granite-code:34b-instruct-q4_K

granite-code:34b-instruct-q4_K_M

592.7K Downloads Updated 1 year ago

A family of open foundation models by IBM for Code Intelligence

3b 8b 20b 34b

ollama run granite-code:34b-instruct-q4_K_M

curl http://localhost:11434/api/chat \
  -d '{
    "model": "granite-code:34b-instruct-q4_K_M",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from ollama import chat

response = chat(
    model='granite-code:34b-instruct-q4_K_M',
    messages=[{'role': 'user', 'content': 'Hello!'}],
)
print(response.message.content)

import ollama from 'ollama'

const response = await ollama.chat({
  model: 'granite-code:34b-instruct-q4_K_M',
  messages: [{role: 'user', content: 'Hello!'}],
})
console.log(response.message.content)

Details

Updated 1 year ago

1 year ago

74723d97951a · 21GB ·

model

archstarcoder

parameters33.7B

quantizationQ4_K_M

21GB

params

{ "stop": [ "<fim_prefix>", "<fim_middle>", "<fim_suffix>", "<fi

108B

license

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

11kB

template

{{ if .System }} System: {{ .System }} {{ end }}{{ if .Prompt }}Question: {{ .Prompt }} {{ end }}Ans

123B

Readme

Granite Code is a family of decoder-only code model designed for code generative tasks (e.g. code generation, code explanation, code fixing, etc.).

Parameter Sizes

34B Parameters ollama run granite-code:34b
20B Parameters ollama run granite-code:20b
8B Parameters (with 128K context window) ollama run granite-code:8b
3B Parameters (with 128K context window) ollama run granite-code:3b

A family of open foundation models by IBM for Code Intelligence

Details

Readme

Parameter Sizes

Resources