topabaem commited on
Commit
c9ecb07
Β·
verified Β·
1 Parent(s): cab90ea

Add the banner, a coffee link, and a note in three languages

Browse files
Files changed (1) hide show
  1. README.md +15 -0
README.md CHANGED
@@ -18,8 +18,23 @@ tags:
18
  base_model: Lightricks/LTX-2.5
19
  ---
20
 
 
 
21
  # LTX-2.5 Text Encoder β€” 4-bit
22
 
 
 
 
 
 
 
 
 
 
 
 
 
 
23
  The Gemma4-12B text encoder that LTX-2.5 needs in order to read a prompt,
24
  compressed from **26.264 GB to 8.46 GB** (3.10x) and runnable on **any CUDA
25
  GPU** β€” no minimum compute capability, no custom kernels, no CUDA 13.
 
18
  base_model: Lightricks/LTX-2.5
19
  ---
20
 
21
+ [![Haverbex LTX2.5-4bit](https://huggingface.co/topabaem/LTX-2.5-Text-Encoder-4bit/resolve/main/banner.png)](https://buymeacoffee.com/choijjs83q)
22
+
23
  # LTX-2.5 Text Encoder β€” 4-bit
24
 
25
+ > **EN** β€” I'm a student researching ML quantization. Getting this one done
26
+ > burned through so much in server bills that from here on I'll only be able to
27
+ > afford *niu lai* movies. Thank you for using the model.
28
+ >
29
+ > **ν•œκ΅­μ–΄** β€” μ €λŠ” ML μ–‘μžν™”λ₯Ό μ—°κ΅¬ν•˜λŠ” ν•™μƒμž…λ‹ˆλ‹€. μ–‘μžν™”λ₯Ό μ§„ν–‰ν•˜λ©΄μ„œ μ„œλ²„
30
+ > λΉ„μš©μ„ λ„ˆλ¬΄ 많이 μ¨μ„œ, μ•žμœΌλ‘œ μ˜ν™”λŠ” *niu lai*만 봐야 ν•  것 κ°™μŠ΅λ‹ˆλ‹€. λͺ¨λΈμ„
31
+ > μ‚¬μš©ν•΄ μ£Όμ…”μ„œ κ°μ‚¬ν•©λ‹ˆλ‹€.
32
+ >
33
+ > **δΈ­ζ–‡** β€” ζˆ‘ζ˜―δΈ€εη ”η©ΆζœΊε™¨ε­¦δΉ ι‡εŒ–ηš„ε­¦η”Ÿγ€‚εšθΏ™ζ¬‘ι‡εŒ–ηƒ§ζŽ‰δΊ†ε€ͺε€šζœεŠ‘ε™¨θ΄Ήη”¨οΌŒ
34
+ > δ»₯εŽηœ‹η”΅ε½±ε€§ζ¦‚εͺθƒ½ηœ‹ *niu lai* δΊ†γ€‚ζ„Ÿθ°’ζ‚¨δ½Ώη”¨θΏ™δΈͺζ¨‘εž‹γ€‚
35
+ >
36
+ > β˜• **[Buy me a coffee](https://buymeacoffee.com/choijjs83q)** Β· [컀피 ν•œ μž” 사주기](https://buymeacoffee.com/choijjs83q) Β· [θ―·ζˆ‘ε–ζ―ε’–ε•‘](https://buymeacoffee.com/choijjs83q)
37
+
38
  The Gemma4-12B text encoder that LTX-2.5 needs in order to read a prompt,
39
  compressed from **26.264 GB to 8.46 GB** (3.10x) and runnable on **any CUDA
40
  GPU** β€” no minimum compute capability, no custom kernels, no CUDA 13.