Skip to content

Issues: ggerganov/ggml

ggml : unified file format
#220 by philpax was closed Nov 1, 2023
Closed 82
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

Clear current search query, filters, and sorts
207 Open 168 Closed
207 Open 168 Closed
Author
Filter by author
Label
Filter by label
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Milestones
Filter by milestone
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

core dumps when running examples
#3 by mcthulhu was closed Oct 13, 2022 updated Oct 13, 2022
4
T0pp GGML port?
#14 by walking-octopus was closed Jan 6, 2023 updated Jan 6, 2023
Temp not used in gpt utils bug Something isn't working
#16 by farmersrice was closed Jan 15, 2023 updated Jan 15, 2023
Segmentation fault
#11 by kevin01881 was closed Dec 20, 2022 updated Mar 19, 2023
2
Sorry, this is just a request from a novice programmer :(
#42 by ClarissaGazalaEvanthe was closed Mar 22, 2023 updated Mar 22, 2023
1
ggml_init: Illegal instruction at address 0x<address>
#44 by maihd was closed Mar 25, 2023 updated Mar 25, 2023
1
2
[Feature request] Implement 8-bit GPT-J enhancement New feature or request
#5 by pablogranolabar was closed Mar 29, 2023 updated Mar 29, 2023
1
Failing to load Cerebras-gpt after 4-bit quantization.
#53 by pikalover6 was closed Mar 30, 2023 updated Mar 30, 2023
1
gpt2 and gpt-j load error: tensor has wrong shape in model file
#63 by loretoparisi was closed Apr 7, 2023 updated Apr 7, 2023
1
Quantizing GPT-J Produces Nonsense
#71 by zanussbaum was closed Apr 14, 2023 updated Apr 14, 2023
4
GPT-2: Wrong shape in model file: got [768, 2304], expected [2304, 768]
#67 by donge was closed Apr 15, 2023 updated Apr 15, 2023
1
convert-h5-to-ggml.py does not match the official convert-ckpt-to-ggml.py
#72 by yunfanye was closed Apr 15, 2023 updated Apr 15, 2023
Cerberas 2.7B yields garbage tokens after quantizing to 4bits
#54 by lxe was closed Apr 15, 2023 updated Apr 15, 2023
5
pls update ggml models on https://huggingface.co/datasets/ggerganov/ggml/tree/main ,they have an outdated shape 😿
#87 by mettemfurfur000 was closed Apr 16, 2023 updated Apr 16, 2023
1
Need StableLM support
#94 by x-legion was closed Apr 20, 2023 updated Apr 20, 2023
2
Compile error: ‘max_element’ is not a member of ‘std’
#92 by lindeer was closed Apr 21, 2023 updated Apr 21, 2023
1
GPT-J: Incomplete response
#103 by aaambrosio was closed Apr 23, 2023 updated Apr 23, 2023
3
gcc-8: _mm_loadu_si64 missing
#99 by jploski was closed Apr 24, 2023 updated Apr 24, 2023
6
GPT-J broken after transpose changes in ggml_new_tensor_2d enhancement New feature or request
#52 by djinn was closed Apr 16, 2023 updated Apr 28, 2023
13
Pulling new quantization format Q4_1_O into upstream ggml
#89 by saharNooby was closed Apr 29, 2023 updated Apr 29, 2023
17
bert.cpp q4_0 performance degradation from commit abea4b7
#122 by skeskinen was closed May 1, 2023 updated May 1, 2023
7
bug in stablelm implementation
#125 by mgrabban was closed May 2, 2023 updated May 2, 2023
2
GGML operations appear to have no documentation or description - let's change that! documentation Improvements or additions to documentation
#118 by KerfuffleV2 was closed May 3, 2023 updated May 3, 2023
Vectorize quantize_row_q8_0() enhancement New feature or request
#124 by ggerganov was closed May 3, 2023 updated May 3, 2023
1
@ggerganov
Models output <|endoftext|> when n is a larger value enhancement New feature or request good first issue Good for newcomers
#9 by trholding was closed May 6, 2023 updated May 6, 2023
ProTip! Follow long discussions with comments:>50.