Update README.md

README.md

@@ -1,199 +1,274 @@
 ---
-library_name: transformers
-tags: []
+license: apache-2.0
+language:
+  - en
+  - fr
+  - de
+  - es
+  - it
+  - pt
+  - ru
+  - zh
+  - ja
+
+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>.
 ---
 
-# Model Card for Model ID
+# This is a (8bit, eetq) quantized version of [Mistral-Nemo-Instruct-2407](https://huggingface.co/mistralai/Mistral-Nemo-Instruct-2407).
+The original model card follows.
 
-<!-- Provide a quick summary of what the model is/does. -->
 
+# Model Card for Mistral-Nemo-Instruct-2407
 
+The Mistral-Nemo-Instruct-2407 Large Language Model (LLM) is an instruct fine-tuned version of the [Mistral-Nemo-Base-2407](https://huggingface.co/mistralai/Mistral-Nemo-Base-2407). Trained jointly by Mistral AI and NVIDIA, it significantly outperforms existing models smaller or similar in size.
 
-## Model Details
+For more details about this model please refer to our release [blog post](https://mistral.ai/news/mistral-nemo/).
 
-### Model Description
+## Key features
+- Released under the **Apache 2 License**
+- Pre-trained and instructed versions
+- Trained with a **128k context window**
+- Trained on a large proportion of **multilingual and code data**
+- Drop-in replacement of Mistral 7B
 
-<!-- Provide a longer summary of what this model is. -->
+## Model Architecture
+Mistral Nemo is a transformer model, with the following architecture choices:
+- **Layers:** 40
+- **Dim:** 5,120
+- **Head dim:** 128
+- **Hidden dim:** 14,336
+- **Activation Function:** SwiGLU
+- **Number of heads:** 32
+- **Number of kv-heads:** 8 (GQA)
+- **Vocabulary size:** 2**17 ~= 128k
+- **Rotary embeddings (theta = 1M)**
 
-This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
+## Metrics
 
-- **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]
+### Main Benchmarks
 
-### Model Sources [optional]
+| Benchmark | Score |
+| --- | --- |
+| HellaSwag (0-shot) | 83.5% |
+| Winogrande (0-shot) | 76.8% |
+| OpenBookQA (0-shot) | 60.6% |
+| CommonSenseQA (0-shot) | 70.4% |
+| TruthfulQA (0-shot) | 50.3% |
+| MMLU (5-shot) | 68.0% |
+| TriviaQA (5-shot) | 73.8% |
+| NaturalQuestions (5-shot) | 31.2% |
 
-<!-- Provide the basic links for the model. -->
+### Multilingual Benchmarks (MMLU)
 
-- **Repository:** [More Information Needed]
-- **Paper [optional]:** [More Information Needed]
-- **Demo [optional]:** [More Information Needed]
+| Language | Score |
+| --- | --- |
+| French | 62.3% |
+| German | 62.7% |
+| Spanish | 64.6% |
+| Italian | 61.3% |
+| Portuguese | 63.3% |
+| Russian | 59.2% |
+| Chinese | 59.0% |
+| Japanese | 59.0% |
 
-## Uses
+## Usage
 
-<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+The model can be used with three different frameworks
 
-### Direct Use
+- [`mistral_inference`](https://github.com/mistralai/mistral-inference): See [here](https://huggingface.co/mistralai/Mistral-Nemo-Instruct-2407#mistral-inference)
+- [`transformers`](https://github.com/huggingface/transformers): See [here](#transformers)
+- [`NeMo`](https://github.com/NVIDIA/NeMo): See [nvidia/Mistral-NeMo-12B-Instruct](https://huggingface.co/nvidia/Mistral-NeMo-12B-Instruct)
 
-<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+### Mistral Inference
 
-[More Information Needed]
+#### Install
 
-### Downstream Use [optional]
+It is recommended to use `mistralai/Mistral-Nemo-Instruct-2407` with [mistral-inference](https://github.com/mistralai/mistral-inference). For HF transformers code snippets, please keep scrolling.
 
-<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+```
+pip install mistral_inference
+```
 
-[More Information Needed]
+#### Download
 
-### Out-of-Scope Use
+```py
+from huggingface_hub import snapshot_download
+from pathlib import Path
 
-<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+mistral_models_path = Path.home().joinpath('mistral_models', 'Nemo-Instruct')
+mistral_models_path.mkdir(parents=True, exist_ok=True)
 
-[More Information Needed]
+snapshot_download(repo_id="mistralai/Mistral-Nemo-Instruct-2407", allow_patterns=["params.json", "consolidated.safetensors", "tekken.json"], local_dir=mistral_models_path)
+```
 
-## Bias, Risks, and Limitations
+#### Chat
 
-<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+After installing `mistral_inference`, a `mistral-chat` CLI command should be available in your environment. You can chat with the model using
 
-[More Information Needed]
+```
+mistral-chat $HOME/mistral_models/Nemo-Instruct --instruct --max_tokens 256 --temperature 0.35
+```
 
-### Recommendations
+*E.g.* Try out something like:
+```
+How expensive would it be to ask a window cleaner to clean all windows in Paris. Make a reasonable guess in US Dollar.
+```
 
-<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+#### Instruct following
 
-Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+```py
+from mistral_inference.transformer import Transformer
+from mistral_inference.generate import generate
 
-## How to Get Started with the Model
+from mistral_common.tokens.tokenizers.mistral import MistralTokenizer
+from mistral_common.protocol.instruct.messages import UserMessage
+from mistral_common.protocol.instruct.request import ChatCompletionRequest
+
+tokenizer = MistralTokenizer.from_file(f"{mistral_models_path}/tekken.json")
+model = Transformer.from_folder(mistral_models_path)
+
+prompt = "How expensive would it be to ask a window cleaner to clean all windows in Paris. Make a reasonable guess in US Dollar."
 
-Use the code below to get started with the model.
+completion_request = ChatCompletionRequest(messages=[UserMessage(content=prompt)])
 
-[More Information Needed]
+tokens = tokenizer.encode_chat_completion(completion_request).tokens
+
+out_tokens, _ = generate([tokens], model, max_tokens=64, temperature=0.35, eos_id=tokenizer.instruct_tokenizer.tokenizer.eos_id)
+result = tokenizer.decode(out_tokens[0])
 
-## Training Details
+print(result)
+```
 
-### Training Data
+#### Function calling
 
-<!-- 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. -->
+```py
+from mistral_common.protocol.instruct.tool_calls import Function, Tool
+from mistral_inference.transformer import Transformer
+from mistral_inference.generate import generate
 
-[More Information Needed]
+from mistral_common.tokens.tokenizers.mistral import MistralTokenizer
+from mistral_common.protocol.instruct.messages import UserMessage
+from mistral_common.protocol.instruct.request import ChatCompletionRequest
 
-### Training Procedure
 
-<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+tokenizer = MistralTokenizer.from_file(f"{mistral_models_path}/tekken.json")
+model = Transformer.from_folder(mistral_models_path)
 
-#### Preprocessing [optional]
+completion_request = ChatCompletionRequest(
+    tools=[
+        Tool(
+            function=Function(
+                name="get_current_weather",
+                description="Get the current weather",
+                parameters={
+                    "type": "object",
+                    "properties": {
+                        "location": {
+                            "type": "string",
+                            "description": "The city and state, e.g. San Francisco, CA",
+                        },
+                        "format": {
+                            "type": "string",
+                            "enum": ["celsius", "fahrenheit"],
+                            "description": "The temperature unit to use. Infer this from the users location.",
+                        },
+                    },
+                    "required": ["location", "format"],
+                },
+            )
+        )
+    ],
+    messages=[
+        UserMessage(content="What's the weather like today in Paris?"),
+        ],
+)
 
-[More Information Needed]
+tokens = tokenizer.encode_chat_completion(completion_request).tokens
 
+out_tokens, _ = generate([tokens], model, max_tokens=256, temperature=0.35, eos_id=tokenizer.instruct_tokenizer.tokenizer.eos_id)
+result = tokenizer.decode(out_tokens[0])
 
-#### Training Hyperparameters
+print(result)
+```
 
-- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+### Transformers
 
-#### Speeds, Sizes, Times [optional]
+> [!IMPORTANT]
+> NOTE: Until a new release has been made, you need to install transformers from source:
+> ```sh
+> pip install git+https://github.com/huggingface/transformers.git
+> ```
 
-<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+If you want to use Hugging Face `transformers` to generate text, you can do something like this.
 
-[More Information Needed]
+```py
+from transformers import pipeline
 
-## Evaluation
+messages = [
+    {"role": "system", "content": "You are a pirate chatbot who always responds in pirate speak!"},
+    {"role": "user", "content": "Who are you?"},
+]
+chatbot = pipeline("text-generation", model="mistralai/Mistral-Nemo-Instruct-2407",max_new_tokens=128)
+chatbot(messages)
+```
 
-<!-- This section describes the evaluation protocols and provides the results. -->
+## Function calling with `transformers`
 
-### Testing Data, Factors & Metrics
+To use this example, you'll need `transformers` version 4.42.0 or higher. Please see the 
+[function calling guide](https://huggingface.co/docs/transformers/main/chat_templating#advanced-tool-use--function-calling)
+in the `transformers` docs for more information.
 
-#### Testing Data
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+import torch
 
-<!-- This should link to a Dataset Card if possible. -->
+model_id = "mistralai/Mistral-Nemo-Instruct-2407"
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+
+def get_current_weather(location: str, format: str):
+    """
+    Get the current weather
+
+    Args:
+        location: The city and state, e.g. San Francisco, CA
+        format: The temperature unit to use. Infer this from the users location. (choices: ["celsius", "fahrenheit"])
+    """
+    pass
+
+conversation = [{"role": "user", "content": "What's the weather like in Paris?"}]
+tools = [get_current_weather]
+
+# render the tool use prompt as a string:
+tool_use_prompt = tokenizer.apply_chat_template(
+            conversation,
+            tools=tools,
+            tokenize=False,
+            add_generation_prompt=True,
+)
+
+inputs = tokenizer(tool_use_prompt, return_tensors="pt")
+
+model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")
+
+outputs = model.generate(**inputs, max_new_tokens=1000)
+print(tokenizer.decode(outputs[0], skip_special_tokens=True))
+```
+
+Note that, for reasons of space, this example does not show a complete cycle of calling a tool and adding the tool call and tool
+results to the chat history so that the model can use them in its next generation. For a full tool calling example, please
+see the [function calling guide](https://huggingface.co/docs/transformers/main/chat_templating#advanced-tool-use--function-calling), 
+and note that Mistral **does** use tool call IDs, so these must be included in your tool calls and tool results. They should be
+exactly 9 alphanumeric characters.
+
+> [!TIP]
+> Unlike previous Mistral models, Mistral Nemo requires smaller temperatures. We recommend to use a temperature of 0.3.
+
+## Limitations
+
+The Mistral Nemo Instruct model is a quick demonstration that the base model can be easily fine-tuned to achieve compelling performance. 
+It does not have any moderation mechanisms. We're looking forward to engaging with the community on ways to
+make the model finely respect guardrails, allowing for deployment in environments requiring moderated outputs.
+
+## The Mistral AI Team
 
-[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]
+Albert Jiang, Alexandre Sablayrolles, Alexis Tacnet, Alok Kothari, Antoine Roux, Arthur Mensch, Audrey Herblin-Stoop, Augustin Garreau, Austin Birky, Bam4d, Baptiste Bout, Baudouin de Monicault, Blanche Savary, Carole Rambaud, Caroline Feldman, Devendra Singh Chaplot, Diego de las Casas, Eleonore Arcelin, Emma Bou Hanna, Etienne Metzger, Gaspard Blanchet, Gianna Lengyel, Guillaume Bour, Guillaume Lample, Harizo Rajaona, Henri Roussez, Hichem Sattouf, Ian Mack, Jean-Malo Delignon, Jessica Chudnovsky, Justus Murke, Kartik Khandelwal, Lawrence Stewart, Louis Martin, Louis Ternon, Lucile Saulnier, Lélio Renard Lavaud, Margaret Jennings, Marie Pellat, Marie Torelli, Marie-Anne Lachaux, Marjorie Janiewicz, Mickaël Seznec, Nicolas Schuhl, Niklas Muhs, Olivier de Garrigues, Patrick von Platen, Paul Jacob, Pauline Buche, Pavan Kumar Reddy, Perry Savas, Pierre Stock, Romain Sauvestre, Sagar Vaze, Sandeep Subramanian, Saurabh Garg, Sophia Yang, Szymon Antoniak, Teven Le Scao, Thibault Schueller, Thibaut Lavril, Thomas Wang, Théophile Gervet, Timothée Lacroix, Valera Nemychnikova, Wendy Shang, William El Sayed, William Marshall