frob/ ling-3.0-flash:124b

75 Downloads Updated 1 month ago

ollama run frob/ling-3.0-flash:124b

curl http://localhost:11434/api/chat \
  -d '{
    "model": "frob/ling-3.0-flash:124b",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from ollama import chat

response = chat(
    model='frob/ling-3.0-flash:124b',
    messages=[{'role': 'user', 'content': 'Hello!'}],
)
print(response.message.content)

import ollama from 'ollama'

const response = await ollama.chat({
  model: 'frob/ling-3.0-flash:124b',
  messages: [{role: 'user', content: 'Hello!'}],
})
console.log(response.message.content)

Details

Updated 1 month ago

1 month ago

e9709a9878a0 · 77GB

model

archbailingmoe3

parameters127B

quantizationQ4_K_M

77GB

license

MIT License Copyright (c) [year] [fullname] Permission is hereby granted, free of charge, to any per

1.1kB

params

{ "temperature": 0.6, "top_k": 20, "top_p": 0.95 }

44B

Readme

Imported from https://huggingface.co/inclusionAI/Ling-3.0-flash.

Needs ollama v0.32.15+.

Chat/thinking

$ ollama run frob/ling-3.0-flash
>>> hello
Thinking...
The user has sent a simple greeting: "hello." This is a conversational opener with
no specific question, request, or technical query. The appropriate response is a
friendly greeting in return.
...done thinking.

Hello! 👋 How can I help you today?

>>> /set nothink
Set 'nothink' mode.
>>> hello
Hello again! 👋 Is there anything I can help you with today?

Tools

$ ollama launch opencode \
    --model frob/ling-3.0-flash \
    -- \
    run 'create a file called README with the contents "hello world"'

> build · frob/ling-3.0-flash:latest

$ ls /home/rick/ollama/issues/ling/README* 2>/dev/null; echo "---"; pwd
---
/home/rick/ollama/issues/ling

← Write README
Wrote file successfully.

Created `/home/rick/ollama/issues/ling/README` with contents "hello world".

$ cat README 
hello world