Arxiv:2112.10668 Ar Autotrain compatible Bg Bn Ca De El En Es Et Eu Fi Fr Hi Ht Id It Ja Ko Multilingual My Pt Pytorch Qu Region:us Ru Sw Ta Te Tf Th Tr Ur Vi Xglm Zh
Model Card on HF 🤗: https://huggingface.co/facebook/xglm-1.7B
Xglm 1.7B Benchmarks
ARC: 25.85 vs 96.7 (so35)-73.3%
HellaSwag: 45.68 vs 95.3 (gpt4)-52.1%
MMLU: 25.1 vs 88.3 (so35)-71.6%
TruthfulQA: 37.21 vs 59 (gpt4)-36.9%
WinoGrande: 53.91 vs 87.5 (gpt4)-38.4%
GSM8K: 0.76 vs 96.4 (so35)-99.2%
LLME Score: 0.06421
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)
Xglm 1.7B Parameters and Internals
| Model Type |
| |||
| Supported Languages |
| |||
| Training Details |
|
| LLM Name | Xglm 1.7B |
| Repository 🤗 | https://huggingface.co/facebook/xglm-1.7B |
| Model Size | 1.7b |
| Required VRAM | 3.5 GB |
| Updated | 2025-08-18 |
| Maintainer | |
| Model Type | xglm |
| Model Files | |
| Supported Languages | en ru zh de es fr ja it pt el ko fi id tr ar vi th bg ca hi et bn ta ur sw te eu my ht qu |
| Model Architecture | XGLMForCausalLM |
| License | mit |
| Context Length | 2048 |
| Model Max Length | 2048 |
| Transformers Version | 4.16.0.dev0 |
| Tokenizer Class | XGLMTokenizer |
| Padding Token | <pad> |
| Vocabulary Size | 256008 |
| Activation Function | gelu |
Best Alternatives to Xglm 1.7B
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Xglm Instruct 2 | 2K / 6.9 GB | 5 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than facebook/xglm-1.7B .
Rank the Xglm 1.7B 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? 50729 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124