Instructions to use vid-GENR/NanoWeb-7B-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use vid-GENR/NanoWeb-7B-Instruct with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf vid-GENR/NanoWeb-7B-Instruct:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf vid-GENR/NanoWeb-7B-Instruct:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf vid-GENR/NanoWeb-7B-Instruct:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf vid-GENR/NanoWeb-7B-Instruct: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 vid-GENR/NanoWeb-7B-Instruct:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama cli -hf vid-GENR/NanoWeb-7B-Instruct:Q4_K_M

Use Docker

docker model run hf.co/vid-GENR/NanoWeb-7B-Instruct:Q4_K_M

Llama new
LM Studio
Jan
Ollama
How to use vid-GENR/NanoWeb-7B-Instruct with Ollama:
```
ollama run hf.co/vid-GENR/NanoWeb-7B-Instruct:Q4_K_M
```
Unsloth Desktop

How to use vid-GENR/NanoWeb-7B-Instruct with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf vid-GENR/NanoWeb-7B-Instruct: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": "vid-GENR/NanoWeb-7B-Instruct:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use vid-GENR/NanoWeb-7B-Instruct with Docker Model Runner:
```
docker model run hf.co/vid-GENR/NanoWeb-7B-Instruct:Q4_K_M
```

Lemonade

How to use vid-GENR/NanoWeb-7B-Instruct with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull vid-GENR/NanoWeb-7B-Instruct:Q4_K_M

Run and chat with the model

lemonade run user.NanoWeb-7B-Instruct-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use vid-GENR/NanoWeb-7B-Instruct with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf vid-GENR/NanoWeb-7B-Instruct: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 vid-GENR/NanoWeb-7B-Instruct:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use vid-GENR/NanoWeb-7B-Instruct with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf vid-GENR/NanoWeb-7B-Instruct: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 "vid-GENR/NanoWeb-7B-Instruct: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"

NanoWeb-7B-Instruct / README.md

vid-GENR

feat: upload Phase 2 abliterated 7B multi-domain browser agent GGUFs and benchmarks

742d3a9 verified 8 days ago

preview code

Raw History Blame Contribute Delete

2.51 kB

---
license: apache-2.0
base_model: Qwen/Qwen2.5-7B-Instruct
tags:
  - web-agent
  - browser-agent
  - abliterated
  - function-calling
  - llama.cpp
  - gguf
---
# NanoWeb-7B-Instruct (Phase 2 - Multi-Domain Distillation)

NanoWeb-7B-Instruct v2 is an autonomous, sovereign, refusal-abliterated browser-agent model fine-tuned on **8,280 multi-domain web flight-recorder trajectories** (~31,000 tool calls) from base `Qwen/Qwen2.5-7B-Instruct`.

## Interaction Domains Covered
1. **E-Commerce & Price Intelligence**: Product navigation, price comparison, specification extraction, stock alerts.
2. **Academic & Technical Research**: ArXiv paper synthesis, GitHub repository inspection, documentation navigation.
3. **Financial & Market Intelligence**: Ticker analysis, earnings report lookups, crypto metrics, macroeconomic indicators.
4. **News & Geopolitical Tracking**: Breaking news cross-referencing, primary source verification, fact-checking.
5. **Travel, Hospitality & Flight Schedules**: Routing queries, hotel amenity comparisons, booking workflow traversal.
6. **Complex Multi-Hop Web Synthesis**: Multi-source reconciliation, adversarial error recovery, dynamic DOM element interaction.

## Tool Schemas
Pre-tuned with native Hermes function calling on:
- `fetch_page(url)`: Stealth headless retrieval with Jev-pruned numbered interactive DOM elements.
- `read_page(url, chunk_index)`: Sequential chunked reading for dense textual content.
- `find_in_page(url, pattern)`: Regex and keyword search across DOM elements.
- `browser_action(action, element_id, text, key, value)`: Interactive element execution (`click`, `type`, `select`, `press_enter`).
- `web_search(query)`: Multi-provider search querying.
- `finish_research(answer, sources)`: Final evidence synthesis.

## Mechanistic Refusal Abliteration
Refusal representations are mathematically annihilated via in-place orthogonal subspace projection ($W \leftarrow (I - \hat{r}\hat{r}^T)W$) across layers 14, 15, 16, 17, 18, 19, and 20 on both MLP down-projections and self-attention output projections ($P_\perp W_{\text{down}}$ & $P_\perp W_o$), eliminating false refusals on sovereign research, web scraping, and DOM automation.

## Quantized GGUF Deliverables (SHA-256 Verified)
- `nanoweb-7b-v2-instruct-Q4_K_M.gguf`: ~4.5 GB (Optimal for consumer GPUs / Ollama / llama.cpp)
- `nanoweb-7b-v2-instruct-Q8_0.gguf`: ~7.5 GB (High-precision near-FP16 fidelity)
- Accompanying `.sha256` manifest files for cryptographic integrity verification.

	---
	license: apache-2.0
	base_model: Qwen/Qwen2.5-7B-Instruct
	tags:
	- web-agent
	- browser-agent
	- abliterated
	- function-calling
	- llama.cpp
	- gguf
	---

	# NanoWeb-7B-Instruct (Phase 2 - Multi-Domain Distillation)

	NanoWeb-7B-Instruct v2 is an autonomous, sovereign, refusal-abliterated browser-agent model fine-tuned on 8,280 multi-domain web flight-recorder trajectories (~31,000 tool calls) from base `Qwen/Qwen2.5-7B-Instruct`.

	## Interaction Domains Covered
	1. E-Commerce & Price Intelligence: Product navigation, price comparison, specification extraction, stock alerts.
	2. Academic & Technical Research: ArXiv paper synthesis, GitHub repository inspection, documentation navigation.
	3. Financial & Market Intelligence: Ticker analysis, earnings report lookups, crypto metrics, macroeconomic indicators.
	4. News & Geopolitical Tracking: Breaking news cross-referencing, primary source verification, fact-checking.
	5. Travel, Hospitality & Flight Schedules: Routing queries, hotel amenity comparisons, booking workflow traversal.
	6. Complex Multi-Hop Web Synthesis: Multi-source reconciliation, adversarial error recovery, dynamic DOM element interaction.

	## Tool Schemas
	Pre-tuned with native Hermes function calling on:
	- `fetch_page(url)`: Stealth headless retrieval with Jev-pruned numbered interactive DOM elements.
	- `read_page(url, chunk_index)`: Sequential chunked reading for dense textual content.
	- `find_in_page(url, pattern)`: Regex and keyword search across DOM elements.
	- `browser_action(action, element_id, text, key, value)`: Interactive element execution (`click`, `type`, `select`, `press_enter`).
	- `web_search(query)`: Multi-provider search querying.
	- `finish_research(answer, sources)`: Final evidence synthesis.

	## Mechanistic Refusal Abliteration
	Refusal representations are mathematically annihilated via in-place orthogonal subspace projection ($W \leftarrow (I - \hat{r}\hat{r}^T)W$) across layers 14, 15, 16, 17, 18, 19, and 20 on both MLP down-projections and self-attention output projections ($P_\perp W_{\text{down}}$ & $P_\perp W_o$), eliminating false refusals on sovereign research, web scraping, and DOM automation.

	## Quantized GGUF Deliverables (SHA-256 Verified)
	- `nanoweb-7b-v2-instruct-Q4_K_M.gguf`: ~4.5 GB (Optimal for consumer GPUs / Ollama / llama.cpp)
	- `nanoweb-7b-v2-instruct-Q8_0.gguf`: ~7.5 GB (High-precision near-FP16 fidelity)
	- Accompanying `.sha256` manifest files for cryptographic integrity verification.