Alibaba-NLP
/

gte-Qwen2-7B-instruct

Sentence Similarity

sentence-transformers

text-generation

Eval Results (legacy)

text-embeddings-inference

Model card Files Files and versions

Resources

View closed (14)

chore: migrate to official transformers Qwen2 implementation

#60 opened 6 months ago by

AttributeError: 'DynamicCache' object has no attribute 'get_usable_length'. Did you mean: 'get_seq_length'?

#59 opened 7 months ago by

关于MTEB库版本的问题

#58 opened 10 months ago by

Embedding Dimension

#57 opened 11 months ago by

How to change dataset

#54 opened about 1 year ago by

这个模型怎么做Reranking

#53 opened about 1 year ago by

training code supported

#51 opened about 1 year ago by

Training data annotations for MTEB

#50 opened about 1 year ago by

Onnx format?

#49 opened about 1 year ago by

请问task的编写有什么原则吗

#45 opened over 1 year ago by

Inquiry about Future Plans for GTE-Qwen Models Based on Qwen2.5

#43 opened over 1 year ago by

欢迎大家使用我们的开源代码来进一步微调gte模型

#42 opened over 1 year ago by

Fine-tuning Alibaba-NLP/gte-Qwen2-7B-instruct for Domain-Specific Retrieval with Query, Positive, and Hard Negatives

#41 opened over 1 year ago by

测试效果bad case

#40 opened over 1 year ago by

微调后验证和训练阶段验证不一致

#37 opened over 1 year ago by

使用scripts/eval_mteb.py 无法复现效果

#35 opened over 1 year ago by

bfloat16 vs. float32

#34 opened over 1 year ago by

Fix eval_mteb.py of undefined variables

#33 opened over 1 year ago by

Add base_model metadata

#32 opened over 1 year ago by

请问如何对这个模型进行微调？

#31 opened over 1 year ago by

关于bidirectional attention的问题

#30 opened over 1 year ago by

会考虑发布到ollama上吗？

#29 opened over 1 year ago by

请问flash-attn可以关闭吗？是否可以直接使用transformers库里提供的qwen2模型加载？

#28 opened over 1 year ago by

Recommanded hyperparameters?

#27 opened over 1 year ago by

Retrieval 效果一般，仅和bm25持平

#26 opened over 1 year ago by

Pooling method: mean vs last?

#25 opened over 1 year ago by

Padding token for batched embedding in Transformers?

#24 opened over 1 year ago by

请问支持fp16推理吗？

#23 opened over 1 year ago by

测试效果一般

#22 opened over 1 year ago by

Parameters for peak performance

#21 opened over 1 year ago by

What languages are supported?

#20 opened over 1 year ago by

config_sentence_transformers.json does not include the prompt to embeddings mappings

#19 opened over 1 year ago by

[AUTOMATED] Model Memory Requirements

#18 opened over 1 year ago by

model-sizer-bot

Running this model without flash-attn

#17 opened almost 2 years ago by

输出的向量维度可以压缩吗？

#16 opened almost 2 years ago by

AWS Sagemaker Deployment error

#14 opened almost 2 years ago by

The performance of full-parameter finetuning

#13 opened almost 2 years ago by

question about quants

#12 opened almost 2 years ago by

Model architecture should be Qwen2Model instead of Qwen2ForCausalLM?

#11 opened almost 2 years ago by

need gguf q4km

#10 opened almost 2 years ago by

Training embadding Issues.

#8 opened almost 2 years ago by

Hi, can you tell me how to train?

#7 opened almost 2 years ago by

输出的embedding size是多少

#6 opened almost 2 years ago by

跪求训练数据

#4 opened almost 2 years ago by

模型太耗内存了，有量化版本吗？flashatt是不是可以关闭，对显卡限制太多

#3 opened almost 2 years ago by

Is it consistent with the multi-language support of qwen2, or only Chinese and English?

#2 opened almost 2 years ago by