Instructions to use Pramodith/topN_sigma_generation with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Pramodith/topN_sigma_generation with Transformers:

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

pipe = pipeline("text-generation", model="Pramodith/topN_sigma_generation")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Pramodith/topN_sigma_generation")
model = AutoModelForCausalLM.from_pretrained("Pramodith/topN_sigma_generation")
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 Pramodith/topN_sigma_generation with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/Pramodith/topN_sigma_generation

SGLang

How to use Pramodith/topN_sigma_generation 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 "Pramodith/topN_sigma_generation" \
    --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": "Pramodith/topN_sigma_generation",
		"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 "Pramodith/topN_sigma_generation" \
        --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": "Pramodith/topN_sigma_generation",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Pramodith/topN_sigma_generation with Docker Model Runner:
```
docker model run hf.co/Pramodith/topN_sigma_generation
```

Pramodith commited on Aug 5, 2025

Commit

9c424bf

1 Parent(s): 1c08fac

Update Readme.md

Browse files

Files changed (1) hide show

README.md +17 -7

README.md CHANGED Viewed

@@ -46,14 +46,24 @@ The authors recommend using `n_sigma=1.0` for most use cases, but you can experi
 ```py
 from transformers import AutoModelForCausalLM, AutoTokenizer
-tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen2.5-0.5B-Instruct")
-model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2.5-0.5B-Instruct", device_map="auto")
-inputs = tokenizer(["The quick brown"], return_tensors="pt").to(model.device)
 # There is a print message hardcoded in the custom generation method
-gen_out = model.generate(**inputs, n_sigma=1.0, custom_generate="Pramodith/topN_sigma_generation", trust_remote_code=True)
-print(tokenizer.batch_decode(gen_out))
 ```
 ### Citation

 ```py
 from transformers import AutoModelForCausalLM, AutoTokenizer
+from transformers import GenerationConfig
+tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen3-0.6B")
+model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3-0.6B", device_map="auto")
+generation_config = GenerationConfig(temperature=1.5, max_length=128)
+messages = [{"role":"user", "content": "Write a story about a dog and cat becoming friends."}]
+text = tokenizer.apply_chat_template(
+    messages,
+    tokenize=False,
+    add_generation_prompt=True,
+    enable_thinking=False # Switches between thinking and non-thinking modes. Default is True.
+)
+model_inputs = tokenizer([text], return_tensors="pt").to(model.device)
 # There is a print message hardcoded in the custom generation method
+gen_out = model.generate(**model_inputs, n_sigma=1.0, generation_config=generation_config, custom_generate="Pramodith/topN_sigma_generation", trust_remote_code=True)
+print(tokenizer.batch_decode(gen_out, skip_special_tokens=True)[0])
 ```
 ### Citation