Ecosyste.ms: Issues

An open API service for providing issue and pull request metadata for open source projects.

GitHub / OpenNMT/CTranslate2 issues and pull requests

#1394 - Error in translating with alternatives

Issue - State: closed - Opened by pdakwal about 1 year ago - 4 comments
Labels: bug

#1393 - Fix typo in llama 2 example

Pull Request - State: closed - Opened by vadi2 about 1 year ago

#1392 - how to obtain get past_kv_cache values?

Issue - State: open - Opened by arunpatro about 1 year ago - 3 comments

#1391 - Provide HF AutoModel interface

Issue - State: open - Opened by QuietRocket about 1 year ago - 4 comments

#1390 - AttributeError: module 'ctranslate2' has no attribute 'StorageView'

Issue - State: closed - Opened by Geremia about 1 year ago - 5 comments

#1389 - By default, keep the same FP precision when converting models

Pull Request - State: closed - Opened by guillaumekln about 1 year ago

#1388 - Extremely slow generation speed for llama 2 70B chat model

Issue - State: open - Opened by k21993 about 1 year ago - 2 comments

#1387 - How to sample multiple completions?

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

#1386 - How to extract the logits from using `forward_batch` in cpu?

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

#1385 - Bigger models unproportionally slower

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

#1384 - Question about characters not allowed

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

#1383 - token_type_ids for BERT models

Issue - State: closed - Opened by hachall about 1 year ago - 1 comment
Labels: enhancement

#1382 - Fixed a small error for model conversion

Pull Request - State: closed - Opened by RistoAle97 about 1 year ago

#1381 - Conversion of models does not work with torch <=1.12.1

Issue - State: closed - Opened by RistoAle97 about 1 year ago - 2 comments

#1380 - Update Llama converter to accept extra tokens in the vocabulary

Pull Request - State: closed - Opened by guillaumekln about 1 year ago

#1378 - Build error with CUDA 10.2 Jetson Nano

Issue - State: open - Opened by alexismailov2 about 1 year ago - 24 comments

#1377 - CT2 a custom fine-tuned LLAMA2 model?

Issue - State: closed - Opened by salahzoubi about 1 year ago - 8 comments

#1376 - The accuracy of model improved after quantized with ct2 in 8bit

Issue - State: closed - Opened by curname about 1 year ago - 4 comments

#1375 - Marian converter and SPM Vocabulary

Issue - State: closed - Opened by m-resta about 1 year ago - 4 comments

#1374 - Accept left offsets when applying position encodings

Pull Request - State: open - Opened by guillaumekln about 1 year ago

#1373 - distilbert-base-uncased-mnli

Issue - State: closed - Opened by AparnaAgrawal02 about 1 year ago - 1 comment
Labels: enhancement, help wanted

#1372 - Accept left offsets in the rotary embeddings layer

Pull Request - State: open - Opened by guillaumekln about 1 year ago

#1371 - Enable GPU tests for Alibi and RotaryEmbeddings layers

Pull Request - State: closed - Opened by guillaumekln about 1 year ago

#1370 - Accept left offsets in the masked softmax operator

Pull Request - State: open - Opened by guillaumekln about 1 year ago

#1369 - Remove vocabulary workaround in the Llama converter

Pull Request - State: closed - Opened by guillaumekln about 1 year ago

#1368 - ct2-transformers-converter errror for --model meta-llama/Llama-2-70b-chat-hf

Issue - State: closed - Opened by silvacarl2 about 1 year ago - 3 comments

#1367 - Support dtype conversion for the StorageView Python class

Pull Request - State: closed - Opened by guillaumekln about 1 year ago

#1366 - Fix bfloat16 dispatch in logits processor ApplyTimestampRules

Pull Request - State: closed - Opened by guillaumekln about 1 year ago

#1365 - Some questions

Issue - State: closed - Opened by breaddance about 1 year ago - 8 comments

#1364 - Pass the system prompt in static_prompt in the Llama 2 example

Pull Request - State: closed - Opened by guillaumekln about 1 year ago

#1363 - Llama 2 fails with context length >> 2000

Issue - State: closed - Opened by Joemgu7 about 1 year ago - 7 comments

#1362 - Converted Falcon 40B weights can not loaded

Issue - State: closed - Opened by mallorbc about 1 year ago - 4 comments

#1361 - Request for Implementing Support for wav2vec2, MMS, and XLS-R Models

Issue - State: open - Opened by nabil6391 about 1 year ago - 1 comment
Labels: enhancement

#1360 - Representing non-ASCII characters using ASCII

Pull Request - State: closed - Opened by BrightXiaoHan about 1 year ago - 2 comments

#1355 - LLAMA 2 support [Question] [Enhancement]

Issue - State: closed - Opened by trholding about 1 year ago - 4 comments

#1349 - Support left padding to forward batch prompts in a single step

Issue - State: open - Opened by guillaumekln about 1 year ago
Labels: enhancement

#1348 - A keyerror is raised when using the FALCON 40B model converted by ctranslate2

Issue - State: closed - Opened by srimouli04 about 1 year ago - 9 comments

#1343 - CPP inference Error. ** Error in `./run': double free or corruption (!prev):

Issue - State: closed - Opened by ustcdane about 1 year ago - 7 comments

#1337 - Get encoding from flan T5

Issue - State: open - Opened by Alexander-Jin about 1 year ago - 1 comment

#1333 - Continuous batching

Issue - State: open - Opened by andreapiso about 1 year ago - 6 comments
Labels: enhancement

#1330 - CMake error: CUDA_cublas_LIBRARY set to NOTFOUND

Issue - State: closed - Opened by Geremia about 1 year ago - 4 comments

#1329 - Code for chat inference server

Issue - State: closed - Opened by hobodrifterdavid about 1 year ago - 19 comments

#1324 - Exception when exporting bloomz model

Issue - State: open - Opened by jordimas about 1 year ago - 2 comments
Labels: bug

#1320 - ct2-transformers-converter fails on falcon-rw-1b

Issue - State: closed - Opened by julianmukaj over 1 year ago - 3 comments
Labels: bug

#1306 - This CTranslate2 package was not compiled with CUDA support

Issue - State: closed - Opened by ciayomin over 1 year ago - 15 comments

#1300 - Request to support FlashAttention in cuda attention.cc

Issue - State: closed - Opened by nemoramo over 1 year ago - 23 comments
Labels: enhancement

#1296 - BERT Models: Huge difference in last hidden states of similar examples

Issue - State: closed - Opened by vakkov over 1 year ago - 5 comments

#1285 - Question for asynchronous in generate_batch

Issue - State: closed - Opened by Snowdar over 1 year ago - 2 comments

#1283 - can't convert opennmt.py model with alibi or rotary embeddings to ctranslate2

Issue - State: open - Opened by totaltube over 1 year ago - 8 comments
Labels: enhancement

#1250 - CUDA 12 support (libcublas.so.11 is not found)

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

#1239 - Keep FFN output layer in float32 for T5 models

Pull Request - State: open - Opened by guillaumekln over 1 year ago - 3 comments

#1238 - Do not hardcode the library major version in CMakeLists.txt

Pull Request - State: closed - Opened by guillaumekln over 1 year ago

#1237 - same GPU memory between GPT2-13B-fp16 to GPT2-13B-int8 in CTranslate2

Issue - State: open - Opened by vicwer over 1 year ago - 2 comments

#1236 - Repeated text with Marian Model generation

Issue - State: open - Opened by zzgsty over 1 year ago - 1 comment

#1235 - Fix compilation with BUILD_SHARED_LIBS=OFF

Pull Request - State: closed - Opened by panosk over 1 year ago - 3 comments

#1234 - Assisted Generation feature

Issue - State: open - Opened by wsxiaoys over 1 year ago

#1233 - Quantized RedPajama responds in chinese

Issue - State: closed - Opened by NeonBohdan over 1 year ago - 1 comment

#1231 - Support for GPTBigCodeForCausalLM (StarCoder/ SantaCoder)

Issue - State: open - Opened by michaelfeil over 1 year ago - 4 comments

#1230 - Adding support for transformers - Salesforce/CodeGen architecture

Pull Request - State: closed - Opened by michaelfeil over 1 year ago - 3 comments

#1229 - Support for CodeT5pConfig

Issue - State: open - Opened by ferboz over 1 year ago - 1 comment

#1228 - Support the MPT model from MosaicML

Pull Request - State: closed - Opened by guillaumekln over 1 year ago

#1227 - Support paths with Unicode characters on Windows

Pull Request - State: closed - Opened by guillaumekln over 1 year ago

#1226 - Generalize conversion of encoder-decoder models from OpenNMT-tf

Pull Request - State: closed - Opened by guillaumekln over 1 year ago

#1225 - Raise asynchronous exception from generate_tokens method

Pull Request - State: closed - Opened by guillaumekln over 1 year ago

#1224 - Invalid opcode on older AMD opteron cpu (avx support?)

Issue - State: closed - Opened by agittins over 1 year ago - 3 comments

#1223 - add fairseq nllb insttructions

Issue - State: open - Opened by Omicronlawful over 1 year ago - 1 comment

#1222 - Fix installation of Intel MKL package in manylinux2014

Pull Request - State: closed - Opened by guillaumekln over 1 year ago

#1221 - add onmt-py converter for llama-onmt mpt-onmt

Pull Request - State: closed - Opened by vince62s over 1 year ago

#1219 - CTranslate2 can support Llama?

Issue - State: closed - Opened by moseshu over 1 year ago - 1 comment

#1218 - binary version v67324752 load problem

Issue - State: closed - Opened by syngokhan over 1 year ago - 3 comments

#1217 - Extract last hidden state

Issue - State: open - Opened by dathudeptrai over 1 year ago - 4 comments
Labels: enhancement

#1216 - ct2-fairseq-converter --vocab_mapping

Issue - State: closed - Opened by Omicronlawful over 1 year ago - 1 comment

#1215 - ct2-fairseq-converter

Issue - State: closed - Opened by Omicronlawful over 1 year ago

#1214 - It works fine, but gives an error.

Issue - State: closed - Opened by mayjack0312 over 1 year ago - 2 comments

#1213 - How to add context to translation models?

Issue - State: closed - Opened by eyalmazuz over 1 year ago - 11 comments

#1212 - Support for Mosaic ML MPT 7B

Issue - State: closed - Opened by praneetreddy017 over 1 year ago - 4 comments

#1211 - How to trans a model with Parallel encoder

Issue - State: open - Opened by wangshauitj over 1 year ago - 1 comment

#1210 - Resume model execution from where it stopped

Issue - State: closed - Opened by NeonBohdan over 1 year ago - 1 comment
Labels: enhancement

#1209 - Different generation parameters in the same batch

Issue - State: open - Opened by juliensalinas over 1 year ago

#1208 - Python Interface AutoModelConvert for Huggingface Transformers

Issue - State: closed - Opened by michaelfeil over 1 year ago - 3 comments

#1207 - Model running fine on cpu but not on gpu

Issue - State: closed - Opened by mayanksinha900 over 1 year ago - 4 comments

#1206 - GPT-NeoX

Issue - State: open - Opened by palladium123 over 1 year ago - 3 comments

#1205 - MKL not used when static linking with WHOLE_ARCHIVE

Issue - State: open - Opened by panosk over 1 year ago - 4 comments

#1204 - Optimize rotary embedding recreation

Issue - State: closed - Opened by janekb04 over 1 year ago - 2 comments

#1203 - How to build the prebuild binaries?

Issue - State: closed - Opened by JustFrederik over 1 year ago - 7 comments

#1202 - support ChatGLM

Issue - State: open - Opened by nghuyong over 1 year ago - 6 comments

#1201 - Manually destroy cuBLAS and cuDNN handles before threads exit

Pull Request - State: open - Opened by guillaumekln over 1 year ago

#1199 - Does CT2 support loading of two GPUs

Issue - State: open - Opened by lx0126z over 1 year ago - 1 comment

#1198 - Update docstring for end_token argument

Pull Request - State: closed - Opened by guillaumekln over 1 year ago

#1197 - Older architectures are not inserted to CUDA_ARCH_LIST

Issue - State: closed - Opened by panosk over 1 year ago - 2 comments

#1196 - CMake errors when using -DBUILD_SHARED_LIBS=OFF after #1178

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

#1195 - Add option to keep the end token in the results

Pull Request - State: closed - Opened by guillaumekln over 1 year ago

#1194 - Centos 8 support

Issue - State: closed - Opened by kolserdav over 1 year ago - 1 comment