Spaces:

build-small-hackathon
/

step-zero

Runtime error

App Files Files Community

step-zero

Commit History

Jun 14

14:42
perf: preload both models in parallel background threads for instant UI + fast first inference

tc043

59f43e1
14:30
perf: implement lazy loading for LLM models to enable instant Gradio UI startup

tc043

47ba524
14:21
fix: improve semantic overlap validation, strip task prefixes, and refine fallback prompts

tc043

f156e8b
13:41
fix: resolve port 7860 conflicts from zombie processes during restart

tc043

ef6005f
13:24
fix: download models at build time to prevent HF Space startup timeout⁠

tc043

4505a0c
13:12
Use prebuilt CPU wheel index for llama-cpp-python

Antigravity

bf80d2c
13:01
Bump llama-cpp-python to 0.3.29 to support minicpm3

Antigravity

40751d8
12:47
Revert llama-cpp-python to 0.2.90 to support Nemotron model architecture

Antigravity

9ddff89
12:45
Install git in Dockerfile to satisfy HF Dev Mode build requirements

Antigravity

220d576
12:44
Fix requirements.txt structure and pin llama-cpp-python to CPU pre-built version 0.2.62

Antigravity

23a2a3e
12:15
Update requirements.txt

TONG

Unverified signature
9c9a4a4
12:14
Create packages.txt

TONG

Unverified signature
83df957
12:11
Update requirements.txt

TONG

Unverified signature
03f08d4
12:04
Install build-essential for llama-cpp-python⁠

TONG

Unverified signature
3a5cb1a
11:20
Refactor Hugging Face sync workflow⁠

TONG

Unverified signature
8ac8ba2
11:16
Change colorFrom from black to gray

TONG

Unverified signature
61af1de
11:13
Update Hugging Face repository ID in workflow

TONG

Unverified signature
a463c8e

Jun 13

14:44
docs: update setup instructions and clarify repetition mitigation strategy in README

tc043

cfd1a53
14:20
refactor: update grammar, remove unused project files, and clean up workspace configuration⁠

tc043 +1: Codex

144132f
14:03
refactor: remove experimental test files and enable production mode in Dockerfile⁠

tc043 +1: Codex

19a5a7c
13:40
feat: increase max_tokens to 64 and add model download instructions to README⁠

tc043 +1: Codex

e41aa9d
13:06
feat: add extensive test suite and debugging utilities for Gradio app API validation⁠

tc043 +1: Codex

473cb68
12:33
feat: implement event handler wrappers and add test suite for Gradio components and app integration⁠

tc043 +1: Codex

eae9568
12:17
refactor: update startup command to use app.py instead of uvicorn and add HF_TOKEN note to documentation⁠

tc043 +1: Codex

3eaf8cd
12:11
refactor: replace FastAPI/Static setup with custom Gradio UI and update task generation with grammar-enforced inference and semantic repetition checks.⁠

tc043 +1: Codex

2318a54
08:17
perf: bound session trace memory⁠

tc043 +1: Codex

64f4a9c

Jun 12

18:18
docs: update project documentation to reflect fine-tuned model integration and remove standalone model dependencies

tc043

8bc210e
17:56
refactor: limit task history to three items and add explicit constraints to prevent fallback repetition, with added test script

tc043

7dc4c08
17:41
fix: refine system prompts to enforce physical actions and single-sentence output while adding repetition detection for model responses

tc043

043aa6b
17:30
feat: improve task generation logic with line-by-line parsing, refined system prompts, and enhanced state tracking for raw task history

tc043

20eda77
17:14
feat: implement MiniCPM fallback to break down rejected tasks into atomic steps and add verification script

tc043

44d6800
17:11
refactor: expand and diversify dataset entries while removing deprecated testing scripts

tc043

913be0b
16:36
feat: update training pipeline to use full-precision merge and add volume verification test

tc043

5a8eee8
16:03
refactor: remove post-processing constraints in app.py and update model training to export HF merged format via llama.cpp conversion

tc043

66b1bc1
15:54
feat: create export directory before saving GGUF model

tc043

3c194fb
15:47
feat: update GGUF export path and implement volume commit logic for training artifacts

tc043

eac67fe
15:41
feat: disable model checkpoints during training in modal_train.py

tc043

3f0b366
15:40
feat: implement Unsloth training pipeline with Modal volumes and update documentation on model persona mitigation

tc043

8207f22
15:23
refactor: optimize inference with async locking, prompt engineering, and input post-processing while adding comprehensive testing suites

tc043

0b80cf0
14:57
feat: add environment variable support and expand grammar allowed character set

tc043

c8f975e
14:31
Merge branch 'main' and remove venv from tracking

tc043

6c0dd9b
14:26
chore: upgrade python version, add git dependency to modal image, and update gitignore entries

tc043

37aa665
14:23
Delete __pycache__ directory

TONG

Unverified signature
0089f6c
14:23
Delete .venv directory

TONG

Unverified signature
9f7ee69
13:44
feat: harden Step-Zero demo runtime and trace export⁠

tc

d976178
13:31
feat: Generated proprietary Fog of War SPA interface using OpenAI Codex

tc

dd82460
13:13
feat: initialize project configuration and implementation plan for Step-Zero

tc

b096281

Commit History

Jun 14

perf: preload both models in parallel background threads for instant UI + fast first inference

perf: implement lazy loading for LLM models to enable instant Gradio UI startup

fix: improve semantic overlap validation, strip task prefixes, and refine fallback prompts

fix: resolve port 7860 conflicts from zombie processes during restart

fix: download models at build time to prevent HF Space startup timeout⁠

Use prebuilt CPU wheel index for llama-cpp-python

Bump llama-cpp-python to 0.3.29 to support minicpm3

Revert llama-cpp-python to 0.2.90 to support Nemotron model architecture

Install git in Dockerfile to satisfy HF Dev Mode build requirements

Fix requirements.txt structure and pin llama-cpp-python to CPU pre-built version 0.2.62

Update requirements.txt

Create packages.txt

Update requirements.txt

Install build-essential for llama-cpp-python⁠

Refactor Hugging Face sync workflow⁠

Change colorFrom from black to gray

Update Hugging Face repository ID in workflow

Jun 13

docs: update setup instructions and clarify repetition mitigation strategy in README

refactor: update grammar, remove unused project files, and clean up workspace configuration⁠

refactor: remove experimental test files and enable production mode in Dockerfile⁠

feat: increase max_tokens to 64 and add model download instructions to README⁠

feat: add extensive test suite and debugging utilities for Gradio app API validation⁠

feat: implement event handler wrappers and add test suite for Gradio components and app integration⁠

refactor: update startup command to use app.py instead of uvicorn and add HF_TOKEN note to documentation⁠

refactor: replace FastAPI/Static setup with custom Gradio UI and update task generation with grammar-enforced inference and semantic repetition checks.⁠

perf: bound session trace memory⁠

Jun 12

docs: update project documentation to reflect fine-tuned model integration and remove standalone model dependencies

refactor: limit task history to three items and add explicit constraints to prevent fallback repetition, with added test script

fix: refine system prompts to enforce physical actions and single-sentence output while adding repetition detection for model responses

feat: improve task generation logic with line-by-line parsing, refined system prompts, and enhanced state tracking for raw task history

feat: implement MiniCPM fallback to break down rejected tasks into atomic steps and add verification script

refactor: expand and diversify dataset entries while removing deprecated testing scripts

feat: update training pipeline to use full-precision merge and add volume verification test

refactor: remove post-processing constraints in app.py and update model training to export HF merged format via llama.cpp conversion

feat: create export directory before saving GGUF model

feat: update GGUF export path and implement volume commit logic for training artifacts

feat: disable model checkpoints during training in modal_train.py

feat: implement Unsloth training pipeline with Modal volumes and update documentation on model persona mitigation

refactor: optimize inference with async locking, prompt engineering, and input post-processing while adding comprehensive testing suites

feat: add environment variable support and expand grammar allowed character set

Merge branch 'main' and remove venv from tracking

chore: upgrade python version, add git dependency to modal image, and update gitignore entries

Delete __pycache__ directory

Delete .venv directory

feat: harden Step-Zero demo runtime and trace export⁠

feat: Generated proprietary Fog of War SPA interface using OpenAI Codex

feat: initialize project configuration and implementation plan for Step-Zero

Delete pycache directory