Instructions to use KrynexLabs/KrynexAI-1.2-25M-Mobile-TFLite with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use KrynexLabs/KrynexAI-1.2-25M-Mobile-TFLite with Transformers:

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

pipe = pipeline("text-generation", model="KrynexLabs/KrynexAI-1.2-25M-Mobile-TFLite")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("KrynexLabs/KrynexAI-1.2-25M-Mobile-TFLite", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use KrynexLabs/KrynexAI-1.2-25M-Mobile-TFLite with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "KrynexLabs/KrynexAI-1.2-25M-Mobile-TFLite"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "KrynexLabs/KrynexAI-1.2-25M-Mobile-TFLite",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/KrynexLabs/KrynexAI-1.2-25M-Mobile-TFLite

SGLang

How to use KrynexLabs/KrynexAI-1.2-25M-Mobile-TFLite 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 "KrynexLabs/KrynexAI-1.2-25M-Mobile-TFLite" \
    --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": "KrynexLabs/KrynexAI-1.2-25M-Mobile-TFLite",
		"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 "KrynexLabs/KrynexAI-1.2-25M-Mobile-TFLite" \
        --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": "KrynexLabs/KrynexAI-1.2-25M-Mobile-TFLite",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use KrynexLabs/KrynexAI-1.2-25M-Mobile-TFLite with Docker Model Runner:
```
docker model run hf.co/KrynexLabs/KrynexAI-1.2-25M-Mobile-TFLite
```

KrynexAI 25M Instruct

KrynexAI 25M is a compact, hybrid autoregressive chat language model. It combines the efficiency of state-space models with the proven performance of attention layers, optimized using a custom Muon + AdamW optimizer split. ## Model Details - Architecture: Hybrid Mamba2 / Transformer - Block Pattern: 3 Mamba2 blocks : 1 Attention block (repeating) - Parameters: 25,000,000 (25M) - Hidden Dimension: 608 - Layers: 8 (6 Mamba2, 2 Attention) - Vocab Size: 2,048 (Custom Byte-Level BPE) - Context Length: 2048 - Pretraining Tokens: ~25,000,000,000 (25 Billion) - SFT Tokens: 250,000,000 (250 Million) - Optimizer: Muon (for 2D hidden weights) + AdamW (for embeddings, norms, and scalars) - Precision: fp32 master weights with bf16 autocast

Dataset Sources

The base model was pretrained on a 25B token subset of the following datasets:

Dataset	Token Allocation	Share
FineWeb-Edu	7.50 billion	30%
DCLM	5.00 billion	20%
Cosmopedia-v2	3.75 billion	15%
FineMath-4+	3.75 billion	15%
FinePhrase	3.00 billion	12%
NPset	2.00 billion	8%

Evaluation Notes

PIQA, ARC-Easy, ARC-Challenge, and HellaSwag were evaluated on their respective test splits.
ArithMark-2.0 and ArithMark-3.0 were evaluated on their train splits.
Results were obtained using zero-shot multiple-choice evaluation.
The model was additionally fine-tuned using supervised fine-tuning (SFT).
Original author: Pebble (25M), It's fine-tuned version.

Usage

To run the model for text generation, you will need to install the required dependencies. The included Mamba2 implementation relies on CUDA/Triton kernels and is intended to run on a CUDA-enabled GPU. Ampere-class GPUs or newer are recommended.

Note: The model uses custom architecture code, so you must pass trust_remote_code=True when loading both the tokenizer and the model.

License & Attribution

Licensed under Apache License 2.0. Based on original work by Pebble developers.

Downloads last month: 430

Safetensors

Model size

24.5M params

Tensor type

F32