Downloads · 30 days
10
4% of all-time downloads
Llama-Spark-fp8
juliensimon/Llama-Spark-fp8
Llama-Spark-fp8 is a text generation model from juliensimon. Use it when you need the model to write or continue text.
FP8-quantized version of Arcee Llama Spark, an improved Llama 3.1 8B model from Arcee AI. FP8 quantization reduces memory footprint while preserving model quality.
All-time downloads
230
Public
Parameters
8B
11.2 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors11.2 GB · 100%
Parameter types
How the weights are stored.
F8_E4M37B · 87%
Try a prompt
Base models
Model card
From the Hugging Face model README
Llama Spark — FP8
FP8-quantized version of Arcee Llama Spark, an improved Llama 3.1 8B model from Arcee AI. FP8 quantization reduces memory footprint while preserving model quality.
Video walkthroughs:
Model Details
| Detail | Value |
|---|---|
| Base model | arcee-ai/Llama-Spark |
| Architecture | Llama 3.1 (8B parameters) |
| Quantization | FP8 (8-bit floating point) |
| Model size | ~11 GB (3 shards) |
| Format | Safetensors |
Usage
from transformers import AutoModelForCausalLM, AutoTokenizer
model = AutoModelForCausalLM.from_pretrained(
"juliensimon/Llama-Spark-fp8", torch_dtype="auto", device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained("juliensimon/Llama-Spark-fp8")
- Task
- Text Generation
- Type
- llama
- Created
- Aug 15, 2024
- Updated
- Mar 22, 2026