Instructions to use SupraLabs/Supra2-100M-Base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use SupraLabs/Supra2-100M-Base with Transformers:

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

pipe = pipeline("text-generation", model="SupraLabs/Supra2-100M-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/Supra2-100M-Base")
model = AutoModelForCausalLM.from_pretrained("SupraLabs/Supra2-100M-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/Supra2-100M-Base with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "SupraLabs/Supra2-100M-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/Supra2-100M-Base",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/SupraLabs/Supra2-100M-Base

SGLang

How to use SupraLabs/Supra2-100M-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/Supra2-100M-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/Supra2-100M-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/Supra2-100M-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/Supra2-100M-Base",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use SupraLabs/Supra2-100M-Base with Docker Model Runner:
```
docker model run hf.co/SupraLabs/Supra2-100M-Base
```

LH-Tech-AI commited on Aug 3

Commit

99ffdce

verified ·

1 Parent(s): c3570a1

Update README.md

Browse files

Files changed (1) hide show

README.md +0 -97

README.md CHANGED Viewed

@@ -1,97 +0,0 @@
----
-library_name: transformers
-tags:
-- generated_from_trainer
-model-index:
-- name: Supra2-100M
-  results: []
----
-<!-- This model card has been generated automatically according to the information the Trainer had access to. You
-should probably proofread and complete it, then remove this comment. -->
-# Supra2-100M
-This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
-It achieves the following results on the evaluation set:
-- Loss: 2.9153
-## Model description
-More information needed
-## Intended uses & limitations
-More information needed
-## Training and evaluation data
-More information needed
-## Training procedure
-### Training hyperparameters
-The following hyperparameters were used during training:
-- learning_rate: 0.001
-- train_batch_size: 16
-- eval_batch_size: 16
-- seed: 1234
-- gradient_accumulation_steps: 16
-- total_train_batch_size: 256
-- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.95) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
-- lr_scheduler_type: warmup_stable_decay
-- lr_scheduler_warmup_steps: 2000
-- training_steps: 114440
-### Training results
-| Training Loss | Epoch  | Step   | Validation Loss |
-|:-------------:|:------:|:------:|:---------------:|
-| 3.5184        | 0.0262 | 3000   | 3.5187          |
-| 3.3231        | 0.0524 | 6000   | 3.3262          |
-| 3.2557        | 0.0786 | 9000   | 3.2579          |
-| 3.2145        | 0.1049 | 12000  | 3.2213          |
-| 3.1894        | 0.1311 | 15000  | 3.1985          |
-| 3.1680        | 0.1573 | 18000  | 3.1807          |
-| 3.1595        | 0.1835 | 21000  | 3.1685          |
-| 3.1447        | 0.2097 | 24000  | 3.1584          |
-| 3.1394        | 0.2359 | 27000  | 3.1513          |
-| 3.1370        | 0.2621 | 30000  | 3.1445          |
-| 3.1274        | 0.2884 | 33000  | 3.1397          |
-| 3.1241        | 0.3146 | 36000  | 3.1342          |
-| 3.1209        | 0.3408 | 39000  | 3.1284          |
-| 3.1139        | 0.3670 | 42000  | 3.1263          |
-| 3.1111        | 0.3932 | 45000  | 3.1220          |
-| 3.1054        | 0.4194 | 48000  | 3.1174          |
-| 3.1098        | 0.4456 | 51000  | 3.1145          |
-| 3.1013        | 0.4719 | 54000  | 3.1148          |
-| 3.0979        | 0.4981 | 57000  | 3.1115          |
-| 3.0997        | 0.5243 | 60000  | 3.1096          |
-| 3.0936        | 0.5505 | 63000  | 3.1063          |
-| 3.0929        | 0.5767 | 66000  | 3.1047          |
-| 3.0921        | 0.6029 | 69000  | 3.1037          |
-| 3.0859        | 0.6291 | 72000  | 3.1005          |
-| 3.0870        | 0.6554 | 75000  | 3.0998          |
-| 3.0855        | 0.6816 | 78000  | 3.0960          |
-| 3.0831        | 0.7078 | 81000  | 3.0957          |
-| 3.0825        | 0.7340 | 84000  | 3.0944          |
-| 3.0784        | 0.7602 | 87000  | 3.0934          |
-| 3.0758        | 0.7864 | 90000  | 3.0901          |
-| 3.0499        | 0.8126 | 93000  | 3.0621          |
-| 3.0132        | 0.8389 | 96000  | 3.0291          |
-| 2.9880        | 0.8651 | 99000  | 3.0066          |
-| 2.9662        | 0.8913 | 102000 | 2.9853          |
-| 2.9533        | 0.9175 | 105000 | 2.9670          |
-| 2.9310        | 0.9437 | 108000 | 2.9481          |
-| 2.9156        | 0.9699 | 111000 | 2.9308          |
-| 2.8962        | 0.9961 | 114000 | 2.9161          |
-| 2.8954        | 1.0000 | 114440 | 2.9153          |
-### Framework versions
-- Transformers 5.14.1
-- Pytorch 2.13.0+cu130
-- Datasets 5.0.1
-- Tokenizers 0.22.2