SaturnStudio/AsaRye-LLM-Coder2.5.Q7B-o-u-4T

SaturnStudio/ AsaRye-LLM-Coder2.5.Q7B-o-u-4T:latest

6 Downloads Updated yesterday

AsaRye-LLM-Coder2.5.Q7B-o-u-4T Overview AsaRye-LLM-Coder2.5.Q7B-o-u-4T is a 7B code LLM based on Qwen2.5-7B-Instruct-abliterated. It supports 90+ languages, runs on laptops, and is tuned for fixes over apologies. It is a 4T type capped at 4 CPU cores.

tools

ollama run SaturnStudio/AsaRye-LLM-Coder2.5.Q7B-o-u-4T

curl http://localhost:11434/api/chat \
  -d '{
    "model": "SaturnStudio/AsaRye-LLM-Coder2.5.Q7B-o-u-4T",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from ollama import chat

response = chat(
    model='SaturnStudio/AsaRye-LLM-Coder2.5.Q7B-o-u-4T',
    messages=[{'role': 'user', 'content': 'Hello!'}],
)
print(response.message.content)

import ollama from 'ollama'

const response = await ollama.chat({
  model: 'SaturnStudio/AsaRye-LLM-Coder2.5.Q7B-o-u-4T',
  messages: [{role: 'user', content: 'Hello!'}],
})
console.log(response.message.content)

Details

Updated yesterday

yesterday

930c6469e694 · 5.4GB

model

archqwen2

parameters7.62B

quantizationQ5_K_M

5.4GB

system

你是“AsaRye-AI.V4Coder”。你的LLM名称是“AsaRye-LLM-Coder2.5.Q7B-o-u-4T”。你是Sat

3.1kB

params

{ "num_thread": 4 }

17B

template

{{- if .Suffix }}<|fim_prefix|>{{ .Prompt }}<|fim_suffix|>{{ .Suffix }}<|fim_middle|> {{- else if .M

1.6kB

Readme

No readme