Enterprise coding & engineering assistant by GOCOSYS Technologies — built on Qwen2.5-Coder-7B. Great for PHP, Laravel, Python, JS/TS, React, Node, Docker & DevOps.

Details

Updated yesterday

yesterday

7ce2676353ae · 4.7GB ·

model

archqwen2

parameters7.62B

quantizationQ4_K_M

4.7GB

template

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

1.6kB

license

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

11kB

system

You are NAVI AI, an enterprise engineering assistant created by GOCOSYS Technologies. You specialize

290B

params

{ "num_ctx": 8192, "stop": [ "<|im_start|>", "<|im_end|>" ], "temper

104B

NAVI

Enterprise coding & engineering assistant by GOCOSYS Technologies.

NAVI is an AI assistant for software engineers. It writes, reviews, and debugs code across the full stack, and answers architecture, DevOps, and general engineering questions in a clear, ChatGPT-style manner — identifying itself as NAVI, created by GOCOSYS Technologies.

Built on Qwen2.5-Coder-7B (Apache-2.0), packaged with the NAVI engineering persona and tuned decoding defaults. Served as Q4_K_M (~4.7 GB) — runs on a single 8 GB+ GPU or on CPU.

Quickstart

ollama run gocosys/navi:7b

# one-shot
ollama run gocosys/navi:7b "Write a Laravel migration for a posts table."

Use it from code (OpenAI-compatible)

from openai import OpenAI
client = OpenAI(base_url="http://localhost:11434/v1", api_key="ollama")
print(client.chat.completions.create(
    model="gocosys/navi:7b",
    messages=[{"role": "user", "content": "Write a Python function to reverse a string."}],
).choices[0].message.content)

curl http://localhost:11434/api/chat -d '{
  "model": "gocosys/navi:7b",
  "stream": false,
  "messages": [{"role": "user", "content": "Explain N+1 queries and how to fix them."}]
}'

Expertise

PHP · Laravel · Python · Django · JavaScript · TypeScript · React · Node.js · HTML/CSS · SQL · MongoDB · Redis · REST & GraphQL APIs · Docker · Linux · Git · AWS · Azure · DevOps / CI-CD · security · testing · code review · debugging · system architecture.

Defaults

Parameter	Value
Context length	8192
Temperature	0.2
top_p	0.9
Quantization	Q4_K_M
Template	ChatML

Capabilities

completion — chat & code generation
tools — function/tool calling (inherited from Qwen2.5-Coder)

Limitations

Based on Qwen2.5-Coder-7B; it inherits that model’s knowledge and training cutoff. Verify security-sensitive or production code before use.
7B size — for the largest tasks, use a bigger backend.