Text Generation
Transformers
Safetensors
English
qwen3
small
tiny
supra
supra2-5
supra2.5
efficient
conversational
text-generation-inference
Instructions to use SupraLabs/Supra2.5-Pro-Base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use SupraLabs/Supra2.5-Pro-Base with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="SupraLabs/Supra2.5-Pro-Base") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("SupraLabs/Supra2.5-Pro-Base") model = AutoModelForCausalLM.from_pretrained("SupraLabs/Supra2.5-Pro-Base", device_map="auto") messages = [ {"role": "user", "content": "Who are you?"}, ] inputs = tokenizer.apply_chat_template( messages, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors="pt", ).to(model.device) outputs = model.generate(**inputs, max_new_tokens=256) print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use SupraLabs/Supra2.5-Pro-Base with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "SupraLabs/Supra2.5-Pro-Base" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "SupraLabs/Supra2.5-Pro-Base", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/SupraLabs/Supra2.5-Pro-Base
- SGLang
How to use SupraLabs/Supra2.5-Pro-Base 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 "SupraLabs/Supra2.5-Pro-Base" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "SupraLabs/Supra2.5-Pro-Base", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'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 "SupraLabs/Supra2.5-Pro-Base" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "SupraLabs/Supra2.5-Pro-Base", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use SupraLabs/Supra2.5-Pro-Base with Docker Model Runner:
docker model run hf.co/SupraLabs/Supra2.5-Pro-Base
Update README.md
Browse files
README.md
CHANGED
|
@@ -85,6 +85,8 @@ Now with 65M parameters, better data and improved training processes, Supra2.5-P
|
|
| 85 |
|
| 86 |
## Model details
|
| 87 |
|
|
|
|
|
|
|
| 88 |
| | |
|
| 89 |
| ----- | ----- |
|
| 90 |
| **Developed by** | SupraLabs |
|
|
@@ -96,10 +98,11 @@ Now with 65M parameters, better data and improved training processes, Supra2.5-P
|
|
| 96 |
| **Precision** | bfloat16 |
|
| 97 |
| **License** | Apache 2.0 |
|
| 98 |
|
| 99 |
-
###
|
| 100 |
|
| 101 |
| Hyperparameter | Value |
|
| 102 |
| ----- | ----- |
|
|
|
|
| 103 |
| Hidden size | 640 |
|
| 104 |
| Layers | 12 |
|
| 105 |
| Attention heads | 10 (MHA) |
|
|
@@ -109,8 +112,6 @@ Now with 65M parameters, better data and improved training processes, Supra2.5-P
|
|
| 109 |
| Positional encoding | RoPE θ=10,000 |
|
| 110 |
| Normalization | RMSNorm, ε=10⁻⁶ |
|
| 111 |
| Tied embeddings | Yes |
|
| 112 |
-
| Attention implementation | SDPA |
|
| 113 |
-
| Architecture | `Qwen3ForCausalLM` |
|
| 114 |
|
| 115 |
---
|
| 116 |
|
|
@@ -126,10 +127,109 @@ Now with 65M parameters, better data and improved training processes, Supra2.5-P
|
|
| 126 |
### Data
|
| 127 |
|
| 128 |
| Source | Approx. tokens | Phase |
|
| 129 |
-
| ----- | ----- |
|
| 130 |
| `Ultra-FineWeb-en` | 44B | Warmup + Stable |
|
| 131 |
| `dclm_100BT-shuffled` | 28B | Warmup + Stable |
|
| 132 |
-
| `UltraData-Code-L2` (70% py / 30% js) | 8B | Warmup + Stable |
|
| 133 |
| Mix of Ultra-FineWeb-en, Finephrase, TxT360-v2, Dolma3-Dolmino-Mix-100B-1025, UltraData-Math and IFM/Pretrain-Behaviors | 20B | Decay |
|
| 134 |
|
| 135 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 85 |
|
| 86 |
## Model details
|
| 87 |
|
| 88 |
+
### Basic information
|
| 89 |
+
|
| 90 |
| | |
|
| 91 |
| ----- | ----- |
|
| 92 |
| **Developed by** | SupraLabs |
|
|
|
|
| 98 |
| **Precision** | bfloat16 |
|
| 99 |
| **License** | Apache 2.0 |
|
| 100 |
|
| 101 |
+
### Architecture details
|
| 102 |
|
| 103 |
| Hyperparameter | Value |
|
| 104 |
| ----- | ----- |
|
| 105 |
+
| Architecture | `Qwen3ForCausalLM` |
|
| 106 |
| Hidden size | 640 |
|
| 107 |
| Layers | 12 |
|
| 108 |
| Attention heads | 10 (MHA) |
|
|
|
|
| 112 |
| Positional encoding | RoPE θ=10,000 |
|
| 113 |
| Normalization | RMSNorm, ε=10⁻⁶ |
|
| 114 |
| Tied embeddings | Yes |
|
|
|
|
|
|
|
| 115 |
|
| 116 |
---
|
| 117 |
|
|
|
|
| 127 |
### Data
|
| 128 |
|
| 129 |
| Source | Approx. tokens | Phase |
|
| 130 |
+
| ----- | ----- | ----- |
|
| 131 |
| `Ultra-FineWeb-en` | 44B | Warmup + Stable |
|
| 132 |
| `dclm_100BT-shuffled` | 28B | Warmup + Stable |
|
| 133 |
+
| `UltraData-Code-L2` (70% `py` / 30% `js`) | 8B | Warmup + Stable |
|
| 134 |
| Mix of Ultra-FineWeb-en, Finephrase, TxT360-v2, Dolma3-Dolmino-Mix-100B-1025, UltraData-Math and IFM/Pretrain-Behaviors | 20B | Decay |
|
| 135 |
|
| 136 |
+
---
|
| 137 |
+
|
| 138 |
+
## Training Procedure
|
| 139 |
+
|
| 140 |
+
| Setting | Value |
|
| 141 |
+
| ----- | ----- |
|
| 142 |
+
| Optimizer | AdamW (fused), β₁=0.9, β₂=0.95, ε=10⁻⁸ |
|
| 143 |
+
| Peak learning rate | 3.8e-4 |
|
| 144 |
+
| LR schedule | WSD |
|
| 145 |
+
| Micro batch size per device | 256 |
|
| 146 |
+
| Gradient accumulation | 1 |
|
| 147 |
+
| Weight decay | 0.1 |
|
| 148 |
+
| Gradient clipping | 1.0 |
|
| 149 |
+
| Mixed precision | BF16 \+ TF32 |
|
| 150 |
+
| Hardware | 2× RTX A6000 48GB NVLink |
|
| 151 |
+
| Training optimizations | Liger Kernel, DDP bucketing (10MB), gradient\_as\_bucket\_view |
|
| 152 |
+
|
| 153 |
+
---
|
| 154 |
+
|
| 155 |
+
## What makes this model good
|
| 156 |
+
|
| 157 |
+
### Higher quality data
|
| 158 |
+
|
| 159 |
+
Not just only FineWeb-Edu, but: high quality webdata, code, math, synthetic data, reasoning, Q&A and more...
|
| 160 |
+
|
| 161 |
+
### A new decay
|
| 162 |
+
|
| 163 |
+
We tried decaying the last 20B tokens just with the same data mix as in the warmup & stable phase. We found out, that this procedure was not leading to good benchmark and overall results.
|
| 164 |
+
So we tried to push our model even further and changed the data to a mix of Q&A, synthetic, math, reasoning data and much more!
|
| 165 |
+
And it increased the OpenSLM Leaderboard INT Index from 19 to 21!
|
| 166 |
+
|
| 167 |
+
### WSD Scheduler instead of cosine decay
|
| 168 |
+
|
| 169 |
+
We applied a WSD-Scheduler instead of using boring ol' cosine decay. And it worked. The model learned much more, leading to an end loss of around 2.1
|
| 170 |
+
|
| 171 |
+
---
|
| 172 |
+
|
| 173 |
+
## Usage
|
| 174 |
+
|
| 175 |
+
> Note: this is a base model, not an instruction-tuned variant! Keep that in mind.
|
| 176 |
+
|
| 177 |
+
```python
|
| 178 |
+
import torch
|
| 179 |
+
from transformers import AutoModelForCausalLM, AutoTokenizer
|
| 180 |
+
|
| 181 |
+
model_id = "SupraLabs/Supra2.5-Pro-Base"
|
| 182 |
+
|
| 183 |
+
tokenizer = AutoTokenizer.from_pretrained(model_id)
|
| 184 |
+
model = AutoModelForCausalLM.from_pretrained(
|
| 185 |
+
model_id,
|
| 186 |
+
torch_dtype=torch.bfloat16,
|
| 187 |
+
device_map="auto",
|
| 188 |
+
)
|
| 189 |
+
model.eval()
|
| 190 |
+
|
| 191 |
+
prompt = "The future of artificial intelligence"
|
| 192 |
+
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
|
| 193 |
+
|
| 194 |
+
with torch.no_grad():
|
| 195 |
+
out = model.generate(
|
| 196 |
+
**inputs,
|
| 197 |
+
max_new_tokens=384,
|
| 198 |
+
do_sample=True,
|
| 199 |
+
temperature=0.1,
|
| 200 |
+
top_p=0.8,
|
| 201 |
+
top_k=5,
|
| 202 |
+
no_repeat_ngram_size=3,
|
| 203 |
+
repetition_penalty=1.2,
|
| 204 |
+
)
|
| 205 |
+
|
| 206 |
+
print(tokenizer.decode(out[0], skip_special_tokens=True))
|
| 207 |
+
```
|
| 208 |
+
|
| 209 |
+
---
|
| 210 |
+
|
| 211 |
+
## Intended use & limitations
|
| 212 |
+
|
| 213 |
+
Use the model for:
|
| 214 |
+
- finetuning
|
| 215 |
+
- experiments
|
| 216 |
+
- research
|
| 217 |
+
- inspiration for your next project
|
| 218 |
+
- ablation studies
|
| 219 |
+
|
| 220 |
+
But keep in mind, that the model has limitations:
|
| 221 |
+
- it's very small so we cannot guarantee fact correctness
|
| 222 |
+
- the model is a base model, so it cannot really "answer" questions
|
| 223 |
+
- it currently does English-only very well; other languages may be supported and we already saw the model write e.g. German, French and Spanish; but the models' main language is English.
|
| 224 |
+
- it was trained on webdata so it may have a bias
|
| 225 |
+
|
| 226 |
+
---
|
| 227 |
+
|
| 228 |
+
## What's next
|
| 229 |
+
|
| 230 |
+
At SupraLabs, we are heavily developing the next architectures, improving our models and hoping to give you the next best model soon!
|
| 231 |
+
Give us a follow and a like on Hugging Face if you want to support our work.
|
| 232 |
+
|
| 233 |
+
---
|
| 234 |
+
|
| 235 |
+
*© SupraLabs 2026*
|