Instructions to use digitous/13B-Chimera with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use digitous/13B-Chimera with Transformers:

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

pipe = pipeline("text-generation", model="digitous/13B-Chimera")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("digitous/13B-Chimera")
model = AutoModelForCausalLM.from_pretrained("digitous/13B-Chimera")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use digitous/13B-Chimera with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/digitous/13B-Chimera

SGLang

How to use digitous/13B-Chimera 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 "digitous/13B-Chimera" \
    --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": "digitous/13B-Chimera",
		"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 "digitous/13B-Chimera" \
        --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": "digitous/13B-Chimera",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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

13B-Chimera

Composition:

[] = applied as LoRA to a composite model | () = combined as composite models

((MantiCore3E+VicunaCocktail)+[SuperCOT+[StorytellingV2+(SuperHOTProtoType-8192ctx+Metharme)]])

This model is the result of an experimental use of LoRAs on language models and model merges that are not the base HuggingFace-format LLaMA model they were intended for. The desired outcome is to additively apply desired features without paradoxically watering down a model's effective behavior.

Potential limitations - LoRAs applied on top of each other may intercompete.

Subjective results - very promising. Further experimental tests and objective tests are required.

Instruct and Setup Suggestions:

Alpaca instruct verified working, Vicuna instruct formats should work. If using KoboldAI or Text-Generation-WebUI, recommend switching between Godlike and Storywriter presets and adjusting output length + instructions in memory. Other presets as well as custom settings can yield highly different results, especially Temperature. If poking it with a stick doesn't work try another stick.

Language Models and LoRAs Used Credits:

manticore-13b [Epoch3] by openaccess-ai-collective

https://huggingface.co/openaccess-ai-collective/manticore-13b

vicuna-13b-cocktail by reeducator

https://huggingface.co/reeducator/vicuna-13b-cocktail

SuperCOT-LoRA [13B] by kaiokendev

https://huggingface.co/kaiokendev/SuperCOT-LoRA

Storytelling-LLaMa-LoRA [13B, Version 2] by GamerUnTouch

https://huggingface.co/GamerUntouch/Storytelling-LLaMa-LoRAs

SuperHOT Prototype [13b 8k ctx] by kaiokendev

https://huggingface.co/kaiokendev/SuperHOT-LoRA-prototype

Metharme 13b by PygmalionAI

https://huggingface.co/PygmalionAI/metharme-13b

Also thanks to Meta for LLaMA.

Each model and LoRA was hand picked and considered for what it could contribute to this ensemble. Thanks to each and every one of you for your incredible work developing some of the best things to come out of this community.

Downloads last month: 1,001

Model tree for digitous/13B-Chimera

Quantizations

3 models

digitous
/

13B-Chimera

13B-Chimera

Composition:

Language Models and LoRAs Used Credits:

Model tree for digitous/13B-Chimera

Spaces using digitous/13B-Chimera 29