Instructions to use DRUPEs/CherryPit-1.0-2B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use DRUPEs/CherryPit-1.0-2B with Transformers:

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

pipe = pipeline("text-generation", model="DRUPEs/CherryPit-1.0-2B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("DRUPEs/CherryPit-1.0-2B")
model = AutoModelForCausalLM.from_pretrained("DRUPEs/CherryPit-1.0-2B", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use DRUPEs/CherryPit-1.0-2B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "DRUPEs/CherryPit-1.0-2B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "DRUPEs/CherryPit-1.0-2B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/DRUPEs/CherryPit-1.0-2B

SGLang

How to use DRUPEs/CherryPit-1.0-2B 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 "DRUPEs/CherryPit-1.0-2B" \
    --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": "DRUPEs/CherryPit-1.0-2B",
		"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 "DRUPEs/CherryPit-1.0-2B" \
        --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": "DRUPEs/CherryPit-1.0-2B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use DRUPEs/CherryPit-1.0-2B with Docker Model Runner:
```
docker model run hf.co/DRUPEs/CherryPit-1.0-2B
```

CherryPit-1.0-2B

Full-precision (bf16 safetensors) weights of CherryPit-1.0-2B, the first release of CherryPit from DRUPEs (Dense Representation & Unified Parameter Encoding Systems), built on MiniCPM5-2B. It is a drop-in upgrade of the base model with a gain in coding, small gains in math and reasoning, and the same size, architecture and speed.

These are the exact weights the CherryPit-1.0-2B-GGUF files were made from, for transformers, vLLM and further fine-tuning. The newer CherryPit-1.1-2B is stronger at math, thinking-mode coding and web apps.

Results vs MiniCPM5-2B

Both models were run on the same harness, items, prompts and seeds (bf16 weights in vLLM). Thinking mode off.

Benchmark	Setting	MiniCPM5-2B	CherryPit-1.0-2B	Δ
Coding
LiveCodeBench v6 (2025-01..04)	pass@1, avg of 8, T=1.0	30.4	32.4	+1.9
— easy / medium / hard		81.7 / 27.2 / 5.0	84.3 / 28.8 / 6.7	+2.6 / +1.6 / +1.7
MBPP+ (EvalPlus)	greedy	61.9	65.1	+3.2
HumanEval	greedy	89.6	90.9	+1.2
HumanEval+	greedy	85.4	86.0	+0.6
General
MATH-500	greedy	79.4	79.8	+0.4
BBH	0-shot CoT	77.8	78.4	+0.6
MMLU-Pro	answer-letter scoring	35.0	34.8	−0.2
HotpotQA (distractor)	F1	55.1	54.7	−0.4
HellaSwag	acc_norm	50.5	49.5	−1.0

Answer length is unchanged (≈2,100 tokens per LiveCodeBench answer for both models).

Model Details

Developed by: DRUPEs
Model type: Causal language model
Parameters: ~2B
Base model: MiniCPM5-2B
Architecture: Standard Llama (381 tensors)
Context length: 128K tokens (131,072)
Tool calling: Supported (via the built-in chat template)
Precision: bf16
Language(s): English
License: Apache 2.0
Version: 1.0

How to Use

For llama.cpp, Ollama or LM Studio use DRUPEs/CherryPit-1.0-2B-GGUF.

from transformers import AutoModelForCausalLM, AutoTokenizer
tok = AutoTokenizer.from_pretrained("DRUPEs/CherryPit-1.0-2B")
model = AutoModelForCausalLM.from_pretrained("DRUPEs/CherryPit-1.0-2B", torch_dtype="bfloat16", device_map="auto")
msgs = [{"role": "user", "content": "Write a Python function that checks whether a string is a palindrome."}]
ids = tok.apply_chat_template(msgs, add_generation_prompt=True, return_tensors="pt").to(model.device)
out = model.generate(ids, max_new_tokens=4096, do_sample=True, temperature=1.0, top_p=0.95)
print(tok.decode(out[0][ids.shape[1]:], skip_special_tokens=True))

vllm serve DRUPEs/CherryPit-1.0-2B --max-model-len 32768

Recommended sampling: temperature 1.0, top_p 0.95. Pass enable_thinking=False to apply_chat_template (vLLM: chat_template_kwargs) for short, direct answers. With no system prompt the model introduces itself as CherryPit.

Limitations

CherryPit is a 2B model and shares the limits of its base: it can make factual errors and write buggy code, so review its output before relying on it.
The largest gains are in coding; improvements in other areas are smaller.
Evaluations were run in English with thinking mode off.

Citation

@misc{drupes2026cherrypit,
  title  = {CherryPit-1.0-2B},
  author = {DRUPEs},
  year   = {2026},
  url    = {https://huggingface.co/DRUPEs/CherryPit-1.0-2B}
}

Downloads last month: 22

Safetensors

Model size

3B params

Tensor type

BF16

Model tree for DRUPEs/CherryPit-1.0-2B

Base model

openbmb/MiniCPM5-2B

Finetuned

(87)

this model

Collection including DRUPEs/CherryPit-1.0-2B

All CherryPit models

Collection

Every CherryPit release from DRUPEs, newest first. Small models that run on your laptop. • 7 items • Updated about 7 hours ago • 1