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

Libraries

How to use CodeSoft/sorbet-mini-experimental with Transformers:

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

pipe = pipeline("text-generation", model="CodeSoft/sorbet-mini-experimental")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

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

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use CodeSoft/sorbet-mini-experimental 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-mini-experimental:F16
# Run inference directly in the terminal:
llama cli -hf CodeSoft/sorbet-mini-experimental:F16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf CodeSoft/sorbet-mini-experimental:F16
# Run inference directly in the terminal:
llama cli -hf CodeSoft/sorbet-mini-experimental: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 CodeSoft/sorbet-mini-experimental:F16
# Run inference directly in the terminal:
./llama-cli -hf CodeSoft/sorbet-mini-experimental: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 CodeSoft/sorbet-mini-experimental:F16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf CodeSoft/sorbet-mini-experimental:F16

Use Docker

docker model run hf.co/CodeSoft/sorbet-mini-experimental:F16

LM Studio
Jan

vLLM

How to use CodeSoft/sorbet-mini-experimental with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/CodeSoft/sorbet-mini-experimental:F16

SGLang

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

Ollama
How to use CodeSoft/sorbet-mini-experimental with Ollama:
```
ollama run hf.co/CodeSoft/sorbet-mini-experimental:F16
```
Unsloth Desktop
Docker Model Runner
How to use CodeSoft/sorbet-mini-experimental with Docker Model Runner:
```
docker model run hf.co/CodeSoft/sorbet-mini-experimental:F16
```

Lemonade

How to use CodeSoft/sorbet-mini-experimental with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull CodeSoft/sorbet-mini-experimental:F16

Run and chat with the model

lemonade run user.sorbet-mini-experimental-F16

List all available models

lemonade list

Atomic Chat

Sorbet Mini Experimental

This model isn't meant to be "good", yet. The whole point of Sorbet Mini Experimental is to have a base fast enough that you can iterate on without burning hours per experiment. It exists to make the bigger experiments cheaper.

What makes this so important for Sorbet

Sorbet Mini Experimental was trained on 150M tokens, in 12 minutes, with one RTX 5060 Ti.

What matters is that a full pretrain run in twelve minutes means every change on the Sorbet line can be tested quickly without burning hours on a larger model.

What's next for Sorbet Mini

Since Sorbet Mini is so cheap to train, it's a no brainer to keep training it. TinyStories was used to target basic language coherence as a starting point. Eventually, the full release, Sorbet Mini, will release and hopefully perform closer to other similarly sized models.

What it is

Arch: Qwen2ForCausalLM (native in transformers and llama.cpp)
Shape: h192 × 8 layers, heads 6 (dim 32), GQA kv=1, inter 576, tied embeddings
Vocab: 8192 (same tokenizer as the sorbet-25m family)
Params: 4,920,512 total | bf16 ≈ 9.9 MB | Q8_0 ≈ 5.2 MB
Context: 256 train / up to 512 inference

Training recipe

Architecture graph

knob	value
tokens	149,999,872 (~37× Chinchilla)
steps	1144 @ 512 seqs/step (seq 256)
data	TinyStories
precision	bf16, 8-bit AdamW
optimizer	AdamW lr 3e-4 → 1e-5 cosine, wd 0.1 (no decay on emb/norm), grad clip 1.0
hardware	RTX 5060 Ti 16GB

Result: train loss 8.13 → 2.81, val perplexity 3595 → 19.47.

Run it

# very close to f16 (recommended)
llama-completion -m sorbet-mini-experimental-q8_0.gguf \
  -p "Once upon a time," -n 128 --temp 0.8 --top-p 0.95

# reference full-precision build
llama-cli -m sorbet-mini-experimental-f16.gguf -p "Hello, " -n 32

Run the safetensors (transformers)

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tok = AutoTokenizer.from_pretrained("CodeSoft/sorbet-mini-experimental")
model = AutoModelForCausalLM.from_pretrained("CodeSoft/sorbet-mini-experimental", dtype=torch.bfloat16)
# model.to("cuda")  # if you have a GPU

prompt = "Once upon a time,"
ids = tok(prompt, return_tensors="pt").input_ids
out = model.generate(ids, max_new_tokens=128, do_sample=True,
                     temperature=0.8, top_p=0.95)
print(tok.decode(out[0], skip_special_tokens=True))

Downloads last month: -

Safetensors

Model size

4.92M params

Tensor type

BF16

CodeSoft
/

sorbet-mini-experimental