Update README.md

README.md

@@ -1,3 +1,460 @@
----
-license: apache-2.0
----
+---
+license: apache-2.0
+pipeline_tag: text-generation
+language:
+- en
+license_link: LICENSE
+base_model:
+- ibm-granite/granite-3.1-2b-instruct
+quantized_by: bartowski
+tags:
+- llamafile
+- language
+- granite-3.2
+---
+
+# Granite 3.2 2B Instruct - llamafile
+
+- Model creator: [IBM](https://huggingface.co/ibm-granite)
+- Original model: [ibm-granite/granite-3.2-2b-instruct](https://huggingface.co/ibm-granite/granite-3.2-2b-instruct)
+
+Mozilla packaged the IBM Granite 3.2 models into executable weights that we
+call [llamafiles](https://github.com/Mozilla-Ocho/llamafile). This gives
+you the easiest fastest way to use the model on Linux, MacOS, Windows,
+FreeBSD, OpenBSD and NetBSD systems you control on both AMD64 and ARM64.
+
+*Software Last Updated: 2025-03-31*
+
+*Llamafile Version: 0.9.2*
+
+## Quickstart
+
+To get started, you need both the Granite 3.2 weights, and the llamafile
+software. Both of them are included in a single file, which can be
+downloaded and run as follows:
+
+```
+wget https://huggingface.co/Mozilla/granite-3.2-2b-instruct-llamafile/resolve/main/granite-3.2-2b-instruct-Q6_K.llamafile
+chmod +x granite-3.2-2b-instruct-Q6_K.llamafile
+./granite-3.2-2b-instruct-Q6_K.llamafile
+```
+
+The default mode of operation for these llamafiles is our new command
+line chatbot interface.
+
+## Usage
+
+You can use triple quotes to ask questions on multiple lines. You can
+pass commands like `/stats` and `/context` to see runtime status
+information. You can change the system prompt by passing the `-p "new
+system prompt"` flag. You can press CTRL-C to interrupt the model.
+Finally CTRL-D may be used to exit.
+
+If you prefer to use a web GUI, then a `--server` mode is provided, that
+will open a tab with a chatbot and completion interface in your browser.
+For additional help on how it may be used, pass the `--help` flag. The
+server also has an OpenAI API compatible completions endpoint that can
+be accessed via Python using the `openai` pip package.
+
+```
+./granite-3.2-2b-instruct-Q6_K.llamafile --server
+```
+
+An advanced CLI mode is provided that's useful for shell scripting. You
+can use it by passing the `--cli` flag. For additional help on how it
+may be used, pass the `--help` flag.
+
+```
+./granite-3.2-2b-instruct-Q6_K.llamafile --cli -p 'four score and seven' --log-disable
+```
+
+## Troubleshooting
+
+Having **trouble?** See the ["Gotchas"
+section](https://github.com/mozilla-ocho/llamafile/?tab=readme-ov-file#gotchas-and-troubleshooting)
+of the README.
+
+On Linux, the way to avoid run-detector errors is to install the APE
+interpreter.
+
+```sh
+sudo wget -O /usr/bin/ape https://cosmo.zip/pub/cosmos/bin/ape-$(uname -m).elf
+sudo chmod +x /usr/bin/ape
+sudo sh -c "echo ':APE:M::MZqFpD::/usr/bin/ape:' >/proc/sys/fs/binfmt_misc/register"
+sudo sh -c "echo ':APE-jart:M::jartsr::/usr/bin/ape:' >/proc/sys/fs/binfmt_misc/register"
+```
+
+On Windows there's a 4GB limit on executable sizes.
+
+## Context Window
+
+This model has a max context window size of 128k tokens. By default, a
+context window size of 8192 tokens is used. You can ask llamafile 
+to use the maximum context size by passing the `-c 0` flag. That's big 
+enough for a small book. If you want to be able to have a conversation
+with your book, you can use the `-f book.txt` flag.
+
+## GPU Acceleration
+
+On GPUs with sufficient RAM, the `-ngl 999` flag may be passed to use
+the system's NVIDIA or AMD GPU(s). On Windows, only the graphics card
+driver needs to be installed if you own an NVIDIA GPU. On Windows, if
+you have an AMD GPU, you should install the ROCm SDK v6.1 and then pass
+the flags `--recompile --gpu amd` the first time you run your llamafile.
+
+On NVIDIA GPUs, by default, the prebuilt tinyBLAS library is used to
+perform matrix multiplications. This is open source software, but it
+doesn't go as fast as closed source cuBLAS. If you have the CUDA SDK
+installed on your system, then you can pass the `--recompile` flag to
+build a GGML CUDA library just for your system that uses cuBLAS. This
+ensures you get maximum performance.
+
+For further information, please see the [llamafile
+README](https://github.com/mozilla-ocho/llamafile/).
+
+## About llamafile
+
+llamafile is a new format introduced by Mozilla on Nov 20th 2023. It
+uses Cosmopolitan Libc to turn LLM weights into runnable llama.cpp
+binaries that run on the stock installs of six OSes for both ARM64 and
+AMD64.
+
+---
+
+# Granite-3.2-2B-Instruct
+
+**Model Summary:**
+Granite-3.2-2B-Instruct is an 2-billion-parameter, long-context AI model fine-tuned for thinking capabilities. Built on top of [Granite-3.1-2B-Instruct](https://huggingface.co/ibm-granite/granite-3.1-2b-instruct), it has been trained using a mix of permissively licensed open-source datasets and internally generated synthetic data designed for reasoning tasks. The model allows controllability of its thinking capability, ensuring it is applied only when required.
+
+
+- **Developers:** Granite Team, IBM
+- **Website**: [Granite Docs](https://www.ibm.com/granite/docs/)
+- **Release Date**: February 26th, 2025
+- **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. However, users may finetune this Granite model for languages beyond these 12 languages.
+
+**Intended Use:** 
+This model is designed to handle general instruction-following tasks and can be integrated into AI assistants across various domains, including business applications.
+
+**Capabilities**
+* **Thinking**
+* Summarization
+* Text classification
+* Text extraction
+* Question-answering
+* Retrieval Augmented Generation (RAG)
+* Code related tasks
+* Function-calling tasks
+* Multilingual dialog use cases
+* Long-context tasks including long document/meeting summarization, long document QA, etc.
+
+
+
+**Generation:** 
+This is a simple example of how to use Granite-3.2-2B-Instruct 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
+from transformers import AutoModelForCausalLM, AutoTokenizer, set_seed
+import torch
+
+model_path="ibm-granite/granite-3.2-2b-instruct"
+device="cuda"
+model = AutoModelForCausalLM.from_pretrained(
+        model_path,
+        device_map=device,
+        torch_dtype=torch.bfloat16,
+    )
+tokenizer = AutoTokenizer.from_pretrained(
+        model_path
+)
+
+conv = [{"role": "user", "content":"You have 10 liters of a 30% acid solution. How many liters of a 70% acid solution must be added to achieve a 50% acid mixture?"}]
+
+input_ids = tokenizer.apply_chat_template(conv, return_tensors="pt", thinking=True, return_dict=True, add_generation_prompt=True).to(device)
+
+set_seed(42)
+output = model.generate(
+    **input_ids,
+    max_new_tokens=8192,
+)
+
+prediction = tokenizer.decode(output[0, input_ids["input_ids"].shape[1]:], skip_special_tokens=True)
+print(prediction)
+```
+
+**Example Outputs**
+- thinking=True
+```md
+Here is my thought process:
+
+1. First, let's understand the composition of the initial 10 liters of 30% acid solution:
+   - Acid content = 30% of 10 liters = 0.30 * 10 = 3 liters
+
+2. We want to end up with a 50% acid solution. Let's denote the volume of the 70% acid solution to be added as 'x' liters.
+
+3. The amount of acid in the final mixture (50% solution) should equal the initial acid content plus the acid from the added 70% solution.
+   - Total acid in final mixture = 0.50 * (10 + x)
+
+4. The equation representing the total acid content is:
+   3 (from initial solution) + 0.70 * x (from added solution) = 0.50 * (10 + x)
+
+5. Now, we solve for 'x':
+   3 + 0.70x = 5 + 0.50x
+   0.70x - 0.50x = 5 - 3
+   0.20x = 2
+   x = 2 / 0.20
+   x = 10 liters
+
+6. Therefore, 10 liters of a 70% acid solution must be added to the initial 10 liters of 30% acid solution to achieve a 50% acid mixture.
+
+Here is my response:
+
+To solve this problem, we need to determine how much of a 70% acid solution must be added to a 10-liter solution that is already 30% acid to create a new mixture that is 50% acid. Here's how to calculate it:
+
+1. **Initial Acid Content**:
+   - The initial 10-liter solution contains 3 liters of acid (since 30% of 10 liters).
+
+2. **Desired Final Acid Content**:
+   - We want the final mixture to be 50% acid.
+
+3. **Equation Setup**:
+   - Let 'x' be the volume (in liters) of the 70% acid solution to be added.
+   - The equation representing the total acid content in the final mixture (which is 10 liters from the initial solution plus 'x' liters of the added solution) should equal 50% of the total volume (10 + x).
+   - This gives us: 3 (acid from initial solution) + 0.70x (acid from added solution) = 0.50(10 + x)
+
+4. **Solving the Equation**:
+   - First, simplify the right side of the equation: 0.50(10 + x) = 5 + 0.50x
+   - Now, the equation is: 3 + 0.70x = 5 + 0.50x
+   - Subtract 0.50x from both sides: 0.20x = 2
+   - Divide both sides by 0.20: x = 2 / 0.20
+   - x = 10 liters
+
+5. **Conclusion**:
+   - To achieve a 50% acid mixture from the initial 30% solution, you need to add 10 liters of a 70% acid solution.
+
+So, the final answer is that 10 liters of a 70% acid solution must be added to the initial 10 liters of 30% acid solution.
+```
+- thinking=False
+```md
+To solve this problem, we'll use the concept of volume and concentration. Let's denote the amount of 70% acid solution we need to add as "x" liters.
+
+First, let's find out how much acid is in the initial 10-liter solution:
+
+Acid in initial solution = 30% of 10 liters = 0.30 * 10 = 3 liters
+
+Now, we want to end up with a 50% acid solution in a total volume of (10 + x) liters. Let's denote the final volume as V.
+
+Final acid concentration = 50%
+Final acid amount = 50% of V = 0.50 * V
+
+We know the initial acid amount and the final acid amount, so we can set up an equation:
+
+Initial acid amount + Acid from added solution = Final acid amount
+3 liters + (70% of x) = 0.50 * (10 + x)
+
+Now, let's solve for x:
+
+0.70x + 3 = 0.50 * 10 + 0.50x
+0.70x - 0.50x = 0.50 * 10 - 3
+0.20x = 5 - 3
+0.20x = 2
+x = 2 / 0.20
+x = 10 liters
+
+So, you need to add 10 liters of a 70% acid solution to the initial 10-liter 30% acid solution to achieve a 50% acid mixture.
+```
+
+**Evaluation Results:**
+<table>
+  
+<thead>
+  <tr>
+    <th style="text-align:left; background-color: #001d6c; color: white;">Models</th>
+    <th style="text-align:center; background-color: #001d6c; color: white;">ArenaHard</th>
+    <th style="text-align:center; background-color: #001d6c; color: white;">Alpaca-Eval-2</th>
+    <th style="text-align:center; background-color: #001d6c; color: white;">MMLU</th>
+    <th style="text-align:center; background-color: #001d6c; color: white;">PopQA</th>
+    <th style="text-align:center; background-color: #001d6c; color: white;">TruthfulQA</th>
+    <th style="text-align:center; background-color: #001d6c; color: white;">BigBenchHard</th>
+    <th style="text-align:center; background-color: #001d6c; color: white;">DROP</th>
+    <th style="text-align:center; background-color: #001d6c; color: white;">GSM8K</th>
+    <th style="text-align:center; background-color: #001d6c; color: white;">HumanEval</th>
+   <th style="text-align:center; background-color: #001d6c; color: white;">HumanEval+</th>
+  <th style="text-align:center; background-color: #001d6c; color: white;">IFEval</th>
+    <th style="text-align:center; background-color: #001d6c; color: white;">AttaQ</th>
+  </tr></thead>
+  <tbody>
+  <tr>
+    <td style="text-align:left; background-color: #DAE8FF; color: black;">Llama-3.1-8B-Instruct</td>
+    <td style="text-align:center; background-color: #DAE8FF; color: black;">36.43</td>
+    <td style="text-align:center; background-color: #DAE8FF; color: black;">27.22</td>
+    <td style="text-align:center; background-color: #DAE8FF; color: black;">69.15</td>
+    <td style="text-align:center; background-color: #DAE8FF; color: black;">28.79</td>
+    <td style="text-align:center; background-color: #DAE8FF; color: black;">52.79</td>
+    <td style="text-align:center; background-color: #DAE8FF; color: black;">72.66</td>
+    <td style="text-align:center; background-color: #DAE8FF; color: black;">61.48</td>
+    <td style="text-align:center; background-color: #DAE8FF; color: black;">83.24</td>
+    <td style="text-align:center; background-color: #DAE8FF; color: black;">85.32</td>
+    <td style="text-align:center; background-color: #DAE8FF; color: black;">80.15</td>
+    <td style="text-align:center; background-color: #DAE8FF; color: black;">79.10</td>
+    <td style="text-align:center; background-color: #DAE8FF; color: black;">83.43</td>
+  </tr>
+           
+  <tr>
+    <td style="text-align:left; background-color: #DAE8FF; color: black;">DeepSeek-R1-Distill-Llama-8B</td>
+    <td style="text-align:center; background-color: #DAE8FF; color: black;">17.17</td>
+    <td style="text-align:center; background-color: #DAE8FF; color: black;">21.85</td>
+    <td style="text-align:center; background-color: #DAE8FF; color: black;">45.80</td>
+    <td style="text-align:center; background-color: #DAE8FF; color: black;">13.25</td>
+    <td style="text-align:center; background-color: #DAE8FF; color: black;">47.43</td>
+    <td style="text-align:center; background-color: #DAE8FF; color: black;">65.71</td>
+    <td style="text-align:center; background-color: #DAE8FF; color: black;">44.46</td>
+    <td style="text-align:center; background-color: #DAE8FF; color: black;">72.18</td>
+    <td style="text-align:center; background-color: #DAE8FF; color: black;">67.54</td>
+    <td style="text-align:center; background-color: #DAE8FF; color: black;">62.91</td>
+    <td style="text-align:center; background-color: #DAE8FF; color: black;">66.50</td>
+    <td style="text-align:center; background-color: #DAE8FF; color: black;">42.87</td>
+  </tr>
+      
+  <tr>
+    <td style="text-align:left; background-color: #DAE8FF; color: black;">Qwen-2.5-7B-Instruct</td>
+    <td style="text-align:center; background-color: #DAE8FF; color: black;">25.44</td>
+    <td style="text-align:center; background-color: #DAE8FF; color: black;">30.34</td>
+    <td style="text-align:center; background-color: #DAE8FF; color: black;">74.30</td>
+    <td style="text-align:center; background-color: #DAE8FF; color: black;">18.12</td>
+    <td style="text-align:center; background-color: #DAE8FF; color: black;">63.06</td>
+    <td style="text-align:center; background-color: #DAE8FF; color: black;">70.40</td>
+    <td style="text-align:center; background-color: #DAE8FF; color: black;">54.71</td>
+    <td style="text-align:center; background-color: #DAE8FF; color: black;">84.46</td>
+    <td style="text-align:center; background-color: #DAE8FF; color: black;">93.35</td>
+    <td style="text-align:center; background-color: #DAE8FF; color: black;">89.91</td>
+    <td style="text-align:center; background-color: #DAE8FF; color: black;">74.90</td>
+    <td style="text-align:center; background-color: #DAE8FF; color: black;">81.90</td>
+  </tr>
+      
+  <tr>
+    <td style="text-align:left; background-color: #DAE8FF; color: black;">DeepSeek-R1-Distill-Qwen-7B</td>
+    <td style="text-align:center; background-color: #DAE8FF; color: black;">10.36</td>
+    <td style="text-align:center; background-color: #DAE8FF; color: black;">15.35</td>
+    <td style="text-align:center; background-color: #DAE8FF; color: black;">50.72</td>
+    <td style="text-align:center; background-color: #DAE8FF; color: black;">9.94</td>
+    <td style="text-align:center; background-color: #DAE8FF; color: black;">47.14</td>
+    <td style="text-align:center; background-color: #DAE8FF; color: black;">65.04</td>
+    <td style="text-align:center; background-color: #DAE8FF; color: black;">42.76</td>
+    <td style="text-align:center; background-color: #DAE8FF; color: black;">78.47</td>
+    <td style="text-align:center; background-color: #DAE8FF; color: black;">79.89</td>
+    <td style="text-align:center; background-color: #DAE8FF; color: black;">78.43</td>
+    <td style="text-align:center; background-color: #DAE8FF; color: black;">59.10</td>
+    <td style="text-align:center; background-color: #DAE8FF; color: black;">42.45</td>
+  </tr>
+
+  <tr>
+    <td style="text-align:left; background-color: #DAE8FF; color: black;">Granite-3.1-8B-Instruct</td>
+    <td style="text-align:center; background-color: #DAE8FF; color: black;">37.58</td>
+    <td style="text-align:center; background-color: #DAE8FF; color: black;">30.34</td>
+    <td style="text-align:center; background-color: #DAE8FF; color: black;">66.77</td>
+    <td style="text-align:center; background-color: #DAE8FF; color: black;">28.7</td>
+    <td style="text-align:center; background-color: #DAE8FF; color: black;">65.84</td>
+    <td style="text-align:center; background-color: #DAE8FF; color: black;">68.55</td>
+    <td style="text-align:center; background-color: #DAE8FF; color: black;">50.78</td>
+    <td style="text-align:center; background-color: #DAE8FF; color: black;">79.15</td>
+    <td style="text-align:center; background-color: #DAE8FF; color: black;">89.63</td>
+    <td style="text-align:center; background-color: #DAE8FF; color: black;">85.79</td>
+    <td style="text-align:center; background-color: #DAE8FF; color: black;">73.20</td>
+    <td style="text-align:center; background-color: #DAE8FF; color: black;">85.73</td>
+  </tr>
+      
+      
+<tr>
+    <td style="text-align:left; background-color: #DAE8FF; color: black;">Granite-3.1-2B-Instruct</td>
+    <td style="text-align:center; background-color: #DAE8FF; color: black;">23.3</td>
+    <td style="text-align:center; background-color: #DAE8FF; color: black;">27.17</td>
+    <td style="text-align:center; background-color: #DAE8FF; color: black;">57.11</td> 
+    <td style="text-align:center; background-color: #DAE8FF; color: black;">20.55</td>
+    <td style="text-align:center; background-color: #DAE8FF; color: black;">59.79</td>
+    <td style="text-align:center; background-color: #DAE8FF; color: black;">54.46</td>
+    <td style="text-align:center; background-color: #DAE8FF; color: black;">18.68</td>
+    <td style="text-align:center; background-color: #DAE8FF; color: black;">67.55</td>
+    <td style="text-align:center; background-color: #DAE8FF; color: black;">79.45</td>
+    <td style="text-align:center; background-color: #DAE8FF; color: black;">75.26</td>
+    <td style="text-align:center; background-color: #DAE8FF; color: black;">63.59</td>
+    <td style="text-align:center; background-color: #DAE8FF; color: black;">84.7</td>
+  </tr>
+
+<tr>
+      <td style="text-align:left; background-color: #DAE8FF; color: black;">Granite-3.2-8B-Instruct</td>
+    <td style="text-align:center; background-color: #DAE8FF; color: black;">55.25</td>
+    <td style="text-align:center; background-color: #DAE8FF; color: black;">61.19</td>
+   <td style="text-align:center; background-color: #DAE8FF; color: black;">66.79</td>
+    <td style="text-align:center; background-color: #DAE8FF; color: black;">28.04</td>
+    <td style="text-align:center; background-color: #DAE8FF; color: black;">66.92</td>
+    <td style="text-align:center; background-color: #DAE8FF; color: black;">64.77</td>
+    <td style="text-align:center; background-color: #DAE8FF; color: black;">50.95</td>
+    <td style="text-align:center; background-color: #DAE8FF; color: black;">81.65</td>
+    <td style="text-align:center; background-color: #DAE8FF; color: black;">89.35</td>
+    <td style="text-align:center; background-color: #DAE8FF; color: black;">85.72</td>
+    <td style="text-align:center; background-color: #DAE8FF; color: black;">74.31</td>
+    <td style="text-align:center; background-color: #DAE8FF; color: black;">85.42</td>
+ 
+  </tr>
+ 
+  <tr>
+      <td style="text-align:left; background-color: #DAE8FF; color: black;"><b>Granite-3.2-2B-Instruct</b></td>
+    <td style="text-align:center; background-color: #DAE8FF; color: black;">24.86</td>
+    <td style="text-align:center; background-color: #DAE8FF; color: black;">34.51</td>
+    <td style="text-align:center; background-color: #DAE8FF; color: black;">57.18</td>
+    <td style="text-align:center; background-color: #DAE8FF; color: black;">20.56</td>
+    <td style="text-align:center; background-color: #DAE8FF; color: black;">59.8</td>
+    <td style="text-align:center; background-color: #DAE8FF; color: black;">52.27</td>
+    <td style="text-align:center; background-color: #DAE8FF; color: black;">21.12</td>
+    <td style="text-align:center; background-color: #DAE8FF; color: black;">67.02</td>
+    <td style="text-align:center; background-color: #DAE8FF; color: black;">80.13</td>
+    <td style="text-align:center; background-color: #DAE8FF; color: black;">73.39</td>
+    <td style="text-align:center; background-color: #DAE8FF; color: black;">61.55</td>
+    <td style="text-align:center; background-color: #DAE8FF; color: black;">83.23</td>
+  </tr> 
+      
+
+
+     
+      
+</tbody></table>
+
+**Training Data:** 
+Overall, our training data is largely comprised of two key sources: (1) publicly available datasets with permissive license, (2) internal synthetically generated data targeted to enhance reasoning capabilites. 
+<!-- A detailed attribution of datasets can be found in [Granite 3.2 Technical Report (coming soon)](#), and [Accompanying Author List](https://github.com/ibm-granite/granite-3.0-language-models/blob/main/author-ack.pdf). -->
+
+**Infrastructure:**
+We train Granite-3.2-2B-Instruct using IBM's super computing cluster, Blue Vela, which is outfitted with NVIDIA H100 GPUs. This cluster provides a scalable and efficient infrastructure for training our models over thousands of GPUs.
+
+**Ethical Considerations and Limitations:** 
+Granite-3.2-2B-Instruct builds upon Granite-3.1-2B-Instruct, leveraging both permissively licensed open-source and select proprietary data for enhanced performance. Since it inherits its foundation from the previous model, all ethical considerations and limitations applicable to [Granite-3.1-2B-Instruct](https://huggingface.co/ibm-granite/granite-3.1-2b-instruct) remain relevant.
+
+
+**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},
+}
+``` -->