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

Libraries

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

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("webAI-Official/TwIL-LM")
model = AutoModelForCausalLM.from_pretrained("webAI-Official/TwIL-LM", 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-LM 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-LM:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf webAI-Official/TwIL-LM: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-LM:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf webAI-Official/TwIL-LM: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-LM:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf webAI-Official/TwIL-LM: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-LM:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf webAI-Official/TwIL-LM:Q4_K_M

Use Docker

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

LM Studio
Jan

vLLM

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

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "webAI-Official/TwIL-LM"
# 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-LM",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

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

SGLang

How to use webAI-Official/TwIL-LM 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-LM" \
    --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-LM",
		"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-LM" \
        --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-LM",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use webAI-Official/TwIL-LM with Ollama:
```
ollama run hf.co/webAI-Official/TwIL-LM:Q4_K_M
```
Unsloth Desktop
Docker Model Runner
How to use webAI-Official/TwIL-LM with Docker Model Runner:
```
docker model run hf.co/webAI-Official/TwIL-LM:Q4_K_M
```

Lemonade

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

Pull the model

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

Run and chat with the model

lemonade run user.TwIL-LM-Q4_K_M

List all available models

lemonade list

Atomic Chat

Removed the plot assets

by anurag051194 - opened Jul 29

base: refs/heads/main

←

from: refs/pr/1

Discussion Files changed

-15

Files changed (1) hide show

README.md +1 -15

README.md CHANGED Viewed

@@ -116,7 +116,7 @@ hardware, wall-clock time, and energy consumption are not documented in the
 current release artifacts. These should be added when verified records become
 available.
-![TwiL-LM data creation, training, and evaluation workflow](card_assets/data_workflow_v2.png)
 ## Evaluation
@@ -128,16 +128,11 @@ over the eligible objectives. `mcq_answer` and `procedural` use
 `max(accuracy, loose_match)`. `lean_prove` and perplexity corpora are excluded
 from the macro score.
-![Macro accuracy compared with base models](card_assets/macro_vs_bases.png)
-![Macro accuracy compared across Base and LoRA models](card_assets/macro_vs_bases_and_lora.png)
 The broader comparison includes checkpoints with different parameter counts,
 training procedures, and adaptation methods. It is useful for context but is not
 a controlled architecture or scaling study.
-![TwiL-LM compared with SmolLM2-1.7B by objective](card_assets/objectives_vs_smollm2.png)
 TwiL-LM performs best on entailment labeling (**0.655**) and improves FOL
 translation (**0.235**, compared with approximately zero for the base). Lean
 formalization, Lean proving, and procedural reasoning remain weak.
@@ -147,22 +142,13 @@ formalization, Lean proving, and procedural reasoning remain weak.
 OOD transfer was measured on GSM8K, ARC-Challenge chain-of-thought,
 ARC-Challenge 25-shot log-likelihood (`acc_norm`), and LogicBench BQA.
-![TwiL-LM and SmolLM2-1.7B on OOD benchmarks](card_assets/unseen_benchmarks.png)
 Compared with SmolLM2-1.7B, TwiL-LM improves LogicBench BQA
 (**0.590 vs 0.563**) but is lower on GSM8K (**0.380 vs 0.413**), ARC-C
 chain-of-thought (**0.463 vs 0.587**), and ARC-C 25-shot log-likelihood
 (**0.460 vs 0.490**).
-![OOD benchmark macro accuracy for Base, FT, and PS variants](card_assets/unseen_macro_no_gsm8k.png)
-These results indicate mixed transfer outside the formal-logic training
-distribution. Larger general reasoning models remain stronger on several OOD
-benchmarks.
 ### Throughput evaluation
-![Aggregate generation throughput](card_assets/throughput.png)
 The formal-logic run generated 422,627 tokens in 1,152.34 generation seconds,
 or **366.8 aggregate tokens per second**. The configuration used a maximum of

 current release artifacts. These should be added when verified records become
 available.
 ## Evaluation
 `max(accuracy, loose_match)`. `lean_prove` and perplexity corpora are excluded
 from the macro score.
 The broader comparison includes checkpoints with different parameter counts,
 training procedures, and adaptation methods. It is useful for context but is not
 a controlled architecture or scaling study.
 TwiL-LM performs best on entailment labeling (**0.655**) and improves FOL
 translation (**0.235**, compared with approximately zero for the base). Lean
 formalization, Lean proving, and procedural reasoning remain weak.
 OOD transfer was measured on GSM8K, ARC-Challenge chain-of-thought,
 ARC-Challenge 25-shot log-likelihood (`acc_norm`), and LogicBench BQA.
 Compared with SmolLM2-1.7B, TwiL-LM improves LogicBench BQA
 (**0.590 vs 0.563**) but is lower on GSM8K (**0.380 vs 0.413**), ARC-C
 chain-of-thought (**0.463 vs 0.587**), and ARC-C 25-shot log-likelihood
 (**0.460 vs 0.490**).
 ### Throughput evaluation
 The formal-logic run generated 422,627 tokens in 1,152.34 generation seconds,
 or **366.8 aggregate tokens per second**. The configuration used a maximum of