update readme for instructions for usage with infinity
#39 opened 1 day ago
by
michaelfeil
微调后验证和训练阶段验证不一致
#37 opened 7 days ago
by
penghui1
使用scripts/eval_mteb.py 无法复现效果
#35 opened about 2 months ago
by
whucai
bfloat16 vs. float32
#34 opened about 2 months ago
by
tanliboy
Fix eval_mteb.py of undefined variables
#33 opened about 2 months ago
by
tongyx361
Add base_model metadata
#32 opened 3 months ago
by
davanstrien
请问如何对这个模型进行微调?
#31 opened 3 months ago
by
Doublebear
关于bidirectional attention的问题
1
#30 opened 3 months ago
by
JoeBlack18
会考虑发布到ollama上吗?
1
#29 opened 3 months ago
by
huyueeer
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?
1
#28 opened 3 months ago
by
shizue
Recommanded hyperparameters?
1
#27 opened 3 months ago
by
zhilinw6
Retrieval 效果一般,仅和bm25持平
8
#26 opened 3 months ago
by
Stefan8
Pooling method: mean vs last?
2
#25 opened 3 months ago
by
alexzhou689
Padding token for batched embedding in Transformers?
1
#24 opened 3 months ago
by
ChrisCrass
请问支持fp16推理吗?
2
#23 opened 4 months ago
by
DJCan
测试效果一般
2
#22 opened 4 months ago
by
dhajshdkajs
Parameters for peak performance
1
#21 opened 4 months ago
by
cvdbdo
What languages are supported?
1
#20 opened 4 months ago
by
jasonrayles
config_sentence_transformers.json does not include the prompt to embeddings mappings
1
#19 opened 4 months ago
by
Tonic
[AUTOMATED] Model Memory Requirements
#18 opened 4 months ago
by
model-sizer-bot
Running this model without flash-attn
2
#17 opened 4 months ago
by
lisa-tse
输出的向量维度可以压缩吗?
1
#16 opened 4 months ago
by
sen63
AWS Sagemaker Deployment error
2
#14 opened 4 months ago
by
gauravsirola
The performance of full-parameter finetuning
1
#13 opened 5 months ago
by
stephenshuang
question about quants
3
#12 opened 5 months ago
by
prudant
Model architecture should be Qwen2Model instead of Qwen2ForCausalLM?
#11 opened 5 months ago
by
kavin1337
need gguf q4km
#10 opened 5 months ago
by
windkkk
Training embadding Issues.
2
#8 opened 5 months ago
by
Imran1
Hi, can you tell me how to train?
2
#7 opened 5 months ago
by
EEEmpty
输出的embedding size是多少
3
#6 opened 5 months ago
by
seleven11
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
8
#3 opened 5 months ago
by
fukai
Is it consistent with the multi-language support of qwen2, or only Chinese and English?
1
#2 opened 5 months ago
by
fukai