Downloads · 30 days
25
15% of all-time downloads
cello78/sambanova-llama2-100-gguf-q8
sambanova-llama2-100-gguf-q8 is a text generation model from cello78. Use it when you need the model to write or continue text. The card lists the license as apache-2.0.
Bu model, cello78/sambanova-llama2-100 modelinin 8-bit quantized GGUF versiyonudur.
Downloads · 30 days
25
15% of all-time downloads
All-time downloads
172
Public
Repo size
7.4 GB
Likes
0
Public
Click a slice to open those files.
.gguf7.4 GB · 100%
From the Hugging Face model README
Bu model, cello78/sambanova-llama2-100 modelinin 8-bit quantized GGUF versiyonudur.
from llama_cpp import Llama
llm = Llama( model_path="model-q8_0.gguf", n_ctx=2048, # Context length n_threads=8, # CPU thread sayısı )
Metin üret
prompt = "Merhaba, nasılsın?" output = llm(prompt, max_tokens=100, temperature=0.7) print(output['choices'][0]['text'])
### Ollama ile:
```bash
# Modeli indir
ollama pull cello78/sambanova-llama2-100-gguf-q8
Kullan
ollama run cello78/sambanova-llama2-100-gguf-q8 "Merhaba dünya!"
### LM Studio ile:
1. LM Studio'yu açın
2. "Search" kısmına `cello78/sambanova-llama2-100-gguf-q8` yazın
3. Modeli indirin ve kullanın
## ⚡ Performans
- **Hız**: Orijinal modelden ~2x daha hızlı
- **Bellek**: ~%50 daha az RAM kullanımı
- **Kalite**: Minimal kalite kaybı
## 🔧 Teknik Bilgiler
- **Quantization Method**: Q8_0 (8-bit integer quantization)
- **Conversion Tool**: llama.cpp
- **Original Precision**: FP16
- **Target Precision**: INT8
## 📄 Lisans
Bu model orijinal modelin lisansını takip eder.
## 🙏 Teşekkürler
- Orijinal model: [cello78/sambanova-llama2-100](https://huggingface.co/cello78/sambanova-llama2-100)
- Quantization: [llama.cpp](https://github.com/ggerganov/llama.cpp)