Text Generation
Transformers
Safetensors
GGUF
English
granite
granite-4.2
twil
reasoning
math
code
instruction-following
reinforcement-learning
grpo
conversational
Instructions to use webAI-Official/TwIL-8B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use webAI-Official/TwIL-8B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="webAI-Official/TwIL-8B") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("webAI-Official/TwIL-8B") model = AutoModelForCausalLM.from_pretrained("webAI-Official/TwIL-8B", 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=256) 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-8B 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-8B:Q4_K_M # Run inference directly in the terminal: llama cli -hf webAI-Official/TwIL-8B: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-8B:Q4_K_M # Run inference directly in the terminal: llama cli -hf webAI-Official/TwIL-8B: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 webAI-Official/TwIL-8B:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama cli -hf webAI-Official/TwIL-8B:Q4_K_M
Use Docker
docker model run hf.co/webAI-Official/TwIL-8B:Q4_K_M
- Llama new
- LM Studio
- Jan
- vLLM
How to use webAI-Official/TwIL-8B with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "webAI-Official/TwIL-8B" # 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-8B", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/webAI-Official/TwIL-8B:Q4_K_M
- SGLang
How to use webAI-Official/TwIL-8B 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-8B" \ --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-8B", "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-8B" \ --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-8B", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Ollama
How to use webAI-Official/TwIL-8B with Ollama:
ollama run hf.co/webAI-Official/TwIL-8B:Q4_K_M
- Unsloth Desktop
- Pi
How to use webAI-Official/TwIL-8B 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-8B: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": "webAI-Official/TwIL-8B:Q4_K_M" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Docker Model Runner
How to use webAI-Official/TwIL-8B with Docker Model Runner:
docker model run hf.co/webAI-Official/TwIL-8B:Q4_K_M
- Lemonade
How to use webAI-Official/TwIL-8B with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull webAI-Official/TwIL-8B:Q4_K_M
Run and chat with the model
lemonade run user.TwIL-8B-Q4_K_M
List all available models
lemonade list
- Hermes Agent
How to use webAI-Official/TwIL-8B 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-8B: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-8B:Q4_K_M
Run Hermes
hermes
- Atomic Chat
- OpenClaw
How to use webAI-Official/TwIL-8B 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-8B: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-8B: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"
Relicense under the webAI Non-Commercial License ver. 1.0
Browse filesCard metadata and License section now point to LICENSE.md. The Apache-2.0 text is kept for the IBM Granite base model. Adds the verbose-variant marker to two summary mentions of MMLU-Pro and HLE.
- LICENSE.md +36 -0
- README.md +12 -7
LICENSE.md
ADDED
|
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
webAI Non-Commercial License ver. 1.0
|
| 2 |
+
|
| 3 |
+
|
| 4 |
+
1. Definitions
|
| 5 |
+
|
| 6 |
+
“Licensor” means any person or entity that distributes its Work. “Work” means (a) the original work of authorship made available under this license, which may include software, documentation, or other files, and (b) any additions to or derivative works thereof that are made available under this license. The terms “reproduce,” “reproduction,” “derivative works,” and “distribution” have the meaning as provided under U.S. copyright law; provided, however, that for the purposes of this license, derivative works shall not include works that remain separable from, or merely link (or bind by name) to the interfaces of, the Work. Works are “made available” under this license by including in or with the Work either (a) a copyright notice referencing the applicability of this license to the Work, or (b) a copy of this license.
|
| 7 |
+
|
| 8 |
+
|
| 9 |
+
2. License Grant
|
| 10 |
+
|
| 11 |
+
2.1 Copyright Grant. Subject to the terms and conditions of this license, each Licensor grants to you a perpetual, worldwide, non-exclusive, royalty-free, copyright license to use, reproduce, prepare derivative works of, publicly display, publicly perform, sublicense and distribute its Work and any resulting derivative works in any form.
|
| 12 |
+
|
| 13 |
+
|
| 14 |
+
3. Limitations
|
| 15 |
+
|
| 16 |
+
3.1 Redistribution. You may reproduce or distribute the Work only if (a) you do so under this license, (b) you include a complete copy of this license with your distribution, and (c) you retain without modification any copyright, patent, trademark, or attribution notices that are present in the Work.
|
| 17 |
+
|
| 18 |
+
3.2 Derivative Works. You may specify that additional or different terms apply to the use, reproduction, and distribution of your derivative works of the Work (“Your Terms”) only if (a) Your Terms provide that the use limitation in Section 3.3 applies to your derivative works, and (b) you identify the specific derivative works that are subject to Your Terms. Notwithstanding Your Terms, this license (including the redistribution requirements in Section 3.1) will continue to apply to the Work itself.
|
| 19 |
+
|
| 20 |
+
3.3 Use Limitation. The Work and any derivative works thereof only may be used or intended for use non-commercially. As used herein, “non-commercially” means for non-commercial research and educational purposes only.
|
| 21 |
+
|
| 22 |
+
3.4 Patent Claims. If you bring or threaten to bring a patent claim against any Licensor (including any claim, cross-claim or counterclaim in a lawsuit) to enforce any patents that you allege are infringed by any Work, then your rights under this license from such Licensor (including the grant in Section 2.1) will terminate immediately.
|
| 23 |
+
|
| 24 |
+
3.5 Trademarks. This license does not grant any rights to use any Licensor's or its affiliates' names, logos, or trademarks, except as necessary to reproduce the notices described in this license. Nothing in this license shall be construed as permission to use the trade names, trademarks, service marks, or product names of webAI, Inc. or its affiliates to endorse, promote, or imply association with any derivative work, product, service, or entity, without prior written consent from webAI, Inc. Use of the Work does not imply endorsement by webAI, Inc. of any derivative work, product, service, or entity.
|
| 25 |
+
|
| 26 |
+
3.6 Termination. If you violate any term of this license, then your rights under this license (including the grant in Section 2.1) will terminate immediately.
|
| 27 |
+
|
| 28 |
+
|
| 29 |
+
4. Disclaimer of Warranty.
|
| 30 |
+
|
| 31 |
+
THE WORK IS PROVIDED “AS IS” WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, EITHER EXPRESS OR IMPLIED, INCLUDING WARRANTIES OR CONDITIONS OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE, TITLE OR NON-INFRINGEMENT. YOU BEAR THE RISK OF UNDERTAKING ANY ACTIVITIES UNDER THIS LICENSE.
|
| 32 |
+
|
| 33 |
+
|
| 34 |
+
5. Limitation of Liability.
|
| 35 |
+
|
| 36 |
+
EXCEPT AS PROHIBITED BY APPLICABLE LAW, IN NO EVENT AND UNDER NO LEGAL THEORY, WHETHER IN TORT (INCLUDING NEGLIGENCE), CONTRACT, OR OTHERWISE SHALL ANY LICENSOR BE LIABLE TO YOU FOR DAMAGES, INCLUDING ANY DIRECT, INDIRECT, SPECIAL, INCIDENTAL, OR CONSEQUENTIAL DAMAGES ARISING OUT OF OR RELATED TO THIS LICENSE, THE USE OR INABILITY TO USE THE WORK (INCLUDING BUT NOT LIMITED TO LOSS OF GOODWILL, BUSINESS INTERRUPTION, LOST PROFITS OR DATA, COMPUTER FAILURE OR MALFUNCTION, OR ANY OTHER DAMAGES OR LOSSES), EVEN IF THE LICENSOR HAS BEEN ADVISED OF THE POSSIBILITY OF SUCH DAMAGES.
|
README.md
CHANGED
|
@@ -4,7 +4,9 @@ language:
|
|
| 4 |
library_name: transformers
|
| 5 |
pipeline_tag: text-generation
|
| 6 |
base_model: ibm-granite/granite-4.2-8b
|
| 7 |
-
license:
|
|
|
|
|
|
|
| 8 |
tags:
|
| 9 |
- granite
|
| 10 |
- granite-4.2
|
|
@@ -29,7 +31,7 @@ See [Variants](#variants).
|
|
| 29 |
Against open models of similar size and up to 3.5x larger, TwIL-8B posts the highest MATH-500
|
| 30 |
(98.2) and LiveCodeBench (81.6 †) scores in the comparison and leads Qwen3.5-9B on IFBench
|
| 31 |
(+9.9 †). It is level with Qwen3.5-9B on contest math while using fewer tokens per problem. It
|
| 32 |
-
trails on knowledge-heavy benchmarks: GPQA Diamond, MMLU-Pro and HLE.
|
| 33 |
|
| 34 |

|
| 35 |
|
|
@@ -61,7 +63,7 @@ re-run; see [Evaluation protocol](#evaluation-protocol).*
|
|
| 61 |
modest-VRAM GPUs.
|
| 62 |
|
| 63 |
It is **not** a knowledge model. GPQA Diamond (70.2) trails Qwen3.5-9B by 11.5 and Gemma 4 31B
|
| 64 |
-
by 14.1, and MMLU-Pro and HLE follow the same pattern. It also remains verbose next to the
|
| 65 |
frontier: GPT-5.5 solves AIME 2026 with about 5k tokens per problem. There is no safety or
|
| 66 |
preference tuning beyond what Granite 4.2 carries. See [Limitations](#limitations-and-caveats).
|
| 67 |
|
|
@@ -83,7 +85,7 @@ preference tuning beyond what Granite 4.2 carries. See [Limitations](#limitation
|
|
| 83 |
| Reasoning format | Emits a `<think> … </think>` block before the answer (default chat template) |
|
| 84 |
| Evaluated decoding | High-effort pass@1, thinking enabled |
|
| 85 |
| Specialisation | Contest math, code and instruction following |
|
| 86 |
-
| License | Apache License 2.0 |
|
| 87 |
|
| 88 |
### Variants
|
| 89 |
|
|
@@ -329,10 +331,13 @@ models; TwIL-8B targets contest math, code and instruction following at 8B, on I
|
|
| 329 |
|
| 330 |
## License and attribution
|
| 331 |
|
| 332 |
-
Released under the
|
| 333 |
|
| 334 |
-
The base model, `ibm-granite/granite-4.2-8b`,
|
| 335 |
-
under the Apache License 2.0
|
|
|
|
|
|
|
|
|
|
| 336 |
|
| 337 |
## Sources
|
| 338 |
|
|
|
|
| 4 |
library_name: transformers
|
| 5 |
pipeline_tag: text-generation
|
| 6 |
base_model: ibm-granite/granite-4.2-8b
|
| 7 |
+
license: other
|
| 8 |
+
license_name: webai-non-commercial-license-ver.-1.0
|
| 9 |
+
license_link: https://huggingface.co/webAI-Official/TwIL-8B/blob/main/LICENSE.md
|
| 10 |
tags:
|
| 11 |
- granite
|
| 12 |
- granite-4.2
|
|
|
|
| 31 |
Against open models of similar size and up to 3.5x larger, TwIL-8B posts the highest MATH-500
|
| 32 |
(98.2) and LiveCodeBench (81.6 †) scores in the comparison and leads Qwen3.5-9B on IFBench
|
| 33 |
(+9.9 †). It is level with Qwen3.5-9B on contest math while using fewer tokens per problem. It
|
| 34 |
+
trails on knowledge-heavy benchmarks: GPQA Diamond, MMLU-Pro † and HLE †.
|
| 35 |
|
| 36 |

|
| 37 |
|
|
|
|
| 63 |
modest-VRAM GPUs.
|
| 64 |
|
| 65 |
It is **not** a knowledge model. GPQA Diamond (70.2) trails Qwen3.5-9B by 11.5 and Gemma 4 31B
|
| 66 |
+
by 14.1, and MMLU-Pro † and HLE † follow the same pattern. It also remains verbose next to the
|
| 67 |
frontier: GPT-5.5 solves AIME 2026 with about 5k tokens per problem. There is no safety or
|
| 68 |
preference tuning beyond what Granite 4.2 carries. See [Limitations](#limitations-and-caveats).
|
| 69 |
|
|
|
|
| 85 |
| Reasoning format | Emits a `<think> … </think>` block before the answer (default chat template) |
|
| 86 |
| Evaluated decoding | High-effort pass@1, thinking enabled |
|
| 87 |
| Specialisation | Contest math, code and instruction following |
|
| 88 |
+
| License | webAI Non-Commercial License ver. 1.0 (base model: Apache License 2.0, IBM) |
|
| 89 |
|
| 90 |
### Variants
|
| 91 |
|
|
|
|
| 331 |
|
| 332 |
## License and attribution
|
| 333 |
|
| 334 |
+
Released under the **webAI Non-Commercial License ver. 1.0**; see `LICENSE.md` in this repository.
|
| 335 |
|
| 336 |
+
The base model, [`ibm-granite/granite-4.2-8b`](https://huggingface.co/ibm-granite/granite-4.2-8b),
|
| 337 |
+
is Copyright IBM Corporation and is distributed under the Apache License 2.0; its license text is
|
| 338 |
+
retained as `apache-2.0-LICENSE.txt` and all credit for the base model goes to IBM. Apache 2.0
|
| 339 |
+
permits distributing derivative works under different terms provided attribution is preserved,
|
| 340 |
+
which is what the pair of license files in this repository does.
|
| 341 |
|
| 342 |
## Sources
|
| 343 |
|