Instructions to use Delta-Vector/Plesio-32B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Delta-Vector/Plesio-32B with Transformers:

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

pipe = pipeline("text-generation", model="Delta-Vector/Plesio-32B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Delta-Vector/Plesio-32B")
model = AutoModelForCausalLM.from_pretrained("Delta-Vector/Plesio-32B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Delta-Vector/Plesio-32B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Delta-Vector/Plesio-32B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Delta-Vector/Plesio-32B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Delta-Vector/Plesio-32B

SGLang

How to use Delta-Vector/Plesio-32B 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 "Delta-Vector/Plesio-32B" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Delta-Vector/Plesio-32B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "Delta-Vector/Plesio-32B" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Delta-Vector/Plesio-32B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Delta-Vector/Plesio-32B with Docker Model Runner:
```
docker model run hf.co/Delta-Vector/Plesio-32B
```

Plesio-32B / README.md

Delta-Vector

Update README.md

86eac82 verified 12 months ago

preview code

raw

history blame contribute delete

11.7 kB

metadata

base_model:
  - Delta-Vector/Rei-V1-32B-Base
  - allura-org/GLM4-32B-Neon-v2
library_name: transformers
tags:
  - mergekit
  - merge
  - rolelplay
  - creative_writing

Created by Delta-Vector →

Model Information

Plesio-32B

32B parameters GLM-4 32B Creative / Fresh Prose Co-writing/Roleplay/Adventure Generalist

Another Series of Merges! Since i could never beat Archaeo-32B-KTO! This time starting off with a GLM merge between Rei and Neon (thanks auri!!!)

Using the Oh-so-great 0.2 Slerp merge weight with Neon as the Base.

Support me on Ko-Fi: https://ko-fi.com/deltavector

Quantized Versions

Available Downloads

GGUF FormatFor use with LLama.cpp & Forks(Coming Soon!)
EXL2 FormatFor use with TabbyAPI (Coming Soon!)
EXL3 FormatFor use with TabbyAPI (Slower on Ampere))

Prompting

Model has been tuned with the GLM-4 formatting.

Samplers

For testing of this model, I used Temp=1, 0.1 Min-P.

See Merging Config

https://files.catbox.moe/j9kyfy.yml

Credits

Thank you to Lucy Knada, Auri, Ateron, Alicat, Intervitens, Cgato, Kubernetes Bad and the rest of Anthracite.