返回资讯中心
外部精选
软件工程
#开发者实时流

nioncorp 发布 Nil-3B GGUF 开源模型

来源标题:Nil-3B Open Source Sovereign AI

nioncorp 在 Hugging Face 上发布了 nil-3b-gguf 模型,采用 GGUF 格式、基于 llama-cpp,支持对话式文本生成。页面提供了在 llama.cpp、Google Colab、Kaggle 及本地应用中调用该模型的使用说明。

Hacker News 最新ayakmarial2026/11/13 · 4 天前22 分钟阅读

以下正文同步自 Hacker News 最新,版权归原站所有,已转换为易读排版。

Like 0

Text Generation

GGUF

llama-cpp

conversational

Model card Files Files and versions xet

Community

Deploy

Copy to bucket

Use this model Instructions to use nioncorp/nil-3b-gguf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks

Google Colab

Kaggle

Local Apps Settings

llama.cpp How to use nioncorp/nil-3b-gguf with llama.cpp:

curl -LsSf https://llama.app/install.sh | sh

Start a local OpenAI-compatible server with a web UI:

llama serve -hf nioncorp/nil-3b-gguf:Q4_K_M

Run inference directly in the terminal:

llama cli -hf nioncorp/nil-3b-gguf:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp

Start a local OpenAI-compatible server with a web UI:

llama serve -hf nioncorp/nil-3b-gguf:Q4_K_M

Run inference directly in the terminal:

llama cli -hf nioncorp/nil-3b-gguf:Q4_K_M

Build from source code

git clone https://github.com/ggml-org/llama.cpp.git cd llama.cpp cmake -B build cmake --build build -j --target llama-app

Start a local OpenAI-compatible server with a web UI:

./build/bin/llama serve -hf nioncorp/nil-3b-gguf:Q4_K_M

Run inference directly in the terminal:

./build/bin/llama cli -hf nioncorp/nil-3b-gguf:Q4_K_M

Use Docker

docker model run hf.co/nioncorp/nil-3b-gguf:Q4_K_M

Llama new

LM Studio

Jan

vLLM How to use nioncorp/nil-3b-gguf with vLLM:

Install vLLM from pip:

pip install vllm

Start the vLLM server:

vllm serve "nioncorp/nil-3b-gguf"

Call the server using curl (OpenAI-compatible API):

curl -X POST "http://localhost:8000/v1/chat/completions"
-H "Content-Type: application/json"
--data '{ "model": "nioncorp/nil-3b-gguf", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'

Use Docker

docker model run hf.co/nioncorp/nil-3b-gguf:Q4_K_M

Ollama How to use nioncorp/nil-3b-gguf with Ollama:

ollama run hf.co/nioncorp/nil-3b-gguf:Q4_K_M

Unsloth Desktop

Pi How to use nioncorp/nil-3b-gguf with Pi:

Install llama.cpp:

brew install llama.cpp

Start a local OpenAI-compatible server:

llama serve -hf nioncorp/nil-3b-gguf:Q4_K_M

Configure the model in Pi

Install Pi:

npm install -g @earendil-works/pi-coding-agent

Add to ~/.pi/agent/models.json:

{ "providers": { "llama-cpp": { "baseUrl": "http://localhost:8080/v1", "api": "openai-completions", "apiKey": "none", "models": [ { "id": "nioncorp/nil-3b-gguf:Q4_K_M" } ] } } }

Run Pi

Start Pi in your project directory:

pi

Docker Model Runner How to use nioncorp/nil-3b-gguf with Docker Model Runner:

docker model run hf.co/nioncorp/nil-3b-gguf:Q4_K_M

Lemonade How to use nioncorp/nil-3b-gguf with Lemonade:

Download Lemonade from https://lemonade-server.ai/

lemonade pull nioncorp/nil-3b-gguf:Q4_K_M

Run and chat with the model

lemonade run user.nil-3b-gguf-Q4_K_M

List all available models

lemonade list

Hermes Agent How to use nioncorp/nil-3b-gguf with Hermes Agent:

Install llama.cpp:

brew install llama.cpp

Start a local OpenAI-compatible server:

llama serve -hf nioncorp/nil-3b-gguf:Q4_K_M

Configure Hermes

Install Hermes:

curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash hermes setup

Point Hermes at the local server:

hermes config set model.provider custom hermes config set model.base_url http://127.0.0.1:8080/v1 hermes config set model.default nioncorp/nil-3b-gguf:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw How to use nioncorp/nil-3b-gguf with OpenClaw:

Install llama.cpp:

brew install llama.cpp

Start a local OpenAI-compatible server:

llama serve -hf nioncorp/nil-3b-gguf:Q4_K_M

Configure OpenClaw

Install OpenClaw:

npm install -g openclaw@latest

Register the local server and set it as the default model:

openclaw onboard --non-interactive --mode local
--auth-choice custom-api-key
--custom-base-url http://127.0.0.1:8080/v1
--custom-model-id "nioncorp/nil-3b-gguf:Q4_K_M"
--custom-provider-id llama-cpp
--custom-compatibility openai
--custom-text-input
--accept-risk
--skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

NIL-3B GGUF Local inference

Uploading this model

Licensing and model details

NIL-3B GGUF

This repository contains the nil-3b-q4_k_m.gguf file for running the NIL-3B project locally with a GGUF-compatible inference runtime.

Local inference

Install the project's dependencies, then run:

python -m pip install -r requirements.txt python -m src.chat

The chat script expects nil-3b-q4_k_m.gguf in the project root.

Uploading this model

If you do not already have a .env, copy .env.example to .env. Set HF_TOKEN to a Hugging Face token with write access and HF_REPO_ID to the intended owner/repository. The .env file is ignored by Git and must not be committed or shared.

Install the uploader dependencies if they are not already installed:

python -m pip install huggingface_hub python-dotenv

Run the uploader from any working directory:

python upload_hf.py

It creates the model repository if needed and uploads the GGUF file. Review the target repository and its visibility on Hugging Face before running the upload.

Licensing and model details

The root LICENSE covers the project source code; it does not by itself confirm the license or redistribution rights for the model weights or training data. Confirm those rights and document the model's base model, training data, and supported capabilities before making this repository public.

system<|end_header_id|>\n\n" }}\n{%- if tools is not none %}\n {{- "Environment: ipython\n" }}\n{%- endif %}\n{{- "Cutting Knowledge Date: December 2023\n" }}\n{{- "Today Date: " + date_string + "\n\n" }}\n{%- if tools is not none and not tools_in_user_message %}\n {{- "You have access to the following functions. To call a function, please respond with JSON for a function call." }}\n {{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }}\n {{- "Do not use variables.\n\n" }}\n {%- for t in tools %}\n {{- t | tojson(indent=4) }}\n {{- "\n\n" }}\n {%- endfor %}\n{%- endif %}\n{{- system_message }}\n{{- "<|eot_id|>" }}\n\n{#- Custom tools are passed in a user message with some extra guidance #}\n{%- if tools_in_user_message and not tools is none %}\n {#- Extract the first user message so we can plug it in here #}\n {%- if messages | length != 0 %}\n {%- set first_user_message = messages[0]['content']|trim %}\n {%- set messages = messages[1:] %}\n {%- else %}\n {{- raise_exception("Cannot put tools in the first user message when there's no first user message!") }}\n{%- endif %}\n {{- '<|start_header_id|>user<|end_header_id|>\n\n' -}}\n {{- "Given the following functions, please respond with a JSON for a function call " }}\n {{- "with its proper arguments that best answers the given prompt.\n\n" }}\n {{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }}\n {{- "Do not use variables.\n\n" }}\n {%- for t in tools %}\n {{- t | tojson(indent=4) }}\n {{- "\n\n" }}\n {%- endfor %}\n {{- first_user_message + "<|eot_id|>"}}\n{%- endif %}\n\n{%- for message in messages %}\n {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}\n {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' }}\n {%- elif 'tool_calls' in message %}\n {%- if not message.tool_calls|length == 1 %}\n {{- raise_exception("This model only supports single tool-calls at once!") }}\n {%- endif %}\n {%- set tool_call = message.tool_calls[0].function %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}}\n {{- '{"name": "' + tool_call.name + '", ' }}\n {{- '"parameters": ' }}\n {{- tool_call.arguments | tojson }}\n {{- "}" }}\n {{- "<|eot_id|>" }}\n {%- elif message.role == "tool" or message.role == "ipython" %}\n {{- "<|start_header_id|>ipython<|end_header_id|>\n\n" }}\n {%- if message.content is mapping or message.content is iterable %}\n {{- message.content | tojson }}\n {%- else %}\n {{- message.content }}\n {%- endif %}\n {{- "<|eot_id|>" }}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' }}\n{%- endif %}\n","bos_token":"<|begin_of_text|>","eos_token":"<|eot_id|>","totalFileSize":2019377504},"ggufFilePaths":["nil-3b-q4_k_m.gguf"],"hasBlockedOids":false,"region":"us","isQuantized":false},"inferenceContextData":{"billableEntities":[],"entityName2Providers":{},"openRouterRouting":false,"openRouterProviders":[]},"canWrite":false}">

GGUF

Model size

3B params

Architecture

llama

Chat template

Hardware compatibility

Log In to add your hardware

4-bit

正文由 探How 从来源站点 RSS 同步,内容未经改写;遇到排版缺失或需要图片、视频时请以原文为准。

打开原文
去社区讨论 →