lidarbtc/kollava-v1.5 πΌοΈπ’π β π
About
korean version of llava-v1.5

Example Output
Prompt:
"ν΄λΉ μ΄λ―Έμ§μ λ±μ₯νλ μΈλ¬Όμ 볡μ₯μ μ΄λ μν©μ μλ§λ μ·μ΄μΌ?"
Output
μ΄λ―Έμ§ μ μΈλ¬Όμ ν±ν¬ν±κ³Ό κ°μ£½ μ€νΈλ©μ μ°©μ©νκ³ μμΌλ©°, μ΄λ μΊμ£ΌμΌνκ³ νΈμν 볡μ₯μ μμν©λλ€. μ΄ λ³΅μ₯μ λ₯κ±°λ λ°λ»ν λ μ¨μ μ ν©νλ©° μμ§μμ΄ μμ λ‘κ³ νΈμν©λλ€. μ΄ λ³΅μ₯μ νΌν¬λ, ν΄λ³ λλ€μ΄, μΉκ΅¬λ€κ³Όμ μΊμ£ΌμΌν λͺ¨μ λ± μ¬λ¦μ² μΌμΈ νμ¬λ νλμ μ ν©ν©λλ€. λν κ°μ£½ μ€νΈλ©μ μ€νμΌλ¦¬μνκ³ μ£μ§ μλ λλμ λν΄ μΊμ£ΌμΌν λΆμκΈ°μ μΈλ ¨λ―Έλ₯Ό λν©λλ€.
Performance Metrics
9.24s
Prediction Time
109.46s
Total Time
All Input Parameters
{ "image": "https://replicate.delivery/pbxt/K3fzsUGoCa8rhQeHoOCVVVk9xcDbejJ2r3B43RDaE6Xyytii/haerin.jpg", "top_p": 1, "prompt": "ν΄λΉ μ΄λ―Έμ§μ λ±μ₯νλ μΈλ¬Όμ 볡μ₯μ μ΄λ μν©μ μλ§λ μ·μ΄μΌ?", "max_tokens": 1024, "temperature": 0.2 }
Input Parameters
- image (required)
- Input image
- top_p
- When decoding text, samples from the top p percentage of most likely tokens; lower to ignore less likely tokens
- prompt (required)
- Prompt to use for text generation
- max_tokens
- Maximum number of tokens to generate. A word is generally 2-3 tokens
- temperature
- Adjusts randomness of outputs, greater than 1 is random and 0 is deterministic
Output Schema
Output
Example Execution Logs
/root/.pyenv/versions/3.11.7/lib/python3.11/site-packages/transformers/generation/utils.py:1270: UserWarning: You have modified the pretrained model configuration to control generation. This is a deprecated strategy to control generation and will be removed soon, in a future version. Please use a generation configuration file (see https://huggingface.co/docs/transformers/main_classes/text_generation ) warnings.warn(
Version Details
- Version ID
f86c65854b3e8b3b351758e56827a93b01cbb90f08515531ce2d385bebce7e32
- Version Created
- December 16, 2023