Instructions to use R136a1/TimeCrystal-l2-13B-exl2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use R136a1/TimeCrystal-l2-13B-exl2 with Transformers:

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

pipe = pipeline("text-generation", model="R136a1/TimeCrystal-l2-13B-exl2")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("R136a1/TimeCrystal-l2-13B-exl2")
model = AutoModelForCausalLM.from_pretrained("R136a1/TimeCrystal-l2-13B-exl2")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use R136a1/TimeCrystal-l2-13B-exl2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "R136a1/TimeCrystal-l2-13B-exl2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "R136a1/TimeCrystal-l2-13B-exl2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/R136a1/TimeCrystal-l2-13B-exl2

SGLang

How to use R136a1/TimeCrystal-l2-13B-exl2 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 "R136a1/TimeCrystal-l2-13B-exl2" \
    --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": "R136a1/TimeCrystal-l2-13B-exl2",
		"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 "R136a1/TimeCrystal-l2-13B-exl2" \
        --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": "R136a1/TimeCrystal-l2-13B-exl2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use R136a1/TimeCrystal-l2-13B-exl2 with Docker Model Runner:
```
docker model run hf.co/R136a1/TimeCrystal-l2-13B-exl2
```

EXL2 Quantization of TimeCrystal-l2-13B.

Quantized at 6.13bpw.

Original model card

This 13B model, TimeCrystal-l2-13B is built to maximize logic and instruct following, whilst also increasing the vividness of prose found in Chronos based models like Mythomax, over the more romantic prose, hopefully without losing the elegent narrative structure touch of newer models like synthia and xwin. TLDR: Attempt at more clever, better prose.

Tentative test results: I'm not certain if logic/instruct was improved or not (haven't tested much), but the prose infusion seems to have worked really well.

It is built so:

SLERPS: Amethyst + Openchat Super = OpenStone

MythoMax + Chronos = ChronoMax

ChronoMax + Amethyst = TimeStone

Gradient Merge:

TimeStone + OpenStone (0.9,0,0) = TimeCrystal

Props to all the mergers, fine tuners!

All models in Merge: Many, lol.

Downloads last month: 8

Collection including R136a1/TimeCrystal-l2-13B-exl2

13B

Collection

11 items • Updated Mar 2