-
您好，非常感谢您开源这么优秀的项目。我在复现您论文的实验时Out-of-domain evaluation验证的结果和您论文里的数据接近，但是在验证in-domain supervised时，数据结果差异比较大，英文的平均f1只有70几（论文的结果是83.85），我使用的数据是B2NER_all，语言模型使用的是InternLM2-7b（internlm/internlm2-7b），训练脚本使用的…
-
Hi,
I am interested in reproducing the results from the CIRR dataset. Could you please share the evaluation code for CIRR?
I saw the CIRR evaluation results from your paper.
Thank you.
-
Hi - The current code does not seem to cover the proposed evaluation portion. Would the authors potentially consider sharing their evaluation pipeline ? More specifically the implementations behind AI…
-
Thank you for you sharing. After I download the trained model, how to evaluate its performance and submit to leaderboard?
-
Many many places use recursion to solve the expressions, which is not the best in the case of unrolling a sum. Try to either use a dynamic alloc stack or remove the recursion Altogether
-
Hi, when I try to run the evaluation follow the given example and your code, there is a problem on downloading data from github, id there any solutions?
2. random forest or similar on the embeddings
3. neural network on top of …
-
I'm really impressed with the work presented in your paper. I've been trying to replicate the evaluation process for my own research, but I'm having difficulty finding the exact metrics used. Would yo…
-
Thanks for your great work! Could you additionally evaluate the Qwen2.5 and Qwen2 models? They also support 128K context length.