Instructions to use mrcuddle/Unbound-Llama3-8B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mrcuddle/Unbound-Llama3-8B with Transformers:

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

pipe = pipeline("text-generation", model="mrcuddle/Unbound-Llama3-8B")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("mrcuddle/Unbound-Llama3-8B")
model = AutoModelForCausalLM.from_pretrained("mrcuddle/Unbound-Llama3-8B")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use mrcuddle/Unbound-Llama3-8B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "mrcuddle/Unbound-Llama3-8B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "mrcuddle/Unbound-Llama3-8B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/mrcuddle/Unbound-Llama3-8B

SGLang

How to use mrcuddle/Unbound-Llama3-8B 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 "mrcuddle/Unbound-Llama3-8B" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "mrcuddle/Unbound-Llama3-8B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "mrcuddle/Unbound-Llama3-8B" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "mrcuddle/Unbound-Llama3-8B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use mrcuddle/Unbound-Llama3-8B with Docker Model Runner:
```
docker model run hf.co/mrcuddle/Unbound-Llama3-8B
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

merge

This is a merge of pre-trained language models created using mergekit.

Merge Details

Merge Method

This model was merged using the task arithmetic merge method using winglian/llama-3-8b-1m-PoSE as a base.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: aifeifei798/llama3-8B-DarkIdol-2.3-Uncensored-32K
    parameters:
      density: 0.65
      weight: 0.15
  - model: NeverSleep/Llama-3-Lumimaid-8B-v0.1
    parameters:
      density: 0.70
      weight: 0.20
  - model: mergekit-community/because_im_bored_nsfw1
    parameters:
      density: 0.60
      weight: 0.10
  - model: jondurbin/bagel-8b-v1.0
    parameters:
      density: 0.60
      weight: 0.10
  - model: Orenguteng/Llama-3.1-8B-Lexi-Uncensored-V2
    parameters:
      density: 0.65
      weight: 0.15
  - model: Undi95/Llama-3-LewdPlay-8B-evo
    parameters:
      density: 0.75
      weight: 0.25
  - model: Deev124/hermes-llama3-roleplay-4000-v1
    parameters:
      density: 0.60
      weight: 0.10
  - model: DevsDoCode/LLama-3-8b-Uncensored
    parameters:
      density: 0.60
      weight: 0.10
  - model: mlabonne/Hermes-3-Llama-3.1-8B-lorablated
    parameters:
      density: 0.65
      weight: 0.15
  - model: vicgalle/Roleplay-Llama-3-8B
    parameters:
      density: 0.70
      weight: 0.20
  - model: Gryphe/Pantheon-RP-1.0-8b-Llama-3
    parameters:
      density: 0.70
      weight: 0.20
  - model: vicgalle/Humanish-Roleplay-Llama-3.1-8B
    parameters:
      density: 0.70
      weight: 0.20
  - model: vicgalle/Unsafe-Llama-3-8B
    parameters:
      density: 0.70
      weight: 0.20
  - model: winglian/llama-3-8b-1m-PoSE
    parameters:
      density: 0.70
      weight: 0.20

merge_method: task_arithmetic
base_model: winglian/llama-3-8b-1m-PoSE
parameters:
  normalize: true
  int8_mask: true
dtype: float16