sammcj/ llama-3-1-8b-smcleod-golang-coder-v1

10 Downloads Updated 1 year ago

tools

ollama run sammcj/llama-3-1-8b-smcleod-golang-coder-v1:Q8_0

curl http://localhost:11434/api/chat \
  -d '{
    "model": "sammcj/llama-3-1-8b-smcleod-golang-coder-v1:Q8_0",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from ollama import chat

response = chat(
    model='sammcj/llama-3-1-8b-smcleod-golang-coder-v1:Q8_0',
    messages=[{'role': 'user', 'content': 'Hello!'}],
)
print(response.message.content)

import ollama from 'ollama'

const response = await ollama.chat({
  model: 'sammcj/llama-3-1-8b-smcleod-golang-coder-v1:Q8_0',
  messages: [{role: 'user', content: 'Hello!'}],
})
console.log(response.message.content)

Applications

Claude Code ollama launch claude --model sammcj/llama-3-1-8b-smcleod-golang-coder-v1:Q8_0

Codex ollama launch codex --model sammcj/llama-3-1-8b-smcleod-golang-coder-v1:Q8_0

OpenCode ollama launch opencode --model sammcj/llama-3-1-8b-smcleod-golang-coder-v1:Q8_0

OpenClaw ollama launch openclaw --model sammcj/llama-3-1-8b-smcleod-golang-coder-v1:Q8_0

Models

View all →

Name

1 model

Size

Context

Input

llama-3-1-8b-smcleod-golang-coder-v1:Q8_0

9.0GB · 128K context window · Text · 1 year ago

llama-3-1-8b-smcleod-golang-coder-v1:Q8_0

9.0GB

128K

Text

Readme

v3 is out! https://ollama.com/sammcj/llama-3-1-8b-smcleod-golang-coder-v3

Llama 3.1 8b Golang Coder v1

This model has been trained on Golang style guides, best practices and code examples. This should (hopefully) make it quite capable with Golang coding tasks.

Ollama

https://ollama.com/sammcj/llama-3-1-8b-smcleod-golang-coder-v1

Training

I trained this model (based on Llama 3.1 8b) on a merged dataset I created consisting of 50,627 rows, 13.3M input tokens and 2.2M output tokens. The total training consisted of 1,020,719 input tokens and 445,810 output tokens from 45,565 items in the dataset.

The dataset I created for this consists of multiple golang/programming focused datasets cleaned and merged and my own synthetically generated dataset based on several open source golang coding guides.