Update README.md

README.md

@@ -1,199 +1,292 @@
 ---
-library_name: transformers
-tags: []
+base_model: mistralai/Mistral-Small-Instruct-2409
+license: other
+license_name: mrl
+license_link: https://mistral.ai/licenses/MRL-0.1.md
+tags:
+- unsloth
+- mistral
 ---
 
-# Model Card for Model ID
 
-<!-- Provide a quick summary of what the model is/does. -->
+# Finetune Llama 3.1, Gemma 2, Mistral 2-5x faster with 70% less memory via Unsloth!
 
+We have a free Google Colab Tesla T4 notebook for Llama 3.1 (8B) here: https://colab.research.google.com/drive/1Ys44kVvmeZtnICzWz0xgpRnrIOjZAuxp?usp=sharing
 
+[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/Discord%20button.png" width="200"/>](https://discord.gg/unsloth)
+[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
 
-## Model Details
+## ✨ Finetune for Free
 
-### Model Description
+All notebooks are **beginner friendly**! Add your dataset, click "Run All", and you'll get a 2x faster finetuned model which can be exported to GGUF, vLLM or uploaded to Hugging Face.
 
-<!-- Provide a longer summary of what this model is. -->
+| Unsloth supports          |    Free Notebooks                                                                                           | Performance | Memory use |
+|-----------------|--------------------------------------------------------------------------------------------------------------------------|-------------|----------|
+| **Llama-3.1 8b**      | [▶️ Start on Colab](https://colab.research.google.com/drive/1Ys44kVvmeZtnICzWz0xgpRnrIOjZAuxp?usp=sharing)               | 2.4x faster | 58% less |
+| **Phi-3.5 (mini)** | [▶️ Start on Colab](https://colab.research.google.com/drive/1lN6hPQveB_mHSnTOYifygFcrO8C1bxq4?usp=sharing)               | 2x faster | 50% less |
+| **Gemma-2 9b**      | [▶️ Start on Colab](https://colab.research.google.com/drive/1vIrqH5uYDQwsJ4-OO3DErvuv4pBgVwk4?usp=sharing)               | 2.4x faster | 58% less |
+| **Mistral 7b**    | [▶️ Start on Colab](https://colab.research.google.com/drive/1Dyauq4kTZoLewQ1cApceUQVNcnnNTzg_?usp=sharing)               | 2.2x faster | 62% less |
+| **TinyLlama**  | [▶️ Start on Colab](https://colab.research.google.com/drive/1AZghoNBQaMDgWJpi4RbffGM1h6raLUj9?usp=sharing)              | 3.9x faster | 74% less |
+| **DPO - Zephyr**     | [▶️ Start on Colab](https://colab.research.google.com/drive/15vttTpzzVXv_tJwEk-hIcQ0S9FcEWvwP?usp=sharing)               | 1.9x faster | 19% less |
 
-This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
+- This [conversational notebook](https://colab.research.google.com/drive/1Aau3lgPzeZKQ-98h69CCu1UJcvIBLmy2?usp=sharing) is useful for ShareGPT ChatML / Vicuna templates.
+- This [text completion notebook](https://colab.research.google.com/drive/1ef-tab5bhkvWmBOObepl1WgJvfvSzn5Q?usp=sharing) is for raw text. This [DPO notebook](https://colab.research.google.com/drive/15vttTpzzVXv_tJwEk-hIcQ0S9FcEWvwP?usp=sharing) replicates Zephyr.
+- \* Kaggle has 2x T4s, but we use 1. Due to overhead, 1x T4 is 5x faster.
 
-- **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]
+# Model Card for Mistral-Small-Instruct-2409
 
-<!-- Provide the basic links for the model. -->
+Mistral-Small-Instruct-2409 is an instruct fine-tuned version with the following characteristics:
 
-- **Repository:** [More Information Needed]
-- **Paper [optional]:** [More Information Needed]
-- **Demo [optional]:** [More Information Needed]
+- 22B parameters
+- Vocabulary to 32768
+- Supports function calling
+- 128k sequence length
 
-## Uses
+  
+## Usage Examples
 
-<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+### vLLM (recommended)
 
-### Direct Use
+We recommend using this model with the [vLLM library](https://github.com/vllm-project/vllm)
+to implement production-ready inference pipelines.
 
-<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+**_Installation_**
 
-[More Information Needed]
+Make sure you install `vLLM >= v0.6.1.post1`:
 
-### Downstream Use [optional]
+```
+pip install --upgrade vllm
+```
 
-<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+Also make sure you have `mistral_common >= 1.4.1` installed:
 
-[More Information Needed]
+```
+pip install --upgrade mistral_common
+```
 
-### Out-of-Scope Use
+You can also make use of a ready-to-go [docker image](https://hub.docker.com/layers/vllm/vllm-openai/latest/images/sha256-de9032a92ffea7b5c007dad80b38fd44aac11eddc31c435f8e52f3b7404bbf39?context=explore).
 
-<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
 
-[More Information Needed]
+**_Offline_**
 
-## Bias, Risks, and Limitations
+```py
+from vllm import LLM
+from vllm.sampling_params import SamplingParams
 
-<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+model_name = "mistralai/Mistral-Small-Instruct-2409"
 
-[More Information Needed]
+sampling_params = SamplingParams(max_tokens=8192)
 
-### Recommendations
+# note that running Mistral-Small on a single GPU requires at least 44 GB of GPU RAM
+# If you want to divide the GPU requirement over multiple devices, please add *e.g.* `tensor_parallel=2`
+llm = LLM(model=model_name, tokenizer_mode="mistral", config_format="mistral", load_format="mistral")
 
-<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+prompt = "How often does the letter r occur in Mistral?"
 
-Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+messages = [
+    {
+        "role": "user",
+        "content": prompt
+    },
+]
 
-## How to Get Started with the Model
+outputs = llm.chat(messages, sampling_params=sampling_params)
 
-Use the code below to get started with the model.
+print(outputs[0].outputs[0].text)
+```
 
-[More Information Needed]
+**_Server_**
 
-## Training Details
+You can also use Mistral Small in a server/client setting. 
 
-### Training Data
+1. Spin up a server:
 
-<!-- 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]
+```
+vllm serve mistralai/Mistral-Small-Instruct-2409 --tokenizer_mode mistral --config_format mistral --load_format mistral
+```
 
-### Training Procedure
+**Note:** Running Mistral-Small on a single GPU requires at least 44 GB of GPU RAM. 
 
-<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+If you want to divide the GPU requirement over multiple devices, please add *e.g.* `--tensor_parallel=2`
 
-#### Preprocessing [optional]
+2. And ping the client:
 
-[More Information Needed]
+```
+curl --location 'http://<your-node-url>:8000/v1/chat/completions' \
+--header 'Content-Type: application/json' \
+--header 'Authorization: Bearer token' \
+--data '{
+    "model": "mistralai/Mistral-Small-Instruct-2409",
+    "messages": [
+      {
+        "role": "user",
+        "content": "How often does the letter r occur in Mistral?"
+      }
+    ]
+}'
 
+```
 
-#### Training Hyperparameters
+### Mistral-inference
 
-- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+We recommend using [mistral-inference](https://github.com/mistralai/mistral-inference) to quickly try out / "vibe-check" the model.
 
-#### Speeds, Sizes, Times [optional]
 
-<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+**_Install_**
 
-[More Information Needed]
+Make sure to have `mistral_inference >= 1.4.1` installed.
 
-## Evaluation
+```
+pip install mistral_inference --upgrade
+```
 
-<!-- This section describes the evaluation protocols and provides the results. -->
+**_Download_**
 
-### Testing Data, Factors & Metrics
+```py
+from huggingface_hub import snapshot_download
+from pathlib import Path
 
-#### Testing Data
+mistral_models_path = Path.home().joinpath('mistral_models', '22B-Instruct-Small')
+mistral_models_path.mkdir(parents=True, exist_ok=True)
 
-<!-- This should link to a Dataset Card if possible. -->
+snapshot_download(repo_id="mistralai/Mistral-Small-Instruct-2409", allow_patterns=["params.json", "consolidated.safetensors", "tokenizer.model.v3"], local_dir=mistral_models_path)
+```
 
-[More Information Needed]
+### Chat
 
-#### Factors
+After installing `mistral_inference`, a `mistral-chat` CLI command should be available in your environment. You can chat with the model using
 
-<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+```
+mistral-chat $HOME/mistral_models/22B-Instruct-Small --instruct --max_tokens 256
+```
 
-[More Information Needed]
+### Instruct following
 
-#### Metrics
+```py
+from mistral_inference.transformer import Transformer
+from mistral_inference.generate import generate
 
-<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+from mistral_common.tokens.tokenizers.mistral import MistralTokenizer
+from mistral_common.protocol.instruct.messages import UserMessage
+from mistral_common.protocol.instruct.request import ChatCompletionRequest
 
-[More Information Needed]
 
-### Results
+tokenizer = MistralTokenizer.from_file(f"{mistral_models_path}/tokenizer.model.v3")
+model = Transformer.from_folder(mistral_models_path)
 
-[More Information Needed]
+completion_request = ChatCompletionRequest(messages=[UserMessage(content="How often does the letter r occur in Mistral?")])
 
-#### Summary
+tokens = tokenizer.encode_chat_completion(completion_request).tokens
 
+out_tokens, _ = generate([tokens], model, max_tokens=64, temperature=0.0, eos_id=tokenizer.instruct_tokenizer.tokenizer.eos_id)
+result = tokenizer.instruct_tokenizer.tokenizer.decode(out_tokens[0])
 
+print(result)
+```
 
-## Model Examination [optional]
+### Function calling
 
-<!-- Relevant interpretability work for the model goes here -->
+```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
 
-## Environmental Impact
 
-<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+tokenizer = MistralTokenizer.from_file(f"{mistral_models_path}/tokenizer.model.v3")
+model = Transformer.from_folder(mistral_models_path)
 
-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).
+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?"),
+        ],
+)
 
-- **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]
+tokens = tokenizer.encode_chat_completion(completion_request).tokens
 
-## 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]
+out_tokens, _ = generate([tokens], model, max_tokens=64, temperature=0.0, eos_id=tokenizer.instruct_tokenizer.tokenizer.eos_id)
+result = tokenizer.instruct_tokenizer.tokenizer.decode(out_tokens[0])
+
+print(result)
+```
+
+### Usage in Hugging Face Transformers
+
+You can also use Hugging Face `transformers` library to run inference using various chat templates, or fine-tune the model.
+Example for inference:
+
+```python
+from transformers import LlamaTokenizerFast, MistralForCausalLM
+import torch
+
+device = "cuda"
+tokenizer = LlamaTokenizerFast.from_pretrained('mistralai/Mistral-Small-Instruct-2409')
+tokenizer.pad_token = tokenizer.eos_token
+
+model = MistralForCausalLM.from_pretrained('mistralai/Mistral-Small-Instruct-2409', torch_dtype=torch.bfloat16)
+model = model.to(device)
+
+prompt = "How often does the letter r occur in Mistral?"
+
+messages = [
+    {"role": "user", "content": prompt},
+ ]
+
+model_input = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt").to(device)
+gen = model.generate(model_input, max_new_tokens=150)
+dec = tokenizer.batch_decode(gen)
+print(dec)
+```
+
+And you should obtain 
+```text
+<s>
+  [INST]
+  How often does the letter r occur in Mistral?
+  [/INST]
+  To determine how often the letter "r" occurs in the word "Mistral,"
+  we can simply count the instances of "r" in the word.
+  The word "Mistral" is broken down as follows:
+    - M
+    - i
+    - s
+    - t
+    - r
+    - a
+    - l
+  Counting the "r"s, we find that there is only one "r" in "Mistral."
+  Therefore, the letter "r" occurs once in the word "Mistral."
+</s>
+```
+
+## The Mistral AI Team
+
+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, Diogo Costa, 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