Instructions to use Meridian-MRM/cagliari-114m with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Meridian-MRM/cagliari-114m with Transformers:

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

pipe = pipeline("text-generation", model="Meridian-MRM/cagliari-114m")

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

tokenizer = AutoTokenizer.from_pretrained("Meridian-MRM/cagliari-114m")
model = AutoModelForCausalLM.from_pretrained("Meridian-MRM/cagliari-114m", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use Meridian-MRM/cagliari-114m with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Meridian-MRM/cagliari-114m:F16
# Run inference directly in the terminal:
llama cli -hf Meridian-MRM/cagliari-114m:F16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Meridian-MRM/cagliari-114m:F16
# Run inference directly in the terminal:
llama cli -hf Meridian-MRM/cagliari-114m:F16

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf Meridian-MRM/cagliari-114m:F16
# Run inference directly in the terminal:
./llama-cli -hf Meridian-MRM/cagliari-114m:F16

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf Meridian-MRM/cagliari-114m:F16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Meridian-MRM/cagliari-114m:F16

Use Docker

docker model run hf.co/Meridian-MRM/cagliari-114m:F16

LM Studio
Jan

vLLM

How to use Meridian-MRM/cagliari-114m with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Meridian-MRM/cagliari-114m"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Meridian-MRM/cagliari-114m",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Meridian-MRM/cagliari-114m:F16

SGLang

How to use Meridian-MRM/cagliari-114m 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 "Meridian-MRM/cagliari-114m" \
    --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": "Meridian-MRM/cagliari-114m",
		"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 "Meridian-MRM/cagliari-114m" \
        --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": "Meridian-MRM/cagliari-114m",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Ollama
How to use Meridian-MRM/cagliari-114m with Ollama:
```
ollama run hf.co/Meridian-MRM/cagliari-114m:F16
```
Unsloth Desktop
Docker Model Runner
How to use Meridian-MRM/cagliari-114m with Docker Model Runner:
```
docker model run hf.co/Meridian-MRM/cagliari-114m:F16
```

Lemonade

How to use Meridian-MRM/cagliari-114m with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Meridian-MRM/cagliari-114m:F16

Run and chat with the model

lemonade run user.cagliari-114m-F16

List all available models

lemonade list

Atomic Chat

Cagliari-114M

Base language model, 114M params. Qwen3-compatible architecture, GPT-2 BPE tokenizer with 4 additional special tokens. Pretrained from scratch on 8.16B tokens.

No instruction tuning. No chat behavior. Completion only.

Architecture


Layers	24
Hidden size	576
Intermediate size	1536
Attention	GQA, 9 Q / 3 KV heads, head_dim 64
Norm	RMSNorm + QK-Norm
Embeddings	tied
RoPE theta	10000.0
Context	1024
Vocab	50304 (50261 used)
Tokenizer	GPT-2 BPE
Specials	`<\|im_start\|>`, `<\|im_end\|>`, `<think>`, `</think>`, `<\|endoftext\|>`
EOS / BOS / PAD	50256

Corpus

Source	Tokens	License
Gutenberg	4.5B	Public Domain
Wikipedia	2.37B	CC BY-SA 4.0
OpenThoughts	0.82B	Apache 2.0
OpenHermes	0.39B	Apache 2.0
StackExchange	0.08B	CC BY-SA 4.0
Total	8.16B

Training


Training Time	4 hours
Mix change (S2b)	OpenThoughts 12% -> 2%, StackExchange 4% -> 2%
Tokens seen	5.24B (64.3% of corpus)
Optimizer	AdamW, b1 0.9, b2 0.95, wd 0.01, clip 1.0
Batch	128 x 1024
Hardware	TPU v5e-8

Benchmarks

Evaluated using the lm-evaluation-harness (v0.4.13) suite, zero-shot (num_fewshot=0) on full splits.

Benchmark	Metric	Score
BLiMP	Accuracy	80.22%
ARC-Easy	Accuracy	38.30%
	Normalized Accuracy	35.40%
WikiText-2	Byte Perplexity	1.96
	Word Perplexity	36.95
	Bits Per Byte	0.97

Limitations

114M params. Limited factual recall and reasoning.
Base model. No instruction following, no finetuning, no chat behavior.
Context 1024 tokens.
Outputs reflect pretraining data biases.
Not for production or safety-critical use.

License

Apache 2.0.

Citation

@misc{cagliari114m,
  title  = {Cagliari-114M},
  author = {Meridian-MRM},
  howpublished = {\url{https://huggingface.co/Meridian-MRM/cagliari-114m}}
}

Credits

Project Gutenberg (Public Domain)
Wikipedia (CC BY-SA 4.0)
OpenThoughts (Apache 2.0)
OpenHermes (Apache 2.0)
StackExchange (CC BY-SA 4.0)
GPT-2 BPE (OpenAI)
JAX / Flax / Optax, tiktoken, llama.cpp, Hugging Face

Downloads last month: 834

Safetensors

Model size

0.1B params

Tensor type

F16

Space using Meridian-MRM/cagliari-114m 1

Evaluation results

Accuracy on BLiMP
lm-eval 0.4.13

80.220
Accuracy on PIQA
lm-eval 0.4.13

58.270
Normalized Accuracy on PIQA
lm-eval 0.4.13

55.980
Accuracy on WinoGrande
lm-eval 0.4.13

50.360
Accuracy on BoolQ
lm-eval 0.4.13

41.440
Accuracy on AI2 Reasoning Challenge
lm-eval 0.4.13

38.300
Normalized Accuracy on AI2 Reasoning Challenge
lm-eval 0.4.13

35.400
Accuracy on OpenBookQA
lm-eval 0.4.13

14.800