Yz

wizardlm2

State of the art large language model from Microsoft AI with improved performance on complex chat, multilingual, reasoning and agent use cases.

7b 8x22b
Hızlı Kurulum (Ollama kuruluysa) 
ollama run wizardlm2

Ollama kurulu değil mi? ollama.com/download — Windows, macOS ve Linux için ücretsiz. İlk çalıştırmada model indirilir, sonrası tamamen çevrimdışıdır.

Varyantlar

Boyut büyüdükçe kalite artar, donanım ihtiyacı yükselir. Başlangıç için küçük varyantı deneyin.

EtiketBoyutBağlamGirdiKomut
latest 4.1GB 32K Text ollama run wizardlm2:latest
7b 4.1GB 32K Text ollama run wizardlm2:7b
8x22b 80GB 64K Text ollama run wizardlm2:8x22b
7b-q2_K 2.7GB 32K Text ollama run wizardlm2:7b-q2_K
7b-q3_K_S 3.2GB 32K Text ollama run wizardlm2:7b-q3_K_S
7b-q3_K_M 3.5GB 32K Text ollama run wizardlm2:7b-q3_K_M
7b-q3_K_L 3.8GB 32K Text ollama run wizardlm2:7b-q3_K_L
7b-q4_0 4.1GB 32K Text ollama run wizardlm2:7b-q4_0
7b-q4_1 4.6GB 32K Text ollama run wizardlm2:7b-q4_1
7b-q4_K_S 4.1GB 32K Text ollama run wizardlm2:7b-q4_K_S
7b-q4_K_M 4.4GB 32K Text ollama run wizardlm2:7b-q4_K_M
7b-q5_0 5.0GB 32K Text ollama run wizardlm2:7b-q5_0
7b-q5_1 5.4GB 32K Text ollama run wizardlm2:7b-q5_1
7b-q5_K_S 5.0GB 32K Text ollama run wizardlm2:7b-q5_K_S
7b-q5_K_M 5.1GB 32K Text ollama run wizardlm2:7b-q5_K_M
7b-q6_K 5.9GB 32K Text ollama run wizardlm2:7b-q6_K
7b-q8_0 7.7GB 32K Text ollama run wizardlm2:7b-q8_0
7b-fp16 14GB 32K Text ollama run wizardlm2:7b-fp16
8x22b-q2_K 52GB 64K Text ollama run wizardlm2:8x22b-q2_K
8x22b-q4_0 80GB 64K Text ollama run wizardlm2:8x22b-q4_0
8x22b-q8_0 149GB 64K Text ollama run wizardlm2:8x22b-q8_0
8x22b-fp16 281GB 64K Text ollama run wizardlm2:8x22b-fp16

Model Detayları ve Benchmarklar (kaynak: ollama.com)

WizardLM-2 is a next generation state-of-the-art large language model with improved performance on complex chat, multilingual, reasoning and agent use cases. This family includes three cutting-edge models:

  • wizardlm2:7b: fastest model, comparable performance with 10x larger open-source models.
  • wizardlm2:8x22b: the most advanced model, and the best opensource LLM in Microsoft’s internal evaluation on highly complex tasks.
  • wizardlm2:70b: model with top-tier reasoning capabilities for its size (coming soon)

References

Blog Post

HuggingFace