onlyfans

twitch

girlfriend-experience

conversational

text-generation-inference

Model card Files Files and versions

xet

Community

Instructions to use QuixiAI/Ina-v11.1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

Transformers

How to use QuixiAI/Ina-v11.1 with Transformers:

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

pipe = pipeline("text-generation", model="QuixiAI/Ina-v11.1")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("QuixiAI/Ina-v11.1")
model = AutoModelForCausalLM.from_pretrained("QuixiAI/Ina-v11.1", 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=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use QuixiAI/Ina-v11.1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "QuixiAI/Ina-v11.1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "QuixiAI/Ina-v11.1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/QuixiAI/Ina-v11.1

SGLang

How to use QuixiAI/Ina-v11.1 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 "QuixiAI/Ina-v11.1" \
    --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": "QuixiAI/Ina-v11.1",
		"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 "QuixiAI/Ina-v11.1" \
        --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": "QuixiAI/Ina-v11.1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use QuixiAI/Ina-v11.1 with Docker Model Runner:
```
docker model run hf.co/QuixiAI/Ina-v11.1
```

ehartford commited on Nov 29, 2025

Commit

c27e35a

verified ·

1 Parent(s): 557f89b

Create chat_template.jinja

Browse files

Files changed (1) hide show

chat_template.jinja +39 -0

chat_template.jinja ADDED Viewed

	@@ -0,0 +1,39 @@

+{# ============================================================
+   Ina-v11.1 Chat Template (Llama-3.1 header style)
+   ============================================================ #}
+{{- '<|begin_of_text|>' }}
+{%- for message in messages %}
+    {%- if message['role'] == 'system' %}
+        {{- '<|start_header_id|>system<|end_header_id|>' + '\n' }}
+        {{- message['content'] }}
+        {{- '<|eot_id|>' }}
+    {%- elif message['role'] == 'user' %}
+        {{- '<|start_header_id|>user<|end_header_id|>' + '\n' }}
+        {{- message['content'] }}
+        {{- '<|eot_id|>' }}
+    {%- elif message['role'] == 'assistant' %}
+        {{- '<|start_header_id|>assistant<|end_header_id|>' + '\n' }}
+        {{- message['content'] }}
+        {{- '<|eot_id|>' }}
+    {%- elif message['role'] == 'tool' %}
+        {# Optional: format tool responses if you ever add tools #}
+        {{- '<|start_header_id|>tool<|end_header_id|>' + '\n' }}
+        {{- message['content'] }}
+        {{- '<|eot_id|>' }}
+    {%- endif %}
+{%- endfor %}
+{# ============================================================
+   Optional: add generation header if user requests it
+   ============================================================ #}
+{%- if add_generation_prompt %}
+    {{- '<|start_header_id|>assistant<|end_header_id|>' + '\n' }}
+{%- endif %}