Downloads · 30 days
11
0% of all-time downloads
Qwen3.5-4B
friday-and-co/Qwen3.5-4B
Qwen3.5-4B is a machine learning model from friday-and-co. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
Verbatim copy of Qwen/Qwen3.5-4B with the only change being the addition of a generationconfig.json carrying both stop ids:
All-time downloads
5.7K
Public
Parameters
4.7B
9.3 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors9.3 GB · 100%
Parameter types
How the weights are stored.
BF164.7B · 100%
Base models
Model card
From the Hugging Face model README
Qwen3.5-4B (+ generation_config.json)
Verbatim copy of Qwen/Qwen3.5-4B with the only change being the addition of a
generation_config.json carrying both stop ids:
{"eos_token_id": [248046, 248044]} // <|im_end|>, <|endoftext|>
Upstream Qwen/Qwen3.5-4B ships no generation_config.json, so inference engines
(sglang/vLLM) fall back to config.json's eos = <|endoftext|> (248044) and never
stop on the chat turn terminator <|im_end|> (248046) — causing runaway generation
in multi-turn / tool-use rollouts. The 35B-A3B checkpoint ships this file; 4B/9B do not.
This repo restores it so multi-turn generation halts correctly at each turn.
- Type
- qwen3_5
- License
- apache-2.0
- Created
- Jun 20, 2026
- Updated
- Jun 20, 2026