Instructions to use Azazelle/Llama-3-Nerdy-RP-8B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Azazelle/Llama-3-Nerdy-RP-8B with Transformers:

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

pipe = pipeline("text-generation", model="Azazelle/Llama-3-Nerdy-RP-8B")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Azazelle/Llama-3-Nerdy-RP-8B")
model = AutoModelForCausalLM.from_pretrained("Azazelle/Llama-3-Nerdy-RP-8B", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Azazelle/Llama-3-Nerdy-RP-8B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Azazelle/Llama-3-Nerdy-RP-8B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Azazelle/Llama-3-Nerdy-RP-8B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Azazelle/Llama-3-Nerdy-RP-8B

SGLang

How to use Azazelle/Llama-3-Nerdy-RP-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 "Azazelle/Llama-3-Nerdy-RP-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": "Azazelle/Llama-3-Nerdy-RP-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 "Azazelle/Llama-3-Nerdy-RP-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": "Azazelle/Llama-3-Nerdy-RP-8B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Azazelle/Llama-3-Nerdy-RP-8B with Docker Model Runner:
```
docker model run hf.co/Azazelle/Llama-3-Nerdy-RP-8B
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

nerdy_rp

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

Merge Details

Merge Method

This model was merged using the Model Stock merge method using output/stop_it_nerd as a base.

Models Merged

The following models were included in the merge:

output/stop_it_nerd + ToastyPigeon/Llama-3-8B-Instruct-SpringDragon-V2-QLoRA
output/stop_it_nerd + Azazelle/Aura_Llama3
output/stop_it_nerd + Azazelle/llama3-8b-hikikomori-v0.4
output/stop_it_nerd + Azazelle/RP_Format_QuoteAsterisk_Llama3
output/stop_it_nerd + Azazelle/Theory_of_Mind_Llama3
output/stop_it_nerd + Azazelle/Llama-3-Instruct-LiPPA-LoRA-8B
output/stop_it_nerd + Azazelle/ANJIR-ADAPTER-128
output/stop_it_nerd + Azazelle/Llama3_RP_ORPO_LoRA
output/stop_it_nerd + Azazelle/Smarts_Llama3
output/stop_it_nerd + Azazelle/BlueMoon_Llama3
output/stop_it_nerd + Azazelle/Llama-3-LimaRP-Instruct-LoRA-8B
output/stop_it_nerd + Azazelle/Nimue-8B
output/stop_it_nerd + Azazelle/Luna_Llama3
output/stop_it_nerd + Azazelle/Llama-3-LongStory-LORA
output/stop_it_nerd + Azazelle/Llama-3-8B-Abomination-LORA

Configuration

The following YAML configuration was used to produce this model:

base_model: output/stop_it_nerd
dtype: bfloat16
merge_method: model_stock
slices:
- sources:
  - layer_range: [0, 32]
    model: output/stop_it_nerd+Azazelle/Llama-3-8B-Abomination-LORA
  - layer_range: [0, 32]
    model: output/stop_it_nerd+Azazelle/Llama-3-LimaRP-Instruct-LoRA-8B
  - layer_range: [0, 32]
    model: output/stop_it_nerd+ToastyPigeon/Llama-3-8B-Instruct-SpringDragon-V2-QLoRA
  - layer_range: [0, 32]
    model: output/stop_it_nerd+Azazelle/Llama-3-LongStory-LORA
  - layer_range: [0, 32]
    model: output/stop_it_nerd+Azazelle/ANJIR-ADAPTER-128
  - layer_range: [0, 32]
    model: output/stop_it_nerd+Azazelle/Llama3_RP_ORPO_LoRA
  - layer_range: [0, 32]
    model: output/stop_it_nerd+Azazelle/RP_Format_QuoteAsterisk_Llama3
  - layer_range: [0, 32]
    model: output/stop_it_nerd+Azazelle/Theory_of_Mind_Llama3
  - layer_range: [0, 32]
    model: output/stop_it_nerd+Azazelle/Aura_Llama3
  - layer_range: [0, 32]
    model: output/stop_it_nerd+Azazelle/Luna_Llama3
  - layer_range: [0, 32]
    model: output/stop_it_nerd+Azazelle/BlueMoon_Llama3
  - layer_range: [0, 32]
    model: output/stop_it_nerd+Azazelle/Smarts_Llama3
  - layer_range: [0, 32]
    model: output/stop_it_nerd+Azazelle/llama3-8b-hikikomori-v0.4
  - layer_range: [0, 32]
    model: output/stop_it_nerd+Azazelle/Nimue-8B
  - layer_range: [0, 32]
    model: output/stop_it_nerd+Azazelle/Llama-3-Instruct-LiPPA-LoRA-8B
  - layer_range: [0, 32]
    model: output/stop_it_nerd