Update README.md

README.md

@@ -8,7 +8,7 @@ base_model: deepseek-ai/DeepSeek-R1-Distill-Llama-8B
 library_name: transformers
 ---
 
-# DeepSeek-R1-Distill-Llama-8B-FP8-Dynamic
+# DeepSeek-R1-Distill-Llama-8B-FP8-dynamic
 
 ## Model Overview
 - **Model Architecture:** LlamaForCausalLM
@@ -42,7 +42,7 @@ from transformers import AutoTokenizer
 from vllm import LLM, SamplingParams
 
 number_gpus = 1
-model_name = "neuralmagic/DeepSeek-R1-Distill-Llama-8B-FP8-Dynamic"
+model_name = "neuralmagic/DeepSeek-R1-Distill-Llama-8B-FP8-dynamic"
 
 tokenizer = AutoTokenizer.from_pretrained(model_name)
 sampling_params = SamplingParams(temperature=0.6, max_tokens=256, stop_token_ids=[tokenizer.eos_token_id])
@@ -112,7 +112,7 @@ OpenLLM Leaderboard V1:
 ```
 lm_eval \
   --model vllm \
-  --model_args pretrained="neuralmagic/DeepSeek-R1-Distill-Llama-8B-FP8-Dynamic",dtype=auto,max_model_len=4096,enable_chunked_prefill=True \
+  --model_args pretrained="neuralmagic/DeepSeek-R1-Distill-Llama-8B-FP8-dynamic",dtype=auto,max_model_len=4096,enable_chunked_prefill=True \
   --tasks openllm \
   --write_out \
   --batch_size auto \
@@ -124,7 +124,7 @@ OpenLLM Leaderboard V2:
 ```
 lm_eval \
   --model vllm \
-  --model_args pretrained="neuralmagic/DeepSeek-R1-Distill-Llama-8B-FP8-Dynamic",dtype=auto,max_model_len=4096,enable_chunked_prefill=True \
+  --model_args pretrained="neuralmagic/DeepSeek-R1-Distill-Llama-8B-FP8-dynamic",dtype=auto,max_model_len=4096,enable_chunked_prefill=True \
   --apply_chat_template \
   --fewshot_as_multiturn \
   --tasks leaderboard \
@@ -142,7 +142,7 @@ lm_eval \
       <th>Category</th>
       <th>Metric</th>
       <th>deepseek-ai/DeepSeek-R1-Distill-Llama-8B</th>
-      <th>neuralmagic/DeepSeek-R1-Distill-Llama-8B-FP8-Dynamic</th>
+      <th>neuralmagic/DeepSeek-R1-Distill-Llama-8B-FP8-dynamic</th>
       <th>Recovery</th>
     </tr>
   </thead>