HuggingFaceFW/fineweb-edu
Viewer β’ Updated β’ 3.5B β’ 424k β’ 1.42k
How to use RessAI/Onner-300m with Transformers:
# Use a pipeline as a high-level helper
from transformers import pipeline
pipe = pipeline("text-generation", model="RessAI/Onner-300m") # pip install -U transformers accelerate
# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("RessAI/Onner-300m", device_map="auto")How to use RessAI/Onner-300m with vLLM:
# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "RessAI/Onner-300m"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
-H "Content-Type: application/json" \
--data '{
"model": "RessAI/Onner-300m",
"prompt": "Once upon a time,",
"max_tokens": 512,
"temperature": 0.5
}'docker model run hf.co/RessAI/Onner-300m
How to use RessAI/Onner-300m with SGLang:
# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
--model-path "RessAI/Onner-300m" \
--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": "RessAI/Onner-300m",
"prompt": "Once upon a time,",
"max_tokens": 512,
"temperature": 0.5
}'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 "RessAI/Onner-300m" \
--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": "RessAI/Onner-300m",
"prompt": "Once upon a time,",
"max_tokens": 512,
"temperature": 0.5
}'How to use RessAI/Onner-300m with Docker Model Runner:
docker model run hf.co/RessAI/Onner-300m
Onner-300m (internally RessAI-Ultra-300M) is a compact, high-efficiency language model designed for educational reasoning and lightweight deployment. With approximately 200 Million parameters, it follows a "Dense & Deep" philosophy scaled down for speed and accessibility.
It is trained on the high-quality FineWeb-Edu dataset, utilizing a custom architecture (RessAiForCausalLM) optimized for efficient inference.
RessAiForCausalLMonnerThis model uses a custom configuration inspired by BERT-base sizing but with Llama's causal attention mechanisms:
| Hyperparameter | Value | Description |
|---|---|---|
| Hidden Size | 768 | Embedding dimension (Compact) |
| Layers | 12 | Network depth |
| Attention Heads | 12 | Query heads |
| KV Heads | 2 | Grouped Query Attention (GQA 6:1) |
| Intermediate Size | 3,072 | MLP Width |
| RoPE Theta | 500,000 | Rotary Embeddings Base |
| Max Sequence | 4,096 | Context Length |
docker model run hf.co/RessAI/Onner-300m