Instructions to use PollardWeights/Ling-3.0-tiny-Pollard with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use PollardWeights/Ling-3.0-tiny-Pollard 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 PollardWeights/Ling-3.0-tiny-Pollard:IQ3_S
# Run inference directly in the terminal:
llama cli -hf PollardWeights/Ling-3.0-tiny-Pollard:IQ3_S

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf PollardWeights/Ling-3.0-tiny-Pollard:IQ3_S
# Run inference directly in the terminal:
llama cli -hf PollardWeights/Ling-3.0-tiny-Pollard:IQ3_S

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf PollardWeights/Ling-3.0-tiny-Pollard:IQ3_S
# Run inference directly in the terminal:
./llama-cli -hf PollardWeights/Ling-3.0-tiny-Pollard:IQ3_S

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf PollardWeights/Ling-3.0-tiny-Pollard:IQ3_S
# Run inference directly in the terminal:
./build/bin/llama-cli -hf PollardWeights/Ling-3.0-tiny-Pollard:IQ3_S

Use Docker

docker model run hf.co/PollardWeights/Ling-3.0-tiny-Pollard:IQ3_S

LM Studio
Jan

vLLM

How to use PollardWeights/Ling-3.0-tiny-Pollard with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "PollardWeights/Ling-3.0-tiny-Pollard"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "PollardWeights/Ling-3.0-tiny-Pollard",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/PollardWeights/Ling-3.0-tiny-Pollard:IQ3_S

Ollama
How to use PollardWeights/Ling-3.0-tiny-Pollard with Ollama:
```
ollama run hf.co/PollardWeights/Ling-3.0-tiny-Pollard:IQ3_S
```

Unsloth Studio

How to use PollardWeights/Ling-3.0-tiny-Pollard with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for PollardWeights/Ling-3.0-tiny-Pollard to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for PollardWeights/Ling-3.0-tiny-Pollard to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for PollardWeights/Ling-3.0-tiny-Pollard to start chatting

How to use PollardWeights/Ling-3.0-tiny-Pollard with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf PollardWeights/Ling-3.0-tiny-Pollard:IQ3_S

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": "PollardWeights/Ling-3.0-tiny-Pollard:IQ3_S"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use PollardWeights/Ling-3.0-tiny-Pollard with Docker Model Runner:
```
docker model run hf.co/PollardWeights/Ling-3.0-tiny-Pollard:IQ3_S
```

Lemonade

How to use PollardWeights/Ling-3.0-tiny-Pollard with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull PollardWeights/Ling-3.0-tiny-Pollard:IQ3_S

Run and chat with the model

lemonade run user.Ling-3.0-tiny-Pollard-IQ3_S

List all available models

lemonade list

Hermes Agent

How to use PollardWeights/Ling-3.0-tiny-Pollard with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf PollardWeights/Ling-3.0-tiny-Pollard:IQ3_S

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 PollardWeights/Ling-3.0-tiny-Pollard:IQ3_S

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use PollardWeights/Ling-3.0-tiny-Pollard with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf PollardWeights/Ling-3.0-tiny-Pollard:IQ3_S

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 "PollardWeights/Ling-3.0-tiny-Pollard:IQ3_S" \
  --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"

westwaters commited on 2 days ago

Commit

ee10d14

verified ·

1 Parent(s): c29fa75

Upload Ling-3.0-tiny-Pollard.tensor-types.txt with huggingface_hub

Browse files

Files changed (1) hide show

Ling-3.0-tiny-Pollard.tensor-types.txt +96 -0

Ling-3.0-tiny-Pollard.tensor-types.txt ADDED Viewed

	@@ -0,0 +1,96 @@

+blk.0.ffn_up_exps=iq4_xs
+blk.0.ffn_down_exps=iq4_xs
+blk.0.ffn_gate_exps=iq4_xs
+blk\.0\.attn_.*=q6_K
+blk.1.ffn_up_exps=iq4_xs
+blk.1.ffn_down_exps=iq4_xs
+blk.1.ffn_gate_exps=iq4_xs
+blk\.1\.attn_.*=q6_K
+blk.2.ffn_up_exps=iq4_xs
+blk.2.ffn_down_exps=iq4_xs
+blk.2.ffn_gate_exps=iq4_xs
+blk\.2\.attn_.*=q6_K
+blk.3.ffn_up_exps=iq4_xs
+blk.3.ffn_down_exps=iq4_xs
+blk.3.ffn_gate_exps=iq4_xs
+blk\.3\.attn_.*=q6_K
+blk.4.ffn_up_exps=iq4_xs
+blk.4.ffn_down_exps=iq4_xs
+blk.4.ffn_gate_exps=iq4_xs
+blk\.4\.attn_.*=q6_K
+blk.5.ffn_up_exps=iq4_xs
+blk.5.ffn_down_exps=iq4_xs
+blk.5.ffn_gate_exps=iq4_xs
+blk\.5\.attn_.*=q6_K
+blk.6.ffn_up_exps=iq4_xs
+blk.6.ffn_down_exps=iq4_xs
+blk.6.ffn_gate_exps=iq4_xs
+blk\.6\.attn_.*=q6_K
+blk.7.ffn_up_exps=iq3_s
+blk.7.ffn_down_exps=iq3_s
+blk.7.ffn_gate_exps=iq3_s
+blk\.7\.attn_.*=q6_K
+blk.8.ffn_up_exps=iq3_s
+blk.8.ffn_down_exps=iq3_s
+blk.8.ffn_gate_exps=iq3_s
+blk\.8\.attn_.*=q5_K
+blk.9.ffn_up_exps=iq3_s
+blk.9.ffn_down_exps=iq3_s
+blk.9.ffn_gate_exps=iq3_s
+blk\.9\.attn_.*=q5_K
+blk.10.ffn_up_exps=iq3_s
+blk.10.ffn_down_exps=iq3_s
+blk.10.ffn_gate_exps=iq3_s
+blk\.10\.attn_.*=q6_K
+blk.11.ffn_up_exps=iq3_s
+blk.11.ffn_down_exps=iq3_s
+blk.11.ffn_gate_exps=iq3_s
+blk\.11\.attn_.*=q6_K
+blk.12.ffn_up_exps=iq3_s
+blk.12.ffn_down_exps=iq3_s
+blk.12.ffn_gate_exps=iq3_s
+blk\.12\.attn_.*=q5_K
+blk.13.ffn_up_exps=iq3_s
+blk.13.ffn_down_exps=iq3_s
+blk.13.ffn_gate_exps=iq3_s
+blk\.13\.attn_.*=q5_K
+blk.14.ffn_up_exps=iq3_s
+blk.14.ffn_down_exps=iq3_s
+blk.14.ffn_gate_exps=iq3_s
+blk\.14\.attn_.*=q5_K
+blk.15.ffn_up_exps=iq3_s
+blk.15.ffn_down_exps=iq3_s
+blk.15.ffn_gate_exps=iq3_s
+blk\.15\.attn_.*=q5_K
+blk.16.ffn_up_exps=iq3_s
+blk.16.ffn_down_exps=iq3_s
+blk.16.ffn_gate_exps=iq3_s
+blk\.16\.attn_.*=iq4_xs
+blk.17.ffn_up_exps=iq3_s
+blk.17.ffn_down_exps=iq3_s
+blk.17.ffn_gate_exps=iq3_s
+blk\.17\.attn_.*=iq4_xs
+blk.18.ffn_up_exps=iq3_s
+blk.18.ffn_down_exps=iq3_s
+blk.18.ffn_gate_exps=iq3_s
+blk\.18\.attn_.*=iq4_xs
+blk.19.ffn_up_exps=iq3_s
+blk.19.ffn_down_exps=iq3_s
+blk.19.ffn_gate_exps=iq3_s
+blk\.19\.attn_.*=q5_K
+blk.20.ffn_up_exps=iq3_s
+blk.20.ffn_down_exps=iq3_s
+blk.20.ffn_gate_exps=iq3_s
+blk\.20\.attn_.*=iq3_s
+blk.21.ffn_up_exps=iq3_s
+blk.21.ffn_down_exps=iq3_s
+blk.21.ffn_gate_exps=iq3_s
+blk\.21\.attn_.*=iq3_s
+blk.22.ffn_up_exps=iq2_s
+blk.22.ffn_down_exps=iq2_s
+blk.22.ffn_gate_exps=iq2_s
+blk\.22\.attn_.*=iq4_xs
+blk.23.ffn_up_exps=iq3_s
+blk.23.ffn_down_exps=iq3_s
+blk.23.ffn_gate_exps=iq3_s
+blk\.23\.attn_.*=iq4_xs