Instructions to use CodeSoft/sorbet-25m with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use CodeSoft/sorbet-25m with Transformers:

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

pipe = pipeline("text-generation", model="CodeSoft/sorbet-25m")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("CodeSoft/sorbet-25m")
model = AutoModelForCausalLM.from_pretrained("CodeSoft/sorbet-25m", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use CodeSoft/sorbet-25m with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "CodeSoft/sorbet-25m"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "CodeSoft/sorbet-25m",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/CodeSoft/sorbet-25m

SGLang

How to use CodeSoft/sorbet-25m 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 "CodeSoft/sorbet-25m" \
    --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": "CodeSoft/sorbet-25m",
		"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 "CodeSoft/sorbet-25m" \
        --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": "CodeSoft/sorbet-25m",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use CodeSoft/sorbet-25m with Docker Model Runner:
```
docker model run hf.co/CodeSoft/sorbet-25m
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Sorbet-25M

Architecture graph

From-scratch ~25M-parameter Qwen2-style decoder LM trained in under 4h on a single RTX 5060 Ti (16GB).

Architecture


Params	25,185,920 (~87% non-embedding)
Layers / hidden	14 / 384
Attention	GQA 6 heads / 2 KV heads, RoPE θ=100k
FFN	1024 (SwiGLU)
Context	4096
Vocab	8,192 custom byte-level BPE (tied embeddings)
Precision	bf16

Training data

0.8B-token weighted mix: fineweb-edu 70% / infiwebmath 10% / DCLM-baseline 20%, block-shuffled. ~3000 steps at 262,144 tok/step, cosine LR, 8-bit AdamW.

Benchmarks

Task	n	Random	acc	acc_norm
HellaSwag	10,042	25%	26.52 ±0.44	26.12 ±0.44
ARC-easy	2,376	~25%	29.50 ±0.94	29.59 ±0.94
ARC-challenge	1,172	~25%	17.66 ±1.11	22.95 ±1.23
PIQA	1,838	50%	54.46 ±1.16	53.43 ±1.16
ArithMark-3.0	1,000	25%	32.70 ±1.48	32.90 ±1.48

Notes:

ArithMark-3.0 (AxiomicLabs/Arithmark-3.0) is the strongest relative result (+7.9 pts over random), consistent with the math share of the pretraining mix.
ARC-challenge raw accuracy sits below chance due to a length bias in unnormalized scores; acc_norm is the meaningful metric there.

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

repo = "CodeSoft/sorbet-25m"
model = AutoModelForCausalLM.from_pretrained(repo, dtype="bfloat16").to("cuda")
tok = AutoTokenizer.from_pretrained(repo, subfolder="tokenizer")
ids = tok("Once upon a time", return_tensors="pt").input_ids.cuda()
print(tok.decode(model.generate(ids, max_new_tokens=64)[0]))

Limitations

Expect shallow world knowledge and weak performance on knowledge-heavy benchmarks due to the model's small parameter count and limited training budget.

License

Apache-2.0.

Downloads last month: -

Safetensors

Model size

25.2M params

Tensor type

BF16

Model tree for CodeSoft/sorbet-25m

Quantizations

1 model

Datasets used to train CodeSoft/sorbet-25m

Collection including CodeSoft/sorbet-25m

Sorbet-25M

Collection

Models based on Sorbet-25M • 2 items • Updated about 3 hours ago