Hugging Face's logo

TitleOS
/
Spark-270M-FP16

Text Generation
Transformers
Safetensors
English
gemma3_text
gemma-3
synthetic-data
textbooks
distillation
utility
summarization
lightning
conversational
text-generation-inference
Model card Files
xet
Community
TitleOS commited on
Commit
f0005f7
·
verified ·
1 Parent(s): 8862b8a

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +4 -1
README.md CHANGED
@@ -77,11 +77,14 @@ input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")
77
 
78
  outputs = model.generate(**input_ids, max_new_tokens=128)
79
  print(tokenizer.d ecode(outputs[0]))
80
-
81
 
82
  Quants:
83
 
84
  Q4_K_M: https://huggingface.co/TitleOS/Spark-270M-FP16-Q4_K_M-GGUF
 
85
  Q8: https://huggingface.co/TitleOS/Spark-270M-FP16-Q8_0-GGUF
 
86
  FP16: https://huggingface.co/TitleOS/Spark-270M-FP16
 
87
  Adaptor: https://huggingface.co/TitleOS/Spark-270M-LoRA
 
77
 
78
  outputs = model.generate(**input_ids, max_new_tokens=128)
79
  print(tokenizer.d ecode(outputs[0]))
80
+ ```
81
 
82
  Quants:
83
 
84
  Q4_K_M: https://huggingface.co/TitleOS/Spark-270M-FP16-Q4_K_M-GGUF
85
+
86
  Q8: https://huggingface.co/TitleOS/Spark-270M-FP16-Q8_0-GGUF
87
+
88
  FP16: https://huggingface.co/TitleOS/Spark-270M-FP16
89
+
90
  Adaptor: https://huggingface.co/TitleOS/Spark-270M-LoRA