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")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("rain1955/emotion-vector-replication", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

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
```

emotion-vector-replication

Commit History

Apr 6

13:11
Fix arousal groupings per @dejanseo feedback: revised emotion categories, added threshold check for unclear axes

rain1955

Verified signature
8e7c29e
09:32
SEO: add multilingual tags, model-index metrics, thumbnail, expand search coverage

rain1955

Verified signature
feb586c

Apr 5

14:15
Add metadata tags for discoverability

rain1955

Verified signature
8f44761
14:14
Sanitize: remove internal codenames

rain1955

Verified signature
43e30a3
14:13
Add data/emotion_stories.jsonl

rain1955

Verified signature
f9f4958
14:13
Add requirements.txt

rain1955

Verified signature
939aca0
14:13
Add results/THREADS_DATA.md

rain1955

Verified signature
86dd93c
14:13
Add results/fig4_scale_comparison.png

rain1955

Verified signature
48d5418
14:13
Add results/fig3_logit_lens.png

rain1955

Verified signature
8336bc5
14:13
Add results/fig2_cosine_heatmap.png

rain1955

Verified signature
a8bbbfc
14:13
Add results/fig1_pca_scatter.png

rain1955

Verified signature
af1d3ec
14:13
Add results/emotion_vectors.npz

rain1955

Verified signature
33da913
14:13
Add results/experiment_results.json

rain1955

Verified signature
b6c4f54
14:13
Add generate_stories.py

rain1955

Verified signature
6afd58f
14:13
Add analyze_vectors.py

rain1955

Verified signature
c339092
14:13
Add extract_vectors.py

rain1955

Verified signature
051c56b
14:13
Add README.md

rain1955

Verified signature
b10ae02
14:11
initial commit

rain1955

Verified signature
9dcd1ef

Commit History

Apr 6

Fix arousal groupings per @dejanseo feedback: revised emotion categories, added threshold check for unclear axes

SEO: add multilingual tags, model-index metrics, thumbnail, expand search coverage

Apr 5

Add metadata tags for discoverability

Sanitize: remove internal codenames

Add data/emotion_stories.jsonl

Add requirements.txt

Add results/THREADS_DATA.md

Add results/fig4_scale_comparison.png

Add results/fig3_logit_lens.png

Add results/fig2_cosine_heatmap.png

Add results/fig1_pca_scatter.png

Add results/emotion_vectors.npz

Add results/experiment_results.json

Add generate_stories.py

Add analyze_vectors.py

Add extract_vectors.py

Add README.md

initial commit