Hugging Face's logo

kalle07
/
embedder_collection

Sentence Similarity
sentence-transformers
GGUF
English
German
feature-extraction
embedder
embedding
models
GGUF
Bert
Nomic
Gist
Granite
BGE
Jina
gemma
Snowflake
Qwen
text-embeddings-inference
RAG
Rerank
similarity
PDF
Parsing
Parser
Model card Files
xet
 Community
1
kalle07 commited on
Commit
c19c1c2
·
verified ·
1 Parent(s): 4f15d72

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +3 -3
README.md CHANGED
@@ -81,9 +81,9 @@ but ~5000 characters is one page of a book (no matter ger/en). But if you calcul
81
  The example is english, for german you can add apox 50% more token/word (1000 words ~1800t)<br>
82
  <li>1200t (~1000 words ~5000 chracter) ~0.1GB, this is aprox one page with small font</li>
83
  <li>best to get in mind: 5000-6000 characters correspond to approximately one page and approximately 1200-1400 token.</li>
84
- <li>8000t (~6000 words) ~0.8GB VRAM usage</li>
85
- <li>16000t (~12000 words) ~1.5GB VRAM usage</li>
86
- <li>32000t (~24000 words) ~3GB VRAM usage</li>
87
  <br>
88
  Vector Size (Dimensions- you can not change)
89
 
 
81
  The example is english, for german you can add apox 50% more token/word (1000 words ~1800t)<br>
82
  <li>1200t (~1000 words ~5000 chracter) ~0.1GB, this is aprox one page with small font</li>
83
  <li>best to get in mind: 5000-6000 characters correspond to approximately one page and approximately 1200-1400 token.</li>
84
+ <li>8000t (~6000 words) ~1.5GB VRAM usage</li>
85
+ <li>16000t (~12000 words) ~3GB VRAM usage</li>
86
+ <li>32000t (~24000 words) ~6GB VRAM usage</li>
87
  <br>
88
  Vector Size (Dimensions- you can not change)
89