Instructions to use Indexnusrefather/Nyx-RP-Mini-2.6B-Instruct-2608-v0.1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Indexnusrefather/Nyx-RP-Mini-2.6B-Instruct-2608-v0.1 with Transformers:

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

pipe = pipeline("text-generation", model="Indexnusrefather/Nyx-RP-Mini-2.6B-Instruct-2608-v0.1")
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("Indexnusrefather/Nyx-RP-Mini-2.6B-Instruct-2608-v0.1")
model = AutoModelForCausalLM.from_pretrained("Indexnusrefather/Nyx-RP-Mini-2.6B-Instruct-2608-v0.1", 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 Indexnusrefather/Nyx-RP-Mini-2.6B-Instruct-2608-v0.1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Indexnusrefather/Nyx-RP-Mini-2.6B-Instruct-2608-v0.1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Indexnusrefather/Nyx-RP-Mini-2.6B-Instruct-2608-v0.1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Indexnusrefather/Nyx-RP-Mini-2.6B-Instruct-2608-v0.1

SGLang

How to use Indexnusrefather/Nyx-RP-Mini-2.6B-Instruct-2608-v0.1 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 "Indexnusrefather/Nyx-RP-Mini-2.6B-Instruct-2608-v0.1" \
    --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": "Indexnusrefather/Nyx-RP-Mini-2.6B-Instruct-2608-v0.1",
		"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 "Indexnusrefather/Nyx-RP-Mini-2.6B-Instruct-2608-v0.1" \
        --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": "Indexnusrefather/Nyx-RP-Mini-2.6B-Instruct-2608-v0.1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Indexnusrefather/Nyx-RP-Mini-2.6B-Instruct-2608-v0.1 with Docker Model Runner:
```
docker model run hf.co/Indexnusrefather/Nyx-RP-Mini-2.6B-Instruct-2608-v0.1
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Nyx-RP-Mini-2.6B-Instruct-2608-v0.1: A tiny model that inherited writing style of much bigger models!

"Does high quality and engaging roleplay, even at its smallest!"

Quick Overview:

What was done:

Thinking was fully removed
Writing and narrative consistency was improved
Performance over long roleplay sessions was improved
Stability and model intelligence was fully maintained

Quants(This time quants and safetensor files will be in DIFFERENT repos!):

BF16: Overkill
Q8_0: Highest quality
Q6_K: Very high quality, lossless
Q5_K_M: Very high quality, near lossless
Q4_K_M: Decent quality, fast

Creator Note:

I think I will release a next version sooner or later, this is only my first attempt, I will also work on expanding my dataset soon.

Downloads last month: 20

Safetensors

Model size

3B params

Tensor type

F32

BF16

Model tree for Indexnusrefather/Nyx-RP-Mini-2.6B-Instruct-2608-v0.1

Base model

LiquidAI/LFM2.5-2.6B-Base

Finetuned

LiquidAI/LFM2.5-2.6B

Finetuned

(75)

this model

Quantizations

2 models