cieloforge/qwen2.5-coder-7b-instruct-spec

cieloforge/ qwen2.5-coder-7b-instruct-spec

213 Downloads Updated 1 week ago

A custom model of Qwen2.5-coder:7B-Instruct with the Qwen2.5-coder:3B-instruct used as a speculative fill model to speed up inference. Primarily made for TabbyML Usage.

tools

ollama run cieloforge/qwen2.5-coder-7b-instruct-spec

curl http://localhost:11434/api/chat \
  -d '{
    "model": "cieloforge/qwen2.5-coder-7b-instruct-spec",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from ollama import chat

response = chat(
    model='cieloforge/qwen2.5-coder-7b-instruct-spec',
    messages=[{'role': 'user', 'content': 'Hello!'}],
)
print(response.message.content)

import ollama from 'ollama'

const response = await ollama.chat({
  model: 'cieloforge/qwen2.5-coder-7b-instruct-spec',
  messages: [{role: 'user', content: 'Hello!'}],
})
console.log(response.message.content)

Applications

Claude Code ollama launch claude --model cieloforge/qwen2.5-coder-7b-instruct-spec

Codex App ollama launch codex-app --model cieloforge/qwen2.5-coder-7b-instruct-spec

OpenClaw ollama launch openclaw --model cieloforge/qwen2.5-coder-7b-instruct-spec

Hermes Agent ollama launch hermes --model cieloforge/qwen2.5-coder-7b-instruct-spec

Codex ollama launch codex --model cieloforge/qwen2.5-coder-7b-instruct-spec

OpenCode ollama launch opencode --model cieloforge/qwen2.5-coder-7b-instruct-spec

Models

View all →

Name

1 model

Size / Usage

Context

Input

qwen2.5-coder-7b-instruct-spec:latest

6.6GB · 32K context window · Text · 1 week ago

qwen2.5-coder-7b-instruct-spec:latest

6.6GB

32K

Text

Readme

No readme