jamescallander commited on
Commit
46329f3
·
verified ·
1 Parent(s): 10c2434

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +9 -1
README.md CHANGED
@@ -31,6 +31,15 @@ tags:
31
  - Quantization: `w8a8_g128`
32
  - Output: single-file `.rkllm` artifact
33
  - Tokenizer: not required at runtime (UI handles prompt I/O)
 
 
 
 
 
 
 
 
 
34
 
35
  ## Intended use
36
 
@@ -40,7 +49,6 @@ tags:
40
 
41
  ## Limitations
42
 
43
- - ⚠️ **Not substitutable for professional medical advice, diagnosis, or treatment.** Always consult qualified medical professionals for health decisions.
44
  - Requires 5.5GB free memory
45
  - Requires ~8–12GB of free system memory depending on board and workload.
46
  - Quantization (`w8a8_g128`) may slightly impact model fidelity vs. upstream FP16.
 
31
  - Quantization: `w8a8_g128`
32
  - Output: single-file `.rkllm` artifact
33
  - Tokenizer: not required at runtime (UI handles prompt I/O)
34
+
35
+ ## ⚠️ Safety disclaimer
36
+
37
+ 🛑 **This model is not a substitute for professional advice, diagnosis, or treatment.**
38
+
39
+ - It is intended for **research, educational, and experimental purposes only**.
40
+ - Do **not** rely on its outputs for decisions related to health, safety, or legal/financial matters.
41
+ - Always consult a qualified professional for real-world guidance in these domains.
42
+ - Use responsibly and in compliance with the source model’s license and Acceptable Use Policy.
43
 
44
  ## Intended use
45
 
 
49
 
50
  ## Limitations
51
 
 
52
  - Requires 5.5GB free memory
53
  - Requires ~8–12GB of free system memory depending on board and workload.
54
  - Quantization (`w8a8_g128`) may slightly impact model fidelity vs. upstream FP16.