Devstral-Small-2507-GGUF

export MISTRAL_API_KEY=<MY_KEY>

mkdir -p ~/.openhands && echo '{"language":"en","agent":"CodeActAgent","max_iterations":null,"security_analyzer":null,"confirmation_mode":false,"llm_model":"mistral/devstral-small-2507","llm_api_key":"'$MISTRAL_API_KEY'","remote_runtime_resource_factor":null,"github_token":null,"enable_default_condenser":true}' > ~/.openhands-state/settings.json

docker pull docker.all-hands.dev/all-hands-ai/runtime:0.48-nikolaik

docker run -it --rm --pull=always \
    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.48-nikolaik \
    -e LOG_ALL_EVENTS=true \
    -v /var/run/docker.sock:/var/run/docker.sock \
    -v ~/.openhands:/.openhands \
    -p 3000:3000 \
    --add-host host.docker.internal:host-gateway \
    --name openhands-app \
    docker.all-hands.dev/all-hands-ai/openhands:0.48

pip install vllm --upgrade

pip install mistral-common --upgrade

python -c "import mistral_common; print(mistral_common.__version__)"

vllm serve mistralai/Devstral-Small-2507 --tokenizer_mode mistral --config_format mistral --load_format mistral --tool-call-parser mistral --enable-auto-tool-choice --tensor-parallel-size 2

import requests
import json
from huggingface_hub import hf_hub_download


url = "http://<your-server-url>:8000/v1/chat/completions"
headers = {"Content-Type": "application/json", "Authorization": "Bearer token"}

model = "mistralai/Devstral-Small-2507"

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

SYSTEM_PROMPT = load_system_prompt(model, "SYSTEM_PROMPT.txt")

messages = [
    {"role": "system", "content": SYSTEM_PROMPT},
    {
        "role": "user",
        "content": [
            {
                "type": "text",
                "text": "<your-command>",
            },
        ],
    },
]

data = {"model": model, "messages": messages, "temperature": 0.15}

# Devstral Small 1.1 supports tool calling. If you want to use tools, follow this:
# tools = [ # Define tools for vLLM
#     {
#         "type": "function",
#         "function": {
#             "name": "git_clone",
#             "description": "Clone a git repository",
#             "parameters": {
#                 "type": "object",
#                 "properties": {
#                     "url": {
#                         "type": "string",
#                         "description": "The url of the git repository",
#                     },
#                 },
#                 "required": ["url"],
#             },
#         },
#     }
# ] 
# data = {"model": model, "messages": messages, "temperature": 0.15, "tools": tools} # Pass tools to payload.

response = requests.post(url, headers=headers, data=json.dumps(data))
print(response.json()["choices"][0]["message"]["content"])

pip install mistral_inference --upgrade

from huggingface_hub import snapshot_download
from pathlib import Path

mistral_models_path = Path.home().joinpath('mistral_models', 'Devstral')
mistral_models_path.mkdir(parents=True, exist_ok=True)

snapshot_download(repo_id="mistralai/Devstral-Small-2507", allow_patterns=["params.json", "consolidated.safetensors", "tekken.json"], local_dir=mistral_models_path)

mistral-chat $HOME/mistral_models/Devstral --instruct --max_tokens 300

pip install mistral-common --upgrade

import torch

from mistral_common.protocol.instruct.messages import (
    SystemMessage, UserMessage
)
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 AutoModelForCausalLM

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/Devstral-Small-2507"
SYSTEM_PROMPT = load_system_prompt(model_id, "SYSTEM_PROMPT.txt")


tokenizer = MistralTokenizer.from_hf_hub(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id)

tokenized = tokenizer.encode_chat_completion(
    ChatCompletionRequest(
        messages=[
            SystemMessage(content=SYSTEM_PROMPT),
            UserMessage(content="<your-command>"),
        ],
    )
)

output = model.generate(
    input_ids=torch.tensor([tokenized.tokens]),
    max_new_tokens=1000,
)[0]

decoded_output = tokenizer.decode(output[len(tokenized.tokens):])
print(decoded_output)

pip install -U "huggingface_hub[cli]"
huggingface-cli download \
"lmstudio-community/Devstral-Small-2507-GGUF" \ # or mistralai/Devstral-Small-2507_gguf
--include "Devstral-Small-2507-Q4_K_M.gguf" \
--local-dir "Devstral-Small-2507_gguf/"

pip install -U "huggingface_hub[cli]"
huggingface-cli download \
"mistralai/Devstral-Small-2507_gguf" \
--include "Devstral-Small-2507-Q4_K_M.gguf" \
--local-dir "mistralai/Devstral-Small-2507_gguf/"

./llama-server -m mistralai/Devstral-Small-2507_gguf/Devstral-Small-2507-Q4_K_M.gguf -c 0 # -c configure the context size, 0 means model's default, here 128k.

vllm serve mistralai/Devstral-Small-2507 --tokenizer_mode mistral --config_format mistral --load_format mistral --tool-call-parser mistral --enable-auto-tool-choice --tensor-parallel-size 2

docker pull docker.all-hands.dev/all-hands-ai/runtime:0.48-nikolaik

docker run -it --rm --pull=always \
    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.48-nikolaik \
    -e LOG_ALL_EVENTS=true \
    -v /var/run/docker.sock:/var/run/docker.sock \
    -v ~/.openhands:/.openhands \
    -p 3000:3000 \
    --add-host host.docker.internal:host-gateway \
    --name openhands-app \
    docker.all-hands.dev/all-hands-ai/openhands:0.48

vllm serve mistralai/Devstral-Small-2507 --tokenizer_mode mistral --config_format mistral --load_format mistral --tool-call-parser mistral --enable-auto-tool-choice --tensor-parallel-size 2

Check the test coverage of the repo and then create a visualization of test coverage. Try plotting a few different types of graphs and save them to a png.

Create a video game that mixes Space Invaders and Pong for the web.

Follow these instructions:
- There are two players one at the top and one at the bottom. The players are controling a bar to bounce a ball.
- The first player plays with the keys "a" and "d", the second with the right and left arrows.
- The invaders are located at the center of the screen. They shoud look like the ones in Space Invaders. Their goal is to shoot on the players randomly. They cannot be destroyed by the ball that pass through them. This means that invaders never die.
- The players goal is to avoid shootings from the space invaders and send the ball to the edge of the over player.
- The ball bounces on the left and right edges.
- Once the ball touch one of the player's edge, the player loses.
- Once a player is touched 3 times or more by a shooting, the player loses.
- The player winning is the last one standing.
- Display on the UI, the number of times a player touched the ball, and the remaining health.