Update README.md
Browse files
README.md
CHANGED
@@ -68,15 +68,13 @@ It is supported by:
|
|
68 |
<!-- description end -->
|
69 |
<!-- repositories-available start -->
|
70 |
|
71 |
-
##
|
72 |
-
|
73 |
-
I currently release 128g GEMM models only. The addition of group_size 32 models, and GEMV kernel models, is being actively considered.
|
74 |
|
75 |
Models are released as sharded safetensors files.
|
76 |
|
77 |
| Branch | Bits | GS | AWQ Dataset | Seq Len | Size |
|
78 |
| ------ | ---- | -- | ----------- | ------- | ---- |
|
79 |
-
| [main](https://huggingface.co/
|
80 |
|
81 |
<!-- README_AWQ.md-provided-files end -->
|
82 |
|
|
|
68 |
<!-- description end -->
|
69 |
<!-- repositories-available start -->
|
70 |
|
71 |
+
## Shared files, and GPTQ parameters
|
|
|
|
|
72 |
|
73 |
Models are released as sharded safetensors files.
|
74 |
|
75 |
| Branch | Bits | GS | AWQ Dataset | Seq Len | Size |
|
76 |
| ------ | ---- | -- | ----------- | ------- | ---- |
|
77 |
+
| [main](https://huggingface.co/Inferless/SOLAR-10.7B-Instruct-v1.0-GPTQ/tree/main) | 4 | 128 | [VMware Open Instruct](https://huggingface.co/datasets/VMware/open-instruct/viewer/) | 4096 | 5.96 GB
|
78 |
|
79 |
<!-- README_AWQ.md-provided-files end -->
|
80 |
|