Ollama-optimized version of Rombos-LLM-V2.6-Qwen-14b

ollama run koill/rombos-llm-v2.6-qwen-14b

curl http://localhost:11434/api/chat \
  -d '{
    "model": "koill/rombos-llm-v2.6-qwen-14b",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from ollama import chat

response = chat(
    model='koill/rombos-llm-v2.6-qwen-14b',
    messages=[{'role': 'user', 'content': 'Hello!'}],
)
print(response.message.content)

import ollama from 'ollama'

const response = await ollama.chat({
  model: 'koill/rombos-llm-v2.6-qwen-14b',
  messages: [{role: 'user', content: 'Hello!'}],
})
console.log(response.message.content)

Details

Updated 1 year ago

1 year ago

ee2392403199 · 9.0GB ·

model

archqwen2

parameters14.8B

quantizationQ4_K_M

9.0GB

system

You are a helpful AI assistant.

31B

template

{{ if .System }}<|im_start|>system{{.System}}<|im_end|>{{ end }} {{ if .Prompt }}<|im_start|>user{{.

165B

license

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

11kB

params

{ "stop": [ "<|im_start|>", "<|im_end|>" ] }

59B

Readme

Rombos-LLM-V2.6-Qwen-14b for Ollama

This repository contains an Ollama-optimized version of Rombos-LLM-V2.6-Qwen-14b, making it easier for users to run the model locally with improved performance.

Overview

The original Rombos-LLM-V2.6-Qwen-14b model, created by Rombodawg, is now available in an Ollama-compatible format. This adaptation allows for faster inference and simpler deployment using the Ollama framework.

Resources

Original Model: Rombos-LLM-V2.6-Qwen-14b
Quantized Version: GGUF Model by Bartowski