Optimized for real-world data science decisions. It delivers method selection, alternative comparison, and validation planning in one response. Trained on 16.5K expert insight dialogues, it focuses on actionable guidance over generic theory.

tools

ollama run Zero9Tech/llama3.1-8b-data-science

curl http://localhost:11434/api/chat \
  -d '{
    "model": "Zero9Tech/llama3.1-8b-data-science",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from ollama import chat

response = chat(
    model='Zero9Tech/llama3.1-8b-data-science',
    messages=[{'role': 'user', 'content': 'Hello!'}],
)
print(response.message.content)

import ollama from 'ollama'

const response = await ollama.chat({
  model: 'Zero9Tech/llama3.1-8b-data-science',
  messages: [{role: 'user', content: 'Hello!'}],
})
console.log(response.message.content)

Details

Updated 3 weeks ago

3 weeks ago

b72138734fd9 · 5.6GB ·

model

archqwen35

parameters8.95B

quantizationQ4_K_M

5.6GB

template

{{- if or .System .Tools }}<|start_header_id|>system<|end_header_id|> {{- if .System }} {{ .System }

826B

params

{ "stop": [ "<|eot_id|>", "<|start_header_id|>" ], "temperature": 0.8,

107B

Readme

Llama-3.1-8B-Data-Science-Insight-16.5K

This model is tuned for decision-oriented data mining and applied data science assistance.

Training Setup

Domain SFT: zero9tech/data-scientist-insight-dialog-en-16.5k.

Dataset Test Highlights

Total records: 16,463
Split: train: 14,021 · validation: 801 · test: 1,641
assistant_first_unique_ratio: 0.8408
assistant_final_unique_ratio: 1.0000

Usage Note

Model behavior is optimized for decision-focused responses (method choice, alternatives, risk signals, validation planning).

Copyright

License

Apache-2.0