Transformers
GGUF
code
Ivan Dolgov commited on
Commit
d9ec8e1
·
1 Parent(s): cca085c

add fim example for llama-cli

Browse files
Files changed (1) hide show
  1. README.md +9 -0
README.md CHANGED
@@ -28,6 +28,15 @@ Designed for integration into professional developer tooling (e.g., intelligent
28
  - Security: Code suggestions should not be assumed to be secure or free of vulnerabilities.
29
  - Format: This model is suitable mostly for FIM Completion objective with context's files.
30
 
 
 
 
 
 
 
 
 
 
31
  # Citation
32
  If you use this model, please cite:
33
 
 
28
  - Security: Code suggestions should not be assumed to be secure or free of vulnerabilities.
29
  - Format: This model is suitable mostly for FIM Completion objective with context's files.
30
 
31
+ # Sample Usage
32
+ Here are examples of how to run and sample from the model.
33
+
34
+ ## Fill-in-the-middle example
35
+
36
+ ```bash
37
+ llama-cli -m mellum-4b-sft-python.Q8_0.gguf --temp 0 -p $'<filename>main.py\n<fim_suffix><fim_prefix>def fibonacci(n):\n <fim_middle>'
38
+ ```
39
+
40
  # Citation
41
  If you use this model, please cite:
42