Xglm 1.7B is an open-source language model by facebook. Features: 1.7b LLM, VRAM: 3.5GB, Context: 2K, License: mit, HF Score: 31.4, LLM Explorer Score: 0.06, Arc: 25.9, HellaSwag: 45.7, MMLU: 25.1, TruthfulQA: 37.2, WinoGrande: 53.9, GSM8K: 0.8.
| Model Type |
| |||
| Supported Languages |
| |||
| Training Details |
|
| LLM Name | Xglm 1.7B |
| Repository ๐ค | https://huggingface.co/facebook/xglm-1.7B |
| Model Size | 1.7b |
| Required VRAM | 3.5 GB |
| Updated | 2026-04-03 |
| 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 |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Xglm Instruct 2 | 2K / 6.9 GB | 8 | 0 |
๐ 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! ๐