Upload README.md with huggingface_hub

README.md

@@ -1,199 +1,726 @@
 ---
-library_name: transformers
-tags: []
+library_name: vllm
+language:
+- en
+- fr
+- de
+- es
+- pt
+- it
+- ja
+- ko
+- ru
+- zh
+- ar
+- fa
+- id
+- ms
+- ne
+- pl
+- ro
+- sr
+- sv
+- tr
+- uk
+- vi
+- hi
+- bn
+license: apache-2.0
+inference: false
+base_model:
+- mistralai/Mistral-Small-3.1-24B-Base-2503
+extra_gated_description: If you want to learn more about how we process your personal
+  data, please read our <a href="https://mistral.ai/terms/">Privacy Policy</a>.
+tags:
+- mistral-common
+- heretic
+- uncensored
+- decensored
+- abliterated
 ---
+# This is a decensored version of [mistralai/Mistral-Small-3.2-24B-Instruct-2506](https://huggingface.co/mistralai/Mistral-Small-3.2-24B-Instruct-2506), made using [Heretic](https://github.com/p-e-w/heretic) v1.1.0
 
-# Model Card for Model ID
+## Abliteration parameters
 
-<!-- Provide a quick summary of what the model is/does. -->
+| Parameter | Value |
+| :-------- | :---: |
+| **direction_index** | per layer |
+| **attn.o_proj.max_weight** | 1.28 |
+| **attn.o_proj.max_weight_position** | 23.69 |
+| **attn.o_proj.min_weight** | 0.06 |
+| **attn.o_proj.min_weight_distance** | 6.19 |
+| **mlp.down_proj.max_weight** | 1.43 |
+| **mlp.down_proj.max_weight_position** | 24.70 |
+| **mlp.down_proj.min_weight** | 0.73 |
+| **mlp.down_proj.min_weight_distance** | 22.95 |
 
+## Performance
 
+| Metric | This model | Original model ([mistralai/Mistral-Small-3.2-24B-Instruct-2506](https://huggingface.co/mistralai/Mistral-Small-3.2-24B-Instruct-2506)) |
+| :----- | :--------: | :---------------------------: |
+| **KL divergence** | 0.1383 | 0 *(by definition)* |
+| **Refusals** | 5/100 | 97/100 |
 
-## Model Details
+-----
 
-### Model Description
 
-<!-- Provide a longer summary of what this model is. -->
+# Mistral-Small-3.2-24B-Instruct-2506
 
-This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
+Mistral-Small-3.2-24B-Instruct-2506 is a minor update of [Mistral-Small-3.1-24B-Instruct-2503](https://huggingface.co/mistralai/Mistral-Small-3.1-24B-Instruct-2503).
 
-- **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]
+Small-3.2 improves in the following categories:
+- **Instruction following**: Small-3.2 is better at following precise instructions
+- **Repetition errors**: Small-3.2 produces less infinite generations or repetitive answers
+- **Function calling**: Small-3.2's function calling template is more robust (see [here](https://github.com/mistralai/mistral-common/blob/535b4d0a0fc94674ea17db6cf8dc2079b81cbcfa/src/mistral_common/tokens/tokenizers/instruct.py#L778) and [examples](#function-calling))
 
-### Model Sources [optional]
+In all other categories Small-3.2 should match or slightly improve compared to [Mistral-Small-3.1-24B-Instruct-2503](https://huggingface.co/mistralai/Mistral-Small-3.1-24B-Instruct-2503).
 
-<!-- Provide the basic links for the model. -->
+## Key Features
+- same as [Mistral-Small-3.1-24B-Instruct-2503](https://huggingface.co/mistralai/Mistral-Small-3.1-24B-Instruct-2503#key-features)
 
-- **Repository:** [More Information Needed]
-- **Paper [optional]:** [More Information Needed]
-- **Demo [optional]:** [More Information Needed]
+## Benchmark Results
 
-## Uses
+We compare Mistral-Small-3.2-24B to [Mistral-Small-3.1-24B-Instruct-2503](https://huggingface.co/mistralai/Mistral-Small-3.1-24B-Instruct-2503).
+For more comparison against other models of similar size, please check [Mistral-Small-3.1's Benchmarks'](https://huggingface.co/mistralai/Mistral-Small-3.1-24B-Instruct-2503#benchmark-results)
 
-<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+### Text 
 
-### Direct Use
+#### Instruction Following / Chat / Tone
 
-<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+| Model | Wildbench v2 | Arena Hard v2 | IF (Internal; accuracy) |
+|-------|---------------|---------------|------------------------|
+| Small 3.1 24B Instruct | 55.6% | 19.56% | 82.75% |
+| **Small 3.2 24B Instruct** | **65.33%** | **43.1%** | **84.78%** |
 
-[More Information Needed]
+#### Infinite Generations
 
-### Downstream Use [optional]
+Small 3.2 reduces infinite generations by 2x on challenging, long and repetitive prompts.
 
-<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+| Model | Infinite Generations (Internal; Lower is better) |
+|-------|-------|
+| Small 3.1 24B Instruct | 2.11% |
+| **Small 3.2 24B Instruct** | **1.29%** |
 
-[More Information Needed]
+#### STEM
 
-### Out-of-Scope Use
+| Model                          | MMLU      | MMLU Pro (5-shot CoT) | MATH                   | GPQA Main (5-shot CoT) | GPQA Diamond (5-shot CoT )| MBPP Plus - Pass@5 | HumanEval Plus - Pass@5 | SimpleQA (TotalAcc)|
+|--------------------------------|-----------|-----------------------|------------------------|------------------------|---------------------------|--------------------|-------------------------|--------------------|
+| Small 3.1 24B Instruct         | 80.62%    | 66.76%                | 69.30%                 | 44.42%                 | 45.96%                    | 74.63%             | 88.99%                  | 10.43%             |
+| **Small 3.2 24B Instruct**     | 80.50%    | **69.06%**            | 69.42%                 | 44.22%                 | 46.13%                    | **78.33%**         | **92.90%**              | **12.10%**         |
 
-<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+### Vision
 
-[More Information Needed]
+| Model                          | MMMU       | Mathvista | ChartQA   | DocVQA    | AI2D      |
+|--------------------------------|------------|-----------|-----------|-----------|-----------|
+| Small 3.1 24B Instruct         | **64.00%** | **68.91%**| 86.24%    | 94.08%    | 93.72%  | 
+| **Small 3.2 24B Instruct**     | 62.50%     | 67.09%    | **87.4%** | 94.86%    | 92.91%  | 
 
-## Bias, Risks, and Limitations
 
-<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+## Usage
 
-[More Information Needed]
+The model can be used with the following frameworks;
+- [`vllm (recommended)`](https://github.com/vllm-project/vllm): See [here](#vllm-recommended)
+- [`transformers`](https://github.com/huggingface/transformers): See [here](#transformers)
 
-### Recommendations
+**Note 1**: We recommend using a relatively low temperature, such as `temperature=0.15`.
 
-<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+**Note 2**: Make sure to add a system prompt to the model to best tailor it to your needs. If you want to use the model as a general assistant, we recommend to use the one provided in the [SYSTEM_PROMPT.txt](https://huggingface.co/mistralai/Mistral-Small-3.2-24B-Instruct-2506/blob/main/SYSTEM_PROMPT.txt) file.
 
-Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+### vLLM (recommended)
 
-## How to Get Started with the Model
+We recommend using this model with [vLLM](https://github.com/vllm-project/vllm).
 
-Use the code below to get started with the model.
+#### Installation
 
-[More Information Needed]
+Make sure to install [`vLLM >= 0.9.1`](https://github.com/vllm-project/vllm/releases/tag/v0.9.1):
 
-## Training Details
+```
+pip install vllm --upgrade
+```
 
-### Training Data
+Doing so should automatically install [`mistral_common >= 1.6.2`](https://github.com/mistralai/mistral-common/releases/tag/v1.6.2).
 
-<!-- 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. -->
+To check:
+```
+python -c "import mistral_common; print(mistral_common.__version__)"
+```
 
-[More Information Needed]
+You can also make use of a ready-to-go [docker image](https://github.com/vllm-project/vllm/blob/main/Dockerfile) or on the [docker hub](https://hub.docker.com/layers/vllm/vllm-openai/latest/images/sha256-de9032a92ffea7b5c007dad80b38fd44aac11eddc31c435f8e52f3b7404bbf39).
 
-### Training Procedure
+#### Serve
 
-<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+We recommend that you use Mistral-Small-3.2-24B-Instruct-2506 in a server/client setting. 
 
-#### Preprocessing [optional]
+1. Spin up a server:
 
-[More Information Needed]
+```
+vllm serve mistralai/Mistral-Small-3.2-24B-Instruct-2506 \
+  --tokenizer_mode mistral --config_format mistral \
+  --load_format mistral --tool-call-parser mistral \
+  --enable-auto-tool-choice --limit-mm-per-prompt '{"image":10}' \
+  --tensor-parallel-size 2
+```
 
+**Note:** Running Mistral-Small-3.2-24B-Instruct-2506 on GPU requires ~55 GB of GPU RAM in bf16 or fp16. 
 
-#### 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 -->
+2. To ping the client you can use a simple Python snippet. See the following examples.
 
-#### Speeds, Sizes, Times [optional]
 
-<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+#### Vision reasoning
 
-[More Information Needed]
+Leverage the vision capabilities of Mistral-Small-3.2-24B-Instruct-2506 to make the best choice given a scenario, go catch them all !
 
-## Evaluation
+<details>
+  <summary>Python snippet</summary>
 
-<!-- This section describes the evaluation protocols and provides the results. -->
+```py
+from datetime import datetime, timedelta
 
-### Testing Data, Factors & Metrics
+from openai import OpenAI
+from huggingface_hub import hf_hub_download
 
-#### Testing Data
+# Modify OpenAI's API key and API base to use vLLM's API server.
+openai_api_key = "EMPTY"
+openai_api_base = "http://localhost:8000/v1"
 
-<!-- This should link to a Dataset Card if possible. -->
+TEMP = 0.15
+MAX_TOK = 131072
 
-[More Information Needed]
+client = OpenAI(
+    api_key=openai_api_key,
+    base_url=openai_api_base,
+)
 
-#### Factors
+models = client.models.list()
+model = models.data[0].id
 
-<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
 
-[More Information Needed]
+def load_system_prompt(repo_id: str, filename: str) -> str:
+    file_path = hf_hub_download(repo_id=repo_id, filename=filename)
+    with open(file_path, "r") as file:
+        system_prompt = file.read()
+    today = datetime.today().strftime("%Y-%m-%d")
+    yesterday = (datetime.today() - timedelta(days=1)).strftime("%Y-%m-%d")
+    model_name = repo_id.split("/")[-1]
+    return system_prompt.format(name=model_name, today=today, yesterday=yesterday)
 
-#### Metrics
 
-<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+model_id = "mistralai/Mistral-Small-3.2-24B-Instruct-2506"
+SYSTEM_PROMPT = load_system_prompt(model_id, "SYSTEM_PROMPT.txt")
+image_url = "https://static.wikia.nocookie.net/essentialsdocs/images/7/70/Battle.png/revision/latest?cb=20220523172438"
 
-[More Information Needed]
+messages = [
+    {"role": "system", "content": SYSTEM_PROMPT},
+    {
+        "role": "user",
+        "content": [
+            {
+                "type": "text",
+                "text": "What action do you think I should take in this situation? List all the possible actions and explain why you think they are good or bad.",
+            },
+            {"type": "image_url", "image_url": {"url": image_url}},
+        ],
+    },
+]
 
-### Results
 
-[More Information Needed]
+response = client.chat.completions.create(
+    model=model,
+    messages=messages,
+    temperature=TEMP,
+    max_tokens=MAX_TOK,
+)
+
+print(response.choices[0].message.content)
+# In this situation, you are playing a Pokémon game where your Pikachu (Level 42) is facing a wild Pidgey (Level 17). Here are the possible actions you can take and an analysis of each:
+
+# 1. **FIGHT**:
+#    - **Pros**: Pikachu is significantly higher level than the wild Pidgey, which suggests that it should be able to defeat Pidgey easily. This could be a good opportunity to gain experience points and possibly items or money.
+#    - **Cons**: There is always a small risk of Pikachu fainting, especially if Pidgey has a powerful move or a status effect that could hinder Pikachu. However, given the large level difference, this risk is minimal.
+
+# 2. **BAG**:
+#    - **Pros**: You might have items in your bag that could help in this battle, such as Potions, Poké Balls, or Berries. Using an item could help you capture the Pidgey or heal your Pikachu if needed.
+#    - **Cons**: Using items might not be necessary given the level difference. It could be more efficient to just fight and defeat the Pidgey quickly.
+
+# 3. **POKÉMON**:
+#    - **Pros**: You might have another Pokémon in your party that is better suited for this battle or that you want to gain experience. Switching Pokémon could also be a strategic move if you want to train a lower-level Pokémon.
+#    - **Cons**: Switching Pokémon might not be necessary since Pikachu is at a significant advantage. It could also waste time and potentially give Pidgey a turn to attack.
+
+# 4. **RUN**:
+#    - **Pros**: Running away could save time and conserve your Pokémon's health and resources. If you are in a hurry or do not need the experience or items, running away is a safe option.
+#    - **Cons**: Running away means you miss out on the experience points and potential items or money that you could gain from defeating the Pidgey. It also means you do not get the chance to capture the Pidgey if you wanted to.
+
+# ### Recommendation:
+# Given the significant level advantage, the best action is likely to **FIGHT**. This will allow you to quickly defeat the Pidgey, gain experience points, and potentially earn items or money. If you are concerned about Pikachu's health, you could use an item from your **BAG** to heal it before or during the battle. Running away or switching Pokémon does not seem necessary in this situation.
+```
+</details>
+
+#### Function calling
+
+Mistral-Small-3.2-24B-Instruct-2506 is excellent at function / tool calling tasks via vLLM. *E.g.:*
+
+<details>
+  <summary>Python snippet - easy</summary>
+
+```py
+from openai import OpenAI
+from huggingface_hub import hf_hub_download
+
+# Modify OpenAI's API key and API base to use vLLM's API server.
+openai_api_key = "EMPTY"
+openai_api_base = "http://localhost:8000/v1"
+
+TEMP = 0.15
+MAX_TOK = 131072
+
+client = OpenAI(
+    api_key=openai_api_key,
+    base_url=openai_api_base,
+)
+
+models = client.models.list()
+model = models.data[0].id
+
+def load_system_prompt(repo_id: str, filename: str) -> str:
+    file_path = hf_hub_download(repo_id=repo_id, filename=filename)
+    with open(file_path, "r") as file:
+        system_prompt = file.read()
+    return system_prompt
+
+model_id = "mistralai/Mistral-Small-3.2-24B-Instruct-2506"
+SYSTEM_PROMPT = load_system_prompt(model_id, "SYSTEM_PROMPT.txt")
+
+image_url = "https://huggingface.co/datasets/patrickvonplaten/random_img/resolve/main/europe.png"
+
+tools = [
+    {
+        "type": "function",
+        "function": {
+            "name": "get_current_population",
+            "description": "Get the up-to-date population of a given country.",
+            "parameters": {
+                "type": "object",
+                "properties": {
+                    "country": {
+                        "type": "string",
+                        "description": "The country to find the population of.",
+                    },
+                    "unit": {
+                        "type": "string",
+                        "description": "The unit for the population.",
+                        "enum": ["millions", "thousands"],
+                    },
+                },
+                "required": ["country", "unit"],
+            },
+        },
+    },
+    {
+        "type": "function",
+        "function": {
+            "name": "rewrite",
+            "description": "Rewrite a given text for improved clarity",
+            "parameters": {
+                "type": "object",
+                "properties": {
+                    "text": {
+                        "type": "string",
+                        "description": "The input text to rewrite",
+                    }
+                },
+            },
+        },
+    },
+]
+
+messages = [
+    {"role": "system", "content": SYSTEM_PROMPT},
+    {
+        "role": "user",
+        "content": "Could you please make the below article more concise?\n\nOpenAI is an artificial intelligence research laboratory consisting of the non-profit OpenAI Incorporated and its for-profit subsidiary corporation OpenAI Limited Partnership.",
+    },
+    {
+        "role": "assistant",
+        "content": "",
+        "tool_calls": [
+            {
+                "id": "bbc5b7ede",
+                "type": "function",
+                "function": {
+                    "name": "rewrite",
+                    "arguments": '{"text": "OpenAI is an artificial intelligence research laboratory consisting of the non-profit OpenAI Incorporated and its for-profit subsidiary corporation OpenAI Limited Partnership."}',
+                },
+            }
+        ],
+    },
+    {
+        "role": "tool",
+        "content": '{"action":"rewrite","outcome":"OpenAI is a FOR-profit company."}',
+        "tool_call_id": "bbc5b7ede",
+        "name": "rewrite",
+    },
+    {
+        "role": "assistant",
+        "content": "---\n\nOpenAI is a FOR-profit company.",
+    },
+    {
+        "role": "user",
+        "content": [
+            {
+                "type": "text",
+                "text": "Can you tell me what is the biggest country depicted on the map?",
+            },
+            {
+                "type": "image_url",
+                "image_url": {
+                    "url": image_url,
+                },
+            },
+        ],
+    }
+]
+
+response = client.chat.completions.create(
+    model=model,
+    messages=messages,
+    temperature=TEMP,
+    max_tokens=MAX_TOK,
+    tools=tools,
+    tool_choice="auto",
+)
+
+assistant_message = response.choices[0].message.content
+print(assistant_message)
+# The biggest country depicted on the map is Russia.
+
+messages.extend([
+    {"role": "assistant", "content": assistant_message},
+    {"role": "user", "content": "What is the population of that country in millions?"},
+])
+
+response = client.chat.completions.create(
+    model=model,
+    messages=messages,
+    temperature=TEMP,
+    max_tokens=MAX_TOK,
+    tools=tools,
+    tool_choice="auto",
+)
+
+print(response.choices[0].message.tool_calls)
+# [ChatCompletionMessageToolCall(id='3e92V6Vfo', function=Function(arguments='{"country": "Russia", "unit": "millions"}', name='get_current_population'), type='function')]
+```
+
+</details>
+
+<details>
+  <summary>Python snippet - complex</summary>
+
+```python
+import json
+from openai import OpenAI
+from huggingface_hub import hf_hub_download
+
+# Modify OpenAI's API key and API base to use vLLM's API server.
+openai_api_key = "EMPTY"
+openai_api_base = "http://localhost:8000/v1"
+
+TEMP = 0.15
+MAX_TOK = 131072
+
+client = OpenAI(
+    api_key=openai_api_key,
+    base_url=openai_api_base,
+)
+
+models = client.models.list()
+model = models.data[0].id
+
+
+def load_system_prompt(repo_id: str, filename: str) -> str:
+    file_path = hf_hub_download(repo_id=repo_id, filename=filename)
+    with open(file_path, "r") as file:
+        system_prompt = file.read()
+    return system_prompt
+
+
+model_id = "mistralai/Mistral-Small-3.2-24B-Instruct-2506"
+SYSTEM_PROMPT = load_system_prompt(model_id, "SYSTEM_PROMPT.txt")
+
+image_url = "https://math-coaching.com/img/fiche/46/expressions-mathematiques.jpg"
+
+
+def my_calculator(expression: str) -> str:
+    return str(eval(expression))
+
+
+tools = [
+    {
+        "type": "function",
+        "function": {
+            "name": "my_calculator",
+            "description": "A calculator that can evaluate a mathematical expression.",
+            "parameters": {
+                "type": "object",
+                "properties": {
+                    "expression": {
+                        "type": "string",
+                        "description": "The mathematical expression to evaluate.",
+                    },
+                },
+                "required": ["expression"],
+            },
+        },
+    },
+    {
+        "type": "function",
+        "function": {
+            "name": "rewrite",
+            "description": "Rewrite a given text for improved clarity",
+            "parameters": {
+                "type": "object",
+                "properties": {
+                    "text": {
+                        "type": "string",
+                        "description": "The input text to rewrite",
+                    }
+                },
+            },
+        },
+    },
+]
+
+messages = [
+    {"role": "system", "content": SYSTEM_PROMPT},
+    {
+        "role": "user",
+        "content": [
+            {
+                "type": "text",
+                "text": "Can you calculate the results for all the equations displayed in the image? Only compute the ones that involve numbers.",
+            },
+            {
+                "type": "image_url",
+                "image_url": {
+                    "url": image_url,
+                },
+            },
+        ],
+    },
+]
+
+response = client.chat.completions.create(
+    model=model,
+    messages=messages,
+    temperature=TEMP,
+    max_tokens=MAX_TOK,
+    tools=tools,
+    tool_choice="auto",
+)
+
+tool_calls = response.choices[0].message.tool_calls
+print(tool_calls)
+# [ChatCompletionMessageToolCall(id='CyQBSAtGh', function=Function(arguments='{"expression": "6 + 2 * 3"}', name='my_calculator'), type='function'), ChatCompletionMessageToolCall(id='KQqRCqvzc', function=Function(arguments='{"expression": "19 - (8 + 2) + 1"}', name='my_calculator'), type='function')]
+
+results = []
+for tool_call in tool_calls:
+    function_name = tool_call.function.name
+    function_args = tool_call.function.arguments
+    if function_name == "my_calculator":
+        result = my_calculator(**json.loads(function_args))
+        results.append(result)
+
+messages.append({"role": "assistant", "tool_calls": tool_calls})
+for tool_call, result in zip(tool_calls, results):
+    messages.append(
+        {
+            "role": "tool",
+            "tool_call_id": tool_call.id,
+            "name": tool_call.function.name,
+            "content": result,
+        }
+    )
+
+
+response = client.chat.completions.create(
+    model=model,
+    messages=messages,
+    temperature=TEMP,
+    max_tokens=MAX_TOK,
+)
+
+print(response.choices[0].message.content)
+# Here are the results for the equations that involve numbers:
+
+# 1. \( 6 + 2 \times 3 = 12 \)
+# 3. \( 19 - (8 + 2) + 1 = 10 \)
+
+# For the other equations, you need to substitute the variables with specific values to compute the results.
+```
+
+</details>
+
+#### Instruction following
+
+Mistral-Small-3.2-24B-Instruct-2506 will follow your instructions down to the last letter ! 
+
+<details>
+  <summary>Python snippet</summary>
+
+```python
+from openai import OpenAI
+from huggingface_hub import hf_hub_download
+
+# Modify OpenAI's API key and API base to use vLLM's API server.
+openai_api_key = "EMPTY"
+openai_api_base = "http://localhost:8000/v1"
+
+TEMP = 0.15
+MAX_TOK = 131072
+
+client = OpenAI(
+    api_key=openai_api_key,
+    base_url=openai_api_base,
+)
+
+models = client.models.list()
+model = models.data[0].id
+
+
+def load_system_prompt(repo_id: str, filename: str) -> str:
+    file_path = hf_hub_download(repo_id=repo_id, filename=filename)
+    with open(file_path, "r") as file:
+        system_prompt = file.read()
+    return system_prompt
+
+
+model_id = "mistralai/Mistral-Small-3.2-24B-Instruct-2506"
+SYSTEM_PROMPT = load_system_prompt(model_id, "SYSTEM_PROMPT.txt")
+
+messages = [
+    {"role": "system", "content": SYSTEM_PROMPT},
+    {
+        "role": "user",
+        "content": "Write me a sentence where every word starts with the next letter in the alphabet - start with 'a' and end with 'z'.",
+    },
+]
+
+response = client.chat.completions.create(
+    model=model,
+    messages=messages,
+    temperature=TEMP,
+    max_tokens=MAX_TOK,
+)
 
-#### Summary
+assistant_message = response.choices[0].message.content
+print(assistant_message)
 
+# Here's a sentence where each word starts with the next letter of the alphabet, starting from 'a' and ending with 'z':
 
+# "Always brave cats dance elegantly, fluffy giraffes happily ignore jungle kites, lovingly munching nuts, observing playful quails racing swiftly, tiny unicorns vaulting while xylophones yodel zealously."
 
-## Model Examination [optional]
+# This sentence follows the sequence from A to Z without skipping any letters.
+```
+</details>
 
-<!-- Relevant interpretability work for the model goes here -->
+### Transformers
 
-[More Information Needed]
+You can also use Mistral-Small-3.2-24B-Instruct-2506 with `Transformers` !
 
-## Environmental Impact
+To make the best use of our model with `Transformers` make sure to have [installed](https://github.com/mistralai/mistral-common) `mistral-common >= 1.6.2` to use our tokenizer.
 
-<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+```bash
+pip install mistral-common --upgrade
+```
 
-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).
+Then load our tokenizer along with the model and generate:
 
-- **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]
+<details>
+  <summary>Python snippet</summary>
 
-## Technical Specifications [optional]
+```python
+from datetime import datetime, timedelta
+import torch
 
-### Model Architecture and Objective
+from mistral_common.protocol.instruct.request import ChatCompletionRequest
+from mistral_common.tokens.tokenizers.mistral import MistralTokenizer
+from huggingface_hub import hf_hub_download
+from transformers import Mistral3ForConditionalGeneration
 
-[More Information Needed]
 
-### Compute Infrastructure
+def load_system_prompt(repo_id: str, filename: str) -> str:
+    file_path = hf_hub_download(repo_id=repo_id, filename=filename)
+    with open(file_path, "r") as file:
+        system_prompt = file.read()
+    today = datetime.today().strftime("%Y-%m-%d")
+    yesterday = (datetime.today() - timedelta(days=1)).strftime("%Y-%m-%d")
+    model_name = repo_id.split("/")[-1]
+    return system_prompt.format(name=model_name, today=today, yesterday=yesterday)
 
-[More Information Needed]
 
-#### Hardware
+model_id = "mistralai/Mistral-Small-3.2-24B-Instruct-2506"
+SYSTEM_PROMPT = load_system_prompt(model_id, "SYSTEM_PROMPT.txt")
 
-[More Information Needed]
+tokenizer = MistralTokenizer.from_hf_hub(model_id)
 
-#### Software
+model = Mistral3ForConditionalGeneration.from_pretrained(
+    model_id, torch_dtype=torch.bfloat16
+)
 
-[More Information Needed]
+image_url = "https://static.wikia.nocookie.net/essentialsdocs/images/7/70/Battle.png/revision/latest?cb=20220523172438"
 
-## Citation [optional]
+messages = [
+    {"role": "system", "content": SYSTEM_PROMPT},
+    {
+        "role": "user",
+        "content": [
+            {
+                "type": "text",
+                "text": "What action do you think I should take in this situation? List all the possible actions and explain why you think they are good or bad.",
+            },
+            {"type": "image_url", "image_url": {"url": image_url}},
+        ],
+    },
+]
 
-<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+tokenized = tokenizer.encode_chat_completion(ChatCompletionRequest(messages=messages))
 
-**BibTeX:**
+input_ids = torch.tensor([tokenized.tokens])
+attention_mask = torch.ones_like(input_ids)
+pixel_values = torch.tensor(tokenized.images[0], dtype=torch.bfloat16).unsqueeze(0)
+image_sizes = torch.tensor([pixel_values.shape[-2:]])
 
-[More Information Needed]
+output = model.generate(
+    input_ids=input_ids,
+    attention_mask=attention_mask,
+    pixel_values=pixel_values,
+    image_sizes=image_sizes,
+    max_new_tokens=1000,
+)[0]
 
-**APA:**
+decoded_output = tokenizer.decode(output[len(tokenized.tokens) :])
+print(decoded_output)
+# In this situation, you are playing a Pokémon game where your Pikachu (Level 42) is facing a wild Pidgey (Level 17). Here are the possible actions you can take and an analysis of each:
 
-[More Information Needed]
+# 1. **FIGHT**:
+#    - **Pros**: Pikachu is significantly higher level than the wild Pidgey, which suggests that it should be able to defeat Pidgey easily. This could be a good opportunity to gain experience points and possibly items or money.
+#    - **Cons**: There is always a small risk of Pikachu fainting, especially if Pidgey has a powerful move or a status effect that could hinder Pikachu. However, given the large level difference, this risk is minimal.
 
-## Glossary [optional]
+# 2. **BAG**:
+#    - **Pros**: You might have items in your bag that could help in this battle, such as Potions, Poké Balls, or Berries. Using an item could help you capture Pidgey or heal Pikachu if needed.
+#    - **Cons**: Using items might not be necessary given the level difference. It could be more efficient to just fight and defeat Pidgey quickly.
 
-<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+# 3. **POKÉMON**:
+#    - **Pros**: You might have another Pokémon in your party that is better suited for this battle or that you want to gain experience. Switching Pokémon could also be strategic if you want to train a lower-level Pokémon.
+#    - **Cons**: Switching Pokémon might not be necessary since Pikachu is at a significant advantage. It could also waste time and potentially give Pidgey a turn to attack.
 
-[More Information Needed]
+# 4. **RUN**:
+#    - **Pros**: Running away could be a quick way to avoid the battle altogether. This might be useful if you are trying to conserve resources or if you are in a hurry to get to another location.
+#    - **Cons**: Running away means you miss out on the experience points, items, or money that you could gain from defeating Pidgey. It also might not be the most efficient use of your time if you are trying to train your Pokémon.
 
-## More Information [optional]
+# ### Recommendation:
+# Given the significant level advantage, the best action to take is likely **FIGHT**. This will allow you to quickly defeat Pidgey and gain experience points for Pikachu. If you are concerned about Pikachu's health, you could use the **BAG** to heal Pikachu before or during the battle. Running away or switching Pokémon does not seem necessary in this situation.
+```
 
-[More Information Needed]
-
-## Model Card Authors [optional]
-
-[More Information Needed]
-
-## Model Card Contact
-
-[More Information Needed]
+</details>