Instructions to use NexVeridian/zeta-2.1-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use NexVeridian/zeta-2.1-4bit with MLX:

# Make sure mlx-lm is installed
# pip install --upgrade mlx-lm
# if on a CUDA device, also pip install mlx[cuda]

# Generate text with mlx-lm
from mlx_lm import load, generate

model, tokenizer = load("NexVeridian/zeta-2.1-4bit")

prompt = "Once upon a time in"
text = generate(model, tokenizer, prompt=prompt, verbose=True)

Transformers

How to use NexVeridian/zeta-2.1-4bit with Transformers:

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

pipe = pipeline("text-generation", model="NexVeridian/zeta-2.1-4bit")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("NexVeridian/zeta-2.1-4bit")
model = AutoModelForCausalLM.from_pretrained("NexVeridian/zeta-2.1-4bit", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings
LM Studio

vLLM

How to use NexVeridian/zeta-2.1-4bit with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "NexVeridian/zeta-2.1-4bit"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "NexVeridian/zeta-2.1-4bit",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/NexVeridian/zeta-2.1-4bit

SGLang

How to use NexVeridian/zeta-2.1-4bit 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 "NexVeridian/zeta-2.1-4bit" \
    --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": "NexVeridian/zeta-2.1-4bit",
		"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 "NexVeridian/zeta-2.1-4bit" \
        --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": "NexVeridian/zeta-2.1-4bit",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

MLX LM

How to use NexVeridian/zeta-2.1-4bit with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Generate some text
mlx_lm.generate --model "NexVeridian/zeta-2.1-4bit" --prompt "Once upon a time"

Docker Model Runner
How to use NexVeridian/zeta-2.1-4bit with Docker Model Runner:
```
docker model run hf.co/NexVeridian/zeta-2.1-4bit
```
Atomic Chat

zeta-2.1-4bit / README.md

NexVeridian

Add files using upload-large-folder tool

618d01c verified about 1 month ago

preview code

Raw History Blame Contribute Delete

929 Bytes

metadata

base_model: zed-industries/zeta-2.1
tags:
  - text-generation-inference
  - transformers
  - edit-prediction
  - next-edit-suggestion
  - mlx
license: apache-2.0
language:
  - en
library_name: mlx
pipeline_tag: text-generation

NexVeridian/zeta-2.1-4bit

This model NexVeridian/zeta-2.1-4bit was converted to MLX format from zed-industries/zeta-2.1 using mlx-lm version 0.32.0.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("NexVeridian/zeta-2.1-4bit")

prompt = "hello"

if tokenizer.chat_template is not None:
    messages = [{"role": "user", "content": prompt}]
    prompt = tokenizer.apply_chat_template(
        messages, add_generation_prompt=True, return_dict=False,
    )

response = generate(model, tokenizer, prompt=prompt, verbose=True)