Arxiv:1607.06450 Arxiv:1910.07467 Arxiv:1911.02150 Arxiv:2108.12409 Autotrain compatible Code Custom code Dataset:bigcode/commitpackft Dataset:bigcode/the-stack-dedu... Dataset:rombodawg/2xuncensored... En Gpt refact Model-index Pytorch Region:us Safetensors
Model Card on HF 🤗: https://huggingface.co/smallcloudai/Refact-1_6B-fim
Refact 1 6B Fim Benchmarks
HumanEvalA: 17.86
Python Eva: 31.1 vs 92 (so35)-66.2%
Java Eval: 22.78
Javascript: 22.36
CPP Eval: 21.12
PHP Eval: 22.36
Julia Eval: 13.84
D Eval: 10.26
Lua Eval: 15.53
R Eval: 13.04
Racket Eva: 4.97
Rust Eval: 18.59
Swift Eval: 18.35
LLME Score: 0.26939
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)
Refact 1 6B Fim Parameters and Internals
| LLM Name | Refact 1 6B Fim |
| Repository 🤗 | https://huggingface.co/smallcloudai/Refact-1_6B-fim |
| Model Size | 6b |
| Required VRAM | 3.2 GB |
| Updated | 2024-12-22 |
| Maintainer | smallcloudai |
| Model Type | gpt_refact |
| Model Files | |
| Supported Languages | en |
| Model Architecture | GPTRefactForCausalLM |
| License | bigscience-openrail-m |
| Transformers Version | 4.31.0 |
| Tokenizer Class | GPT2Tokenizer |
| Vocabulary Size | 49216 |
| Torch Data Type | bfloat16 |
Rank the Refact 1 6B Fim 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? 40066 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241217