Instructions to use Lauarvik/granite-4.1-8b-heretic with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Lauarvik/granite-4.1-8b-heretic with Transformers:

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

pipe = pipeline("text-generation", model="Lauarvik/granite-4.1-8b-heretic")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Lauarvik/granite-4.1-8b-heretic")
model = AutoModelForCausalLM.from_pretrained("Lauarvik/granite-4.1-8b-heretic")
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

vLLM

How to use Lauarvik/granite-4.1-8b-heretic with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Lauarvik/granite-4.1-8b-heretic"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Lauarvik/granite-4.1-8b-heretic",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Lauarvik/granite-4.1-8b-heretic

SGLang

How to use Lauarvik/granite-4.1-8b-heretic 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 "Lauarvik/granite-4.1-8b-heretic" \
    --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": "Lauarvik/granite-4.1-8b-heretic",
		"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 "Lauarvik/granite-4.1-8b-heretic" \
        --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": "Lauarvik/granite-4.1-8b-heretic",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Lauarvik/granite-4.1-8b-heretic with Docker Model Runner:
```
docker model run hf.co/Lauarvik/granite-4.1-8b-heretic
```

Lauarvik commited on Apr 27

Commit

4f8407f

verified ·

1 Parent(s): 75e712f

Upload README.md with huggingface_hub

Browse files

Files changed (1) hide show

README.md +626 -196

README.md CHANGED Viewed

@@ -1,199 +1,629 @@
 ---
 library_name: transformers
-tags: []
 ---
-# Model Card for Model ID
-<!-- Provide a quick summary of what the model is/does. -->
-## Model Details
-### Model Description
-<!-- Provide a longer summary of what this model is. -->
-This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
-- **Developed by:** [More Information Needed]
-- **Funded by [optional]:** [More Information Needed]
-- **Shared by [optional]:** [More Information Needed]
-- **Model type:** [More Information Needed]
-- **Language(s) (NLP):** [More Information Needed]
-- **License:** [More Information Needed]
-- **Finetuned from model [optional]:** [More Information Needed]
-### Model Sources [optional]
-<!-- Provide the basic links for the model. -->
-- **Repository:** [More Information Needed]
-- **Paper [optional]:** [More Information Needed]
-- **Demo [optional]:** [More Information Needed]
-## Uses
-<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
-### Direct Use
-<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
-[More Information Needed]
-### Downstream Use [optional]
-<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
-[More Information Needed]
-### Out-of-Scope Use
-<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
-[More Information Needed]
-## Bias, Risks, and Limitations
-<!-- This section is meant to convey both technical and sociotechnical limitations. -->
-[More Information Needed]
-### Recommendations
-<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
-Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
-## How to Get Started with the Model
-Use the code below to get started with the model.
-[More Information Needed]
-## Training Details
-### Training Data
-<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
-[More Information Needed]
-### Training Procedure
-<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
-#### Preprocessing [optional]
-[More Information Needed]
-#### Training Hyperparameters
-- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
-#### Speeds, Sizes, Times [optional]
-<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
-[More Information Needed]
-## Evaluation
-<!-- This section describes the evaluation protocols and provides the results. -->
-### Testing Data, Factors & Metrics
-#### Testing Data
-<!-- This should link to a Dataset Card if possible. -->
-[More Information Needed]
-#### Factors
-<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
-[More Information Needed]
-#### Metrics
-<!-- These are the evaluation metrics being used, ideally with a description of why. -->
-[More Information Needed]
-### Results
-[More Information Needed]
-#### Summary
-## Model Examination [optional]
-<!-- Relevant interpretability work for the model goes here -->
-[More Information Needed]
-## Environmental Impact
-<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
-Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
-- **Hardware Type:** [More Information Needed]
-- **Hours used:** [More Information Needed]
-- **Cloud Provider:** [More Information Needed]
-- **Compute Region:** [More Information Needed]
-- **Carbon Emitted:** [More Information Needed]
-## Technical Specifications [optional]
-### Model Architecture and Objective
-[More Information Needed]
-### Compute Infrastructure
-[More Information Needed]
-#### Hardware
-[More Information Needed]
-#### Software
-[More Information Needed]
-## Citation [optional]
-<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
-**BibTeX:**
-[More Information Needed]
-**APA:**
-[More Information Needed]
-## Glossary [optional]
-<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
-[More Information Needed]
-## More Information [optional]
-[More Information Needed]
-## Model Card Authors [optional]
-[More Information Needed]
-## Model Card Contact
-[More Information Needed]

 ---
+license: apache-2.0
 library_name: transformers
+tags:
+- language
+- granite-4.1
+- heretic
+- uncensored
+- decensored
+- abliterated
+- reproducible
 ---
+# This is a decensored version of [ibm-granite/granite-4.1-8b](https://huggingface.co/ibm-granite/granite-4.1-8b), made using [Heretic](https://github.com/p-e-w/heretic) v1.2.0
+> [!TIP]
+> **This model is reproducible!**
+>
+> See the [README](reproduce/README.md) in the `reproduce` directory for more information.
+## Abliteration parameters
+| Parameter | Value |
+| :-------- | :---: |
+| **direction_index** | per layer |
+| **attn.o_proj.max_weight** | 1.34 |
+| **attn.o_proj.max_weight_position** | 33.00 |
+| **attn.o_proj.min_weight** | 0.99 |
+| **attn.o_proj.min_weight_distance** | 12.73 |
+| **mlp.down_proj.max_weight** | 1.15 |
+| **mlp.down_proj.max_weight_position** | 32.88 |
+| **mlp.down_proj.min_weight** | 0.65 |
+| **mlp.down_proj.min_weight_distance** | 14.66 |
+## Performance
+| Metric | This model | Original model ([ibm-granite/granite-4.1-8b](https://huggingface.co/ibm-granite/granite-4.1-8b)) |
+| :----- | :--------: | :---------------------------: |
+| **KL divergence** | 0.0647 | 0 *(by definition)* |
+| **Refusals** | 1/100 | 61/100 |
+-----
+[![mof-class3-qualified](https://mot.isitopen.ai/modules/mof/assets/badge_class3_qualified.png)](https://mot.isitopen.ai/model/1160)
+# Granite-4.1-8B
+**Model Summary:**
+Granite-4.1-8B is a 8B parameter long-context instruct model finetuned from *Granite-4.1-8B-Base* using a combination of open source instruction datasets with permissive license and internally collected synthetic datasets. Granite 4.1 models have gone through an improved post-training pipeline, including supervised finetuning and reinforcement learning alignment, resulting in enhanced tool calling, instruction following, and chat capabilities.
+- **Developers:** Granite Team, IBM
+- **HF Collection:** [Granite 4.1 Language Models HF Collection](https://huggingface.co/collections/ibm-granite/granite-41-language-models)
+- **Technical Blog:** [Granite-4.1 Blog](https://huggingface.co/blog/ibm-granite/granit-4-1)
+- **GitHub Repository:** [ibm-granite/granite-4.1-language-models](https://github.com/ibm-granite/granite-4.1-language-models)
+- **Website**: [Granite Docs](https://www.ibm.com/granite/docs/)
+- **Release Date**: April 29th, 2026
+- **License:** [Apache 2.0](https://www.apache.org/licenses/LICENSE-2.0)
+**Supported Languages:**
+English, German, Spanish, French, Japanese, Portuguese, Arabic, Czech, Italian, Korean, Dutch, and Chinese. Users may finetune Granite 4.1 models for languages beyond these languages.
+**Intended use:**
+The model is designed to follow general instructions and can serve as the foundation for AI assistants across diverse domains, including business applications, as well as for LLM agents equipped with tool-use capabilities.
+*Capabilities*
+* Summarization
+* Text classification
+* Text extraction
+* Question-answering
+* Retrieval Augmented Generation (RAG)
+* Code related tasks
+* Function-calling tasks
+* Multilingual dialog use cases
+* Fill-In-the-Middle (FIM) code completions
+<!-- <todo>Need to test the examples. (especially the tool calling and RAG ones)</todo>
+ -->
+**Generation:**
+This is a simple example of how to use Granite-4.1-8B model.
+Install the following libraries:
+```shell
+pip install torch torchvision torchaudio
+pip install accelerate
+pip install transformers
+```
+Then, copy the snippet from the section that is relevant for your use case.
+```python
+import torch
+from transformers import AutoModelForCausalLM, AutoTokenizer
+device = "cuda"
+model_path = "ibm-granite/granite-4.1-8b"
+tokenizer = AutoTokenizer.from_pretrained(model_path)
+# drop device_map if running on CPU
+model = AutoModelForCausalLM.from_pretrained(model_path, device_map=device)
+model.eval()
+# change input text as desired
+chat = [
+    { "role": "user", "content": "Please list one IBM Research laboratory located in the United States. You should only output its name and location." },
+]
+chat = tokenizer.apply_chat_template(chat, tokenize=False, add_generation_prompt=True)
+# tokenize the text
+input_tokens = tokenizer(chat, return_tensors="pt").to(device)
+# generate output tokens
+output = model.generate(**input_tokens,
+                        max_new_tokens=100)
+# decode output tokens into text
+output = tokenizer.batch_decode(output)
+# print output
+print(output[0])
+```
+Expected output:
+```shell
+<|start_of_role|>user<|end_of_role|>Please list one IBM Research laboratory located in the United States. You should only output its name and location.<|end_of_text|>
+<|start_of_role|>assistant<|end_of_role|>IBM Almaden Research Laboratory, San Jose, California, United States.<|end_of_text|>
+```
+<!-- 📣 **Update [2025-10-07]:** Added a *default system prompt* to the chat template to guide the model towards more *professional, accurate, and safe* responses. -->
+**Tool-calling:**
+Granite-4.1-8B comes with enhanced tool calling capabilities, enabling seamless integration with external functions and APIs. To define a list of  tools please follow OpenAI's function [definition schema](https://platform.openai.com/docs/guides/function-calling?api-mode=responses#defining-functions).
+This is an example of how to use Granite-4.1-8B model tool-calling ability:
+```python
+import torch
+from transformers import AutoModelForCausalLM, AutoTokenizer
+device = "cuda"
+model_path = "ibm-granite/granite-4.1-8b"
+tokenizer = AutoTokenizer.from_pretrained(model_path)
+# drop device_map if running on CPU
+model = AutoModelForCausalLM.from_pretrained(model_path, device_map=device)
+model.eval()
+tools = [
+    {
+        "type": "function",
+        "function": {
+            "name": "get_current_weather",
+            "description": "Get the current weather for a specified city.",
+            "parameters": {
+                "type": "object",
+                "properties": {
+                    "city": {
+                        "type": "string",
+                        "description": "Name of the city"
+                    }
+                },
+                "required": ["city"]
+            }
+        }
+    }
+]
+# change input text as desired
+chat = [
+    { "role": "user", "content": "What's the weather like in Boston right now?" },
+]
+chat = tokenizer.apply_chat_template(chat, \
+                                     tokenize=False, \
+                                     tools=tools, \
+                                     add_generation_prompt=True)
+# tokenize the text
+input_tokens = tokenizer(chat, return_tensors="pt").to(device)
+# generate output tokens
+output = model.generate(**input_tokens,
+                        max_new_tokens=100)
+# decode output tokens into text
+output = tokenizer.batch_decode(output)
+# print output
+print(output[0])
+```
+Expected output:
+```shell
+<|start_of_role|>system<|end_of_role|>You are a helpful assistant with access to the following tools. You may call one or more tools to assist with the user query.
+You are provided with function signatures within <tools></tools> XML tags:
+<tools>
+{"type": "function", "function": {"name": "get_current_weather", "description": "Get the current weather for a specified city.", "parameters": {"type": "object", "properties": {"city": {"type": "string", "description": "Name of the city"}}, "required": ["city"]}}}
+</tools>
+For each tool call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:
+<tool_call>
+{"name": <function-name>, "arguments": <args-json-object>}
+</tool_call>. If a tool does not exist in the provided list of tools, notify the user that you do not have the ability to fulfill the request.<|end_of_text|>
+<|start_of_role|>user<|end_of_role|>What's the weather like in Boston right now?<|end_of_text|>
+<|start_of_role|>assistant<|end_of_role|><tool_call>
+{"name": "get_current_weather", "arguments": {"city": "Boston"}}
+</tool_call><|end_of_text|>
+```
+<!-- **Retrieval Augmented Generation:**
+*Coming soon* -->
+**Evaluation Results:**
+<table>
+<!--   <caption><b> All Results</b></caption> -->
+<thead>
+  <tr>
+    <th style="text-align:left; background-color: #001d6c; color: white;">Benchmarks</th>
+    <th style="text-align:left; background-color: #001d6c; color: white;">Metric</th>
+    <th style="text-align:center; background-color: #001d6c; color: white;">3B Dense</th>
+    <th style="text-align:center; background-color: #001d6c; color: white;">8B Dense</th>
+    <th style="text-align:center; background-color: #001d6c; color: white;">30B Dense</th>
+  </tr>
+</thead>
+  <tbody>
+<tr>
+  <td colspan="5" style="text-align:center; background-color:  #FFFFFF; color: #2D2D2D; font-style:italic;">
+    General Tasks
+  </td>
+</tr>
+<tr>
+    <td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">MMLU</td>
+    <td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">5-shot</td>
+    <td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">67.02</td>
+    <td style="text-align:right; background-color: #DAE8FF; color: #2D2D2D;">73.84</td>
+    <td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">80.16</td>
+</tr>
+<tr>
+    <td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">MMLU-Pro</td>
+    <td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">5-shot, CoT</td>
+    <td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">49.83</td>
+    <td style="text-align:right; background-color: #DAE8FF; color: #2D2D2D;">55.99</td>
+    <td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">64.09</td>
+</tr>
+<tr>
+    <td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">BBH</td>
+    <td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">3-shot, CoT</td>
+    <td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">75.83</td>
+    <td style="text-align:right; background-color: #DAE8FF; color: #2D2D2D;">80.51</td>
+    <td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">83.74</td>
+</tr>
+<tr>
+    <td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">AGI EVAL</td>
+    <td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">0-shot, CoT</td>
+    <td style="text-align:right; background-color:#FFFFFF; color: #2D2D2D;">65.16</td>
+    <td style="text-align:right; background-color: #DAE8FF; color: #2D2D2D;">72.43</td>
+    <td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">77.80</td>
+</tr>
+<tr>
+    <td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">GPQA</td>
+    <td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">0-shot, CoT</td>
+    <td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">31.70</td>
+    <td style="text-align:right; background-color: #DAE8FF; color: #2D2D2D;">41.96</td>
+    <td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">45.76</td>
+</tr>
+<tr>
+    <td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">SimpleQA</td>
+    <td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;"></td>
+    <td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">3.68</td>
+    <td style="text-align:right; background-color: #DAE8FF; color: #2D2D2D;">4.82</td>
+    <td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">6.81</td>
+</tr>
+<tr>
+  <td colspan="5" style="text-align:center; background-color:  #FFFFFF; color: #2D2D2D; font-style:italic;">
+    Alignment Tasks
+  </td>
+</tr>
+<tr>
+    <td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">AlpacaEval 2.0</td>
+    <td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;"></td>
+    <td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">38.57</td>
+    <td style="text-align:right; background-color: #DAE8FF; color: #2D2D2D;">50.08</td>
+    <td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">56.16</td>
+</tr>
+<tr>
+    <td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">IFEval Avg</td>
+    <td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;"></td>
+    <td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">82.30</td>
+    <td style="text-align:right; background-color: #DAE8FF; color: #2D2D2D;">87.06</td>
+    <td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">89.65</td>
+</tr>
+<tr>
+    <td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">ArenaHard</td>
+    <td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;"></td>
+    <td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">37.80</td>
+    <td style="text-align:right; background-color: #DAE8FF; color: #2D2D2D;">68.98</td>
+    <td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">71.02</td>
+</tr>
+<tr>
+    <td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">MTBench Avg</td>
+    <td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;"></td>
+    <td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">7.57</td>
+    <td style="text-align:right; background-color: #DAE8FF; color: #2D2D2D;">8.61</td>
+    <td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">8.61</td>
+</tr>
+<tr>
+  <td colspan="5" style="text-align:center; background-color:  #FFFFFF; color: #2D2D2D; font-style:italic;">
+    Math Tasks
+  </td>
+</tr>
+<tr>
+    <td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">GSM8K</td>
+    <td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">8-shot</td>
+    <td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">86.88</td>
+    <td style="text-align:right; background-color: #DAE8FF; color: #2D2D2D;">92.49</td>
+    <td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">94.16</td>
+</tr>
+<tr>
+    <td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">GSM Symbolic</td>
+    <td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">8-shot</td>
+    <td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">81.32</td>
+    <td style="text-align:right; background-color: #DAE8FF; color: #2D2D2D;">83.70</td>
+    <td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">75.70</td>
+</tr>
+<tr>
+    <td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">Minerva Math</td>
+    <td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">0-shot, CoT</td>
+    <td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">67.94</td>
+    <td style="text-align:right; background-color: #DAE8FF; color: #2D2D2D;">80.10</td>
+    <td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">81.32</td>
+</tr>
+<tr>
+    <td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">DeepMind Math</td>
+    <td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">0-shot, CoT</td>
+    <td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">64.64</td>
+    <td style="text-align:right; background-color: #DAE8FF; color: #2D2D2D;">80.07</td>
+    <td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">81.93</td>
+</tr>
+<tr>
+  <td colspan="5" style="text-align:center; background-color:  #FFFFFF; color: #2D2D2D; font-style:italic;">
+    Code Tasks
+  </td>
+</tr>
+<tr>
+    <td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">HumanEval</td>
+    <td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">pass@1</td>
+    <td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">81.71</td>
+    <td style="text-align:right; background-color: #DAE8FF; color: #2D2D2D;">85.37</td>
+    <td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">88.41</td>
+</tr>
+<tr>
+    <td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">HumanEval+</td>
+    <td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">pass@1</td>
+    <td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">76.83</td>
+    <td style="text-align:right; background-color: #DAE8FF; color: #2D2D2D;">79.88</td>
+    <td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">85.37</td>
+</tr>
+<tr>
+    <td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">MBPP</td>
+    <td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">pass@1</td>
+    <td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">71.16</td>
+    <td style="text-align:right; background-color: #DAE8FF; color: #2D2D2D;">87.30</td>
+    <td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">85.45</td>
+</tr>
+<tr>
+    <td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">MBPP+</td>
+    <td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">pass@1</td>
+    <td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">62.17</td>
+    <td style="text-align:right; background-color: #DAE8FF; color: #2D2D2D;">73.81</td>
+    <td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">73.54</td>
+</tr>
+<tr>
+    <td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">CRUXEval-O</td>
+    <td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">pass@1</td>
+    <td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">40.75</td>
+    <td style="text-align:right; background-color: #DAE8FF; color: #2D2D2D;">47.63</td>
+    <td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">55.75</td>
+</tr>
+<tr>
+    <td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">BigCodeBench</td>
+    <td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">pass@1</td>
+    <td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">32.19</td>
+    <td style="text-align:right; background-color: #DAE8FF; color: #2D2D2D;">35.00</td>
+    <td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">38.77</td>
+</tr>
+<tr>
+    <td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">MULTIPLE</td>
+    <td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">pass@1</td>
+    <td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">52.54</td>
+    <td style="text-align:right; background-color: #DAE8FF; color: #2D2D2D;">60.26</td>
+    <td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">62.31</td>
+</tr>
+<tr>
+<tr>
+    <td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">Eval+ Avg</td>
+    <td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">pass@1</td>
+    <td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">67.05</td>
+    <td style="text-align:right; background-color: #DAE8FF; color: #2D2D2D;">80.21</td>
+    <td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">82.66</td>
+</tr>
+<tr>
+  <td colspan="5" style="text-align:center; background-color:  #FFFFFF; color: #2D2D2D; font-style:italic;">
+    Tool Calling Tasks
+  </td>
+</tr>
+<tr>
+    <td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">BFCL v3</td>
+    <td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;"></td>
+    <td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">60.80</td>
+    <td style="text-align:right; background-color: #DAE8FF; color: #2D2D2D;">68.27</td>
+    <td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">73.68</td>
+</tr>
+<tr>
+  <td colspan="5" style="text-align:center; background-color:  #FFFFFF; color: #2D2D2D; font-style:italic;">
+    Multilingual Tasks
+  </td>
+</tr>
+<tr>
+    <td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">MMMLU</td>
+    <td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">5-shot</td>
+    <td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">57.61</td>
+    <td style="text-align:right; background-color: #DAE8FF; color: #2D2D2D;">64.84</td>
+    <td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">73.71</td>
+</tr>
+<tr>
+    <td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">INCLUDE</td>
+    <td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">5-shot</td>
+    <td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">52.05</td>
+    <td style="text-align:right; background-color: #DAE8FF; color: #2D2D2D;">58.89</td>
+    <td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">67.26</td>
+</tr>
+<tr>
+    <td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">MGSM</td>
+    <td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">8-shot</td>
+    <td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">70.00</td>
+    <td style="text-align:right; background-color: #DAE8FF; color: #2D2D2D;">82.32</td>
+    <td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">71.12</td>
+</tr>
+<tr>
+  <td colspan="6" style="text-align:center; background-color:  #FFFFFF; color: #2D2D2D; font-style:italic;">
+    Safety
+  </td>
+</tr>
+<tr>
+    <td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">SALAD-Bench</td>
+    <td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;"></td>
+    <td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">93.95</td>
+    <td style="text-align:right; background-color: #DAE8FF; color: #2D2D2D;">95.80</td>
+    <td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">96.41</td>
+</tr>
+<tr>
+    <td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">AttaQ</td>
+    <td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;"></td>
+    <td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">81.88</td>
+    <td style="text-align:right; background-color: #DAE8FF; color: #2D2D2D;">81.19</td>
+    <td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">85.76</td>
+</tr>
+<tr>
+    <td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">Tulu3 Safety Eval Avg</td>
+    <td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;"></td>
+    <td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">66.84</td>
+    <td style="text-align:right; background-color: #DAE8FF; color: #2D2D2D;">75.57</td>
+    <td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">78.19</td>
+</tr>
+</tbody></table>
+<table>
+  <caption><b>Multilingual Benchmarks and the included languages:</b></caption>
+<thead>
+  <tr>
+    <th style="text-align:left; background-color: #001d6c; color: white;">Benchmarks</th>
+    <th style="text-align:left; background-color: #001d6c; color: white;"># Langs</th>
+    <th style="text-align:center; background-color: #001d6c; color: white;">Languages</th>
+  </tr>
+</thead>
+<tbody>
+<tr>
+    <td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">MMMLU</td>
+    <td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">11</td>
+    <td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">ar, de, en, es, fr, ja, ko, pt, zh, bn, hi</td>
+</tr>
+<tr>
+    <td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">INCLUDE</td>
+    <td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">14</td>
+<!--     <td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">hindi, bengali, tamil, telugu, arabic, german, spanish, french, italian, japanese, korean, dutch, portuguese, chinese</td> -->
+    <td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">hi, bn, ta, te, ar, de, es, fr, it, ja, ko, nl, pt, zh</td>
+</tr>
+<tr>
+    <td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">MGSM</td>
+    <td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">5</td>
+    <td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">en, es, fr, ja, zh</td>
+</tr>
+</tbody>
+</table>
+**Model Architecture:**
+Granite-4.1-8B baseline is built on a decoder-only dense transformer architecture. Core components of this architecture are: GQA, RoPE, MLP with SwiGLU, RMSNorm, and shared input/output embeddings.
+<table>
+<thead>
+  <tr>
+    <th style="text-align:left; background-color: #001d6c; color: white;">Model</th>
+    <th style="text-align:center; background-color: #001d6c; color: white;">3B Dense</th>
+    <th style="text-align:center; background-color: #001d6c; color: white;">8B Dense</th>
+    <th style="text-align:center; background-color: #001d6c; color: white;">30B Dense</th>
+  </tr></thead>
+<tbody>
+  <tr>
+    <td style="text-align:left; background-color: #FFFFFF; color: black;">Embedding size</td>
+    <td style="text-align:center; background-color: #FFFFFF; color: black;">2560</td>
+    <td style="text-align:center; background-color: #DAE8FF; color: black;">4096</td>
+    <td style="text-align:center; background-color: #FFFFFF; color: black;">4096</td>
+  </tr>
+  <tr>
+    <td style="text-align:left; background-color: #FFFFFF; color: black;">Number of layers</td>
+    <td style="text-align:center; background-color: #FFFFFF; color: black;">40</td>
+    <td style="text-align:center; background-color: #DAE8FF; color: black;">40</td>
+    <td style="text-align:center; background-color: #FFFFFF; color: black;">64</td>
+  </tr>
+  <tr>
+    <td style="text-align:left; background-color: #FFFFFF; color: black;">Attention head size</td>
+    <td style="text-align:center; background-color: #FFFFFF; color: black;">64</td>
+    <td style="text-align:center; background-color: #DAE8FF; color: black;">128</td>
+    <td style="text-align:center; background-color: #FFFFFF; color: black;">128</td>
+  </tr>
+  <tr>
+    <td style="text-align:left; background-color: #FFFFFF; color: black;">Number of attention heads</td>
+    <td style="text-align:center; background-color: #FFFFFF; color: black;">40</td>
+    <td style="text-align:center; background-color: #DAE8FF; color: black;">32</td>
+    <td style="text-align:center; background-color: #FFFFFF; color: black;">32</td>
+  </tr>
+  <tr>
+    <td style="text-align:left; background-color: #FFFFFF; color: black;">Number of KV heads</td>
+    <td style="text-align:center; background-color: #FFFFFF; color: black;">8</td>
+    <td style="text-align:center; background-color: #DAE8FF; color: black;">8</td>
+    <td style="text-align:center; background-color: #FFFFFF; color: black;">8</td>
+  </tr>
+  <!--<tr>
+    <td style="text-align:left; background-color: #FFFFFF; color: black;">Mamba2 state size</td>
+    <td style="text-align:center; background-color: #FFFFFF; color: black;">-</td>
+    <td style="text-align:center; background-color: #DAE8FF; color: black;"></td>
+    <td style="text-align:center; background-color: #FFFFFF; color: black;"></td>
+  </tr>
+  <tr>
+    <td style="text-align:left; background-color: #FFFFFF; color: black;">Number of Mamba2 heads</td>
+    <td style="text-align:center; background-color: #FFFFFF; color: black;"></td>
+    <td style="text-align:center; background-color: #DAE8FF; color: black;"></td>
+    <td style="text-align:center; background-color: #FFFFFF; color: black;"></td>
+  </tr>-->
+  <tr>
+    <td style="text-align:left; background-color: #FFFFFF; color: black;">MLP / Shared expert hidden size</td>
+    <td style="text-align:center; background-color: #FFFFFF; color: black;">8192</td>
+    <td style="text-align:center; background-color: #DAE8FF; color: black;">12800</td>
+    <td style="text-align:center; background-color: #FFFFFF; color: black;">32768</td>
+  </tr>
+  <!--<tr>
+    <td style="text-align:left; background-color: #FFFFFF; color: black;">Num. Experts</td>
+    <td style="text-align:center; background-color: #FFFFFF; color: black;"></td>
+    <td style="text-align:center; background-color: #DAE8FF; color: black;"></td>
+    <td style="text-align:center; background-color: #FFFFFF; color: black;"></td>
+  </tr>
+  <tr>
+    <td style="text-align:left; background-color: #FFFFFF; color: black;">Num. active Experts</td>
+    <td style="text-align:center; background-color: #FFFFFF; color: black;"></td>
+    <td style="text-align:center; background-color: #DAE8FF; color: black;"></td>
+    <td style="text-align:center; background-color: #FFFFFF; color: black;"></td>
+  </tr>
+  <tr>
+    <td style="text-align:left; background-color: #FFFFFF; color: black;">Expert hidden size</td>
+    <td style="text-align:center; background-color: #FFFFFF; color: black;"></td>
+    <td style="text-align:center; background-color: #DAE8FF; color: black;"></td>
+    <td style="text-align:center; background-color: #FFFFFF; color: black;"></td>
+  </tr>-->
+  <tr>
+    <td style="text-align:left; background-color: #FFFFFF; color: black;">MLP activation</td>
+    <td style="text-align:center; background-color: #FFFFFF; color: black;">SwiGLU</td>
+    <td style="text-align:center; background-color: #DAE8FF; color: black;">SwiGLU</td>
+    <td style="text-align:center; background-color: #FFFFFF; color: black;">SwiGLU</td>
+  </tr>
+  <tr>
+    <td style="text-align:left; background-color: #FFFFFF; color: black;">Sequence length</td>
+    <td style="text-align:center; background-color: #FFFFFF; color: black;">131072</td>
+    <td style="text-align:center; background-color: #DAE8FF; color: black;">131072</td>
+    <td style="text-align:center; background-color: #FFFFFF; color: black;">131072</td>
+  </tr>
+  <tr>
+    <td style="text-align:left; background-color: #FFFFFF; color: black;">Position embedding</td>
+    <td style="text-align:center; background-color: #FFFFFF; color: black;">RoPE</td>
+    <td style="text-align:center; background-color: #DAE8FF; color: black;">RoPE</td>
+    <td style="text-align:center; background-color: #FFFFFF; color: black;">RoPE</td>
+  </tr>
+  <tr>
+    <td style="text-align:left; background-color: #FFFFFF; color: black;"># Parameters</td>
+    <td style="text-align:center; background-color: #FFFFFF; color: black;">3B</td>
+    <td style="text-align:center; background-color: #DAE8FF; color: black;">8B</td>
+    <td style="text-align:center; background-color: #FFFFFF; color: black;">30B</td>
+  </tr>
+<!--  <tr>
+    <td style="text-align:left; background-color: #FFFFFF; color: black;"># Active parameters</td>
+    <td style="text-align:center; background-color: #FFFFFF; color: black;"></td>
+    <td style="text-align:center; background-color: #DAE8FF; color: black;"></td>
+    <td style="text-align:center; background-color: #FFFFFF; color: black;"></td>
+  </tr>-->
+</tbody></table>
+**Training Data:**
+Overall, our SFT data is largely comprised of three key sources: (1) publicly available datasets with permissive license, (2) internal synthetic data targeting specific capabilities, and (3) a select set of human-curated data.
+**Supervised Fine-Tunning and Reinforcement Learning:**
+Instruct model has been fine tuned with significantly improved SFT-pipeline and Reinforcement learning pipelines with high quality mix of various datasets as mentioned above. With rigorus SFT-RL cycles we have improved Granite-4.1 model's tool calling, instruction following and chat capabilities. For further details please check our [Granite-4.1 Blog]((https://huggingface.co/blog/ibm-granite/granit-4-1)).
+**Infrastructure:**
+We trained the Granite 4.1 Language Models utilizing an NVIDIA GB200 NVL72 cluster hosted in CoreWeave. Intra-rack communication occurs via the 72-GPU NVLink domain, and a non-blocking, full Fat-Tree NDR 400 Gb/s InfiniBand network provides inter-rack communication. This cluster provides a scalable and efficient infrastructure for training our models over thousands of GPUs.
+**Ethical Considerations and Limitations:**
+Granite 4.1 Instruction Models are primarily finetuned using instruction-response pairs mostly in English, but also multilingual data covering multiple languages. Although this model can handle multilingual dialog use cases, its performance might not be similar to English tasks. In such case, introducing a small number of examples (few-shot) can help the model in generating more accurate outputs. While this model has been aligned by keeping safety in consideration, the model may in some cases produce inaccurate, biased, or unsafe responses to user prompts. So we urge the community to use this model with proper safety testing and tuning tailored for their specific tasks.
+**Resources**
+- ⭐️ Learn about the latest updates with Granite: https://www.ibm.com/granite
+- 📄 Get started with tutorials, best practices, and prompt engineering advice: https://www.ibm.com/granite/docs/
+- 💡 Learn about the latest Granite learning resources: https://ibm.biz/granite-learning-resources
+<!-- ## Citation
+```
+@misc{granite-models,
+  author = {author 1, author2, ...},
+  title = {},
+  journal = {},
+  volume = {},
+  year = {2024},
+  url = {https://arxiv.org/abs/0000.00000},
+}
+``` -->