7%
WinoGrande: 62.43 vs 87.5 (gpt4)-28.7%
LLME Score: 0.15263
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)
FLOR 6.3B Xat Parameters and Internals
| LLM Name | FLOR 6.3B Xat |
| Repository 🤗 | https://huggingface.co/xaviviro/FLOR-6.3B-xat |
| Base Model(s) | |
| Model Size | 6.3b |
| Required VRAM | 12.5 GB |
| Updated | 2026-01-03 |
| Maintainer | xaviviro |
| Model Type | bloom |
| Model Files | |
| Supported Languages | ca en es |
| Model Architecture | BloomForCausalLM |
| License | apache-2.0 |
| Transformers Version | 4.36.2 |
| Tokenizer Class | GPT2Tokenizer |
| Padding Token | <|endoftext|> |
| Vocabulary Size | 50257 |
| Torch Data Type | float16 |
| Errors | replace |
Best Alternatives to FLOR 6.3B Xat
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| OpenHermes 2.5 FLOR 6.3B | 0K / 13 GB | 203 | 1 |
| FLOR RAG EADOP | 0K / 12.4 GB | 21 | 0 |
| FLOR 6.3B Instructed | 0K / 12.4 GB | 0 | 0 |
| FlorRAG | 0K / 12.4 GB | 0 | 0 |
| FLOR 6.3B | 0K / 12.5 GB | 0 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than xaviviro/FLOR-6.3B-xat .
Rank the FLOR 6.3B Xat 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? 52758 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