facebookresearch/llama issues and pull requests

#968 - Optim - added quantization code.

Pull Request - State: open - Opened by sgsharma2000 12 months ago - 2 comments

#968 - Optim - added quantization code.

Pull Request - State: open - Opened by sgsharma2000 12 months ago - 2 comments

#965 - Are meta-llama/Llama-2 models Quantized by default?

Issue - State: closed - Opened by Jaswir 12 months ago - 1 comment

#965 - Are meta-llama/Llama-2 models Quantized by default?

Issue - State: closed - Opened by Jaswir 12 months ago - 1 comment

#964 - Able to run 70B 4Q Llama2 on MacBook -- but unexpectedly not 2Q version

Issue - State: closed - Opened by FrankSandqvist 12 months ago - 2 comments

#964 - Able to run 70B 4Q Llama2 on MacBook -- but unexpectedly not 2Q version

Issue - State: closed - Opened by FrankSandqvist 12 months ago - 2 comments

#963 - Whether a word vector can inversely derive a word.(community-discussion)

Issue - State: closed - Opened by zziliang 12 months ago - 2 comments
Labels: community-discussion

#963 - Whether a word vector can inversely derive a word.(community-discussion)

Issue - State: closed - Opened by zziliang 12 months ago - 2 comments
Labels: community-discussion

#962 - Wrong pending for approval for LLama-2 message

Issue - State: closed - Opened by usrikanth 12 months ago - 2 comments
Labels: download-install

#962 - Wrong pending for approval for LLama-2 message

Issue - State: closed - Opened by usrikanth 12 months ago - 2 comments
Labels: download-install

#961 - Is the code in this repository only for inference?

Issue - State: closed - Opened by CodeTal 12 months ago - 4 comments
Labels: fine-tuning

#961 - Is the code in this repository only for inference?

Issue - State: closed - Opened by CodeTal 12 months ago - 4 comments
Labels: fine-tuning

#960 - ERROR:torch.distributed.elastic.multiprocessing.api:failed (exitcode: -9)

Issue - State: closed - Opened by kgopfa 12 months ago - 1 comment

#957 - Speed Issues with Local Inference of llama2-70B-chat Model

Issue - State: closed - Opened by baifanxxx 12 months ago - 2 comments
Labels: performance, model-usage

#956 - Can't get approved to access llama 2

Issue - State: open - Opened by zk 12 months ago - 4 comments
Labels: download-install

#956 - Can't get approved to access llama 2

Issue - State: open - Opened by zk 12 months ago - 4 comments
Labels: download-install

#947 - Support for Mac M1/M2

Pull Request - State: open - Opened by dkrantsberg 12 months ago - 2 comments
Labels: CLA Signed

#942 - Llama 2 Access on Hugging Face

Issue - State: closed - Opened by rosieyzh 12 months ago - 1 comment

#942 - Llama 2 Access on Hugging Face

Issue - State: closed - Opened by rosieyzh 12 months ago - 1 comment

#941 - Llama 2 access

Issue - State: open - Opened by arunasank about 1 year ago - 2 comments
Labels: model-access

#941 - Llama 2 access

Issue - State: open - Opened by arunasank about 1 year ago - 2 comments
Labels: model-access

#940 - Files disappeared after download is finished

Issue - State: closed - Opened by DanielKim15 about 1 year ago - 1 comment
Labels: download-install, needs-more-information

#940 - Files disappeared after download is finished

Issue - State: closed - Opened by DanielKim15 about 1 year ago - 1 comment
Labels: download-install, needs-more-information

#936 - Running llama-2-13b for inferencing in Windows 11 WSL2 resulted in `Killed`

Issue - State: open - Opened by maxloosmu about 1 year ago - 7 comments
Labels: question

#936 - Running llama-2-13b for inferencing in Windows 11 WSL2 resulted in `Killed`

Issue - State: open - Opened by maxloosmu about 1 year ago - 7 comments
Labels: question

#928 - torch.distributed.elastic.multiprocessing.api:failed (exitcode: -9) local_rank: 0 (pid: 403477) of binary: /usr/bin/python3

Issue - State: closed - Opened by Jcoder410 about 1 year ago - 8 comments
Labels: model-usage

#922 - Hi,

Issue - State: closed - Opened by Eyryu about 1 year ago - 2 comments
Labels: model-usage

#922 - Hi,

Issue - State: closed - Opened by Eyryu about 1 year ago - 2 comments
Labels: model-usage

#911 - LLaMA 1 access form not working

Issue - State: closed - Opened by lisaalaz about 1 year ago - 1 comment
Labels: download-install, model-access

#906 - docs. Correct the URL to the FAQ.md file

Pull Request - State: closed - Opened by Abdelkrim about 1 year ago - 1 comment
Labels: CLA Signed

#887 - Llama-2-70b Model: Challenges with Long Token Sequences

Issue - State: closed - Opened by Zuhashaik about 1 year ago - 10 comments
Labels: model-usage

#877 - torch.distributed.elastic.multiprocessing.api: [ERROR] failed (exitcode: -9) local_rank: 0 (pid: 760)

Issue - State: open - Opened by bechellis about 1 year ago - 3 comments
Labels: needs-more-information

#876 - Create python-package-conda.yml

Pull Request - State: closed - Opened by Dmellies about 1 year ago
Labels: CLA Signed

#869 - properly shift tokens for logprobs.

Pull Request - State: closed - Opened by Zhiyuan-Wu about 1 year ago
Labels: CLA Signed

#869 - properly shift tokens for logprobs.

Pull Request - State: closed - Opened by Zhiyuan-Wu about 1 year ago
Labels: CLA Signed

#867 - SQUAD evalution

Issue - State: open - Opened by obhalerao97 about 1 year ago - 27 comments
Labels: research-paper

#865 - TypeError: init() got an unexpected keyword argument 'quantizer'

Issue - State: closed - Opened by yyyddff about 1 year ago - 3 comments
Labels: needs-more-information

#865 - TypeError: init() got an unexpected keyword argument 'quantizer'

Issue - State: closed - Opened by yyyddff about 1 year ago - 3 comments
Labels: needs-more-information

#857 - torch.distributed.elastic.multiprocessing.redirects: [WARNING] NOTE: Redirects are currently not supported in Windows or MacOs.

Issue - State: open - Opened by JishnuChoudhury about 1 year ago - 7 comments
Labels: compatibility

#844 - No Confirmation Response for Llama2 Access. Request Made Several Days Ago

Issue - State: open - Opened by oscardam67 about 1 year ago - 6 comments
Labels: model-access

#843 - Fire module not found when running example script. Please help.

Issue - State: closed - Opened by Harsh-raj about 1 year ago - 2 comments

#843 - Fire module not found when running example script. Please help.

Issue - State: closed - Opened by Harsh-raj about 1 year ago - 2 comments

#837 - Error when using LM Studio

Issue - State: closed - Opened by jepsenwan about 1 year ago - 3 comments
Labels: compatibility

#837 - Error when using LM Studio

Issue - State: closed - Opened by jepsenwan about 1 year ago - 3 comments
Labels: compatibility

#830 - ERROR:torch.distributed.elastic.multiprocessing.api:failed (exitcode: 1) local_rank: 0 (pid: 16079)

Issue - State: closed - Opened by 13555957595 about 1 year ago - 19 comments
Labels: model-usage

#830 - ERROR:torch.distributed.elastic.multiprocessing.api:failed (exitcode: 1) local_rank: 0 (pid: 16079)

Issue - State: closed - Opened by 13555957595 about 1 year ago - 19 comments
Labels: model-usage

#815 - Clear cache after each run

Issue - State: closed - Opened by Mukish45 about 1 year ago - 3 comments
Labels: model-usage

#806 - AssertionError: Loading a checkpoint for MP=8 but world size is 1

Issue - State: closed - Opened by 1ceberg9 about 1 year ago - 3 comments

#805 - LLaMa-2-13B-chat deployed on azureml studio giving out of context response

Issue - State: closed - Opened by Manikanta5112 about 1 year ago - 2 comments
Labels: model-usage, integrations

#797 - How to fine tune the model without conversion to Hugging Face

Issue - State: open - Opened by xuchaozj about 1 year ago - 2 comments
Labels: model-usage, fine-tuning

#797 - How to fine tune the model without conversion to Hugging Face

Issue - State: open - Opened by xuchaozj about 1 year ago - 2 comments
Labels: model-usage, fine-tuning

#792 - Padding for training and inference

Issue - State: open - Opened by Reason-Wang about 1 year ago - 2 comments
Labels: fine-tuning

#760 - wget: server returned error: HTTP/1.1 416 Requested Range Not Satisfiable when trying to download Weights

Issue - State: closed - Opened by GitVex about 1 year ago - 16 comments
Labels: download-install

#736 - AssertionError: Loading a checkpoint for MP=1 but world size is None

Issue - State: open - Opened by teriterance about 1 year ago - 4 comments
Labels: needs-more-information

#717 - Is there a way to prevent llama2 from truncating the answer at the middle of sentence when it reaches the maximum token length?

Issue - State: open - Opened by merveeozbayy over 1 year ago - 7 comments
Labels: question

#710 - Anyway to load a checkpoint with a different world size ?

Issue - State: closed - Opened by marcusobrien over 1 year ago - 2 comments
Labels: model-usage

#710 - Anyway to load a checkpoint with a different world size ?

Issue - State: closed - Opened by marcusobrien over 1 year ago - 2 comments
Labels: model-usage

#699 - Cant use Windows as fire packacge requires NCCL

Issue - State: open - Opened by marcusobrien over 1 year ago - 7 comments
Labels: compatibility

#699 - Cant use Windows as fire packacge requires NCCL

Issue - State: open - Opened by marcusobrien over 1 year ago - 7 comments
Labels: compatibility

#695 - make download.sh executable

Pull Request - State: closed - Opened by dangbert over 1 year ago - 3 comments
Labels: CLA Signed

#694 - failed to create process

Issue - State: open - Opened by marcusobrien over 1 year ago - 9 comments
Labels: compatibility

#694 - failed to create process

Issue - State: open - Opened by marcusobrien over 1 year ago - 9 comments
Labels: compatibility

#615 - RuntimeError: Internal: src/sentencepiece_processor.cc(1101) [model_proto->ParseFromArray(serialized.data(), serialized.size())] error

Issue - State: closed - Opened by ryusangwon over 1 year ago - 6 comments

#592 - Redirects are currently not supported in Windows or MacOs.

Issue - State: open - Opened by YinhaoDeng over 1 year ago - 14 comments
Labels: compatibility, integrations

#563 - Output includes input

Issue - State: open - Opened by Mega4alik over 1 year ago - 3 comments
Labels: model-usage

#563 - Output includes input

Issue - State: open - Opened by Mega4alik over 1 year ago - 3 comments
Labels: model-usage

#542 - Can't get access to llama-2 models

Issue - State: closed - Opened by okhat over 1 year ago - 6 comments
Labels: model-access

#542 - Can't get access to llama-2 models

Issue - State: closed - Opened by okhat over 1 year ago - 6 comments
Labels: model-access

#540 - 4 Bit Inference of LLaMA-2-70B

Issue - State: closed - Opened by ijoffe over 1 year ago - 19 comments

#528 - What is inside llama-2-70b consolidated.00.pth file and how do I read it?

Issue - State: open - Opened by imvetri over 1 year ago - 7 comments
Labels: question

#528 - What is inside llama-2-70b consolidated.00.pth file and how do I read it?

Issue - State: open - Opened by imvetri over 1 year ago - 7 comments
Labels: question

#482 - torch.distributed.elastic.multiprocessing.errors.ChildFailedError:

Issue - State: closed - Opened by MDFARHYN over 1 year ago - 19 comments

#465 - download.sh: add `--no-config` to all wget calls

Pull Request - State: open - Opened by varenc over 1 year ago - 1 comment
Labels: CLA Signed, download-install

#454 - How to run 13B & 70B model? Windows 11 WSL2 single GPU

Issue - State: open - Opened by MissMyth over 1 year ago - 9 comments
Labels: model-usage

#448 - About "HTTPError: 404 Client Error" and "OSError: meta-llama/Llama-2-7b does not appear to have a file named config.json".

Issue - State: open - Opened by githubhyz over 1 year ago - 4 comments
Labels: model-usage

#448 - About "HTTPError: 404 Client Error" and "OSError: meta-llama/Llama-2-7b does not appear to have a file named config.json".

Issue - State: open - Opened by githubhyz over 1 year ago - 4 comments
Labels: model-usage

#439 - Enter the URL from email

Issue - State: closed - Opened by MonkeyTB over 1 year ago - 8 comments
Labels: needs-more-information

#438 - Error while downloading Models using download.sh

Issue - State: open - Opened by BhanuJoshi01 over 1 year ago - 13 comments
Labels: download-install

#426 - Unable to establish SSL connection

Issue - State: open - Opened by todpole3 over 1 year ago - 3 comments
Labels: download-install

#418 - ERROR 403: Forbiden

Issue - State: open - Opened by seonghapark over 1 year ago - 18 comments
Labels: download-install

#418 - ERROR 403: Forbiden

Issue - State: open - Opened by seonghapark over 1 year ago - 18 comments
Labels: download-install

#394 - No config.json in meta-llama/Llama-2-7b

Issue - State: closed - Opened by wuhuaguocao over 1 year ago - 14 comments

#394 - No config.json in meta-llama/Llama-2-7b

Issue - State: closed - Opened by wuhuaguocao over 1 year ago - 14 comments

#387 - Invalid Host Name

Issue - State: closed - Opened by Khwab-kalra over 1 year ago - 6 comments

#380 - RuntimeError: probability tensor contains either `inf`, `nan` or element < 0

Issue - State: open - Opened by Liyan06 over 1 year ago - 33 comments
Labels: model-usage

#374 - can't run llama-2-7b-hf even though I'm using use_auth_token

Issue - State: open - Opened by brando90 over 1 year ago - 33 comments
Labels: model-usage

#374 - can't run llama-2-7b-hf even though I'm using use_auth_token

Issue - State: open - Opened by brando90 over 1 year ago - 33 comments
Labels: model-usage

#373 - download.sh returns 403 forbidden error

Issue - State: open - Opened by DrewWalkup over 1 year ago - 64 comments
Labels: download-install

#370 - download.sh closes without downloading anything.

Issue - State: open - Opened by Vermath over 1 year ago - 37 comments
Labels: download-install

#362 - Checking checksums - Could not parse check file 'checklist.chk' (2)

Issue - State: open - Opened by Anerco over 1 year ago - 30 comments
Labels: download-install

#360 - Unable to download llama2 using pre-signed URL link

Issue - State: closed - Opened by access2rohit over 1 year ago - 25 comments

#347 - Issue with Redirects Not Supported Error in Windows and macOS. When running torchrun, a RuntimeError is encountered with the message "unmatched '}' in format string."

Issue - State: open - Opened by ericoder960803 over 1 year ago - 12 comments
Labels: model-usage

GitHub / facebookresearch/llama issues and pull requests