Instructions to use kingbri/Nous-Hermes-limarp-l2-13B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use kingbri/Nous-Hermes-limarp-l2-13B with Transformers:

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

pipe = pipeline("text-generation", model="kingbri/Nous-Hermes-limarp-l2-13B")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("kingbri/Nous-Hermes-limarp-l2-13B")
model = AutoModelForCausalLM.from_pretrained("kingbri/Nous-Hermes-limarp-l2-13B")

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use kingbri/Nous-Hermes-limarp-l2-13B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "kingbri/Nous-Hermes-limarp-l2-13B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "kingbri/Nous-Hermes-limarp-l2-13B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/kingbri/Nous-Hermes-limarp-l2-13B

SGLang

How to use kingbri/Nous-Hermes-limarp-l2-13B 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 "kingbri/Nous-Hermes-limarp-l2-13B" \
    --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": "kingbri/Nous-Hermes-limarp-l2-13B",
		"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 "kingbri/Nous-Hermes-limarp-l2-13B" \
        --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": "kingbri/Nous-Hermes-limarp-l2-13B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use kingbri/Nous-Hermes-limarp-l2-13B with Docker Model Runner:
```
docker model run hf.co/kingbri/Nous-Hermes-limarp-l2-13B
```

Model Card: Nous-Hermes-limarp-l2-13B

This is a merge between:

Nous Hermes Llama 2 13b
LimaRP llama 2 Lora from July 28, 2023 at a weight of 0.66.

Quantizations provided by myself:

GPTQ

The merge was performed using ez-trainer by CoffeeVampire/Blackroot

The intended objective is to combine NH-2's reasoning and instruction-following capabilities with LimaRP's character roleplay capabilities.

The LimaRP LoRA was merged at a weight of 0.66 since a merge of 1.00 destroyed most nuances of a character's personality due to the LoRA being too strong on the base model. There still may be edge cases. If so, please report them and the lora weight will be dropped.

Usage:

Since this is a merge between NH-2 and LimaRP, the following instruction formats should work:

Alpaca 2:

### Instruction:
<prompt>

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

LimaRP instruction format:

<<SYSTEM>>
<character card and system prompt>

<<USER>>
<prompt>

<<AIBOT>>
<leave a newline blank for model to respond>

Bias, Risks, and Limitations

The model will show biases similar to those observed in niche roleplaying forums on the Internet, besides those exhibited by the base model. It 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: 7