Instructions to use sh0ck0r/Kalypso-FP8-Dynamic with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use sh0ck0r/Kalypso-FP8-Dynamic with Transformers:

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

pipe = pipeline("text-generation", model="sh0ck0r/Kalypso-FP8-Dynamic")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("sh0ck0r/Kalypso-FP8-Dynamic")
model = AutoModelForCausalLM.from_pretrained("sh0ck0r/Kalypso-FP8-Dynamic", 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=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use sh0ck0r/Kalypso-FP8-Dynamic with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "sh0ck0r/Kalypso-FP8-Dynamic"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "sh0ck0r/Kalypso-FP8-Dynamic",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/sh0ck0r/Kalypso-FP8-Dynamic

SGLang

How to use sh0ck0r/Kalypso-FP8-Dynamic 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 "sh0ck0r/Kalypso-FP8-Dynamic" \
    --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": "sh0ck0r/Kalypso-FP8-Dynamic",
		"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 "sh0ck0r/Kalypso-FP8-Dynamic" \
        --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": "sh0ck0r/Kalypso-FP8-Dynamic",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use sh0ck0r/Kalypso-FP8-Dynamic with Docker Model Runner:
```
docker model run hf.co/sh0ck0r/Kalypso-FP8-Dynamic
```

sh0ck0r commited on Dec 23, 2025

Commit

39a6793

verified ·

1 Parent(s): 1d29af6

Upload FP8 quantized version of IIEleven11/Kalypso

Browse files

Files changed (2) hide show

chat_template.jinja +13 -0
tokenizer_config.json +1 -0

chat_template.jinja ADDED Viewed

	@@ -0,0 +1,13 @@

+{% for message in messages -%}
+{% if message['role'] == 'system' -%}
+<|system|>
+{{ message['content'] }}<|end|>
+{% elif message['role'] == 'user' -%}
+<|user|>
+{{ message['content'] }}<|end|>
+{% elif message['role'] == 'assistant' -%}
+<|assistant|>
+{{ message['content'] }}<|end|>
+{% endif -%}
+{% endfor -%}
+<|assistant|>

tokenizer_config.json CHANGED Viewed

@@ -8008,6 +8008,7 @@
   "clean_up_tokenization_spaces": false,
   "eos_token": "</s>",
   "extra_special_tokens": {},
   "model_max_length": 1000000000000000019884624838656,
   "tokenizer_class": "PreTrainedTokenizerFast",
   "unk_token": "<unk>"

   "clean_up_tokenization_spaces": false,
   "eos_token": "</s>",
   "extra_special_tokens": {},
+  "fix_mistral_regex": true,
   "model_max_length": 1000000000000000019884624838656,
   "tokenizer_class": "PreTrainedTokenizerFast",
   "unk_token": "<unk>"