Update README.md

CoderLSF · Nov 16, 2023 · b3328c0 · b3328c0
1 parent c81b254
commit b3328c0
Showing 1 changed file with 4 additions and 3 deletions.
diff --git a/README.md b/README.md
@@ -59,6 +59,8 @@ See [llama2.c](https://github.com/karpathy/llama2.c)
 ./main -c ./models/stories110M.bin -z ./models/tokenizer.bin -j 14 -q int8 -n 200 -i 'That was a long long story happened in the ancient China.'
 ```
 
+<img width="1501" alt="image" src="https://github.com/CoderLSF/fast-llama/assets/65639063/28156af1-142e-417c-9b94-8d931fac8884">
+
 #### 2. Run with hugging face format models
 **`Step 1`**: Download a model
 
@@ -74,6 +76,8 @@ python3 ./tools/convert_flm.py -m /path/to/model-directory -o ./models/model-nam
 ./main -c ./models/model-name-int8.flm -j 40 -n 200 -i 'That was a long long story happened in the ancient China.'
 ```
 
+![image](https://github.com/CoderLSF/RapidLLaMA/assets/65639063/d4477fcb-96fb-4b0a-a1fd-30ca583d0aa2)
+
 > 
 All supported command-line options are as follows:
 
@@ -114,9 +118,6 @@ Core(s) per socket: 28
 Socket(s): 2
 ```
 
-<img width="1501" alt="image" src="https://github.com/CoderLSF/fast-llama/assets/65639063/28156af1-142e-417c-9b94-8d931fac8884">
-
-![image](https://github.com/CoderLSF/RapidLLaMA/assets/65639063/d4477fcb-96fb-4b0a-a1fd-30ca583d0aa2)
 
 ![2a58bda471f0aa2770f349dba73a530d](https://github.com/CoderLSF/fast-llama/assets/65639063/c3634948-280d-47c8-b9e7-ff07d7104b86)