Instructions to use HelloSun/lingtiny30vq3 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 HelloSun/lingtiny30vq3 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 HelloSun/lingtiny30vq3 # Run inference directly in the terminal: llama cli -hf HelloSun/lingtiny30vq3
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf HelloSun/lingtiny30vq3 # Run inference directly in the terminal: llama cli -hf HelloSun/lingtiny30vq3
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 HelloSun/lingtiny30vq3 # Run inference directly in the terminal: ./build/bin/llama cli -hf HelloSun/lingtiny30vq3
Use Docker
docker model run hf.co/HelloSun/lingtiny30vq3
- Llama new
- LM Studio
- Jan
- Ollama
How to use HelloSun/lingtiny30vq3 with Ollama:
ollama run hf.co/HelloSun/lingtiny30vq3
- Unsloth Desktop
- Pi
How to use HelloSun/lingtiny30vq3 with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf HelloSun/lingtiny30vq3
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:9931/v1", "api": "openai-completions", "apiKey": "none", "models": [ { "id": "HelloSun/lingtiny30vq3" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Docker Model Runner
How to use HelloSun/lingtiny30vq3 with Docker Model Runner:
docker model run hf.co/HelloSun/lingtiny30vq3
- Lemonade
How to use HelloSun/lingtiny30vq3 with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull HelloSun/lingtiny30vq3
Run and chat with the model
lemonade run user.lingtiny30vq3-{{QUANT_TAG}}List all available models
lemonade list
- Hermes Agent
How to use HelloSun/lingtiny30vq3 with Hermes Agent:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf HelloSun/lingtiny30vq3
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://127.0.0.1:9931/v1 hermes config set model.default HelloSun/lingtiny30vq3
Run Hermes
hermes
- Atomic Chat
- OpenClaw
How to use HelloSun/lingtiny30vq3 with OpenClaw:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf HelloSun/lingtiny30vq3
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://127.0.0.1:9931/v1 \ --custom-model-id "HelloSun/lingtiny30vq3" \ --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"
Download scripts/run_experiments.sh from HelloSun/lingtiny30vq3: direct link, hf CLI and curl.
- Browser
- Download file 2.26 kB
-
https://huggingface.co/HelloSun/lingtiny30vq3/resolve/main/scripts/run_experiments.sh
- Command line
-
hf download hf://HelloSun/lingtiny30vq3/scripts/run_experiments.sh
-
curl -L -o run_experiments.sh https://huggingface.co/HelloSun/lingtiny30vq3/resolve/main/scripts/run_experiments.sh
2.26 kB
| # One-shot experiment suite for Ling-3.0-tiny VQ3 vs standard quantizations | |
| # Usage: run_experiments.sh (from work root) | |
| set -u | |
| cd "$(dirname "$0")/../.." | |
| BIN=./llama.cpp/build/bin | |
| CORP=corpora/wikitext-2-raw/wiki.test.raw | |
| R=ling-vq3/results | |
| mkdir -p "$R" | |
| T=64 | |
| CHUNKS_PPL=256 | |
| CHUNKS_KLD=128 | |
| declare -A MODELS=( | |
| [bf16]=models/Ling-3.0-tiny-bf16.gguf | |
| [q8_0]=models/Ling-3.0-tiny-Q8_0.gguf | |
| [q4_k_m]=models/Ling-3.0-tiny-Q4_K_M.gguf | |
| [base_q8dq6]=models/Ling-3.0-tiny-base-Q8dQ6.gguf | |
| [vq3]=models/Ling-3.0-tiny-VQ3.gguf | |
| ) | |
| echo "=== [1/5] PPL (wikitext-2 test, $CHUNKS_PPL chunks) ===" | |
| for k in bf16 q8_0 q4_k_m base_q8dq6 vq3; do | |
| m=${MODELS[$k]} | |
| echo "--- PPL $k ---" | |
| $BIN/llama-perplexity -m "$m" -f "$CORP" -c 512 --chunks $CHUNKS_PPL -t $T -ngl 0 \ | |
| > "$R/ppl_$k.log" 2>&1 | |
| grep -E "Final estimate|error" "$R/ppl_$k.log" | tail -2 | |
| done | |
| echo "=== [2/5] Baseline logits from BF16 (KLD reference, $CHUNKS_KLD chunks) ===" | |
| $BIN/llama-perplexity -m models/Ling-3.0-tiny-bf16.gguf -f "$CORP" -c 512 --chunks $CHUNKS_KLD \ | |
| -t $T -ngl 0 --save-all-logits "$R/logits_bf16.bin" > "$R/logits_bf16.log" 2>&1 | |
| grep -E "Final estimate|error" "$R/logits_bf16.log" | tail -2 | |
| echo "=== [3/5] KLD vs BF16 ===" | |
| for k in q8_0 q4_k_m base_q8dq6 vq3; do | |
| m=${MODELS[$k]} | |
| echo "--- KLD $k ---" | |
| $BIN/llama-perplexity -m "$m" -f "$CORP" -c 512 --chunks $CHUNKS_KLD -t $T -ngl 0 \ | |
| --kl-divergence --kl-divergence-base "$R/logits_bf16.bin" > "$R/kld_$k.log" 2>&1 | |
| grep -E "Final estimate|error" "$R/kld_$k.log" | tail -2 | |
| done | |
| echo "=== [4/5] llama-bench pp512/tg128 ===" | |
| $BIN/llama-bench -t $T -p 512 -n 128 -r 2 -mlo 0 \ | |
| -m models/Ling-3.0-tiny-bf16.gguf \ | |
| -m models/Ling-3.0-tiny-Q8_0.gguf \ | |
| -m models/Ling-3.0-tiny-Q4_K_M.gguf \ | |
| -m models/Ling-3.0-tiny-base-Q8dQ6.gguf \ | |
| -m models/Ling-3.0-tiny-VQ3.gguf > "$R/bench.tsv" 2> "$R/bench.err" | |
| cat "$R/bench.tsv" | |
| echo "=== [5/5] Peak RSS via short generation ===" | |
| for k in bf16 q8_0 q4_k_m base_q8dq6 vq3; do | |
| m=${MODELS[$k]} | |
| /usr/bin/time -v $BIN/llama-cli -m "$m" -p "Hello" -n 8 -t $T --no-warmup -ngl 0 --temp 0 \ | |
| > /dev/null 2> "$R/rss_$k.txt" | |
| rss=$(grep "Maximum resident" "$R/rss_$k.txt" | awk '{print $6}') | |
| echo "peak RSS $k: $rss KB" | |
| done | |
| echo "=== ALL DONE ===" | |