Update README.md
Browse files
README.md
CHANGED
|
@@ -14,7 +14,7 @@ license: mit
|
|
| 14 |
# OpenVINO IR model with int4 quantization
|
| 15 |
|
| 16 |
Model definition for LocalAI:
|
| 17 |
-
```
|
| 18 |
name: gemma-2-9b-it-SimPO
|
| 19 |
backend: transformers
|
| 20 |
parameters:
|
|
@@ -23,10 +23,13 @@ context_size: 8192
|
|
| 23 |
type: OVModelForCausalLM
|
| 24 |
template:
|
| 25 |
use_tokenizer_template: true
|
|
|
|
|
|
|
|
|
|
| 26 |
```
|
| 27 |
|
| 28 |
To run the model directly with LocalAI:
|
| 29 |
-
```
|
| 30 |
local-ai run huggingface://fakezeta/gemma-2-9b-it-SimPO-ov-int4/model.yaml
|
| 31 |
```
|
| 32 |
|
|
|
|
| 14 |
# OpenVINO IR model with int4 quantization
|
| 15 |
|
| 16 |
Model definition for LocalAI:
|
| 17 |
+
```yaml
|
| 18 |
name: gemma-2-9b-it-SimPO
|
| 19 |
backend: transformers
|
| 20 |
parameters:
|
|
|
|
| 23 |
type: OVModelForCausalLM
|
| 24 |
template:
|
| 25 |
use_tokenizer_template: true
|
| 26 |
+
stopwords:
|
| 27 |
+
- "<eos>"
|
| 28 |
+
- "<end_of_turn>"
|
| 29 |
```
|
| 30 |
|
| 31 |
To run the model directly with LocalAI:
|
| 32 |
+
```shell
|
| 33 |
local-ai run huggingface://fakezeta/gemma-2-9b-it-SimPO-ov-int4/model.yaml
|
| 34 |
```
|
| 35 |
|