请问如何对这个模型进行微调?
#31 opened 3 days ago
by
Doublebear
关于bidirectional attention的问题
1
#30 opened 10 days ago
by
JoeBlack18
![](https://cdn-avatars.huggingface.co/v1/production/uploads/no-auth/RKU7UnWg4narRtljEzGb5.png)
会考虑发布到ollama上吗?
1
#29 opened 11 days 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 17 days ago
by
shizue
![](https://cdn-avatars.huggingface.co/v1/production/uploads/1637396421928-6198af3a04b5da0c05211dd8.jpeg)
Recommanded hyperparameters?
1
#27 opened 18 days ago
by
zhilinw6
Retrieval 效果一般,仅和bm25持平
7
#26 opened 18 days ago
by
Stefan8
![](https://cdn-avatars.huggingface.co/v1/production/uploads/noauth/X0jRpQ3wEhLD6pfKlXIQe.jpeg)
Pooling method: mean vs last?
1
#25 opened 19 days ago
by
alexzhou689
Padding token for batched embedding in Transformers?
1
#24 opened 22 days ago
by
ChrisCrass
请问支持fp16推理吗?
2
#23 opened 25 days ago
by
DJCan
![](https://cdn-avatars.huggingface.co/v1/production/uploads/62f0babaef9cc6810cec02ff/WnLWjyIchnfNm6ytqw-bT.jpeg)
测试效果一般
2
#22 opened 25 days ago
by
dhajshdkajs
Parameters for peak performance
1
#21 opened about 1 month ago
by
cvdbdo
What languages are supported?
1
#20 opened about 1 month ago
by
jasonrayles
config_sentence_transformers.json does not include the prompt to embeddings mappings
1
#19 opened about 1 month ago
by
Tonic
![](https://cdn-avatars.huggingface.co/v1/production/uploads/62a3bb1cd0d8c2c2169f0b88/eT2TS0IlQbZtz-F_zHLz9.jpeg)
[AUTOMATED] Model Memory Requirements
#18 opened about 1 month ago
by
model-sizer-bot
Running this model without flash-attn
2
#17 opened about 2 months ago
by
lisa-tse
输出的向量维度可以压缩吗?
1
#16 opened about 2 months ago
by
sen63
AWS Sagemaker Deployment error
2
#14 opened about 2 months ago
by
gauravsirola
The performance of full-parameter finetuning
1
#13 opened about 2 months ago
by
stephenshuang
question about quants
3
#12 opened about 2 months ago
by
prudant
![](https://cdn-avatars.huggingface.co/v1/production/uploads/62d2de4a26213de379a2c33c/ow2Uh4Rvoz24rMoPMf2B_.png)
Model architecture should be Qwen2Model instead of Qwen2ForCausalLM?
#11 opened about 2 months ago
by
kavin1337
need gguf q4km
#10 opened 2 months ago
by
windkkk
Training embadding Issues.
2
#8 opened 2 months ago
by
Imran1
![](https://cdn-avatars.huggingface.co/v1/production/uploads/62846faa99bff5076f0a93b4/QO7sgRWOXS6nlQ-GcEg94.jpeg)
Hi, can you tell me how to train?
1
#7 opened 2 months ago
by
EEEmpty
输出的embedding size是多少
3
#6 opened 2 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 2 months ago
by
fukai
Is it consistent with the multi-language support of qwen2, or only Chinese and English?
1
#2 opened 2 months ago
by
fukai