Instructions to use DS-Archive/CalliopeDS-v2-L2-13B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use DS-Archive/CalliopeDS-v2-L2-13B with Transformers:

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

pipe = pipeline("text-generation", model="DS-Archive/CalliopeDS-v2-L2-13B")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("DS-Archive/CalliopeDS-v2-L2-13B")
model = AutoModelForCausalLM.from_pretrained("DS-Archive/CalliopeDS-v2-L2-13B")

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use DS-Archive/CalliopeDS-v2-L2-13B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "DS-Archive/CalliopeDS-v2-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": "DS-Archive/CalliopeDS-v2-L2-13B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/DS-Archive/CalliopeDS-v2-L2-13B

SGLang

How to use DS-Archive/CalliopeDS-v2-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 "DS-Archive/CalliopeDS-v2-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": "DS-Archive/CalliopeDS-v2-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 "DS-Archive/CalliopeDS-v2-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": "DS-Archive/CalliopeDS-v2-L2-13B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use DS-Archive/CalliopeDS-v2-L2-13B with Docker Model Runner:
```
docker model run hf.co/DS-Archive/CalliopeDS-v2-L2-13B
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

CalliopeDS-v2-L2-13B

EXL2 Quants

GGUF Quants

This is a Llama 2-based model consisting of a merge of several models using PEFT adapters and SLERP merging:

Charles Goddard's mergekit repo was used to perform these operations.

The purpose of this merge was to create a model that excels at creative writing and roleplay while maintaining general intelligence and instruction-following capabilities. In testing, it has shown to be capable at producing descriptive and verbose responses while demonstrating a solid understanding of the context.

Usage:

Due to this being a merge of multiple models, different prompt formats may work, but you can try the Alpaca instruction format of LIMARP v3:

### 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.

### Input:
User: {utterance}

### Response:
Character: {utterance}

### Input
User: {utterance}

### Response:
Character: {utterance}

(etc.)

Or the Pygmalion/Metharme format:

<|system|>Enter RP mode. Pretend to be {{char}} whose persona follows:
{{persona}}

You shall reply to the user while staying in character, and generate long responses.
<|user|>Hello!<|model|>{model's response goes here}

The model was also tested using a system prompt with no instruction sequences:

Write Character's next reply in the roleplay between User and Character. Stay in character and write creative responses that move the scenario forward. Narrate in detail, using elaborate descriptions. The following is your persona:
{{persona}}
[Current conversation]
User: {utterance}
Character: {utterance}

Message length control

Due to the inclusion of LimaRP v3, it is possible to append a length modifier to the response instruction sequence, like this:

### Input
User: {utterance}

### Response: (length = medium)
Character: {utterance}

This has an immediately noticeable effect on bot responses. The available lengths are: tiny, short, medium, long, huge, humongous, extreme, unlimited. The recommended starting length is medium. Keep in mind that the AI may ramble or impersonate the user with very long messages.

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 a merge. Please refer to the link repositories of the merged models for details.

Downloads last month: 8

Safetensors

Model size

13B params

Tensor type

BF16

Model tree for DS-Archive/CalliopeDS-v2-L2-13B

Quantizations

2 models