Instructions to use zarakiquemparte/zararp-1.1-l2-7b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use zarakiquemparte/zararp-1.1-l2-7b with Transformers:

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

pipe = pipeline("text-generation", model="zarakiquemparte/zararp-1.1-l2-7b")

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

tokenizer = AutoTokenizer.from_pretrained("zarakiquemparte/zararp-1.1-l2-7b")
model = AutoModelForCausalLM.from_pretrained("zarakiquemparte/zararp-1.1-l2-7b", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use zarakiquemparte/zararp-1.1-l2-7b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "zarakiquemparte/zararp-1.1-l2-7b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "zarakiquemparte/zararp-1.1-l2-7b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/zarakiquemparte/zararp-1.1-l2-7b

SGLang

How to use zarakiquemparte/zararp-1.1-l2-7b 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 "zarakiquemparte/zararp-1.1-l2-7b" \
    --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": "zarakiquemparte/zararp-1.1-l2-7b",
		"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 "zarakiquemparte/zararp-1.1-l2-7b" \
        --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": "zarakiquemparte/zararp-1.1-l2-7b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use zarakiquemparte/zararp-1.1-l2-7b with Docker Model Runner:
```
docker model run hf.co/zarakiquemparte/zararp-1.1-l2-7b
```

Model Card: ZaraRP 1.1 L2 7b

This model uses Nous Hermes Llama2 7b (53%) as a base with Stable Beluga 7b (47%) and the result of this merge was merged with LimaRP Llama2 v2 Lora 7b and PIPPA ShareGPT Subset Variation Two Lora 7b.

This merge of models(hermes and stable beluga) was done with this script

This merge of Lora with Model was done with this script

Merge illustration:

Usage:

Since this is a merge between Nous Hermes, Stable Beluga, LimaRP, and PIPPA ShareGPT, the following instruction formats should work:

Alpaca 2:

### Instruction:
<prompt>

### Response:
<leave a newline blank for model to respond>

Custom:

SYSTEM: Do thing
USER: {prompt}
CHARACTER:

Alpaca LimaRP instruction format:

### Instruction:
Character's Persona: {bot character description}

User's Persona: {user character description}

Scenario: {what happens in the story}

Play the role of Character. You must engage in a roleplaying chat with User below this line. Do not write dialogues and narration for User. Character should respond with messages of medium length.

### Input:
User: {utterance}

### Response:
Character: {utterance}

Bias, Risks, and Limitations

This model is not intended for supplying factual information or advice in any form

Training Details

This model is merged and can be reproduced using the tools mentioned above. Please refer to all provided links for extra model-specific details.

Downloads last month: 59