Yz

wizardlm

General use model based on Llama 2.

Hızlı Kurulum (Ollama kuruluysa) 
ollama run wizardlm

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
7b-q2_K 2.8GB 2K Text ollama run wizardlm:7b-q2_K
7b-q3_K_S 2.9GB 2K Text ollama run wizardlm:7b-q3_K_S
7b-q3_K_M 3.3GB 2K Text ollama run wizardlm:7b-q3_K_M
7b-q3_K_L 3.6GB 2K Text ollama run wizardlm:7b-q3_K_L
7b-q4_0 3.8GB 2K Text ollama run wizardlm:7b-q4_0
7b-q4_1 4.2GB 2K Text ollama run wizardlm:7b-q4_1
7b-q4_K_S 3.9GB 2K Text ollama run wizardlm:7b-q4_K_S
7b-q4_K_M 4.1GB 2K Text ollama run wizardlm:7b-q4_K_M
7b-q5_0 4.7GB 2K Text ollama run wizardlm:7b-q5_0
7b-q5_1 5.1GB 2K Text ollama run wizardlm:7b-q5_1
7b-q5_K_S 4.7GB 2K Text ollama run wizardlm:7b-q5_K_S
7b-q5_K_M 4.8GB 2K Text ollama run wizardlm:7b-q5_K_M
7b-q6_K 5.5GB 2K Text ollama run wizardlm:7b-q6_K
7b-q8_0 7.2GB 2K Text ollama run wizardlm:7b-q8_0
7b-fp16 13GB 2K Text ollama run wizardlm:7b-fp16
13b-llama2-q2_K 5.4GB 4K Text ollama run wizardlm:13b-llama2-q2_K
13b-llama2-q3_K_S 5.7GB 4K Text ollama run wizardlm:13b-llama2-q3_K_S
13b-llama2-q3_K_M 6.3GB 4K Text ollama run wizardlm:13b-llama2-q3_K_M
13b-llama2-q3_K_L 6.9GB 4K Text ollama run wizardlm:13b-llama2-q3_K_L
13b-llama2-q4_0 7.4GB 4K Text ollama run wizardlm:13b-llama2-q4_0
13b-llama2-q4_1 8.2GB 4K Text ollama run wizardlm:13b-llama2-q4_1
13b-llama2-q4_K_S 7.4GB 4K Text ollama run wizardlm:13b-llama2-q4_K_S
13b-llama2-q4_K_M 7.9GB 4K Text ollama run wizardlm:13b-llama2-q4_K_M
13b-llama2-q5_0 9.0GB 4K Text ollama run wizardlm:13b-llama2-q5_0
13b-llama2-q5_1 9.8GB 4K Text ollama run wizardlm:13b-llama2-q5_1

48 varyant daha var — tümü için ollama.com.

Model Detayları ve Benchmarklar (kaynak: ollama.com)

WizardLM is a 70B parameter model based on Llama 2 trained by WizardLM.

Get started with WizardLM

The model used in the example below is the WizardLM model, with 70b parameters, which is a general-use model.

API

  1. Start Ollama server (Run ollama serve)
  2. Run the model
curl -X POST http://localhost:11434/api/generate -d '{
  "model": "wizardlm:70b-llama2-q4_0",
  "prompt":"Why is the sky blue?"
 }'

CLI

  1. Install Ollama
  2. Open the terminal and run ollama run wizardlm:70b-llama2-q4_0

Note: The ollama run command performs an ollama pull if the model is not already downloaded. To download the model without running it, use ollama pull wizardlm:70b-llama2-q4_0

Memory requirements

  • 70b models generally require at least 64GB of RAM

If you run into issues with higher quantization levels, try using the q4 model or shut down any other programs that are using a lot of memory.

Model variants

By default, Ollama uses 4-bit quantization. To try other quantization levels, please try the other tags. The number after the q represents the number of bits used for quantization (i.e. q4 means 4-bit quantization). The higher the number, the more accurate the model is, but the slower it runs, and the more memory it requires.

Model source

WizardLM source on Ollama

70b parameters source: The Bloke

70b parameters original source: WizardLM