Skip to content

Issues: jquesnelle/yarn

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

36 Open 20 Closed
36 Open 20 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Assignee
Filter by who’s assigned
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Issues list

Have you tried Rope_base = 500k in YaRN?
#64 opened Sep 4, 2024 by hannlp
For models with other architectures, such as Qwen family, how to find the best \alpha, \beta and \sqrt{1/t} parameters?
#63 opened Jul 3, 2024 by ki-ljl
the detail of code implements.
#62 opened Jun 14, 2024 by cooper12121
Question related to _yarn_linear_ramp_mask
#60 opened Apr 9, 2024 by chizhang118
1
OOM error of distributed training on 80GB GPUs with Mistral-7b
#59 opened Apr 8, 2024 by TracyPlus
3
cannot connect to hugging face
#58 opened Mar 29, 2024 by RENNY-Jenius
Why the updated cache is initialized with seqlen=256?
#57 opened Mar 27, 2024 by pUmpKin-Co
Trying to set a tensor of shape torch.Size([257, 1024]) in "weight" (which has shape torch.Size([1226, 1024])), this look incorrect
#56 opened Mar 18, 2024 by Litong-sTs
Can we run the replication of the results，8 * 80 A100
#55 opened Mar 15, 2024 by zhanglv0209
1
How should I proceed with conducting an evaluation for lm-evaluation-harness?
#54 opened Mar 15, 2024 by yuri-son
Questions about DynamicNTK
#53 opened Mar 14, 2024 by wutong4012
An OOM error occurred while computing the perplexity of 128k Proofpoint documents with a maximum token count set to 128k.
#52 opened Mar 5, 2024 by HIT-cwh
1
Phi 2
#51 opened Feb 25, 2024 by fakerybakery
Could this repository be used for sft based on YaRN?
#50 opened Feb 19, 2024 by Zheng-Jay
OOM on two 80GB GPUs
#49 opened Jan 9, 2024 by kyleliang919
6
Unexpected larger perplexity on PG19
#48 opened Dec 10, 2023 by Yiyi-philosophy
1
Running Error
#44 opened Nov 22, 2023 by wangyang-stu
2
RoPE scaling config confusing
#40 opened Nov 15, 2023 by tattrongvu
Inquiry Regarding Evaluation Metrics in Your Paper
#39 opened Nov 13, 2023 by teslacool
2
context length and dataset size
#38 opened Nov 6, 2023 by shossain
Hardware equipments and training time?
#37 opened Nov 6, 2023 by zhoumengbo
What is the purpose of finetuned parameter in LlamaDynamicYaRNScaledRotaryEmbedding?
#36 opened Nov 6, 2023 by fahadh4ilyas
Mistral-train error on deepspeed config
#35 opened Nov 2, 2023 by xiechengmude
1
Questions about max-position-embeddings
#34 opened Oct 17, 2023 by Xnhyacinth
How do i increases the context of already fined tuned or base model of llama2 ?
#33 opened Oct 11, 2023 by Tejaswi-kashyap-006
ProTip! no:milestone will show everything without a milestone.