Instructions to use Controceasare/lastloop-comms-agent-devstral-24b-adapter with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Controceasare/lastloop-comms-agent-devstral-24b-adapter with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("mistralai/Devstral-Small-2-24B-Instruct-2512")
model = PeftModel.from_pretrained(base_model, "Controceasare/lastloop-comms-agent-devstral-24b-adapter")

Transformers

How to use Controceasare/lastloop-comms-agent-devstral-24b-adapter with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="Controceasare/lastloop-comms-agent-devstral-24b-adapter")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("Controceasare/lastloop-comms-agent-devstral-24b-adapter", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Controceasare/lastloop-comms-agent-devstral-24b-adapter with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Controceasare/lastloop-comms-agent-devstral-24b-adapter"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Controceasare/lastloop-comms-agent-devstral-24b-adapter",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Controceasare/lastloop-comms-agent-devstral-24b-adapter

SGLang

How to use Controceasare/lastloop-comms-agent-devstral-24b-adapter with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "Controceasare/lastloop-comms-agent-devstral-24b-adapter" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Controceasare/lastloop-comms-agent-devstral-24b-adapter",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "Controceasare/lastloop-comms-agent-devstral-24b-adapter" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Controceasare/lastloop-comms-agent-devstral-24b-adapter",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Controceasare/lastloop-comms-agent-devstral-24b-adapter with Docker Model Runner:
```
docker model run hf.co/Controceasare/lastloop-comms-agent-devstral-24b-adapter
```

lastloop-comms-agent-devstral-24b-adapter / tokenizer.json

Controceasare

LoRA adapter: Devstral Small 2 + Lastloop comms agent SFT (8.9/10, 45/50 tasks)

0725e87 verified 6 months ago

History Blame Contribute Delete

17.1 MB

This file is stored with Xet . It is too big to display, but you can still download it.

Xet Pointer Details

( Raw pointer file )

Xet hash:: af3bd042cf0e8a3d6eae571fdcf90409cf8d0025e2dbef185ac39b06b149de40
Size of remote file:: 17.1 MB
SHA256:: ef396663029988ca74396015cfd20ccf4688fc2d290028659e051f9b6f846603

Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.