intel/intel-extension-for-transformers

Issues

• plugin init failed

  #1377 opened 10 months ago
  5

• pip install missing dependencies

  #1365 opened 10 months ago
  3

• AssertionError: Fail to convert pytorch model with 'Intel/neural-chat-7b-v3-3' WOQ

  #1357 opened 8 months ago
  2

• No effect while running models with `trust_remote_code=True

  #1352 opened 10 months ago
  3

• Running Stable Diffusion on IPEX CPU has error

  #1345 opened 10 months ago
  2

• rag plugin init failed if retrieval_type is bm25

  #1315 opened 10 months ago
  1

• Conflict between ipex and pytorch

  #1311 opened 10 months ago
  2

• Unexpected msg "ERROR - The chosen retrieval type remains outside the supported scope." if retrieval_type = 'default'

  #1309 opened 10 months ago
  2

• RuntimeError: Chatbot instance has not been set.

  #1308 opened 10 months ago
  3

• system prompt can't be assigned via neuralchat frontend

  #1306 opened 8 months ago
  6

• Multiple issues with setting up the text chatbot service on SPR

  #1300 opened 7 months ago
  6

• 422 Unprocessable Entity using Neural Chat via OpenAI interface with meta--lama/llama-2-7b-chat-hf

  #1288 opened a year ago
  2

• QLoRA on CPU - Example ERROR: "undefined symbol"

  #1287 opened a year ago
  5

• Device does not exist / is not supported error with neuralchat deploy_chatbot_on_xpu notebook

  #1276 opened a year ago
  6

• [Neural Chat] Finetuning flow on Xeon SPR for single node fails

  #1274 opened a year ago
  5

• neuralchat int4 quantization failing during inference

  #1267 opened a year ago
  0

• [NeuralChat] Retrieval example failure

  #1252 opened a year ago
  2

• [NeuralChat] Generate fails for LLaVA models

  #1244 opened a year ago
  0

• Cannot import name 'WeightOnlyLinear' when running `from intel_extension_for_transformers.transformers import AutoModelForCausalLM`

  #1239 opened a year ago
  1

• Installed intel-extension-for-transformers and I get an error - No module named 'intel_extension_for_pytorch'"

  #1230 opened a year ago
  6

• i7-12700H CPU Tests

  #1220 opened 10 months ago
  1

• [NeuralChat] Finetuning for LLaVA failing on image + text pairs

  #1201 opened a year ago
  5

• Neural Chat Finetune Mistral Fails

  #1181 opened a year ago
  4

• FileNotFoundError: [Errno 2] No such file or directory: 'Intel/neural-chat-7b-v3-1'

  #1175 opened a year ago
  2

• When I loaded my quantized low-bit model, I encountered the following issue: like that"size mismatch for transformer.h.0.attn.c_attn.weight: copying a parameter with shape torch.Size([31457536]) from the checkpoint, whereas the shape in the current model is torch.Size([12288, 4096])."

  #1172 opened 10 months ago
  9

• Baichuan2-13B-Chat inference problem

  #1148 opened a year ago
  2

• Support Qwen-1.8B-Chat

  #1145 opened 10 months ago
  4

• Qwen-14B-Chat inference repeat

  #1144 opened 7 months ago
  6

• getting error when building from source

  #1142 opened 6 months ago
  7

• [LLM Runtime] OOM when running Llama2-70B, but not having this issue with llama.cpp

  #1136 opened a year ago
  3

• some issues with model.generate in itrex

  #1124 opened a year ago
  4

• None of examples on README page works

  #1117 opened 7 months ago
  5

• BF16 Inference

  #1115 opened a year ago
  1

• Deploying on virtual machines?

  #1106 opened 6 months ago
  2

• When building from source getting errors quantization.

  #1105 opened a year ago
  3

• Can't load woq int4 model

  #1104 opened 7 months ago
  5

• feature request: support for TextIterationstreamer of HF

  #1101 opened a year ago
  4

• AssertionError: Fail to convert pytorch model! Can't use any 6,7 billion transformer model like llama2,chatgml with intel-extension-for-transformers! i'm getting this error!

  #1099 opened a year ago
  10

• What is the best way for the inference process in LORA in PEFT approach

  #1097 opened 7 months ago
  1

• whisper.cpp

  #1094 opened 10 months ago
  7

• environment problem in qat for stable diffusion

  #1093 opened 7 months ago
  1

• Features request llama.cpp statistics for llama2 models

  #1091 opened a year ago
  2

• Segmentation fault (core dumped)

  #1090 opened a year ago
  1

• Load Quantized model

  #1068 opened 7 months ago
  7

• SIGILL, Illegal instruction from libkernellibs.so

  #1063 opened a year ago
  5

• Support Mixtral

  #963 opened 10 months ago
  3

• failed to run model conversion for qwen-7B

  #953 opened a year ago
  3

• main example for qLoRA fails: AttributeError: 'Model' object has no attribute 'named_parameters'

  #951 opened 7 months ago
  4

• Segmentation fault when run llm chat

  #944 opened a year ago
  6

• Generating meaningless results

  #929 opened a year ago
  3