Instructions to use Nitral-AI/Captain-Eris_Violet-GRPO-v0.420 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Nitral-AI/Captain-Eris_Violet-GRPO-v0.420 with Transformers:

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

pipe = pipeline("text-generation", model="Nitral-AI/Captain-Eris_Violet-GRPO-v0.420")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("Nitral-AI/Captain-Eris_Violet-GRPO-v0.420")
model = AutoModelForMultimodalLM.from_pretrained("Nitral-AI/Captain-Eris_Violet-GRPO-v0.420")
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]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Nitral-AI/Captain-Eris_Violet-GRPO-v0.420 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Nitral-AI/Captain-Eris_Violet-GRPO-v0.420"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Nitral-AI/Captain-Eris_Violet-GRPO-v0.420",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Nitral-AI/Captain-Eris_Violet-GRPO-v0.420

SGLang

How to use Nitral-AI/Captain-Eris_Violet-GRPO-v0.420 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 "Nitral-AI/Captain-Eris_Violet-GRPO-v0.420" \
    --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": "Nitral-AI/Captain-Eris_Violet-GRPO-v0.420",
		"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 "Nitral-AI/Captain-Eris_Violet-GRPO-v0.420" \
        --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": "Nitral-AI/Captain-Eris_Violet-GRPO-v0.420",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Nitral-AI/Captain-Eris_Violet-GRPO-v0.420 with Docker Model Runner:
```
docker model run hf.co/Nitral-AI/Captain-Eris_Violet-GRPO-v0.420
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Update: The model image itself is now available as an importable character card for SillyTavern. This serves as an example of how to prepare your own card for use with this model.

Training Notes: This model was developed using a combination of multi-stage supervised fine-tuning, pre-trained QLoRA adapters, and multi-stage RLHF optimized with GRPO. The final model was created by merging the most promising candidates identified during the process.

Quants Here: Thanks to Mradermacher <3 Regular GGUF Imatrix GGUF 4bpw Exl2

SillyTavern Reasoning Block Parsing Example:

SillyTavern Mistral Formatting Example: Master Import Preset Here

Series Comparison:

The following YAML configuration was used to produce this final version of the model:

slices:
  - sources:
      - model: Nitral-AI/Captain-Eris_Violet-0.420-Rebased
        layer_range: [0, 40]
      - model: Nitral-AI/Captain-Eris_Violet-GRPO-Rebased
        layer_range: [0, 40]
merge_method: slerp
base_model: Nitral-AI/Captain-Eris_Violet-0.420-Rebased
parameters:
  t:
    - filter: self_attn
      value: [0, 0.5, 0.3, 0.7, 1]
    - filter: mlp
      value: [1, 0.5, 0.7, 0.3, 0]
    - value: 0.420
dtype: bfloat16

Downloads last month: 7

Safetensors

Model size

12B params

Tensor type

BF16

Model tree for Nitral-AI/Captain-Eris_Violet-GRPO-v0.420

Adapters

1 model

Finetunes

2 models

Merges

17 models

Quantizations

9 models