Update README.md

README.md

@@ -16,6 +16,33 @@ Inference of this model is compatible with AutoGPTQ's Kernel.
 
 
 
+
+### Reproduce the model
+
+Here is the sample command to reproduce the model
+
+```bash
+git clone https://github.com/intel/auto-round
+cd auto-round/examples/language-modeling
+pip install -r requirements.txt
+python3 main.py \
+--model_name  upstage/SOLAR-10.7B-Instruct-v1.0 \
+--device 0 \
+--group_size 128 \
+--bits 4 \
+--iters 1000 \
+--minmax_lr 2e-3 \
+--disable_quanted_input \
+--deployment_device 'gpu' \
+--output_dir "./tmp_autoround" \
+
+```
+
+
+
+
+
+
 ### Evaluate the model 
 
 Install [lm-eval-harness](https://github.com/EleutherAI/lm-evaluation-harness.git) from source, we used the git id 96d185fa6232a5ab685ba7c43e45d1dbb3bb906d
@@ -42,28 +69,6 @@ lm_eval --model hf --model_args pretrained="Intel/SOLAR-10.7B-Instruct-v1.0-int4
 
 
 
-### Reproduce the model
-
-Here is the sample command to reproduce the model
-
-```bash
-git clone https://github.com/intel/auto-round
-cd auto-round/examples/language-modeling
-pip install -r requirements.txt
-python3 main.py \
---model_name  upstage/SOLAR-10.7B-Instruct-v1.0 \
---device 0 \
---group_size 128 \
---bits 4 \
---iters 1000 \
---minmax_lr 2e-3 \
---disable_quanted_input \
---deployment_device 'gpu' \
---output_dir "./tmp_autoround" \
-
-```
-
-