Update README.md

README.md

@@ -1,9 +1,7 @@
 ---
-base_model:
-- microsoft/Phi-3-mini-128k-instruct
-license: mit
+base_model: mistralai/Mistral-7B-v0.1
 ---
-# Phi-3-mini-128k-instruct-Weight-INT4-Per-Group-AWQ-Bfloat16
+# Mistral-7B-v0.1-AWQ-G128-INT4-SYM-BF16
 - ## Introduction
   This model was created by applying [Quark](https://quark.docs.amd.com/latest/index.html) with calibration samples from Pile dataset.
 - ## Quantization Stragegy
@@ -14,7 +12,7 @@ license: mit
 1. [Download and install Quark](https://quark.docs.amd.com/latest/install.html)
 2. Run the quantization script in the example folder using the following command line:
     ```sh
-    export MODEL_DIR = [local model checkpoint folder] or microsoft/Phi-3-mini-128k-instruct
+    export MODEL_DIR = [local model checkpoint folder] or mistralai/Mistral-7B-v0.1 
     # single GPU
     python3 quantize_quark.py --model_dir $MODEL_DIR \
                               --data_type bfloat16 \
@@ -23,7 +21,7 @@ license: mit
                               --quant_algo awq \
                               --dataset pileval_for_awq_benchmark \
                               --seq_len 512 \
-                              --output_dir Phi-3-mini-128k-instruct-W_Int4-Per_Group-AWQ-BFloat16 \
+                              --output_dir Mistral-7B-v0.1-AWQ-G128-INT4-SYM-BF16 \
                               --model_export quark_safetensors
     # cpu
     python3 quantize_quark.py --model_dir $MODEL_DIR \
@@ -33,7 +31,7 @@ license: mit
                               --quant_algo awq \
                               --dataset pileval_for_awq_benchmark \
                               --seq_len 512 \
-                              --output_dir Phi-3-mini-128k-instruct-W_Int4-Per_Group-AWQ-BFloat16 \
+                              --output_dir Mistral-7B-v0.1-AWQ-G128-INT4-SYM-BF16 \
                               --model_export quark_safetensors \
                               --device cpu
     ```
@@ -47,23 +45,25 @@ The quantization evaluation results are conducted in pseudo-quantization mode, w
   <tr>
    <td><strong>Benchmark</strong>
    </td>
-   <td><strong>Phi-3-mini-4k-instruct(Bfloat16) </strong>
+   <td><strong>Mistral-7B-v0.1(Bfloat16) </strong>
    </td>
-   <td><strong>Phi-3-mini-4k-instruct-Weight-INT4-Per-Group-AWQ-Bfloat16(this model)</strong>
+   <td><strong>Mistral-7B-v0.1-AWQ-G128-INT4-SYM-BF16(this model)</strong>
    </td>
   </tr>
   <tr>
    <td>Perplexity-wikitext2
    </td>
-   <td>6.2359
+   <td>5.2527
    </td>
-   <td>6.8193
+   <td>5.4250
    </td>
   </tr>
+  
 </table>
 
 #### License
-Modifications copyright(c) 2024 Advanced Micro Devices, Inc. All rights reserved.
+
+Modifications copyright(c) 2024 Advanced Micro Devices,Inc. All rights reserved.
 
 Licensed under the Apache License, Version 2.0 (the "License");
 you may not use this file except in compliance with the License.
@@ -75,4 +75,4 @@ Unless required by applicable law or agreed to in writing, software
 distributed under the License is distributed on an "AS IS" BASIS,
 WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 See the License for the specific language governing permissions and
-limitations under the License.
+limitations under the License.