Install Mistral Nemo Locally and Test for Multi-Lingual , Function Calling

 This video installs Mistral NeMo locally and tests it on multi-lingual, math, coding, and function calling.

Code:

conda create -n nemo python=3.11 -y && conda activate nemo

pip install torch

pip install git+https://github.com/huggingface/transformers.git

pip install mistral_inference

pip install huggingface_hub pathlib

from huggingface_hub import snapshot_download

from pathlib import Path

mistral_models_path = Path.home().joinpath('mistral_models', 'Nemo-Instruct')

mistral_models_path.mkdir(parents=True, exist_ok=True)

snapshot_download(repo_id="mistralai/Mistral-Nemo-Instruct-2407", allow_patterns=["params.json", "consolidated.safetensors", "tekken.json"], local_dir=mistral_models_path)

conda install jupyter -y

pip uninstall charset_normalizer -y

pip install charset_normalizer

jupyter notebook

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}/tekken.json")

model = Transformer.from_folder(mistral_models_path)

prompt = "Write 10 sentences ending with the word beauty."

completion_request = ChatCompletionRequest(messages=[UserMessage(content=prompt)])

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])

print(result)

#===============================

# Function Calling

#===============================

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

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?"),

        ],

)

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])

print(result)