Instructions to use Maincode/Matilda-Platypus-12B-Base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Maincode/Matilda-Platypus-12B-Base with Transformers:

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

pipe = pipeline("text-generation", model="Maincode/Matilda-Platypus-12B-Base", trust_remote_code=True)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("Maincode/Matilda-Platypus-12B-Base", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Maincode/Matilda-Platypus-12B-Base with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/Maincode/Matilda-Platypus-12B-Base

SGLang

How to use Maincode/Matilda-Platypus-12B-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 "Maincode/Matilda-Platypus-12B-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": "Maincode/Matilda-Platypus-12B-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 "Maincode/Matilda-Platypus-12B-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": "Maincode/Matilda-Platypus-12B-Base",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Maincode/Matilda-Platypus-12B-Base with Docker Model Runner:
```
docker model run hf.co/Maincode/Matilda-Platypus-12B-Base
```

Matilda-Platypus-12B-Base

File size: 1,180 Bytes

b7c0e6b

{
 "protocol": "lm-eval-harness 0.4.13, base-model protocol, HumanEval fence-stripped",
 "cut": "25+15",
 "params_b": 12.57,
 "gflop_per_token": 24.37,
 "compute_pct_of_larger_parent": 85,
 "smaller_parent": {
  "name": "Qwen3-8B-Base",
  "humaneval": 0.677,
  "gsm8k_cot": 0.856,
  "mmlu": 0.7683,
  "bbh_cot_fewshot": 0.7742,
  "hellaswag": 0.7859,
  "arc_easy": 0.7984,
  "arc_challenge": 0.5717,
  "openbookqa": 0.416,
  "winogrande": 0.723,
  "piqa": 0.7943,
  "lambada_openai": 0.7105,
  "mbpp": 0.686,
  "boolq": 0.8321
 },
 "model": {
  "humaneval": 0.671,
  "gsm8k_cot": 0.8802,
  "mmlu": 0.7888,
  "bbh_cot_fewshot": 0.7576,
  "hellaswag": 0.791,
  "arc_easy": 0.7765,
  "arc_challenge": 0.5606,
  "openbookqa": 0.458,
  "winogrande": 0.7632,
  "piqa": 0.8025,
  "lambada_openai": 0.7068,
  "mbpp": 0.712,
  "boolq": 0.8722
 },
 "larger_parent": {
  "name": "Qwen3-14B-Base",
  "humaneval": 0.72,
  "gsm8k_cot": 0.8704,
  "mmlu": 0.8053,
  "bbh_cot_fewshot": 0.7877,
  "hellaswag": 0.8136,
  "arc_easy": 0.8194,
  "arc_challenge": 0.5879,
  "openbookqa": 0.48,
  "winogrande": 0.7466,
  "piqa": 0.8243,
  "lambada_openai": 0.7419,
  "mbpp": 0.748,
  "boolq": 0.8651
 }
}