Instructions to use CodeSoft/sorbet-v2-25m with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use CodeSoft/sorbet-v2-25m with Transformers:

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

pipe = pipeline("text-generation", model="CodeSoft/sorbet-v2-25m")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("CodeSoft/sorbet-v2-25m")
model = AutoModelForCausalLM.from_pretrained("CodeSoft/sorbet-v2-25m", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use CodeSoft/sorbet-v2-25m 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 CodeSoft/sorbet-v2-25m:Q4_K_XL
# Run inference directly in the terminal:
llama cli -hf CodeSoft/sorbet-v2-25m:Q4_K_XL

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf CodeSoft/sorbet-v2-25m:Q4_K_XL
# Run inference directly in the terminal:
llama cli -hf CodeSoft/sorbet-v2-25m:Q4_K_XL

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 CodeSoft/sorbet-v2-25m:Q4_K_XL
# Run inference directly in the terminal:
./llama-cli -hf CodeSoft/sorbet-v2-25m:Q4_K_XL

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 CodeSoft/sorbet-v2-25m:Q4_K_XL
# Run inference directly in the terminal:
./build/bin/llama-cli -hf CodeSoft/sorbet-v2-25m:Q4_K_XL

Use Docker

docker model run hf.co/CodeSoft/sorbet-v2-25m:Q4_K_XL

LM Studio
Jan

vLLM

How to use CodeSoft/sorbet-v2-25m with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "CodeSoft/sorbet-v2-25m"
# 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-v2-25m",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/CodeSoft/sorbet-v2-25m:Q4_K_XL

SGLang

How to use CodeSoft/sorbet-v2-25m 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-v2-25m" \
    --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-v2-25m",
		"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-v2-25m" \
        --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-v2-25m",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Ollama
How to use CodeSoft/sorbet-v2-25m with Ollama:
```
ollama run hf.co/CodeSoft/sorbet-v2-25m:Q4_K_XL
```
Unsloth Desktop
Docker Model Runner
How to use CodeSoft/sorbet-v2-25m with Docker Model Runner:
```
docker model run hf.co/CodeSoft/sorbet-v2-25m:Q4_K_XL
```

Lemonade

How to use CodeSoft/sorbet-v2-25m with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull CodeSoft/sorbet-v2-25m:Q4_K_XL

Run and chat with the model

lemonade run user.sorbet-v2-25m-Q4_K_XL

List all available models

lemonade list

Atomic Chat

sorbet-v2-25m / README.md

CodeSoft

Update README.md

4a9c175 verified 7 days ago

preview code

Raw

History Blame Contribute Delete

3.21 kB

	---
	license: apache-2.0
	model_name: Sorbet-v2-25M
	pipeline_tag: text-generation
	tags:
	- qwen2
	- 25M
	language:
	- en
	datasets:
	- epfml/FineWeb-HQ
	- HuggingFaceTB/finemath
	- mlfoundations/dclm-baseline-1.0-parquet
	library_name: transformers
	---

	<div align="center">
	<img src="https://cdn-uploads.huggingface.co/production/uploads/645aad59c4acfcf664022df5/7_BzxM3bmTilI1xRzElnB.png" alt="Sorbet V2 Header" width="700">

	<h1>Sorbet v2 25M</h1>

	<p>
	25M-parameter Qwen2-style decoder LM, warm-started from Sorbet-25M and continued-trained in two runs.
	</p>
	</div>

	## Architecture graph

	<a href="https://hfviewer.com/CodeSoft/sorbet-v2-25m?utm_source=huggingface&utm_medium=embedded_model_card&utm_campaign=CodeSoft_sorbet-v2-25m_card" target="_blank" rel="noopener">
	<img
	src="https://hfviewer.com/api/card.svg?source=CodeSoft%2Fsorbet-v2-25m&granularity=0"
	alt="Architecture graph for CodeSoft/sorbet-v2-25m. Open in hfviewer"
	width="100%"
	/>
	</a>

	## Architecture

	Identical to Sorbet-25M: stock Qwen2 throughout, no custom code paths, natively supported by both `transformers` and `llama.cpp`.

	\| \| \|
	\|---\|---\|
	\| 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

	v2 continues the v1 checkpoint through two training runs:

	\| Leg \| Data mix (tokens) \| LR schedule \|
	\|---\|---\|---\|
	\| cpt2 \| fineweb-edu 70% / infiwebmath 10% / DCLM-baseline 20%, 0.8B tok \| cosine, 8-bit AdamW \|
	\| v2-final \| FineWeb-HQ 65% / DCLM-baseline 20% / FineMath-4+ 15%, 1.7B tok \| cosine peak 1e-4, fp32 AdamW \|

	Block-shuffled at 131,072 tok/step.

	## Benchmarks

	All numbers zero-shot via lm-evaluation-harness, bf16, identical settings across checkpoints.

	\| Task \| n \| Random \| acc \| acc_norm \|
	\|---\|---\|---\|---\|---\|
	\| HellaSwag \| 10,042 \| 25% \| 26.55 ±0.44 \| 26.63 ±0.44 \|
	\| ARC-easy \| 2,376 \| ~25% \| 30.30 ±0.94 \| 29.92 ±0.94 \|
	\| ARC-challenge \| 1,172 \| ~25% \| 18.60 ±1.14 \| 22.44 ±1.22 \|
	\| PIQA \| 1,838 \| 50% \| 54.52 ±1.16 \| 53.32 ±1.16 \|
	\| ArithMark-3.0 \| 1,000 \| 25% \| 32.90 ±1.48 \| 33.00 ±1.49 \|

	Notes:
	- Every score is at or above the Sorbet-25M baseline within error bars.
	- ArithMark-3.0 (`AxiomicLabs/Arithmark-3.0`) remains the strongest relative result (+8 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

	```python
	from transformers import AutoModelForCausalLM, AutoTokenizer

	repo = "CodeSoft/sorbet-v2-25m"
	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.