robmaster/Spatz-14B-de

robmaster/ Spatz-14B-de:latest

452 Downloads Updated 1 year ago

This is an English and German-speaking, universally applicable multi-talent based on Qwen2.5. It is ideal for working with tools.

tools

ollama run robmaster/Spatz-14B-de

curl http://localhost:11434/api/chat \
  -d '{
    "model": "robmaster/Spatz-14B-de",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from ollama import chat

response = chat(
    model='robmaster/Spatz-14B-de',
    messages=[{'role': 'user', 'content': 'Hello!'}],
)
print(response.message.content)

import ollama from 'ollama'

const response = await ollama.chat({
  model: 'robmaster/Spatz-14B-de',
  messages: [{role: 'user', content: 'Hello!'}],
})
console.log(response.message.content)

Details

Updated 1 year ago

1 year ago

1e7b36961a25 · 16GB ·

model

archqwen2

parameters14.8B

quantizationQ8_0

16GB

license

Apache License Version 2.0, January 2004 http://www.apache.org/licenses/ TERMS AND CONDITIONS FOR US

11kB

params

{ "stop": [ "<|endoftext|>", "<|im_end|>", "<|fim_pad|>", "<|fil

153B

template

{{- if .Messages }} {{- if or .System .Tools }}<|im_start|>system {{- if .System }} {{ .System }} {{

1.5kB

Readme

Attention, the context size must be specified explicitly, otherwise the default is 2048 tokens, up to 128,000 tokens are supported. A good value is 32,000. Start the Ollama server with the following parameters:

OLLAMA_CONTEXT_LENGTH=32000 ollama serve

Now you can test the model with the call

ollama run robmaster/Spatz-14B-de