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

Notebooks
Google Colab
Kaggle
Local Apps Settings

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

Use Docker

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

LM Studio
Jan

vLLM

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

Install from pip and serve model

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

Use Docker

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

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

Lemonade

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

Pull the model

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

Run and chat with the model

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

List all available models

lemonade list

Atomic Chat

Sorbet 25M GGUF

This repository contains GGUF quantizations of CodeSoft/sorbet-25m for use with llama.cpp.

Quantizations

All XL quants are dynamic mixes calibrated with an importance matrix (imatrix from 1M tokens of the pretraining mix).

File	Quantization	Size
Sorbet-25M-BF16.gguf	BF16	50.7MB
Sorbet-25M-F16.gguf	F16	50.7MB
Sorbet-25M-Q8_K_XL.gguf	Q8_0 weights (imatrix) + F16 tied embd/output + F32 norms	30.0MB
Sorbet-25M-Q4_K_XL.gguf	Q4_0 gate/up (imatrix) + Q5_0 attn_output + Q8_0 attn_q/k/v + Q6_K ffn_down + F16 tied embd/output + F32 norms	22.4MB

Perplexity on the 1M-token calibration split: F16 = 45.13, BF16 = 45.13, Q8_K_XL = 45.15 (+0.02), Q4_K_XL = 46.22 (+1.09).

Downloads last month: 102

GGUF

Model size

25.2M params

Architecture

qwen2

Hardware compatibility

4-bit

8-bit

16-bit

Model tree for CodeSoft/sorbet-25m-gguf

Base model

CodeSoft/sorbet-25m

Quantized

(1)

this model

Collection including CodeSoft/sorbet-25m-gguf

Sorbet-25M

Collection

Models based on Sorbet-25M • 2 items • Updated 10 days ago