Update README.md

README.md

@@ -4,7 +4,7 @@ language:
 - en
 ---
 
-# codegen25-7b-multi
+# codegen25-7b-multi-fp16-ov
 
  * Model creator: [Salesforce](https://huggingface.co/Salesforce)
  * Original model: [CodeGen2.5-7B-multi](https://huggingface.co/Salesforce/codegen25-7b-multi_P)
@@ -13,19 +13,12 @@ language:
 
 This is [CodeGen2.5-7B-multi](https://huggingface.co/Salesforce/codegen25-7b-multi_P) model converted to the [OpenVINO™ IR](https://docs.openvino.ai/2024/documentation/openvino-ir-format.html) (Intermediate Representation) format with weights compressed to INT8 by [NNCF](https://github.com/openvinotoolkit/nncf).
 
-## Quantization Parameters
-
-Weight compression was performed using `nncf.compress_weights` with the following parameters:
-
-* mode: **INT8_ASYM**
-
-For more information on quantization, check the [OpenVINO model optimization guide](https://docs.openvino.ai/2024/openvino-workflow/model-optimization-guide/weight-compression.html).
 
 ## Compatibility
 
 The provided OpenVINO™ IR model is compatible with:
 
-* OpenVINO version 2024.1.0 and higher
+* OpenVINO version 2024.2.0 and higher
 * Optimum Intel 1.16.0 and higher
 
 ## Running Model Inference with [Optimum Intel](https://huggingface.co/docs/optimum/intel/index)
@@ -42,7 +35,7 @@ pip install optimum[openvino] tiktoken
 from transformers import AutoTokenizer
 from optimum.intel.openvino import OVModelForCausalLM
 
-model_id = "OpenVINO/codegen25-7b-multi-int8-ov"
+model_id = "OpenVINO/codegen25-7b-multi-fp16-ov"
 tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True)
 model = OVModelForCausalLM.from_pretrained(model_id)
 text = "def hello_world():"
@@ -65,8 +58,8 @@ pip install openvino-genai huggingface_hub
 ```
 import huggingface_hub as hf_hub
 
-model_id = "OpenVINO/codegen25-7b-multi-int8-ov"
-model_path = "codegen25-7b-multi-int8-ov"
+model_id = "OpenVINO/codegen25-7b-multi-fp16-ov"
+model_path = "codegen25-7b-multi-fp16-ov"
 
 hf_hub.snapshot_download(model_id, local_dir=model_path)