CatalogWantedMirrorsLedgerOperating StatementDocsStudio statusCard system
alt.freeweights.text / zeta-2
From: zed-industries <huggingface.co/zed-industries>Newsgroups: alt.freeweights.textSubject:

zeta-2

Date: 2026-11-15Commit: 1529be6Signed: 2DC28CC7B26A283B ✓

Text generation model with 8.3B parameters. Safetensors weights, 16.5 GB in all. Published by zed-industries under Apache-2.0.

8.3B params16.5GBzeta-2safetensorspermissive
FactsParams8.3BSize16.5 GBFormatssafetensorsTasktext generationLicenseApache-2.0From sourcepermissive
$ fw get zed-industries/zeta-2
# manifest sha256 9b0d2fcd9fa6… · 16.5 GB · 13 files
$ fw verify ./zeta-2 zed-industries/zeta-2
From sourceHosted (signed)zed-industries/zeta-2Last check: 2026-11-15 03:48 UTC
Run at homeGet help

Get help: custom fine-tune or private deploy. We review your setup before we quote.

Fine-tune of Seed-Coder-8B-Base.

Works with

Run24Fine-tune29Convert15Evaluate13Scan13Apps58
OverviewModel cardFilesUse itLicenseProvenanceModel tree

Overview

Size
16.5 GB
Weights
16.5 GB (safetensors)
Parameters
8.3B
Formats
safetensors
Task
text generation
License
Apache-2.0 (permissive)
Files
13, each with a sha256
Publisher
zed-industries
Added
2026-11-15
Section
alt.freeweights.text
Lineage

Original release from the publisher.

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

Where these bytes come from
Publisher at the pinned commit→You

Sources are tried in order. A file counts only when its size and sha256 match the manifest. Sources are checked when you ask for them, not on a timer.

Sources
BadgeHostLast checkResult
From sourcehuggingface.co2026-11-15 03:48 UTCpassed

Model card

From the publisher at commit 1529be6. Shown as plain text with links; images open at the publisher.

Zeta 2#

Zeta 2 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: 0225-s3-seed

Prompt format#

The model uses a SPM (suffix-prefix-middle) style prompt with git-merge-style markers for the editable region:

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
<<<<<<< CURRENT
code that
needs to<|user_cursor|>
be rewritten
=======
<[fim-middle]>

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

revised content for
the editable region
>>>>>>> UPDATED

Here is a real-world example:

Files

13 files · 16.5 GBWeights 16.5 GB (safetensors). Sizes and sha256 from the signed manifest.
Hide all 13 files with their sha256
FileSizesha256
.gitattributes1.57 KB34448b82c17d60fec9b65b1f093c115ddbaadc04beb1b0140b6bfed2e012a930
README.md1.35 KB618edddff61a4468a2507d947c606d8f507abba2378d20f4d1a05bb298833b41
config.json852 B6eba0fb7e92d7939643bcbcec73319918728e0b619a073768dcc5c30726c9ad1
model-00001-of-00004.safetensors4.96 GB16e8ab3b3755c8ecfe193dfc322099165433e214203cd9e2dda9fc849b5b6fba
model-00002-of-00004.safetensors4.92 GBa41be18644793a820687f1ab8d8c7c473d9c12578dc5ebb709f33c7955aa7929
model-00003-of-00004.safetensors5.00 GB35f7ee47b0b9f2824e09e7ed5869ed168ab3cf779db9107695d52ca13574a06a
model-00004-of-00004.safetensors1.62 GBe01646aaec477468ee1de65db83a790d1dab0b1a23c8138d0d7b3c1525cbeb7f
model.safetensors.index.json23.9 KB8b4937aa0edd26233125db5f227ddfb58b4279f93a72129380d96175dba28cb5
sample.output1.21 KB7176de19426e730a81d7bf129ac40f3f8296311648fc7727e9879f768c179412
sample.prompt2.48 KB16b95dc5146ee0410f5cc4408e0a645f3ef06fd1c43af10fac982666fe09170d
special_tokens_map.json613 Bdc0c22e96ab28d40c0a808d5bb4d479d22776fd059bddbcc424f25b493a1120d
tokenizer.json11.9 MBdb6520146c388c495a98bbea62ff6d00c0a8935bed33622e33bb33ec71aaafed
tokenizer_config.json27.9 KB9a46051f3866732d0c6303e6369a8e05329153f59188cdc9117f6ca26c74adad
VersionsEach time the pinned upstream commit or file list changed in this repo. Newest first.
Upstream commitDateContents
1529be60e3 pinned now2026-11-15 03:48 UTC13 files · 16.5 GB

Use it

$ fw get zed-industries/zeta-2
# manifest sha256 9b0d2fcd9fa6… · 16.5 GB · 13 files
$ fw verify ./zeta-2 zed-industries/zeta-2
fw.pyChecks the signature and every sha256, tries each source in order, resumes.
$ python3 fw.py get https://freeweights.allternit.com/manifests/zed-industries/zeta-2.json --dir ./zeta-2 $ python3 fw.py verify ./zeta-2 ./zed-industries__zeta-2.json
hfThe Hugging Face CLI with one setting. Same repo id.
$ HF_ENDPOINT=https://freeweights.allternit.com hf download zed-industries/zeta-2 --revision 1529be60e35a55682cb6029e3840b53d9a57e6d0 --local-dir ./zeta-2
transformersLoad the weights in Python.
import os os.environ["HF_ENDPOINT"] = "https://freeweights.allternit.com" from transformers import AutoModelForCausalLM, AutoTokenizer tok = AutoTokenizer.from_pretrained("zed-industries/zeta-2", revision="1529be60e35a55682cb6029e3840b53d9a57e6d0") model = AutoModelForCausalLM.from_pretrained("zed-industries/zeta-2", revision="1529be60e35a55682cb6029e3840b53d9a57e6d0", device_map="auto")
vLLMServe an OpenAI-compatible API.
$ HF_ENDPOINT=https://freeweights.allternit.com vllm serve zed-industries/zeta-2 --revision 1529be60e35a55682cb6029e3840b53d9a57e6d0
Run at home

License

Name
Apache License 2.0
Id
Apache-2.0
Class
Permissive
Redistribution
yes
Listing
Hosted (signed)
Decided
License as declared by the publisher. No person read it. 2026-11-15
Text in
README.md
Text sha256
618edddff61a4468a2507d947c606d8f507abba2378d20f4d1a05bb298833b41
Terms gate
No extra terms beyond the license.

Read the license text

Licenses are checked against the license table. A custom license passes only after a person reads it.

Provenance

From: zed-industries <huggingface.co/zed-industries>Newsgroups: alt.freeweights.textSubject: zeta-2Date: 2026-11-15Commit: 1529be6Signed: 2DC28CC7B26A283B ✓
Upstream
zed-industries/zeta-2
Pinned commit
1529be60e35a55682cb6029e3840b53d9a57e6d0
Manifest
zeta-2.json · .minisig
Manifest sha256
9b0d2fcd9fa6d8473d805d3bb2bb3fe1d3b5cae27566e9dc6d94d513e9f6b83d
Signature
minisign, Ed25519, key 2DC28CC7B26A283B
Created
2026-11-15 03:48 UTC
Generator
freeweights-manifest/0.1.0
Takedowns
None.

How to verify

$ curl -O https://freeweights.allternit.com/manifests/zed-industries/zeta-2.json $ curl -O https://freeweights.allternit.com/manifests/zed-industries/zeta-2.json.minisig $ minisign -Vm zeta-2.json -P RWQ7KGqyx4zCLXtUFOqvfv8L3g+8fpKJ1FsuxPyOYMF+4KufbUxKq1Oq $ shasum -a 256 <file> # compare with the Files tab

A manifest whose signature fails must be rejected. A file whose size or sha256 does not match must be discarded. Verify a download

Model tree

Parent

ByteDance-Seed/Seed-Coder-8B-Base · this model is a finetune of it

1 model in the catalog name this one as their parent.

Quantizations
1
Quantizations 1
Get it
Download
$ HF_ENDPOINT=https://freeweights.allternit.com hf download zed-industries/zeta-2
Open in Freeweights Studio

Pull, verify and run it in the Allternit app on Desktop, web or phone.

Signed manifest
minisign, key 2DC28CC7B26A283B. zeta-2.json. Provenance. Takedown history: none.
Source
huggingface.co/zed-industries/zeta-2

Variants

1 quantized or adapter build of zeta-2. Each has its own license check and page.

SubjectSizeParamsLicenseDate
zed-industries_zeta-2-GGUFHosted (signed) From: bartowski in alt.freeweights.text134 GB—Permissive2026-11-15

Related models

All of alt.freeweights.text →
From: laion <huggingface.co/laion>Subject: a2-rl-e2egit_large-50-32B
From: laion <huggingface.co/laion>Subject: a3-rl-DCAgent_exp_rpt_e2egit-large-15-8B
From: laion <huggingface.co/laion>Subject: a3-rl-DCAgent_exp_rpt_e2egit-v2-10-8B
From: laion <huggingface.co/laion>Subject: a3-rl-DCAgent_exp_rpt_pymethods2test-large-80-8B
From: laion <huggingface.co/laion>Subject: a3-rl-DCAgent_exp_rpt_unitsyn-python-large-10-8B
From: laion <huggingface.co/laion>Subject: a3-rl-DCAgent_mix_h2_language_proportional-65-8B