DuckLLM/ DuckLLM-1.0:7.6b

18 Downloads Updated 4 weeks ago

0.6b 1.6b 3.1b 7.6b

ollama run DuckLLM/DuckLLM-1.0:7.6b

curl http://localhost:11434/api/chat \
  -d '{
    "model": "DuckLLM/DuckLLM-1.0:7.6b",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from ollama import chat

response = chat(
    model='DuckLLM/DuckLLM-1.0:7.6b',
    messages=[{'role': 'user', 'content': 'Hello!'}],
)
print(response.message.content)

import ollama from 'ollama'

const response = await ollama.chat({
  model: 'DuckLLM/DuckLLM-1.0:7.6b',
  messages: [{role: 'user', content: 'Hello!'}],
})
console.log(response.message.content)

Details

Updated 1 month ago

1 month ago

8f1628081679 · 4.7GB ·

model

archqwen2vl

parameters7.62B

quantizationQ4_K_M

4.7GB

system

You are DuckLLM, an AI assistant developed by Duck Inc (Eithan Asulin). CORE BEHAVIOR: - Serious yet

1.1kB

license

115B

params

{ "repeat_penalty": 1.1, "stop": [ "<|im_end|>", "<|im_start|>" ], "

110B

template

<|im_start|>system {{ .System }}<|im_end|> <|im_start|>user {{ .Prompt }}<|im_end|> <|im_start|>assi

106B

Readme

Welcome To DuckLLM 1.0

Welcome To DuckLLM 1.0, The New Age Of AI.

DuckLLM Is an Efficient, Powerful Multi Model Featuring Both Text & Vision. For More Info Please Refer To DuckLLM’s Homepage

DuckLLM 1.0 Is Listed Under DuckLLM PROPRIETARY LICENSE, You Can Use DuckLLM For Personal Usage But For Commerical Usage You Must Purchase a Commerical License From DuckLLM’s Homepage

Clarification

Yes, This Is Basically a Fine Tune I’m Not Hiding This, I Do Not Own Hardware Capable Of Training From Scratch as Of Now But i Hope That In The Future i Would. (Based On Qwen2.5)

If You’re Interested In Benchmarks You Can View Them Here (This Tests Have Been Conducted With Ollama Benchmark And an Nvidia RTX A4500)

# Welcome To DuckLLM 1.0
Welcome To **DuckLLM 1.0**, The New Age Of AI.

DuckLLM Is an **Efficient, Powerful Multi Model** Featuring Both **Text & Vision.**
For More Info Please Refer To **[DuckLLM's Homepage](https://eithanasulin.github.io/DuckLLM/)**

**DuckLLM 1.0** Is Listed Under **[DuckLLM PROPRIETARY LICENSE](https://github.com/EithanAsulin/DuckLLM/blob/index/DuckLLM.license)**, You Can Use DuckLLM For **Personal Usage** But For **Commerical Usage** You Must Purchase a **Commerical License** From **[DuckLLM's Homepage](https://eithanasulin.github.io/DuckLLM/)**

# Clarification
**Yes, This Is Basically a Fine Tune** I'm Not Hiding This, I Do Not Own Hardware Capable Of Training From Scratch as Of Now But i Hope That In The Future i Would.
**(Based On Qwen2.5)**

**If You're Interested In Benchmarks You Can View Them Here**
![newplot(2).png](/assets/DuckLLM/DuckLLM-1.0/fcf5d1aa-321a-48b5-9864-ff52762ab83e)
![newplot(1).png](/assets/DuckLLM/DuckLLM-1.0/01c0b542-a7b0-47ad-a0bc-6fb9b0a75dec)
![newplot.png](/assets/DuckLLM/DuckLLM-1.0/3b967834-4425-495b-b61a-b5ccd7c340ee)
**(This Tests Have Been Conducted With [Ollama Benchmark](https://github.com/CordatusAI/ollama-benchmark) And an [Nvidia RTX A4500](www.nvidia.com/en-eu/products/workstations/rtx-a4500/))**

Paste, drop or click to upload images (.png, .jpeg, .jpg, .svg, .gif)