Update README.md

README.md

@@ -15,11 +15,12 @@ tags:
 - qwen2
 library_name: transformers
 ---
-# Zhi-writing-dsr1-14b
+
+# Zhi-Create-DSR1-14B
 
 ## 1. Introduction
 
-Zhi-writing-dsr1-14b is a fine-tuned model based on DeepSeek-R1-Distill-Qwen-14B, specifically optimized for enhanced creative writing capabilities. Several benchmark evaluations indicate the model's improved creative writing performance.
+Zhi-Create-DSR1-14B is a fine-tuned model based on DeepSeek-R1-Distill-Qwen-14B, specifically optimized for enhanced creative writing capabilities. Several benchmark evaluations indicate the model's improved creative writing performance.
 
 In the [LLM Creative Story-Writing Benchmark](https://github.com/lechmazur/writing), the model achieved a score of **8.33** compared to its base model's **7.8**. In the [WritingBench](https://github.com/X-PLUG/WritingBench) evaluation framework, it scored **8.46**, showing improvement over DeepSeek-R1-Distill-Qwen-14B's **7.93**. The model was also evaluated using GPT-4o on the AlpacaEval dataset, achieving an **82.6%** win rate when compared with the base model.
 
@@ -28,7 +29,7 @@ The figure below shows the performance comparison across different domains in Wr
 ![writingbench](./images/writingbench_score.png)
 
 <figcaption style="text-align:center; font-size:0.9em; color:#666">
-Figure 1: WritingBench performance of Zhi-writing-dsr1-14b and DeepSeek-R1-Distill-Qwen-14B across 6 domains and 3 writing requirements evaluated with WritingBench critic model (scale: 1-10). The six domains include: (D1) Academic & Engineering, (D2) Finance & Business, (D3) Politics & Law, (D4) Literature & Art, (D5) Education, and (D6) Advertising & Marketing. The three writing requirements assessed are: (R1) Style, (R2) Format, and (R3) Length. Here, "C" indicates category-specific scores.
+Figure 1: WritingBench performance of Zhi-Create-DSR1-14B and DeepSeek-R1-Distill-Qwen-14B across 6 domains and 3 writing requirements evaluated with WritingBench critic model (scale: 1-10). The six domains include: (D1) Academic & Engineering, (D2) Finance & Business, (D3) Politics & Law, (D4) Literature & Art, (D5) Education, and (D6) Advertising & Marketing. The three writing requirements assessed are: (R1) Style, (R2) Format, and (R3) Length. Here, "C" indicates category-specific scores.
 </figcaption>
 
 ## 2. Training Process
@@ -46,9 +47,9 @@ To achieve optimal domain coverage, we meticulously balanced the distribution of
 
 ## 3. Evaluation Results
 
-Our evaluation results suggest promising improvements in the model's creative writing capabilities. In the LLM Creative Story-Writing Benchmark evaluation, the model achieved a score of **8.33**, showing an improvement from the base model's **7.87**. When assessed on WritingBench, a comprehensive framework for evaluating large language model writing abilities, the model attained a score of **8.46**. This places it in proximity to DeepSeek-R1's performance and represents an advancement over DeepSeek-R1-Distill-Qwen-14B's score of 7.93.
+Our evaluation results suggest promising improvements in the model's creative writing capabilities. In the LLM Creative Story-Writing Benchmark evaluation, the model achieved a score of **8.33**, showing an improvement from the base model's **7.87**. When assessed on WritingBench, a comprehensive framework for evaluating large language model writing abilities, the model attained a score of **8.46**. This places it in proximity to DeepSeek-R1's performance and represents an advancement over DeepSeek-R1-Distill-Qwen-14B's score of **7.93**.
 
-With respect to general capabilities, evaluations indicate modest improvements of **2%–5% in knowledge and reasoning tasks (CMMLU, MMLU-Pro)**, alongside encouraging progress in mathematical reasoning as measured by benchmarks such as **AIME-2024, AIME-2025, and GSM8K**. The results suggest that the model maintains a balanced performance profile, with improvements observed across creative writing, knowledge/reasoning, and mathematical tasks compared to DeepSeek-R1-Distill-Qwen-14B. These characteristics potentially make it suitable for a range of general-purpose applications.
+With respect to general capabilities, evaluations indicate modest improvements of **2%–5% in knowledge and reasoning tasks (CMMLU, MMLU-Pro)**, alongside encouraging progress in mathematical reasoning as measured by benchmarks such as **AIME-2024, AIME-2025, and GSM8K**. The results suggest that the model maintains a balanced performance profile, with improvements observed across creative writing, knowledge/reasoning, and mathematical tasks compared to DeepSeek-R1-Distill-Qwen-14B. These characteristics potentially make it suitable for a range of general-purpose applications. We conducted additional evaluations on the instruction-following ifeval benchmark, with experimental results demonstrating a performance improvement in model capabilities from an initial score of **71.43** to an enhanced score of **74.71**.
 
 ![general](./images/general_score.png)
 
@@ -58,7 +59,7 @@ Figure 2: When evaluating model performance, it is recommended to conduct multip
 
 ## 4. How to Run Locally
 
-Zhi-writing-dsr1-14b can be deployed on various hardware configurations, including GPUs with 80GB memory, a single H20/A800/H800, or dual RTX 4090. Additionally, the INT4 quantized version Zhi-writing-dsr1-14b-gptq-int4 can be deployed on a single RTX 4090.
+Zhi-Create-DSR1-14B can be deployed on various hardware configurations, including GPUs with 80GB memory, a single H20/A800/H800, or dual RTX 4090. Additionally, the INT4 quantized version Zhi-Create-DSR1-14B-GPTQ-INT4 can be deployed on a single RTX 4090.
 
 ### Transformers
 
@@ -66,7 +67,7 @@ Zhi-writing-dsr1-14b can be deployed on various hardware configurations, includi
 from transformers import AutoModelForCausalLM, AutoTokenizer
 from transformers.generation import GenerationConfig
 
-MODEL_NAME = "Zhihu-ai/Zhi-writing-dsr1-14b"
+MODEL_NAME = "Zhihu-ai/Zhi-Create-DSR1-14B"
 tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME, trust_remote_code=True)
 
 # use bf16
@@ -121,12 +122,12 @@ print(response)
 You can easily start a service using [ZhiLight](https://github.com/zhihu/ZhiLight)
 
 ```bash
-docker run -it --net=host --gpus='"device=0"' -v /path/to/model:/mnt/models --entrypoints="" ghcr.io/zhihu/zhilight/zhilight:0.4.17-cu124 python -m zhilight.server.openai.entrypoints.api_server --model-path /mnt/models --port 8000 --enable-reasoning --reasoning-parser deepseek-r1 --served-model-name Zhi-writing-dsr1-14b
+docker run -it --net=host --gpus='"device=0"' -v /path/to/model:/mnt/models --entrypoints="" ghcr.io/zhihu/zhilight/zhilight:0.4.17-cu124 python -m zhilight.server.openai.entrypoints.api_server --model-path /mnt/models --port 8000 --enable-reasoning --reasoning-parser deepseek-r1 --served-model-name Zhi-Create-DSR1-14B
 
 curl http://localhost:8000/v1/completions \
     -H "Content-Type: application/json" \
     -d '{
-        "model": "Zhi-writing-dsr1-14b",
+        "model": "Zhi-Create-DSR1-14B",
         "prompt": "请你以鲁迅的口吻，写一篇介绍西湖醋鱼的文章",
         "max_tokens": 4096,
         "temperature": 0.6,
@@ -143,15 +144,15 @@ For instance, you can easily start a service using [vLLM](https://github.com/vll
 pip install vllm>=0.6.4.post1
 
 # huggingface model id
-vllm serve Zhihu-ai/Zhi-writing-dsr1-14b --served-model-name Zhi-writing-dsr1-14b --port 8000
+vllm serve Zhihu-ai/Zhi-Create-DSR1-14B --served-model-name Zhi-Create-DSR1-14B --port 8000
 
 # local path
-vllm serve /path/to/model  --served-model-name Zhi-writing-dsr1-14b --port 8000
+vllm serve /path/to/model  --served-model-name Zhi-Create-DSR1-14B --port 8000
 
 curl http://localhost:8000/v1/completions \
     -H "Content-Type: application/json" \
     -d '{
-        "model": "Zhi-writing-dsr1-14b",
+        "model": "Zhi-Create-DSR1-14B",
         "prompt": "请你以鲁迅的口吻，写一篇介绍西湖醋鱼的文章",
         "max_tokens": 4096,
         "temperature": 0.6,
@@ -169,16 +170,16 @@ You can also easily start a service using [SGLang](https://github.com/sgl-projec
 pip install "sglang[all]>=0.4.5" --find-links https://flashinfer.ai/whl/cu124/torch2.5/flashinfer-python
 
 # huggingface model id 
-python -m sglang.launch_server --model-path Zhihu-ai/Zhi-writing-dsr1-14b --served-model-name Zhi-writing-dsr1-14b --port 8000
+python -m sglang.launch_server --model-path Zhihu-ai/Zhi-Create-DSR1-14B --served-model-name Zhi-Create-DSR1-14B --port 8000
 
 # local path
-python -m sglang.launch_server --model-path /path/to/model  --served-model-name Zhi-writing-dsr1-14b --port 8000
+python -m sglang.launch_server --model-path /path/to/model  --served-model-name Zhi-Create-DSR1-14B --port 8000
 
 # send request
 curl http://localhost:8000/v1/completions \
     -H "Content-Type: application/json" \
     -d '{
-        "model": "Zhi-writing-dsr1-14b",
+        "model": "Zhi-Create-DSR1-14B",
         "prompt": "请你以鲁迅的口吻，写一篇介绍西湖醋鱼的文章",
         "max_tokens": 4096,
         "temperature": 0.6,
@@ -193,18 +194,18 @@ You can download ollama using [this](https://ollama.com/download/)
 * quantization: Q4_K_M
 
 ```bash
-ollama run zhihu/zhi-writing-dsr1-14b
+ollama run zhihu/zhi-create-dsr1-14b
 ```
 
 * bf16
 
 ```bash
-ollama run zhihu/zhi-writing-dsr1-14b:bf16
+ollama run zhihu/zhi-create-dsr1-14b:bf16
 ```
 
 ## 5. Usage Recommendations
 
-We recommend adhering to the following configurations when utilizing the Zhi-writing-dsr1-14b, including benchmarking, to achieve the expected performance:
+We recommend adhering to the following configurations when utilizing the Zhi-Create-DSR1-14B, including benchmarking, to achieve the expected performance:
 
 * Set the temperature within the range of 0.5-0.7 (0.6 is recommended) to prevent endless repetitions or incoherent outputs.
 
@@ -215,16 +216,16 @@ We recommend adhering to the following configurations when utilizing the Zhi-wri
 ## 6. Citation
 
 ```text
-@misc{Zhi-writing-dsr1-14b,
-      title={Zhi-writing-dsr1-14b: Curriculum Reinforcement and Direct Preference Optimization for Robust Creative Writing in LLMs}, 
+@misc{Zhi-Create-DSR1-14B,
+      title={Zhi-Create-DSR1-14B: Curriculum Reinforcement and Direct Preference Optimization for Robust Creative Writing in LLMs}, 
       author={Jiewu Wang, Xu Chen, Wenyuan Su, Chao Huang, Hongkui Gao, Lin Feng, Shan Wang, Lu Xu, Penghe Liu, Zebin Ou},
       year={2025},
       eprint={},
       archivePrefix={},
-      url={https://huggingface.co/Zhihu-ai/Zhi-writing-dsr1-14b}, 
+      url={https://huggingface.co/Zhihu-ai/Zhi-Create-DSR1-14B}, 
 }
 ```
 
 ## 7. Contact
 
-If you have any questions, please raise an issue or contact us at [[email protected]](mailto:[email protected]).
+If you have any questions, please raise an issue or contact us at [[email protected]](mailto:[email protected]).