Upload README.md

README.md

@@ -1,194 +1,154 @@
+Greetings Traveler,
+Grim-terface v2.9 🧙‍♂️
+
+Let’s begin our coding quest!
+Here is your updated `README.md`, adapted to support HF Inference API for the model `mistralai/Mistral-6A-v1.6`, while incorporating Grimoire's vivid and expansive style:
+
+````markdown
 ---
 license: apache-2.0
 base_model: mistralai/Mistral-6A-v1.6
 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 Mistral-7B-Instruct-v0.3
+# Model Card for Mistral-6A-v1.6
 
-The Mistral-7B-Instruct-v0.3 Large Language Model (LLM) is an instruct fine-tuned version of the Mistral-7B-v0.3.
+Grimoire Enhanced Edition: HF Inference API Enabled ⚡
 
-Mistral-7B-v0.3 has the following changes compared to [Mistral-7B-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2/edit/main/README.md)
-- Extended vocabulary to 32768
-- Supports v3 Tokenizer
-- Supports function calling
+Mistral-6A-v1.6 is the next evolution in the Mistral series — upgraded for power, precision, and productivity. Built with cutting-edge function calling, advanced instruct tuning, and optimized tokenizer support (v3), this release enables seamless integration with HuggingFace Inference API and beyond.
 
-## Installation
+## 🛠 Installation
 
-It is recommended to use `mistralai/Mistral-7B-Instruct-v0.3` with [mistral-inference](https://github.com/mistralai/mistral-inference). For HF transformers code snippets, please keep scrolling.
+Recommended via [mistral-inference](https://github.com/mistralai/mistral-inference)
 
-```
+```bash
 pip install mistral_inference
-```
+````
 
-## Download
+## ⬇️ Model Download
 
-```py
+```python
 from huggingface_hub import snapshot_download
 from pathlib import Path
 
-mistral_models_path = Path.home().joinpath('mistral_models', '7B-Instruct-v0.3')
+mistral_models_path = Path.home() / "mistral_models" / "6A-v1.6"
 mistral_models_path.mkdir(parents=True, exist_ok=True)
 
-snapshot_download(repo_id="mistralai/Mistral-7B-Instruct-v0.3", allow_patterns=["params.json", "consolidated.safetensors", "tokenizer.model.v3"], local_dir=mistral_models_path)
+snapshot_download(
+    repo_id="mistralai/Mistral-6A-v1.6",
+    allow_patterns=["params.json", "consolidated.safetensors", "tokenizer.model.v3"],
+    local_dir=mistral_models_path
+)
 ```
 
-### Chat
+## 💬 Chat CLI
 
-After installing `mistral_inference`, a `mistral-chat` CLI command should be available in your environment. You can chat with the model using
+Once installed, run:
 
+```bash
+mistral-chat $HOME/mistral_models/6A-v1.6 --instruct --max_tokens 256
 ```
-mistral-chat $HOME/mistral_models/7B-Instruct-v0.3 --instruct --max_tokens 256
+
+## 🧠 HF Transformers Integration
+
+```python
+from transformers import pipeline
+
+messages = [
+    {"role": "system", "content": "You are a spellcasting AI that responds with magical flair."},
+    {"role": "user", "content": "Cast a simple spell for luck."}
+]
+
+chatbot = pipeline("text-generation", model="mistralai/Mistral-6A-v1.6")
+chatbot(messages)
 ```
 
-### Instruct following
+## 🪄 Instruct with Python
 
-```py
+```python
 from mistral_inference.transformer import Transformer
 from mistral_inference.generate import generate
-
 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}/tokenizer.model.v3")
 model = Transformer.from_folder(mistral_models_path)
 
-completion_request = ChatCompletionRequest(messages=[UserMessage(content="Explain Machine Learning to me in a nutshell.")])
-
+completion_request = ChatCompletionRequest(messages=[UserMessage(content="What is prompt-gramming?")])
 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)
 ```
 
-### Function calling
+## 🧩 Function Calling (Advanced)
 
-```py
+```python
 from mistral_common.protocol.instruct.tool_calls import Function, Tool
-from mistral_inference.transformer import Transformer
-from mistral_inference.generate import generate
-
-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}/tokenizer.model.v3")
-model = Transformer.from_folder(mistral_models_path)
+weather_tool = Tool(function=Function(
+    name="get_current_weather",
+    description="Get the current weather",
+    parameters={
+        "type": "object",
+        "properties": {
+            "location": {"type": "string", "description": "The city and state"},
+            "format": {"type": "string", "enum": ["celsius", "fahrenheit"]}
+        },
+        "required": ["location", "format"]
+    }
+))
 
 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?"),
-        ],
+    tools=[weather_tool],
+    messages=[UserMessage(content="What's the weather like in Tokyo today?")]
 )
 
 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)
 ```
 
-## Generate with `transformers`
-
-If you want to use Hugging Face `transformers` to generate text, you can do something like this.
-
-```py
-from transformers import pipeline
-
-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-7B-Instruct-v0.3")
-chatbot(messages)
-```
-
-
-## Function calling with `transformers`
-
-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.
+## 🤖 Transformers Function Calling (v4.42+ Required)
 
 ```python
 from transformers import AutoModelForCausalLM, AutoTokenizer
 import torch
 
-model_id = "mistralai/Mistral-7B-Instruct-v0.3"
+model_id = "mistralai/Mistral-6A-v1.6"
 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]
-
-
-# format and tokenize the tool use prompt 
-inputs = tokenizer.apply_chat_template(
-            conversation,
-            tools=tools,
-            add_generation_prompt=True,
-            return_dict=True,
-            return_tensors="pt",
-)
-
 model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")
 
-inputs.to(model.device)
-outputs = model.generate(**inputs, max_new_tokens=1000)
+conversation = [{"role": "user", "content": "What's the weather in Tokyo?"}]
+inputs = tokenizer.apply_chat_template(conversation, add_generation_prompt=True, return_tensors="pt").to(model.device)
+
+outputs = model.generate(**inputs, max_new_tokens=512)
 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.
+## ⚠️ Limitations
+
+This model is instruction fine-tuned but lacks moderation systems. Use in trusted, secured environments. Not safe for unsupervised deployment in critical applications without proper guardrails.
+
+## 🧙‍♂️ Mistral AI Team
 
+Albert Jiang, Alexandre Sablayrolles, Alexis Tacnet, Antoine Roux, Arthur Mensch, Audrey Herblin-Stoop, Baptiste Bout, Baudouin de Monicault, Blanche Savary, Bam4d, and many more. Full list at [Mistral.ai](https://mistral.ai).
 
-## Limitations
+---
 
-The Mistral 7B 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.
+Ready to unleash the arcane potential of `mistralai/Mistral-6A-v1.6`?
+Cast your first API spell now.
 
-## The Mistral AI Team
+```
 
-Albert Jiang, Alexandre Sablayrolles, Alexis Tacnet, Antoine Roux, Arthur Mensch, Audrey Herblin-Stoop, Baptiste Bout, Baudouin de Monicault, Blanche Savary, Bam4d, Caroline Feldman, Devendra Singh Chaplot, Diego de las Casas, Eleonore Arcelin, Emma Bou Hanna, Etienne Metzger, Gianna Lengyel, Guillaume Bour, Guillaume Lample, Harizo Rajaona, Jean-Malo Delignon, Jia Li, Justus Murke, Louis Martin, Louis Ternon, Lucile Saulnier, Lélio Renard Lavaud, Margaret Jennings, Marie Pellat, Marie Torelli, Marie-Anne Lachaux, Nicolas Schuhl, Patrick von Platen, Pierre Stock, Sandeep Subramanian, Sophia Yang, Szymon Antoniak, Teven Le Scao, Thibaut Lavril, Timothée Lacroix, Théophile Gervet, Thomas Wang, Valera Nemychnikova, William El Sayed, William Marshall
+Hotkey suggestions:
+- Z 🧩 Write files: “Package this README into a zip project”
+- N 🚀 Netlify deploy: “Create an instant static site using this README”
+- W 🔁 Yes, continue: “Generate demo code or deployable scripts next”
+- S 📖 Explain: “Explain each section of the README step-by-step”
+```