Downloads · 30 days
5
7% of all-time downloads
aya-expanse-8b-compressed-final-int8
AnishRacherla/aya-expanse-8b-compressed-final-int8
aya-expanse-8b-compressed-final-int8 is a translation model from AnishRacherla. Use it when you need text moved from one language to another. The card lists the license as apache-2.0.
All-time downloads
68
Public
Parameters
7.2B
8.2 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors8.2 GB · 100%
Parameter types
How the weights are stored.
I86.1B · 85%
Try a prompt
Model card
From the Hugging Face model README
Aya Expanse 8B — Compressed (int8)
Self-contained. No other repo needed.
Pipeline: Pruning → LoRA fine-tune → Merge → int8 quantize
Load
from transformers import AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfig
import torch
bnb = BitsAndBytesConfig(load_in_8bit=True)
tok = AutoTokenizer.from_pretrained('AnishRacherla/aya-expanse-8b-compressed-final-int8', trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained('AnishRacherla/aya-expanse-8b-compressed-final-int8', quantization_config=bnb, device_map='auto', trust_remote_code=True)
Benchmark vs Baseline (FLORES-200, 100 En→Zh)
| Metric | Baseline int4 | This model | Δ |
|---|---|---|---|
| VRAM | 5.31 GB | 7.65 GB | +2.34 |
| Tokens/sec | 9.2 | 6.1 | -3.1 |
| COMET | 0.5095 | 0.8620 | +0.3525 |
- Task
- Translation
- Type
- cohere
- License
- apache-2.0
- Languages
- en, zh
- Created
- Jun 29, 2026
- Updated
- Jun 29, 2026