Instructions to use chargoddard/platypus-2-22b-relora with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use chargoddard/platypus-2-22b-relora with Transformers:

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

pipe = pipeline("text-generation", model="chargoddard/platypus-2-22b-relora")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("chargoddard/platypus-2-22b-relora")
model = AutoModelForCausalLM.from_pretrained("chargoddard/platypus-2-22b-relora")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use chargoddard/platypus-2-22b-relora with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "chargoddard/platypus-2-22b-relora"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "chargoddard/platypus-2-22b-relora",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/chargoddard/platypus-2-22b-relora

SGLang

How to use chargoddard/platypus-2-22b-relora 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 "chargoddard/platypus-2-22b-relora" \
    --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": "chargoddard/platypus-2-22b-relora",
		"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 "chargoddard/platypus-2-22b-relora" \
        --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": "chargoddard/platypus-2-22b-relora",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use chargoddard/platypus-2-22b-relora with Docker Model Runner:
```
docker model run hf.co/chargoddard/platypus-2-22b-relora
```

Experimental ReLoRA-trained model using the OpenPlatypus dataset. Ran for one epoch, with three lora restarts.

Not recommended for use yet. Mostly tossing this up for testing.

Base model was llama2-22b-blocktriangular.

Relevant training parameters:

adapter: qlora
load_in_4bit: true
lora_r: 32
lora_alpha: 16
lora_dropout: 0.001
lora_target_linear: true
relora_steps: 150
relora_warmup_steps: 10
gradient_accumulation_steps: 2
micro_batch_size: 3

Uses the same prompt format as Ypotryll-22b. Prefix messages with " ***System:", " ***Query:", or " ***Response:", paying attention to whitespace.

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	52.21
ARC (25-shot)	57.68
HellaSwag (10-shot)	82.44
MMLU (5-shot)	55.33
TruthfulQA (0-shot)	43.61
Winogrande (5-shot)	77.35
GSM8K (5-shot)	6.6
DROP (3-shot)	42.46

Downloads last month: 217

Safetensors

Model size

22B params

Tensor type

F16

Dataset used to train chargoddard/platypus-2-22b-relora

Spaces using chargoddard/platypus-2-22b-relora 33

Collection including chargoddard/platypus-2-22b-relora

Frankenmodels

Collection

They're not supposed to be that size! Neat, right? • 8 items • Updated Dec 12, 2023 • 3