Instructions to use diffusion-gif/trick-prediction with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use diffusion-gif/trick-prediction with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("image-text-to-text", model="diffusion-gif/trick-prediction")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("diffusion-gif/trick-prediction", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use diffusion-gif/trick-prediction with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "diffusion-gif/trick-prediction"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "diffusion-gif/trick-prediction",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/diffusion-gif/trick-prediction

SGLang

How to use diffusion-gif/trick-prediction with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "diffusion-gif/trick-prediction" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "diffusion-gif/trick-prediction",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "diffusion-gif/trick-prediction" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "diffusion-gif/trick-prediction",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use diffusion-gif/trick-prediction with Docker Model Runner:
```
docker model run hf.co/diffusion-gif/trick-prediction
```

Trick Prediction — legacy mix6 SFT / GRPO checkpoints

这是已有轨迹预测研究检查点的无损分片发布，不是新的训练结果。不是新版单图/历史联合任务 + 单臂一个、双臂两个固定 EEF 原点协议的训练权重；也不冒称本次 DeepSeek 长解释数据的训练产物。复现旧基线时必须沿用 historical mix6 的输入、prompt、多点表示、坐标归一化与评测协议。

检查点

Subfolder	Snapshot	Shards	Raw tensor data
`legacy_sft_step900`	legacy mix6 SFT step900	12	54.713 GB
`legacy_grpo_step250`	legacy mix6 GRPO step250	12	54.713 GB

两个目录各是一份完整的 HF 模型检查点（不是 LoRA），共 24 个标准 safetensors 分片。每文件 <=5,000,000,000 字节（含头），总权重约 109.427 GB；原 tensor key、shape、BF16 value bytes 和 config/tokenizer/processor 文件保持不变。没有拆开单个张量、量化、重训或 GPU 推理。

工程中基座昵称为 Qwen3.8-27B；原配置的 model_type 为 qwen3_5， architecture 为 Qwen3_5ForConditionalGeneration，保存版本为 Transformers 5.9.0。没有为了仓库名称修改架构。SFT 原 config 中 dtype 字段是 float32，但实际存储张量为 BF16；需要显式以 BF16 加载，避免无意扩大内存需求。两个配置的 MTP/EOS 等历史差异保留，不把它们默默改成同一份配置。

加载（示例，不代表已运行 GPU 验证）

这是 multi-checkpoint repo；必须指定 subfolder，不能只对仓库根目录加载模型。使用支持原 qwen3_5 架构的 Transformers（原记录版本 5.9.0）及匹配的 PyTorch/accelerate。模型仓库公开，可匿名读取；不需要在代码或配置里填写密钥。

import torch
from transformers import AutoProcessor, AutoModelForImageTextToText

repo_id = "diffusion-gif/trick-prediction"
subfolder = "legacy_grpo_step250"  # 或 legacy_sft_step900
processor = AutoProcessor.from_pretrained(repo_id, subfolder=subfolder)
model = AutoModelForImageTextToText.from_pretrained(
    repo_id, subfolder=subfolder, dtype=torch.bfloat16, device_map="auto"
)
# 实际预测必须采用该历史 checkpoint 的 prompt / 多点轨迹输出协议。
# 参数本体约54.7GB；还需要额外运行内存/KV cache，示例不会自动下载数据或调用 API。

训练/数据/预测/评测源码与协议： coisini-gif/trick_prediction（私密，需访问权限）。本仓库不包含数据集、CoT 标注、optimizer/RNG states、日志、缓存或视频。使用新的数据生成器并不自动等于这些历史权重的原训练数据。没有声称复现论文/机器人运行指标；HF 文件和 SHA256 完整性检查不是推理精度检验。

文件完整性

bundle_manifest.json 和 CHECKSUMS.sha256 给出发布文件大小/哈希。每个 checkpoint 的 model.safetensors.index.json 覆盖全部 1,184 个张量； reshard_manifest.json 保留原文件/分片和逐张量 SHA256，以及本地独立回读校验记录。 safetensors_reader_validation.json 记录原生 CPU reader 校验，未实例化模型。原分片记录中的 upload_run=false 指导出阶段，不是该 HF 仓库的传输状态。

python tools/verify_model_bundle.py --bundle /your/downloaded/trick-prediction
# 仅CPU/文件读取，不使用GPU、不运行模型，不调用教师API

tools/reshard_safetensors.py 与 tests/test_reshard_safetensors.py 提供同一分片工具和小型测试。上游模型及源码各按自己的许可证使用；本 bundle 不擅自给所有来源改成统一的新许可证。仓库为 Public model repo，增量上传不删除已有文件；不保存/发布凭证。

Public distribution status

Repository: diffusion-gif/trick-prediction (model, Public). All listed tensor files are complete and remote hashes verified. Source export execution booleans describe the original local export, not current Hub upload status. See LICENSES/UPSTREAM.md for upstream attribution and component licenses.

Historical training-data index

TRAINING_DATA_INDEX.json is attached to this model download. It identifies retained ORIGINAL training JSON/CSV/Parquet, pinned protected snapshot revisions, file hashes, original legacy observation backups and separately labeled later data. Original restricted annotations remain private; no data-owner credentials are included.

Public registry: https://huggingface.co/datasets/diffusion-gif/training-data-index

# For old trajectory checkpoints; inspect other dataset IDs for Any2Ego:
python tools/fetch_training_data.py --index TRAINING_DATA_INDEX.json --dataset legacy_mix6_sft --output data_download
# after owner login / dry-run inspection add --execute

A pointer index cannot guarantee that an unbacked original video remains available forever. The large Ego-Exo RGB/GT-mask collection is not mirrored here. Launch-time content hashes were not recorded for all components; current retained snapshots and actual verified path bindings are explicitly distinguished in the index.

Downloads last month: -; Downloads are not tracked for this model. How to track

Model tree for diffusion-gif/trick-prediction

Base model

Qwen/Qwen3.8-27B

Finetuned

(842)

this model