fakezeta
/

gemma-2-9b-it-SimPO-ov-int8

alignment-handbook

Generated from Trainer

Model card Files Files and versions Community

fakezeta commited on Sep 16

Commit

512bce3

•

1 Parent(s): c2962ce

Update README.md

added stopwords to localai configuration

Files changed (1) hide show

README.md +5 -2

README.md CHANGED Viewed

@@ -14,7 +14,7 @@ license: mit
 # OpenVINO IR model with int8 quantization
 Model definition for LocalAI:
-```
 name: gemma-2-9b-it-SimPO
 backend: transformers
 parameters:
@@ -23,10 +23,13 @@ context_size: 8192
 type: OVModelForCausalLM
 template:
   use_tokenizer_template: true
 ```
 To run the model directly with LocalAI:
-```
 local-ai run huggingface://fakezeta/gemma-2-9b-it-SimPO-ov-int8/model.yaml
 ```

 # OpenVINO IR model with int8 quantization
 Model definition for LocalAI:
+```yaml
 name: gemma-2-9b-it-SimPO
 backend: transformers
 parameters:
 type: OVModelForCausalLM
 template:
   use_tokenizer_template: true
+stopwords:
+- "<eos>"
+- "<end_of_turn>"
 ```
 To run the model directly with LocalAI:
+```bash
 local-ai run huggingface://fakezeta/gemma-2-9b-it-SimPO-ov-int8/model.yaml
 ```