Instructions to use webAI-Official/TwIL-LM3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use webAI-Official/TwIL-LM3 with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="webAI-Official/TwIL-LM3")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("webAI-Official/TwIL-LM3")
model = AutoModelForCausalLM.from_pretrained("webAI-Official/TwIL-LM3", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use webAI-Official/TwIL-LM3 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 webAI-Official/TwIL-LM3:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf webAI-Official/TwIL-LM3:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf webAI-Official/TwIL-LM3:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf webAI-Official/TwIL-LM3:Q4_K_M

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 webAI-Official/TwIL-LM3:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf webAI-Official/TwIL-LM3:Q4_K_M

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 webAI-Official/TwIL-LM3:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf webAI-Official/TwIL-LM3:Q4_K_M

Use Docker

docker model run hf.co/webAI-Official/TwIL-LM3:Q4_K_M

LM Studio
Jan

vLLM

How to use webAI-Official/TwIL-LM3 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "webAI-Official/TwIL-LM3"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "webAI-Official/TwIL-LM3",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/webAI-Official/TwIL-LM3:Q4_K_M

SGLang

How to use webAI-Official/TwIL-LM3 with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "webAI-Official/TwIL-LM3" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "webAI-Official/TwIL-LM3",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "webAI-Official/TwIL-LM3" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "webAI-Official/TwIL-LM3",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use webAI-Official/TwIL-LM3 with Ollama:
```
ollama run hf.co/webAI-Official/TwIL-LM3:Q4_K_M
```

Unsloth Studio

How to use webAI-Official/TwIL-LM3 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 webAI-Official/TwIL-LM3 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 webAI-Official/TwIL-LM3 to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for webAI-Official/TwIL-LM3 to start chatting

How to use webAI-Official/TwIL-LM3 with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf webAI-Official/TwIL-LM3:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "webAI-Official/TwIL-LM3:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use webAI-Official/TwIL-LM3 with Docker Model Runner:
```
docker model run hf.co/webAI-Official/TwIL-LM3:Q4_K_M
```

Lemonade

How to use webAI-Official/TwIL-LM3 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull webAI-Official/TwIL-LM3:Q4_K_M

Run and chat with the model

lemonade run user.TwIL-LM3-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use webAI-Official/TwIL-LM3 with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf webAI-Official/TwIL-LM3: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 webAI-Official/TwIL-LM3:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use webAI-Official/TwIL-LM3 with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf webAI-Official/TwIL-LM3: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 "webAI-Official/TwIL-LM3: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"

anurag051194 commited on 13 days ago

Commit

43e7402

verified ·

1 Parent(s): f399275

Update TwIL-LM3: weights, tokenizer and model card

Browse files

Files changed (1) hide show

README.md +33 -27

README.md CHANGED Viewed

@@ -93,27 +93,27 @@ length`, so it measures completed answers rather than raw decode rate.
 #### Track A — in-domain formal logic
-| lane / metric | TwIL-LM3 | SmolLM3-3B base | Llama-3.2-3B | LFM2-2.6B | LFM2.5-8B-A1B | Qwen3-8B |
-|---|---:|---:|---:|---:|---:|---:|
-| lean_formalize token_f1 | **0.5869** | 0.4347 | 0.3690 | 0.1321 | 0.4655 | 0.4022 |
-| rule_induction derivation | 0.3192 | 0.1029 | 0.0825 | 0.0615 | 0.1936 | **0.3680** |
-| entailment_label accuracy | 0.5750 | 0.3750 | 0.3300 | 0.4700 | 0.5400 | **0.5800** |
-| mcq_answer accuracy | **0.1100** | 0.0000 | 0.0000 | 0.0150 | 0.0750 | 0.0000 |
-| semantic_parse token_f1 | **0.4416** | 0.4149 | 0.3102 | 0.3665 | 0.3778 | 0.4257 |
-| lean_critic accuracy | 0.6600 | 0.6500 | 0.5300 | 0.5900 | 0.5500 | **0.7950** |
-| lean_formalize exact_match | 0.0050 | 0.0050 | 0.0000 | 0.0000 | 0.0000 | 0.0050 |
-| fol_translation exact_match | 0.0000 | 0.0050 | 0.0000 | 0.0000 | 0.0000 | 0.0000 |
-| semantic_parse exact_match | 0.0000 | 0.0050 | 0.0000 | 0.0000 | 0.0000 | 0.0000 |
-| procedural accuracy | 0.0300 | 0.0050 | 0.0000 | 0.0300 | 0.0350 | **0.0850** |
-| procedural loose_match | 0.1100 | 0.1050 | 0.1050 | 0.1150 | 0.1400 | **0.1800** |
-| mcq_answer loose_match | 0.4450 | 0.5000 | 0.4150 | 0.5000 | 0.4550 | **0.7450** |
-| lm_corpus perplexity ↓ | 2.8972 | 3.1818 | 2.8478 | 4.3815 | 4.9472 | **2.5440** |
-| math_corpus perplexity ↓ | **3.8229** | 4.0685 | 4.7531 | 6.7472 | 8.3323 | 4.0083 |
-| **macro gate** | 0.4218 | 0.3466 † | 0.2925 | 0.3473 | 0.3757 | **0.5336** |
-| **strict-7** | 0.1971 | 0.1493 | 0.1229 | 0.1579 | 0.1714 | **0.2093** |
-| tok/s | 15880 | 15564 | 16160 | 25000 | 22000 | not measured |
-| mean gen length | **564** | 999 | 696 | 2296 | 1830 | 2094 |
-| **ans/s** | **28.1** | 15.6 | 23.2 | 10.9 | 12.0 | not measured |
 † The base column here comes from the external-comparison run rather than the paired run used
 for the Δ table above, hence 0.3466 against 0.3356 — run-to-run variation of the same
@@ -123,12 +123,18 @@ checkpoint. The paired run is the correct basis for the improvement claim.
 `entailment_label`, `mcq_answer`, `semantic_parse` and `lean_formalize` exact match,
 `lean_critic` and `procedural` accuracy), with no loose-match credit anywhere.
-Qwen3-8B takes the macro gate at roughly 2.7x the parameter count, driven by the classification
-lanes — `lean_critic` 0.7950 and loose MCQ 0.7450. TwIL-LM3 holds the two lanes this pipeline
-targets most directly, `lean_formalize` token-F1 (0.5869 against 0.4022) and strict MCQ accuracy
-(0.1100, the only non-trivial value in that row), and it is the most efficient arm in the table
-by a wide margin: 28.1 answers/sec, from generations averaging 564 tokens where every other arm
-except Llama runs past 690.
 #### Track B — held-out benchmarks

 #### Track A — in-domain formal logic
+| lane / metric | TwIL-LM3 | SmolLM3-3B base | Llama-3.2-3B | LFM2-2.6B | LFM2.5-8B-A1B |
+|---|---:|---:|---:|---:|---:|
+| lean_formalize token_f1 | **0.5869** | 0.4347 | 0.3690 | 0.1321 | 0.4655 |
+| rule_induction derivation | **0.3192** | 0.1029 | 0.0825 | 0.0615 | 0.1936 |
+| entailment_label accuracy | **0.5750** | 0.3750 | 0.3300 | 0.4700 | 0.5400 |
+| mcq_answer accuracy | **0.1100** | 0.0000 | 0.0000 | 0.0150 | 0.0750 |
+| semantic_parse token_f1 | **0.4416** | 0.4149 | 0.3102 | 0.3665 | 0.3778 |
+| lean_critic accuracy | **0.6600** | 0.6500 | 0.5300 | 0.5900 | 0.5500 |
+| lean_formalize exact_match | 0.0050 | 0.0050 | 0.0000 | 0.0000 | 0.0000 |
+| fol_translation exact_match | 0.0000 | 0.0050 | 0.0000 | 0.0000 | 0.0000 |
+| semantic_parse exact_match | 0.0000 | 0.0050 | 0.0000 | 0.0000 | 0.0000 |
+| procedural accuracy | 0.0300 | 0.0050 | 0.0000 | 0.0300 | **0.0350** |
+| procedural loose_match | 0.1100 | 0.1050 | 0.1050 | 0.1150 | **0.1400** |
+| mcq_answer loose_match | 0.4450 | 0.5000 | 0.4150 | 0.5000 | 0.4550 |
+| lm_corpus perplexity ↓ | 2.8972 | 3.1818 | **2.8478** | 4.3815 | 4.9472 |
+| math_corpus perplexity ↓ | **3.8229** | 4.0685 | 4.7531 | 6.7472 | 8.3323 |
+| **macro gate** | **0.4218** | 0.3466 † | 0.2925 | 0.3473 | 0.3757 |
+| **strict-7** | **0.1971** | 0.1493 | 0.1229 | 0.1579 | 0.1714 |
+| tok/s | 15880 | 15564 | 16160 | 25000 | 22000 |
+| mean gen length | **564** | 999 | 696 | 2296 | 1830 |
+| **ans/s** | **28.1** | 15.6 | 23.2 | 10.9 | 12.0 |
 † The base column here comes from the external-comparison run rather than the paired run used
 for the Δ table above, hence 0.3466 against 0.3356 — run-to-run variation of the same
 `entailment_label`, `mcq_answer`, `semantic_parse` and `lean_formalize` exact match,
 `lean_critic` and `procedural` accuracy), with no loose-match credit anywhere.
+TwIL-LM3 leads both headline metrics here and wins every lane the pipeline targets directly:
+`lean_formalize` token-F1 0.5869 against 0.4655 for the nearest arm, `rule_induction` 0.3192
+against 0.1936, and strict MCQ accuracy 0.1100, the only non-trivial value in that row. Its
+closest competitor on the macro gate is LFM2.5-8B-A1B at 0.3757, roughly 2.8x its size. What it
+gives up: `procedural` under both scorings, loose MCQ where the base and LFM2-2.6B reach 0.5000
+against its 0.4450, `lm_corpus` perplexity where Llama-3.2-3B is marginally lower, and the three
+exact-match rows that sit at or near zero for every arm.
+It is also the most efficient arm in the table by a wide margin — 28.1 answers/sec, from
+generations averaging 564 tokens where every other arm except Llama runs past 690. The Liquid
+models decode faster in raw tokens per second, 25000 and 22000 against 15880, but their length
+more than cancels it.
 #### Track B — held-out benchmarks