Instructions to use JetBrains/Mellum2-12B-A2.5B-Base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use JetBrains/Mellum2-12B-A2.5B-Base with Transformers:

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

pipe = pipeline("text-generation", model="JetBrains/Mellum2-12B-A2.5B-Base")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("JetBrains/Mellum2-12B-A2.5B-Base")
model = AutoModelForCausalLM.from_pretrained("JetBrains/Mellum2-12B-A2.5B-Base", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use JetBrains/Mellum2-12B-A2.5B-Base with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "JetBrains/Mellum2-12B-A2.5B-Base"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "JetBrains/Mellum2-12B-A2.5B-Base",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/JetBrains/Mellum2-12B-A2.5B-Base

SGLang

How to use JetBrains/Mellum2-12B-A2.5B-Base 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 "JetBrains/Mellum2-12B-A2.5B-Base" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "JetBrains/Mellum2-12B-A2.5B-Base",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "JetBrains/Mellum2-12B-A2.5B-Base" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "JetBrains/Mellum2-12B-A2.5B-Base",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use JetBrains/Mellum2-12B-A2.5B-Base with Docker Model Runner:
```
docker model run hf.co/JetBrains/Mellum2-12B-A2.5B-Base
```

Mellum2-12B-A2.5B-Base / .eval_results /mellum2.yaml

pavlichenko

Update model card and add evaluation results (#2)

1b68edc about 2 months ago

Raw

History Blame Contribute Delete

1.03 kB

	# Mellum 2 Base — evaluation results
	# Self-reported by JetBrains. Numbers from Mellum 2 Technical Report (Table 5),
	# measured on the pre-extension checkpoint Mellum2-12B-A2.5B-Base-Pretrain; the
	# architecture is identical, only RoPE on global-attention layers was re-mapped
	# via layer-selective YaRN to extend context from 8K to 128K.
	# Only entries for benchmarks confirmed to be registered as HF Hub Benchmarks are listed.

	- dataset:
	id: Idavidrein/gpqa
	task_id: diamond
	value: 31.31
	date: "2026-05-27"
	notes: "pre-training eval (pre-YaRN), no-tools"

	- dataset:
	id: Idavidrein/gpqa
	task_id: main
	value: 35.04
	date: "2026-05-27"
	notes: "pre-training eval (pre-YaRN), no-tools"

	- dataset:
	id: TIGER-Lab/MMLU-Pro
	task_id: mmlu_pro
	value: 59.31
	date: "2026-05-27"
	notes: "pre-training eval (pre-YaRN), no-tools, exact match"

	- dataset:
	id: openai/gsm8k
	task_id: gsm8k
	value: 81.73
	date: "2026-05-27"
	notes: "pre-training eval (pre-YaRN), no-tools, exact match"