Update README.md

README.md

@@ -233,7 +233,7 @@ The results were obtained using the following commands:
 ```
 lm_eval \
   --model vllm \
-  --model_args pretrained="neuralmagic/Meta-Llama-3.1-8B-Instruct-quantized.w8a16",dtype=auto,add_bos_token=True,max_model_len=3850,max_gen_toks=10,tensor_parallel_size=1 \
+  --model_args pretrained="neuralmagic/Meta-Llama-3.1-8B-Instruct-quantized.w4a16",dtype=auto,add_bos_token=True,max_model_len=3850,max_gen_toks=10,tensor_parallel_size=1 \
   --tasks mmlu_llama_3.1_instruct \
   --fewshot_as_multiturn \
   --apply_chat_template \
@@ -245,7 +245,7 @@ lm_eval \
 ```
 lm_eval \
   --model vllm \
-  --model_args pretrained="neuralmagic/Meta-Llama-3.1-8B-Instruct-quantized.w8a16",dtype=auto,add_bos_token=True,max_model_len=4064,max_gen_toks=1024,tensor_parallel_size=1 \
+  --model_args pretrained="neuralmagic/Meta-Llama-3.1-8B-Instruct-quantized.w4a16",dtype=auto,add_bos_token=True,max_model_len=4064,max_gen_toks=1024,tensor_parallel_size=1 \
   --tasks mmlu_cot_0shot_llama_3.1_instruct \
   --apply_chat_template \
   --num_fewshot 0 \
@@ -256,7 +256,7 @@ lm_eval \
 ```
 lm_eval \
   --model vllm \
-  --model_args pretrained="neuralmagic/Meta-Llama-3.1-8B-Instruct-quantized.w8a16",dtype=auto,add_bos_token=True,max_model_len=3940,max_gen_toks=100,tensor_parallel_size=1 \
+  --model_args pretrained="neuralmagic/Meta-Llama-3.1-8B-Instruct-quantized.w4a16",dtype=auto,add_bos_token=True,max_model_len=3940,max_gen_toks=100,tensor_parallel_size=1 \
   --tasks arc_challenge_llama_3.1_instruct \
   --apply_chat_template \
   --num_fewshot 0 \
@@ -267,7 +267,7 @@ lm_eval \
 ```
 lm_eval \
   --model vllm \
-  --model_args pretrained="neuralmagic/Meta-Llama-3.1-8B-Instruct-quantized.w8a16",dtype=auto,add_bos_token=True,max_model_len=4096,max_gen_toks=1024,tensor_parallel_size=1 \
+  --model_args pretrained="neuralmagic/Meta-Llama-3.1-8B-Instruct-quantized.w4a16",dtype=auto,add_bos_token=True,max_model_len=4096,max_gen_toks=1024,tensor_parallel_size=1 \
   --tasks gsm8k_cot_llama_3.1_instruct \
   --fewshot_as_multiturn \
   --apply_chat_template \
@@ -279,7 +279,7 @@ lm_eval \
 ```
 lm_eval \
   --model vllm \
-  --model_args pretrained="neuralmagic/Meta-Llama-3.1-8B-Instruct-quantized.w8a16",dtype=auto,add_bos_token=True,max_model_len=4096,tensor_parallel_size=1 \
+  --model_args pretrained="neuralmagic/Meta-Llama-3.1-8B-Instruct-quantized.w4a16",dtype=auto,add_bos_token=True,max_model_len=4096,tensor_parallel_size=1 \
   --tasks hellaswag \
   --num_fewshot 10 \
   --batch_size auto
@@ -289,7 +289,7 @@ lm_eval \
 ```
 lm_eval \
   --model vllm \
-  --model_args pretrained="neuralmagic/Meta-Llama-3.1-8B-Instruct-quantized.w8a16",dtype=auto,add_bos_token=True,max_model_len=4096,tensor_parallel_size=1 \
+  --model_args pretrained="neuralmagic/Meta-Llama-3.1-8B-Instruct-quantized.w4a16",dtype=auto,add_bos_token=True,max_model_len=4096,tensor_parallel_size=1 \
   --tasks winogrande \
   --num_fewshot 5 \
   --batch_size auto
@@ -299,7 +299,7 @@ lm_eval \
 ```
 lm_eval \
   --model vllm \
-  --model_args pretrained="neuralmagic/Meta-Llama-3.1-8B-Instruct-quantized.w8a16",dtype=auto,add_bos_token=True,max_model_len=4096,tensor_parallel_size=1 \
+  --model_args pretrained="neuralmagic/Meta-Llama-3.1-8B-Instruct-quantized.w4a16",dtype=auto,add_bos_token=True,max_model_len=4096,tensor_parallel_size=1 \
   --tasks truthfulqa \
   --num_fewshot 0 \
   --batch_size auto