Roleplay
Character-driven interaction, personas, dialogue, emotional scenes, and long-form roleplay.
How to use Vortex5/Fenrir-X-26B-A4B with Transformers:
# Use a pipeline as a high-level helper
from transformers import pipeline
pipe = pipeline("image-text-to-text", model="Vortex5/Fenrir-X-26B-A4B")
messages = [
{
"role": "user",
"content": [
{"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
{"type": "text", "text": "What animal is on the candy?"}
]
},
]
pipe(text=messages) # Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM
processor = AutoProcessor.from_pretrained("Vortex5/Fenrir-X-26B-A4B")
model = AutoModelForMultimodalLM.from_pretrained("Vortex5/Fenrir-X-26B-A4B", device_map="auto")
messages = [
{
"role": "user",
"content": [
{"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
{"type": "text", "text": "What animal is on the candy?"}
]
},
]
inputs = processor.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(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))How to use Vortex5/Fenrir-X-26B-A4B with vLLM:
# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Vortex5/Fenrir-X-26B-A4B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
-H "Content-Type: application/json" \
--data '{
"model": "Vortex5/Fenrir-X-26B-A4B",
"messages": [
{
"role": "user",
"content": [
{
"type": "text",
"text": "Describe this image in one sentence."
},
{
"type": "image_url",
"image_url": {
"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
}
}
]
}
]
}'docker model run hf.co/Vortex5/Fenrir-X-26B-A4B
How to use Vortex5/Fenrir-X-26B-A4B with SGLang:
# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
--model-path "Vortex5/Fenrir-X-26B-A4B" \
--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": "Vortex5/Fenrir-X-26B-A4B",
"messages": [
{
"role": "user",
"content": [
{
"type": "text",
"text": "Describe this image in one sentence."
},
{
"type": "image_url",
"image_url": {
"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
}
}
]
}
]
}'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 "Vortex5/Fenrir-X-26B-A4B" \
--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": "Vortex5/Fenrir-X-26B-A4B",
"messages": [
{
"role": "user",
"content": [
{
"type": "text",
"text": "Describe this image in one sentence."
},
{
"type": "image_url",
"image_url": {
"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
}
}
]
}
]
}'How to use Vortex5/Fenrir-X-26B-A4B with Docker Model Runner:
docker model run hf.co/Vortex5/Fenrir-X-26B-A4B
Fenrir-X-26B-A4B was created by combining gemma-4-26B-A4B-it, gemma-4-26B-A4B-it-Claude-Opus-Distill-v2, Pantheon-Reasoning-26B-A4B-1.1-V2, gemma4-26b-fiction-bf16, and Gemma-4-26B-A4B-Animus-V14.1-FFT using a custom merge method.
base_model: google/gemma-4-26B-A4B-it
models:
- model: TeichAI/gemma-4-26B-A4B-it-Claude-Opus-Distill-v2
parameters:
weight:
- filter: self_attn.q_proj.weight
value: [0.16, 0.2, 0.24, 0.26, 0.28]
- filter: self_attn.k_proj.weight
value: [0.15, 0.19, 0.22, 0.24, 0.26]
- filter: self_attn.v_proj.weight
value: [0.15, 0.19, 0.23, 0.25, 0.27]
- filter: self_attn.o_proj.weight
value: [0.09, 0.12, 0.15, 0.17, 0.19]
- filter: mlp.gate_proj.weight
value: [0.09, 0.12, 0.15, 0.17, 0.18]
- filter: mlp.up_proj.weight
value: [0.09, 0.12, 0.15, 0.17, 0.18]
- filter: mlp.down_proj.weight
value: [0.08, 0.11, 0.14, 0.16, 0.17]
- filter: experts.gate_up_proj
value: [0.18, 0.22, 0.25, 0.26, 0.25]
- filter: experts.down_proj
value: [0.2, 0.24, 0.27, 0.28, 0.27]
- value: 0.0
- model: Gryphe/Pantheon-Reasoning-26B-A4B-1.1-V2
parameters:
weight:
- filter: self_attn.q_proj.weight
value: [0.14, 0.17, 0.2, 0.23, 0.25]
- filter: self_attn.k_proj.weight
value: [0.13, 0.16, 0.19, 0.22, 0.24]
- filter: self_attn.v_proj.weight
value: [0.14, 0.17, 0.2, 0.23, 0.25]
- filter: self_attn.o_proj.weight
value: [0.15, 0.19, 0.23, 0.27, 0.31]
- filter: mlp.gate_proj.weight
value: [0.15, 0.19, 0.23, 0.27, 0.31]
- filter: mlp.up_proj.weight
value: [0.15, 0.19, 0.23, 0.27, 0.31]
- filter: mlp.down_proj.weight
value: [0.14, 0.18, 0.22, 0.26, 0.3]
- filter: experts.gate_up_proj
value: [0.14, 0.16, 0.18, 0.19, 0.2]
- filter: experts.down_proj
value: [0.15, 0.17, 0.19, 0.2, 0.21]
- value: 0.0
- model: electroglyph/gemma4-26b-fiction-bf16
parameters:
weight:
- filter: self_attn.q_proj.weight
value: [0.08, 0.1, 0.12, 0.14, 0.16]
- filter: self_attn.k_proj.weight
value: [0.07, 0.09, 0.11, 0.13, 0.15]
- filter: self_attn.v_proj.weight
value: [0.09, 0.11, 0.13, 0.15, 0.17]
- filter: self_attn.o_proj.weight
value: [0.17, 0.21, 0.25, 0.29, 0.33]
- filter: mlp.gate_proj.weight
value: [0.18, 0.22, 0.26, 0.3, 0.34]
- filter: mlp.up_proj.weight
value: [0.18, 0.22, 0.26, 0.3, 0.34]
- filter: mlp.down_proj.weight
value: [0.17, 0.21, 0.25, 0.29, 0.33]
- filter: experts.gate_up_proj
value: [0.22, 0.26, 0.29, 0.3, 0.3]
- filter: experts.down_proj
value: [0.24, 0.28, 0.31, 0.32, 0.32]
- value: 0.0
- model: Darkhn/Gemma-4-26B-A4B-Animus-V14.1-FFT
parameters:
weight:
- filter: experts.gate_up_proj
value: [0.27, 0.32, 0.36, 0.37, 0.36]
- filter: experts.down_proj
value: [0.3, 0.35, 0.39, 0.4, 0.39]
- value: 0.0
merge_method: bsc
chat_template: auto
parameters:
gain: 0.95
balance: 0.95
synthesis: 0.92
anchor: 0.92
dtype: float32
out_dtype: bfloat16
tokenizer:
source: base
Character-driven interaction, personas, dialogue, emotional scenes, and long-form roleplay.
Fiction, dialogue, atmosphere, descriptive writing, stylistic drafting, and imaginative prose.
Long-form narratives, worldbuilding, continuity, evolving characters, and multi-character plots.
Branching narratives, scenario play, character interaction, and continuously evolving stories.