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

Libraries

How to use zed-industries/zeta-2.1 with Transformers:

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

pipe = pipeline("text-generation", model="zed-industries/zeta-2.1")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("zed-industries/zeta-2.1")
model = AutoModelForCausalLM.from_pretrained("zed-industries/zeta-2.1")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use zed-industries/zeta-2.1 with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/zed-industries/zeta-2.1

SGLang

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

Docker Model Runner
How to use zed-industries/zeta-2.1 with Docker Model Runner:
```
docker model run hf.co/zed-industries/zeta-2.1
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Zeta 2.1

Zeta 2.1 is a code edit prediction (also known as next-edit suggestion) model finetuned from ByteDance-Seed/Seed-Coder-8B-Base.

Given code context, edits history and an editable region around the cursor, it predicts the rewritten content for that region.

Developed by: Zed Industries
License: Apache-2.0
Fine-tuned from: ByteDance-Seed/Seed-Coder-8B-Base
Model version: 0323-multi-region-filtered-r3

Prompt format

The model uses a SPM (suffix-prefix-middle) style prompt with numbered multi-region markers for editable regions:

Here is a minimal example:

<[fim-suffix]>
code after editable region
<[fim-prefix]><filename>related/file.py
related file content

<filename>edit_history
--- a/some_file.py
+++ b/some_file.py
-old
+new

<filename>path/to/target_file.py
code before editable region
<|marker_1|>
code that
needs to<|user_cursor|>
be rewritten
<|marker_2|>
<[fim-middle]>

Expected output (should be generated by the model, without backticks):

<|marker_1|>
revised content for
the editable region
<|marker_2|>

Here is a real-world example:

Downloads last month: 178

Safetensors

Model size

8B params

Tensor type

BF16

Model tree for zed-industries/zeta-2.1

Base model

ByteDance-Seed/Seed-Coder-8B-Base

Finetuned

(9)

this model

Quantizations

7 models