Instructions to use rain1955/emotion-vector-replication with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use rain1955/emotion-vector-replication with Transformers:

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

pipe = pipeline("text-generation", model="rain1955/emotion-vector-replication")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("rain1955/emotion-vector-replication", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use rain1955/emotion-vector-replication with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "rain1955/emotion-vector-replication"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "rain1955/emotion-vector-replication",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/rain1955/emotion-vector-replication

SGLang

How to use rain1955/emotion-vector-replication 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 "rain1955/emotion-vector-replication" \
    --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": "rain1955/emotion-vector-replication",
		"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 "rain1955/emotion-vector-replication" \
        --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": "rain1955/emotion-vector-replication",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use rain1955/emotion-vector-replication with Docker Model Runner:
```
docker model run hf.co/rain1955/emotion-vector-replication
```

rain1955 commited on Apr 5

Commit

43e30a3

verified ·

1 Parent(s): f9f4958

Sanitize: remove internal codenames

Browse files

Files changed (1) hide show

results/THREADS_DATA.md +3 -3

results/THREADS_DATA.md CHANGED Viewed

@@ -13,8 +13,8 @@
 | 模型 | Claude Sonnet 4.5（閉源） | Gemma4-E4B（4B，開源） |
 | 情緒數量 | 171 個 | 9 個（MVP） |
 | 故事數量 | 205,200 個 | 1,002 個 |
-| 硬體 | 內部叢集 | GX10 一台（GB10 GPU） |
-| 團隊 | ~16 位研究員 | 1 人 + 1 泉 |
 | 費用 | 不公開 | 電費 |
 ---
@@ -142,5 +142,5 @@
 - 去噪：PCA 投影掉 3 個主成分（中性文本 50% 方差）
 - 向量計算：emotion_mean - global_mean
 - 驗證：Logit Lens + PCA
-- 硬體：NVIDIA GB10（GX10），PyTorch 2.10 + CUDA
 - 總耗時：故事生成 ~20 分鐘 + 向量抽取 ~10 分鐘

 | 模型 | Claude Sonnet 4.5（閉源） | Gemma4-E4B（4B，開源） |
 | 情緒數量 | 171 個 | 9 個（MVP） |
 | 故事數量 | 205,200 個 | 1,002 個 |
+| 硬體 | 內部叢集 | NVIDIA GB10 GPU 一台 |
+| 團隊 | ~16 位研究員 | 1 人 + 1 AI |
 | 費用 | 不公開 | 電費 |
 ---
 - 去噪：PCA 投影掉 3 個主成分（中性文本 50% 方差）
 - 向量計算：emotion_mean - global_mean
 - 驗證：Logit Lens + PCA
+- 硬體：NVIDIA GB10（local server），PyTorch 2.10 + CUDA
 - 總耗時：故事生成 ~20 分鐘 + 向量抽取 ~10 分鐘