Update usage instructions
Browse files
README.md
CHANGED
|
@@ -48,21 +48,9 @@ Llama-3.1-Minitron-4B-Width-Base uses a model embedding size of 3072, 32 attenti
|
|
| 48 |
|
| 49 |
|
| 50 |
## Usage
|
| 51 |
-
|
| 52 |
-
to support this model in Hugging Face Transformers are currently under review
|
| 53 |
-
([#32495](https://github.com/huggingface/transformers/pull/32495) and [#32502](https://github.com/huggingface/transformers/pull/32502))
|
| 54 |
-
and are expected to be merged soon. In the meantime,
|
| 55 |
-
please follow the installation instructions below:
|
| 56 |
-
|
| 57 |
```
|
| 58 |
-
|
| 59 |
-
$ git clone -b suhara/llama-kv-channels --single-branch https://github.com/suhara/transformers.git && cd transformers
|
| 60 |
-
|
| 61 |
-
# Fetch changes from PR 32495
|
| 62 |
-
$ git fetch https://github.com/suiyoubi/transformers.git aot/head_dim_rope && git cherry-pick FETCH_HEAD --strategy-option theirs
|
| 63 |
-
|
| 64 |
-
# Install transformers
|
| 65 |
-
$ pip install -e .
|
| 66 |
```
|
| 67 |
We can now run inference on this model:
|
| 68 |
|
|
|
|
| 48 |
|
| 49 |
|
| 50 |
## Usage
|
| 51 |
+
Support for this model will be added in the upcoming `transformers` release. In the meantime, please install the library from source:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 52 |
```
|
| 53 |
+
pip install git+https://github.com/huggingface/transformers
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 54 |
```
|
| 55 |
We can now run inference on this model:
|
| 56 |
|