Update README.md

README.md

@@ -16,7 +16,7 @@ license: llama3.1
 base_model: meta-llama/Meta-Llama-3.1-405B-Instruct
 ---
 
-# Meta-Llama-3.1-405B-Instruct-quantized.w8a8
+# Meta-Llama-3.1-405B-Instruct-quantized.w8a16
 
 ## Model Overview
 - **Model Architecture:** Meta-Llama-3
@@ -271,7 +271,7 @@ lm_eval \
 ```
 lm_eval \
   --model vllm \
-  --model_args pretrained="neuralmagic/Meta-Llama-3.1-405B-Instruct-quantized.w8a8",dtype=auto,add_bos_token=True,max_model_len=4064,max_gen_toks=1024,enable_chunked_prefill=True,tensor_parallel_size=8 \
+  --model_args pretrained="neuralmagic/Meta-Llama-3.1-405B-Instruct-quantized.w8a16",dtype=auto,add_bos_token=True,max_model_len=4064,max_gen_toks=1024,enable_chunked_prefill=True,tensor_parallel_size=8 \
   --tasks mmlu_cot_0shot_llama_3.1_instruct \
   --apply_chat_template \
   --num_fewshot 0 \
@@ -282,7 +282,7 @@ lm_eval \
 ```
 lm_eval \
   --model vllm \
-  --model_args pretrained="neuralmagic/Meta-Llama-3.1-405B-Instruct-quantized.w8a8",dtype=auto,add_bos_token=True,max_model_len=3940,max_gen_toks=100,enable_chunked_prefill=True,tensor_parallel_size=8 \
+  --model_args pretrained="neuralmagic/Meta-Llama-3.1-405B-Instruct-quantized.w8a16",dtype=auto,add_bos_token=True,max_model_len=3940,max_gen_toks=100,enable_chunked_prefill=True,tensor_parallel_size=8 \
   --tasks arc_challenge_llama_3.1_instruct \
   --apply_chat_template \
   --num_fewshot 0 \
@@ -293,7 +293,7 @@ lm_eval \
 ```
 lm_eval \
   --model vllm \
-  --model_args pretrained="neuralmagic/Meta-Llama-3.1-405B-Instruct-quantized.w8a8",dtype=auto,add_bos_token=True,max_model_len=4096,max_gen_toks=1024,enable_chunked_prefill=True,tensor_parallel_size=8 \
+  --model_args pretrained="neuralmagic/Meta-Llama-3.1-405B-Instruct-quantized.w8a16",dtype=auto,add_bos_token=True,max_model_len=4096,max_gen_toks=1024,enable_chunked_prefill=True,tensor_parallel_size=8 \
   --tasks gsm8k_cot_llama_3.1_instruct \
   --fewshot_as_multiturn \
   --apply_chat_template \
@@ -305,7 +305,7 @@ lm_eval \
 ```
 lm_eval \
   --model vllm \
-  --model_args pretrained="neuralmagic/Meta-Llama-3.1-405B-Instruct-quantized.w8a8",dtype=auto,add_bos_token=True,max_model_len=4096,enable_chunked_prefill=True,tensor_parallel_size=8 \
+  --model_args pretrained="neuralmagic/Meta-Llama-3.1-405B-Instruct-quantized.w8a16",dtype=auto,add_bos_token=True,max_model_len=4096,enable_chunked_prefill=True,tensor_parallel_size=8 \
   --tasks hellaswag \
   --num_fewshot 10 \
   --batch_size auto
@@ -315,7 +315,7 @@ lm_eval \
 ```
 lm_eval \
   --model vllm \
-  --model_args pretrained="neuralmagic/Meta-Llama-3.1-405B-Instruct-quantized.w8a8",dtype=auto,add_bos_token=True,max_model_len=4096,enable_chunked_prefill=True,tensor_parallel_size=8 \
+  --model_args pretrained="neuralmagic/Meta-Llama-3.1-405B-Instruct-quantized.w8a16",dtype=auto,add_bos_token=True,max_model_len=4096,enable_chunked_prefill=True,tensor_parallel_size=8 \
   --tasks winogrande \
   --num_fewshot 5 \
   --batch_size auto
@@ -325,7 +325,7 @@ lm_eval \
 ```
 lm_eval \
   --model vllm \
-  --model_args pretrained="neuralmagic/Meta-Llama-3.1-405B-Instruct-quantized.w8a8",dtype=auto,add_bos_token=True,max_model_len=4096,enable_chunked_prefill=True,tensor_parallel_size=8 \
+  --model_args pretrained="neuralmagic/Meta-Llama-3.1-405B-Instruct-quantized.w8a16",dtype=auto,add_bos_token=True,max_model_len=4096,enable_chunked_prefill=True,tensor_parallel_size=8 \
   --tasks truthfulqa \
   --num_fewshot 0 \
   --batch_size auto