Update README.md
Browse files
README.md
CHANGED
@@ -22,7 +22,7 @@ base_model:
|
|
22 |
- tiiuae/Falcon3-1B-Base
|
23 |
inference: false
|
24 |
library_name: transformers
|
25 |
-
model_creator:
|
26 |
prompt_template: '{prompt} '
|
27 |
quantized_by: fbaldassarri
|
28 |
---
|
@@ -39,7 +39,7 @@ Fast and low memory, 2-3X speedup (slight accuracy drop at W4G128)
|
|
39 |
|
40 |
Quantization framework: [Intel AutoRound](https://github.com/intel/auto-round) v0.4.4
|
41 |
|
42 |
-
Note: this INT4 version of
|
43 |
|
44 |
## Replication Recipe
|
45 |
|
|
|
22 |
- tiiuae/Falcon3-1B-Base
|
23 |
inference: false
|
24 |
library_name: transformers
|
25 |
+
model_creator: tiiuae
|
26 |
prompt_template: '{prompt} '
|
27 |
quantized_by: fbaldassarri
|
28 |
---
|
|
|
39 |
|
40 |
Quantization framework: [Intel AutoRound](https://github.com/intel/auto-round) v0.4.4
|
41 |
|
42 |
+
Note: this INT4 version of Falcon3-1B-Base has been quantized to run inference through CPU.
|
43 |
|
44 |
## Replication Recipe
|
45 |
|