Spaces:
Running
Running
Update app.py
Browse files
app.py
CHANGED
|
@@ -552,7 +552,7 @@ class GGUFConverterUI:
|
|
| 552 |
info="Quantize embeddings tensor separately"
|
| 553 |
)
|
| 554 |
self.embedding_tensor_method = gr.Dropdown(
|
| 555 |
-
choices=["Q2_K", "Q3_K", "Q4_K", "Q5_K", "Q6_K", "Q8_0", "
|
| 556 |
label="Embeddings Quantization Method",
|
| 557 |
info="use a specific quant type for the token embeddings tensor",
|
| 558 |
value="Q8_0",
|
|
@@ -565,7 +565,7 @@ class GGUFConverterUI:
|
|
| 565 |
info="Quantize output tensor separately"
|
| 566 |
)
|
| 567 |
self.output_tensor_method = gr.Dropdown(
|
| 568 |
-
choices=["Q2_K", "Q3_K", "Q4_K", "Q5_K", "Q6_K", "Q8_0", "
|
| 569 |
label="Output Quantization Method",
|
| 570 |
info="use a specific quant type for the output.weight tensor",
|
| 571 |
value="Q8_0",
|
|
|
|
| 552 |
info="Quantize embeddings tensor separately"
|
| 553 |
)
|
| 554 |
self.embedding_tensor_method = gr.Dropdown(
|
| 555 |
+
choices=["Q2_K", "Q3_K", "Q4_K", "Q5_K", "Q6_K", "Q8_0", "F16"],
|
| 556 |
label="Embeddings Quantization Method",
|
| 557 |
info="use a specific quant type for the token embeddings tensor",
|
| 558 |
value="Q8_0",
|
|
|
|
| 565 |
info="Quantize output tensor separately"
|
| 566 |
)
|
| 567 |
self.output_tensor_method = gr.Dropdown(
|
| 568 |
+
choices=["Q2_K", "Q3_K", "Q4_K", "Q5_K", "Q6_K", "Q8_0", "F16"],
|
| 569 |
label="Output Quantization Method",
|
| 570 |
info="use a specific quant type for the output.weight tensor",
|
| 571 |
value="Q8_0",
|