zenlm/zen-eco-instruct
1
0
Fork 0
mirror of https://github.com/zenlm/zen-eco-instruct.git synced 2026-07-26 21:58:56 +00:00
Code Issues Packages Projects Releases Wiki Activity

docs: honest attribution — credit Qwen/Qwen3-4B upstream (Apache-2.0)

Browse Source
This commit is contained in:
z
2026-07-16 10:49:21 -07:00
parent cd728930d8
commit 4ed0ec59f7
1 changed files with 7 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files
README.md
+7 -2
View File
@@ -8,11 +8,12 @@ Efficient instruction-following model. Part of the Zen Eco family.
## Overview
Zen Eco 4B Instruct is the instruction-tuned variant of Zen Eco 4B. Fine-tuned for following complex instructions with high accuracy while maintaining the compact efficiency of the Eco architecture.
Zen Eco 4B Instruct is based on [Qwen/Qwen3-4B](https://huggingface.co/Qwen/Qwen3-4B) (Apache 2.0, Alibaba Qwen), a compact 4B dense instruction model, packaged for the OSS-clean Zen Eco line. Not trained from scratch.
| Property | Value |
|----------|-------|
| Parameters | 4B |
| Parameters | 4B (dense) |
| Architecture | Qwen3 (`Qwen3ForCausalLM`) |
| Context | 32K |
| License | Apache 2.0 |
@@ -30,6 +31,10 @@ output = model.generate(inputs, max_new_tokens=512)
print(tokenizer.decode(output[0], skip_special_tokens=True))
```
## Upstream
Built on [Qwen/Qwen3-4B](https://huggingface.co/Qwen/Qwen3-4B) by Alibaba Qwen, licensed under Apache 2.0. See [NOTICE](NOTICE).
## Related
- [zen-eco](https://huggingface.co/zenlm/zen-eco) — Base 4B model