Instructions to use Sophia-AI/RegTech-32B-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Sophia-AI/RegTech-32B-Instruct with Transformers:

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

pipe = pipeline("text-generation", model="Sophia-AI/RegTech-32B-Instruct")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Sophia-AI/RegTech-32B-Instruct")
model = AutoModelForCausalLM.from_pretrained("Sophia-AI/RegTech-32B-Instruct")
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=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Sophia-AI/RegTech-32B-Instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Sophia-AI/RegTech-32B-Instruct"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Sophia-AI/RegTech-32B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Sophia-AI/RegTech-32B-Instruct

SGLang

How to use Sophia-AI/RegTech-32B-Instruct 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 "Sophia-AI/RegTech-32B-Instruct" \
    --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": "Sophia-AI/RegTech-32B-Instruct",
		"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 "Sophia-AI/RegTech-32B-Instruct" \
        --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": "Sophia-AI/RegTech-32B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Sophia-AI/RegTech-32B-Instruct with Docker Model Runner:
```
docker model run hf.co/Sophia-AI/RegTech-32B-Instruct
```

MwSpace commited on Feb 13

Commit

e77c63e

verified ·

1 Parent(s): a0be32e

Update README.md

Browse files

Files changed (1) hide show

README.md +0 -14

README.md CHANGED Viewed

@@ -201,20 +201,6 @@ messages = [
 | 📦 **Dataset** | 923 train / 102 eval samples |
 | ⏱️ **Duration** | 40.0 minutes |
-### Hyperparameters
-| Parameter | Value |
-|---|---|
-| LoRA Rank / Alpha | 16 / 32 |
-| LoRA Dropout | 0.10 |
-| Target Modules | q, k, v, o, gate, up, down proj |
-| Learning Rate | 5e-6 (cosine scheduler) |
-| Epochs | 3 |
-| Effective Batch Size | 4 (1 × 4 accum) |
-| Max Sequence Length | 4096 |
-| NEFTune Alpha | 5.0 |
-| Warmup Ratio | 0.05 |
 ### 📉 Training Metrics
 | Metric | Value |

 | 📦 **Dataset** | 923 train / 102 eval samples |
 | ⏱️ **Duration** | 40.0 minutes |
 ### 📉 Training Metrics
 | Metric | Value |