Instructions to use Dxniz/Novelist1.0-27b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Dxniz/Novelist1.0-27b with Transformers:

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

pipe = pipeline("text-generation", model="Dxniz/Novelist1.0-27b")
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("Dxniz/Novelist1.0-27b")
model = AutoModelForMultimodalLM.from_pretrained("Dxniz/Novelist1.0-27b", 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]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Dxniz/Novelist1.0-27b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Dxniz/Novelist1.0-27b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Dxniz/Novelist1.0-27b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Dxniz/Novelist1.0-27b

SGLang

How to use Dxniz/Novelist1.0-27b 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 "Dxniz/Novelist1.0-27b" \
    --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": "Dxniz/Novelist1.0-27b",
		"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 "Dxniz/Novelist1.0-27b" \
        --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": "Dxniz/Novelist1.0-27b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Dxniz/Novelist1.0-27b with Docker Model Runner:
```
docker model run hf.co/Dxniz/Novelist1.0-27b
```

Dxniz commited on 6 days ago

Commit

fee7456

verified ·

1 Parent(s): 3522c3b

Update README.md

Browse files

Files changed (1) hide show

README.md +2 -18

README.md CHANGED Viewed

@@ -30,7 +30,6 @@ Novelist1.0 is trained to **stay in the scene**: concrete sensory detail, charac
 - **Scene over slogan.** Prefers objects, weather, gesture, and dialogue to abstract feeling and stock metaphors.
 - **Length as a contract.** If you ask for a word count or a range (`800 words`, `1000 kelime`, `800–1200`), it treats that as part of the task, not decoration.
 - **User text is canon.** Does not “correct” or overwrite what the user already established in the prompt.
-- **Bilingual.** English and Turkish in the same style register — literary, not localizationese.
 - **Anti-slop.** Pushes back on cliché loops, repeated cadence, and empty intensifiers that pad a paragraph without moving the scene.
 It is a writer, not an assistant. Weak on tools, code, and factual Q&A; that is by design.
@@ -43,15 +42,14 @@ Give **situation + constraint**, not a vibe:
 - Length, tense, POV, and what to leave unsaid.
 - Optional: a quota (`Write 600 words.` / `En az 800 en fazla 1200 kelime.`).
-A system line such as *“You are a literary fiction writer. Follow the prompt exactly.”* matches how it was steered.
 ## Sampling (Qwen3.8)
-**Instruct (recommended for stories)** — thinking off:
 `temperature 0.7` · `top_p 0.80` · `top_k 20` · `min_p 0` · `presence_penalty 1.5` · `repetition_penalty 1.0` · `enable_thinking=false`
-**Thinking** — if you want a plan before the prose:
 `temperature 1.0` · `top_p 0.95` · `top_k 20` · `min_p 0` · `presence_penalty 0` · `repetition_penalty 1.0` · `enable_thinking=true`
@@ -87,20 +85,6 @@ out = model.generate(
 print(tok.decode(out[0][inputs.input_ids.shape[-1]:], skip_special_tokens=True))
 ```
-## vLLM
-Comfortable 16-bit serve on a ~96 GB GPU (TurboQuant KV):
-```bash
-vllm serve Dxniz/Novelist1.0-27b \
-  --dtype bfloat16 \
-  --max-model-len 12288 \
-  --kv-cache-dtype turboquant_4bit_nc \
-  --max-num-seqs 20 \
-  --gpu-memory-utilization 0.90 \
-  --trust-remote-code
-```
 On the chat call, set `chat_template_kwargs={"enable_thinking": false}` unless you explicitly want thinking. On 32 GB cards use FP8 or a 4-bit quant of this merge.
 ## Recipe (short)

 - **Scene over slogan.** Prefers objects, weather, gesture, and dialogue to abstract feeling and stock metaphors.
 - **Length as a contract.** If you ask for a word count or a range (`800 words`, `1000 kelime`, `800–1200`), it treats that as part of the task, not decoration.
 - **User text is canon.** Does not “correct” or overwrite what the user already established in the prompt.
 - **Anti-slop.** Pushes back on cliché loops, repeated cadence, and empty intensifiers that pad a paragraph without moving the scene.
 It is a writer, not an assistant. Weak on tools, code, and factual Q&A; that is by design.
 - Length, tense, POV, and what to leave unsaid.
 - Optional: a quota (`Write 600 words.` / `En az 800 en fazla 1200 kelime.`).
 ## Sampling (Qwen3.8)
+**Instruct (recommended for stories)** - thinking off:
 `temperature 0.7` · `top_p 0.80` · `top_k 20` · `min_p 0` · `presence_penalty 1.5` · `repetition_penalty 1.0` · `enable_thinking=false`
+**Thinking** - if you want a plan before the prose:
 `temperature 1.0` · `top_p 0.95` · `top_k 20` · `min_p 0` · `presence_penalty 0` · `repetition_penalty 1.0` · `enable_thinking=true`
 print(tok.decode(out[0][inputs.input_ids.shape[-1]:], skip_special_tokens=True))
 ```
 On the chat call, set `chat_template_kwargs={"enable_thinking": false}` unless you explicitly want thinking. On 32 GB cards use FP8 or a 4-bit quant of this merge.
 ## Recipe (short)