Instructions to use Egrigor/ValheimAssistantV1-16bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Egrigor/ValheimAssistantV1-16bit with Transformers:

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

pipe = pipeline("text-generation", model="Egrigor/ValheimAssistantV1-16bit")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Egrigor/ValheimAssistantV1-16bit")
model = AutoModelForCausalLM.from_pretrained("Egrigor/ValheimAssistantV1-16bit")
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

vLLM

How to use Egrigor/ValheimAssistantV1-16bit with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Egrigor/ValheimAssistantV1-16bit"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Egrigor/ValheimAssistantV1-16bit",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Egrigor/ValheimAssistantV1-16bit

SGLang

How to use Egrigor/ValheimAssistantV1-16bit 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 "Egrigor/ValheimAssistantV1-16bit" \
    --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": "Egrigor/ValheimAssistantV1-16bit",
		"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 "Egrigor/ValheimAssistantV1-16bit" \
        --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": "Egrigor/ValheimAssistantV1-16bit",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Studio new

How to use Egrigor/ValheimAssistantV1-16bit 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 Egrigor/ValheimAssistantV1-16bit 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 Egrigor/ValheimAssistantV1-16bit to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Egrigor/ValheimAssistantV1-16bit to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="Egrigor/ValheimAssistantV1-16bit",
    max_seq_length=2048,
)

Docker Model Runner
How to use Egrigor/ValheimAssistantV1-16bit with Docker Model Runner:
```
docker model run hf.co/Egrigor/ValheimAssistantV1-16bit
```

Valheim Assistant V1 - 16-bit Version

This is a fine-tuned version of the Unsloth Phi-3.5-mini-instruct model. It is designed to provide conversational assistance for the game Valheim, covering gameplay mechanics, lore, and in-game strategies.

This model is part of an ongoing hobbyist project, created by a novice enthusiast exploring fine-tuning techniques. While the dataset and model may have limitations, this project aims to improve over time through community feedback and iteration.

Model Details

Summary

This model has been fine-tuned on Egrigor/ValheimTestData, which contains conversational-style question-and-answer pairs derived from Valheim community resources.

Base Model: Unsloth Phi-3.5-mini-instruct
Language: English
License: Apache-2.0
Fine-Tuning Framework: Unsloth
Training Precision: 16-bit
Dataset: Egrigor/ValheimTestData

How to Use

To load and interact with the model, use the following code:

from unsloth import FastLanguageModel from transformers import AutoTokenizer

Load model and tokenizer

model = FastLanguageModel.from_pretrained("Egrigor/ValheimAssistantV1-16bit") tokenizer = AutoTokenizer.from_pretrained("Egrigor/ValheimAssistantV1-16bit")

Prepare input and generate output

inputs = tokenizer("How do I build a crafting station?", return_tensors="pt") outputs = model.generate(**inputs, max_length=100)

Decode and print the output

print(tokenizer.decode(outputs[0], skip_special_tokens=True))

Training Details

Framework: Unsloth

Batch Size per Device: 2

Gradient Accumulation Steps: 4

Learning Rate: 2e-4

Total Training Steps: 60

Training Time: ~3.5 minutes

Dataset

The dataset consists of gameplay tips, lore insights, and strategic guidance, formatted into conversational question-and-answer pairs.

Note: As this dataset was semi-automatically generated from community resources, it may contain inaccuracies or gaps. Feedback is welcome for future improvements.

Limitations and Future Work

Dataset Gaps: The dataset may not fully cover Valheims gameplay and lore, and some responses may be incomplete or inaccurate.

Generalization: This model is focused solely on Valheim-related content and may not perform well in other contexts.

Iterative Improvement: Future versions will refine the dataset and model based on testing and community feedback.

Contact and Feedback

This is an experimental project created by a novice AI enthusiast. Feedback, suggestions, and collaborations are highly welcome! Feel free to reach out via Hugging Face.

Let me know if there’s anything specific you’d like to tweak or emphasize!

Downloads last month: 9

Model tree for Egrigor/ValheimAssistantV1-16bit

Base model

microsoft/Phi-3.5-mini-instruct

Finetuned

unsloth/Phi-3.5-mini-instruct

Finetuned

(94)

this model