Instructions to use krory/GenBook-Deepseek-R1.Llama-8B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use krory/GenBook-Deepseek-R1.Llama-8B with Transformers:

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

pipe = pipeline("text-generation", model="krory/GenBook-Deepseek-R1.Llama-8B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("krory/GenBook-Deepseek-R1.Llama-8B")
model = AutoModelForMultimodalLM.from_pretrained("krory/GenBook-Deepseek-R1.Llama-8B")
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]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use krory/GenBook-Deepseek-R1.Llama-8B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "krory/GenBook-Deepseek-R1.Llama-8B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "krory/GenBook-Deepseek-R1.Llama-8B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/krory/GenBook-Deepseek-R1.Llama-8B

SGLang

How to use krory/GenBook-Deepseek-R1.Llama-8B 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 "krory/GenBook-Deepseek-R1.Llama-8B" \
    --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": "krory/GenBook-Deepseek-R1.Llama-8B",
		"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 "krory/GenBook-Deepseek-R1.Llama-8B" \
        --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": "krory/GenBook-Deepseek-R1.Llama-8B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Studio

How to use krory/GenBook-Deepseek-R1.Llama-8B with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for krory/GenBook-Deepseek-R1.Llama-8B to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for krory/GenBook-Deepseek-R1.Llama-8B to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for krory/GenBook-Deepseek-R1.Llama-8B to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="krory/GenBook-Deepseek-R1.Llama-8B",
    max_seq_length=2048,
)

Docker Model Runner
How to use krory/GenBook-Deepseek-R1.Llama-8B with Docker Model Runner:
```
docker model run hf.co/krory/GenBook-Deepseek-R1.Llama-8B
```

krory commited on Jan 29, 2025

Commit

ef5aae3

verified ·

1 Parent(s): bac7534

Update README.md

Browse files

Files changed (1) hide show

README.md +24 -6

README.md CHANGED Viewed

@@ -9,15 +9,33 @@ tags:
 - sft
 license: apache-2.0
 language:
 - en
 ---
-# Uploaded  model
-- **Developed by:** krory
-- **License:** apache-2.0
-- **Finetuned from model :** unsloth/deepseek-r1-distill-llama-8b-unsloth-bnb-4bit
-This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
-[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)

 - sft
 license: apache-2.0
 language:
+- es
 - en
 ---
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/6792d6218095a2eec33ce7d9/pDOOJJGZBA2q4Ez-3nrLK.png)
+### **About the Model**
+This model is designed to be a storytelling AI capable of creating fun, engaging, and well-structured narratives. Its purpose is to serve as an interactive tool for generating and experiencing unique stories in real time, tailored to the user's input and preferences.
+### **Key Features**
+- **Interactive Narratives:** Produces coherent and entertaining stories based on user prompts, adapting dynamically to maintain engagement.
+- **Consistent World-Building:** Ensures logical progression and consistency in characters, settings, and events across long narratives.
+- **Optimized for Efficiency:** Built to perform reliably on limited hardware while delivering high-quality outputs.
+### **Training Overview**
+The model was fine-tuned using datasets focused on narrative construction, character development, and immersive descriptions. Key aspects of the training include:
+- **Adaptability:** Special attention was given to creating a system that responds flexibly to varied user inputs while maintaining coherence.
+- **Resource Efficiency:** Techniques like LoRA (Low-Rank Adaptation) and 4-bit quantization were employed to optimize memory usage without compromising output quality.
+- **Long-Context Support:** Enhanced with methods to handle extended interactions and complex storylines.
+### **Purpose**
+The primary goal of this model is to create a personal, customizable storytelling AI, allowing users to immerse themselves in unique, AI-driven stories anytime.
+---