Downloads · 30 days
4
29% of all-time downloads
opus-max.h077.sft_short.step_100
agentic-ptb/opus-max.h077.sft_short.step_100
opus-max.h077.sft_short.step_100 is a machine learning model from agentic-ptb. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
AgentPTB sweep checkpoint. Cell opus-max — Claude Code / claude-opus-5 @ effort max.
All-time downloads
14
Public
Parameters
9.4B
18.8 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors18.8 GB · 100%
At a glance
- Model type
- qwen3_5
- Access
- Public
- Created
- Aug 20, 2026
- Updated
- Aug 20, 2026
- SHA
- b908763e
Base models
Model card
From the Hugging Face model README
opus-max.sft_short.step_100
AgentPTB sweep checkpoint. Cell opus-max — Claude Code / claude-opus-5 @ effort max.
| field | value |
|---|---|
| plot cell | opus-max |
| driver | Claude Code / claude-opus-5 |
| reasoning effort | max |
| run boot (UTC) | 2026-08-13T14:28:54Z |
| role | intermediate |
| checkpoint path in run | ckpt/sft_short/weights/step_100 |
| shards | 4 |
| size | 18.8 GB |
| base model | Qwen/Qwen3.5-9B-Base |
| eos_token_id | [248044, 248046] ✅ correct |
Reading the eos field
248046 is <|im_end|>, the token the Qwen3.5 chat template ends every assistant turn with.
Checkpoints missing it do not stop at end-of-turn and overrun the context window, so their
eval numbers are a floor, not a measurement — compare them only against other checkpoints
with the same eos status, or re-package before evaluating.
Mapping back to the figures
Join on plot cell above. The sweep figures are keyed by these same cell names.
- Type
- qwen3_5
- Created
- Aug 20, 2026
- Updated
- Aug 20, 2026