ValueError: The checkpoint you are trying to load has model type `starcoder2` but Transformers does not recognize this architecture. This could be because of an issue with the checkpoint, or because your version of Transformers is out of date. #1620

coder-xieshijie · 2024-03-04T03:06:54Z

System Info

FROM ghcr.io/huggingface/text-generation-inference:sha-7dbaf9e

Information

Docker
The CLI directly

Tasks

An officially supported command
My own modifications

Reproduction

I built a tgi image myself. The specific dockerfile is as follows:

FROM ghcr.io/huggingface/text-generation-inference:sha-7dbaf9e

# Set the environment variable for PyTorch CUDA Allocator configuration
ENV PYTORCH_CUDA_ALLOC_CONF=max_split_size_mb:512

When I use this built image to load starcoder2-15b, the error is:

ValueError: The checkpoint you are trying to load has model type `starcoder2` but Transformers does not recognize this architecture. This could be because of an issue with the checkpoint, or because your version of Transformers is out of date.

My command to start the model in the image is as follows:

text-generation-launcher --model-id starcoder2-15b_path --port 6006 --num-shard 1 --max-input-length 8000 --max-total-tokens 12000 --max-batch-prefill-tokens 12000 --disable-custom-kernels --cuda-memory-fraction 0.9

It is worth noting that for the same image, when I start starcoder1-15b, it is normal, but when I start starcoder2-15b, it fails. The full error message is as follows:


2024-03-04 10:54:22 | 2024-03-04T02:54:22.500277Z  INFO text_generation_launcher: Shutting down shards
-- | --
  |   | 2024-03-04 10:54:22 | 2024-03-04T02:54:22.500258Z ERROR text_generation_launcher: Shard 0 failed to start
  |   | 2024-03-04 10:54:22 | rank=0
  |   | 2024-03-04 10:54:22 | ValueError: The checkpoint you are trying to load has model type `starcoder2` but Transformers does not recognize this architecture. This could be because of an issue with the checkpoint, or because your version of Transformers is out of date.
  |   | 2024-03-04 10:54:22 |  
  |   | 2024-03-04 10:54:22 | raise ValueError(
  |   | 2024-03-04 10:54:22 | File "/opt/conda/lib/python3.10/site-packages/transformers/models/auto/configuration_auto.py", line 1119, in from_pretrained
  |   | 2024-03-04 10:54:22 |  
  |   | 2024-03-04 10:54:22 | config, kwargs = AutoConfig.from_pretrained(
  |   | 2024-03-04 10:54:22 | File "/opt/conda/lib/python3.10/site-packages/transformers/models/auto/auto_factory.py", line 526, in from_pretrained
  |   | 2024-03-04 10:54:22 |  
  |   | 2024-03-04 10:54:22 | model = AutoModelForCausalLM.from_pretrained(
  |   | 2024-03-04 10:54:22 | File "/opt/conda/lib/python3.10/site-packages/text_generation_server/models/causal_lm.py", line 509, in __init__
  |   | 2024-03-04 10:54:22 |  
  |   | 2024-03-04 10:54:22 | return CausalLM(
  |   | 2024-03-04 10:54:22 | File "/opt/conda/lib/python3.10/site-packages/text_generation_server/models/__init__.py", line 458, in get_model
  |   | 2024-03-04 10:54:22 |  
  |   | 2024-03-04 10:54:22 | model = get_model(
  |   | 2024-03-04 10:54:22 | File "/opt/conda/lib/python3.10/site-packages/text_generation_server/server.py", line 196, in serve_inner
  |   | 2024-03-04 10:54:22 |  
  |   | 2024-03-04 10:54:22 | return future.result()
  |   | 2024-03-04 10:54:22 | File "/opt/conda/lib/python3.10/asyncio/base_events.py", line 649, in run_until_complete
  |   | 2024-03-04 10:54:22 |  
  |   | 2024-03-04 10:54:22 | return loop.run_until_complete(main)
  |   | 2024-03-04 10:54:22 | File "/opt/conda/lib/python3.10/asyncio/runners.py", line 44, in run
  |   | 2024-03-04 10:54:22 |  
  |   | 2024-03-04 10:54:22 | asyncio.run(
  |   | 2024-03-04 10:54:22 | File "/opt/conda/lib/python3.10/site-packages/text_generation_server/server.py", line 235, in serve
  |   | 2024-03-04 10:54:22 |  
  |   | 2024-03-04 10:54:22 | server.serve(
  |   | 2024-03-04 10:54:22 | File "/opt/conda/lib/python3.10/site-packages/text_generation_server/cli.py", line 89, in serve
  |   | 2024-03-04 10:54:22 |  
  |   | 2024-03-04 10:54:22 | sys.exit(app())
  |   | 2024-03-04 10:54:22 | File "/opt/conda/bin/text-generation-server", line 8, in <module>
  |   | 2024-03-04 10:54:22 |  
  |   | 2024-03-04 10:54:22 | Traceback (most recent call last):
  |   | 2024-03-04 10:54:22 |  
  |   | 2024-03-04 10:54:22 |  
  |   | 2024-03-04 10:54:22 | During handling of the above exception, another exception occurred:
  |   | 2024-03-04 10:54:22 |  
  |   | 2024-03-04 10:54:22 |  
  |   | 2024-03-04 10:54:22 | KeyError: 'starcoder2'
  |   | 2024-03-04 10:54:22 |  
  |   | 2024-03-04 10:54:22 | raise KeyError(key)
  |   | 2024-03-04 10:54:22 | File "/opt/conda/lib/python3.10/site-packages/transformers/models/auto/configuration_auto.py", line 813, in __getitem__
  |   | 2024-03-04 10:54:22 |  
  |   | 2024-03-04 10:54:22 | config_class = CONFIG_MAPPING[config_dict["model_type"]]
  |   | 2024-03-04 10:54:22 | File "/opt/conda/lib/python3.10/site-packages/transformers/models/auto/configuration_auto.py", line 1117, in from_pretrained
  |   | 2024-03-04 10:54:22 |  
  |   | 2024-03-04 10:54:22 | Traceback (most recent call last):
  |   | 2024-03-04 10:54:22 | warn("The installed version of bitsandbytes was compiled without GPU support. "
  |   | 2024-03-04 10:54:22 | /opt/conda/lib/python3.10/site-packages/bitsandbytes/cextension.py:34: UserWarning: The installed version of bitsandbytes was compiled without GPU support. 8-bit optimizers, 8-bit multiplication, and GPU quantization are unavailable.
  |   | 2024-03-04 10:54:22 | return torch._C._cuda_getDeviceCount() > 0
  |   | 2024-03-04 10:54:22 | /opt/conda/lib/python3.10/site-packages/torch/cuda/__init__.py:138: UserWarning: CUDA initialization: The NVIDIA driver on your system is too old (found version 11040). Please update your GPU driver by downloading and installing a new version from the URL: http://www.nvidia.com/Download/index.aspx Alternatively, go to: https://pytorch.org to install a PyTorch version that has been compiled with your version of the CUDA driver. (Triggered internally at /opt/conda/conda-bld/pytorch_1699449201336/work/c10/cuda/CUDAFunctions.cpp:108.)
  |   | 2024-03-04 10:54:22 |  
  |   | 2024-03-04 10:54:22 | 2024-03-04T02:54:22.401312Z ERROR shard-manager: text_generation_launcher: Shard complete standard error output:
  |   | 2024-03-04 10:54:21 |  
  |   | 2024-03-04 10:54:21 | ValueError: The checkpoint you are trying to load has model type `starcoder2` but Transformers does not recognize this architecture. This could be because of an issue with the checkpoint, or because your version of Transformers is out of date.
  |   | 2024-03-04 10:54:21 | raise ValueError(
  |   | 2024-03-04 10:54:21 | File "/opt/conda/lib/python3.10/site-packages/transformers/models/auto/configuration_auto.py", line 1119, in from_pretrained
  |   | 2024-03-04 10:54:21 | config, kwargs = AutoConfig.from_pretrained(
  |   | 2024-03-04 10:54:21 | File "/opt/conda/lib/python3.10/site-packages/transformers/models/auto/auto_factory.py", line 526, in from_pretrained
  |   | 2024-03-04 10:54:21 | model = AutoModelForCausalLM.from_pretrained(
  |   | 2024-03-04 10:54:21 | File "/opt/conda/lib/python3.10/site-packages/text_generation_server/models/causal_lm.py", line 509, in __init__
  |   | 2024-03-04 10:54:21 | return CausalLM(
  |   | 2024-03-04 10:54:21 | File "/opt/conda/lib/python3.10/site-packages/text_generation_server/models/__init__.py", line 458, in get_model
  |   | 2024-03-04 10:54:21 | model = get_model(
  |   | 2024-03-04 10:54:21 | > File "/opt/conda/lib/python3.10/site-packages/text_generation_server/server.py", line 196, in serve_inner
  |   | 2024-03-04 10:54:21 | self._context.run(self._callback, *self._args)
  |   | 2024-03-04 10:54:21 | File "/opt/conda/lib/python3.10/asyncio/events.py", line 80, in _run
  |   | 2024-03-04 10:54:21 | handle._run()
  |   | 2024-03-04 10:54:21 | File "/opt/conda/lib/python3.10/asyncio/base_events.py", line 1909, in _run_once
  |   | 2024-03-04 10:54:21 | self._run_once()
  |   | 2024-03-04 10:54:21 | File "/opt/conda/lib/python3.10/asyncio/base_events.py", line 603, in run_forever
  |   | 2024-03-04 10:54:21 | self.run_forever()
  |   | 2024-03-04 10:54:21 | File "/opt/conda/lib/python3.10/asyncio/base_events.py", line 636, in run_until_complete
  |   | 2024-03-04 10:54:21 | return loop.run_until_complete(main)
  |   | 2024-03-04 10:54:21 | File "/opt/conda/lib/python3.10/asyncio/runners.py", line 44, in run
  |   | 2024-03-04 10:54:21 | asyncio.run(
  |   | 2024-03-04 10:54:21 | File "/opt/conda/lib/python3.10/site-packages/text_generation_server/server.py", line 235, in serve
  |   | 2024-03-04 10:54:21 | server.serve(
  |   | 2024-03-04 10:54:21 | File "/opt/conda/lib/python3.10/site-packages/text_generation_server/cli.py", line 89, in serve
  |   | 2024-03-04 10:54:21 | return callback(**use_params)  # type: ignore
  |   | 2024-03-04 10:54:21 | File "/opt/conda/lib/python3.10/site-packages/typer/main.py", line 683, in wrapper
  |   | 2024-03-04 10:54:21 | return __callback(*args, **kwargs)
  |   | 2024-03-04 10:54:21 | File "/opt/conda/lib/python3.10/site-packages/click/core.py", line 783, in invoke
  |   | 2024-03-04 10:54:21 | return ctx.invoke(self.callback, **ctx.params)
  |   | 2024-03-04 10:54:21 | File "/opt/conda/lib/python3.10/site-packages/click/core.py", line 1434, in invoke
  |   | 2024-03-04 10:54:21 | return _process_result(sub_ctx.command.invoke(sub_ctx))
  |   | 2024-03-04 10:54:21 | File "/opt/conda/lib/python3.10/site-packages/click/core.py", line 1688, in invoke
  |   | 2024-03-04 10:54:21 | rv = self.invoke(ctx)
  |   | 2024-03-04 10:54:21 | File "/opt/conda/lib/python3.10/site-packages/typer/core.py", line 216, in _main
  |   | 2024-03-04 10:54:21 | return _main(
  |   | 2024-03-04 10:54:21 | File "/opt/conda/lib/python3.10/site-packages/typer/core.py", line 778, in main
  |   | 2024-03-04 10:54:21 | return self.main(*args, **kwargs)
  |   | 2024-03-04 10:54:21 | File "/opt/conda/lib/python3.10/site-packages/click/core.py", line 1157, in __call__
  |   | 2024-03-04 10:54:21 | return get_command(self)(*args, **kwargs)
  |   | 2024-03-04 10:54:21 | File "/opt/conda/lib/python3.10/site-packages/typer/main.py", line 311, in __call__
  |   | 2024-03-04 10:54:21 | sys.exit(app())
  |   | 2024-03-04 10:54:21 | File "/opt/conda/bin/text-generation-server", line 8, in <module>
  |   | 2024-03-04 10:54:21 | Traceback (most recent call last):
  |   | 2024-03-04 10:54:21 |  
  |   | 2024-03-04 10:54:21 | During handling of the above exception, another exception occurred:
  |   | 2024-03-04 10:54:21 |  
  |   | 2024-03-04 10:54:21 | KeyError: 'starcoder2'
  |   | 2024-03-04 10:54:21 | raise KeyError(key)
  |   | 2024-03-04 10:54:21 | File "/opt/conda/lib/python3.10/site-packages/transformers/models/auto/configuration_auto.py", line 813, in __getitem__
  |   | 2024-03-04 10:54:21 | config_class = CONFIG_MAPPING[config_dict["model_type"]]
  |   | 2024-03-04 10:54:21 | File "/opt/conda/lib/python3.10/site-packages/transformers/models/auto/configuration_auto.py", line 1117, in from_pretrained
  |   | 2024-03-04 10:54:21 | Traceback (most recent call last):
  |   | 2024-03-04 10:54:21 | 2024-03-04T02:54:21.674963Z ERROR text_generation_launcher: Error when initializing model

Expected behavior

I hope to start starcoder2-15b normally through tgi, I ask for help, thank you very much

The text was updated successfully, but these errors were encountered:

coder-xieshijie · 2024-03-04T03:08:56Z

I saw that pr already supports starcoder2, and the docker image I downloaded is also the latest, but I don’t know why the deployment of starcoder2 still failed.

suyashhchougule · 2024-03-04T10:14:10Z

@coder-xieshijie
Uninstall the current version of the transformer and reinstall it from the source.
i.e.
pip install git+https://github.com/huggingface/transformers.git

OlivierDehaene · 2024-03-04T15:30:19Z

I think the problem is your cuda driver version:

  |   | 2024-03-04 10:54:22 | /opt/conda/lib/python3.10/site-packages/torch/cuda/__init__.py:138: UserWarning: CUDA initialization: The NVIDIA driver on your system is too old (found version 11040). Please update your GPU driver by downloading and installing a new version from the URL: http://www.nvidia.com/Download/index.aspx Alternatively, go to: https://pytorch.org to install a PyTorch version that has been compiled with your version of the CUDA driver. (Triggered internally at /opt/conda/conda-bld/pytorch_1699449201336/work/c10/cuda/CUDAFunctions.cpp:108.)

coder-xieshijie · 2024-03-05T06:03:40Z

I think the problem is your cuda driver version:

  |   | 2024-03-04 10:54:22 | /opt/conda/lib/python3.10/site-packages/torch/cuda/__init__.py:138: UserWarning: CUDA initialization: The NVIDIA driver on your system is too old (found version 11040). Please update your GPU driver by downloading and installing a new version from the URL: http://www.nvidia.com/Download/index.aspx Alternatively, go to: https://pytorch.org to install a PyTorch version that has been compiled with your version of the CUDA driver. (Triggered internally at /opt/conda/conda-bld/pytorch_1699449201336/work/c10/cuda/CUDAFunctions.cpp:108.)

@OlivierDehaene

This is my docker image running log.

2024-03-04 10:41,INFO[0000] Retrieving image manifest ghcr.io/huggingface/text-generation-inference:sha-7dbaf9e 
2024-03-04 10:41,INFO[0000] Retrieving image ghcr.io/huggingface/text-generation-inference:sha-7dbaf9e from registry ghcr.io 
2024-03-04 10:41,INFO[0002] Built cross stage deps: map[]                
2024-03-04 10:41,INFO[0002] Retrieving image manifest ghcr.io/huggingface/text-generation-inference:sha-7dbaf9e 
2024-03-04 10:41,INFO[0002] Returning cached image manifest              
2024-03-04 10:41,INFO[0002] Executing 0 build triggers                   
2024-03-04 10:41,INFO[0002] Building stage 'ghcr.io/huggingface/text-generation-inference:sha-7dbaf9e' [idx: '0', base-idx: '-1'] 
2024-03-04 10:41,INFO[0002] Skipping unpacking as no commands require it. 
2024-03-04 10:41,INFO[0002] ENV PYTORCH_CUDA_ALLOC_CONF=max_split_size_mb:512

I completely inherited it from the latest tgi image. The theoretical cuda version is also completely inherited from this image. I saw that tgi’s dockerfile file has a cuda version description from https://github.com/huggingface/text-generation-inference/blob/main/Dockerfile

FROM nvidia/cuda:12.1.0-devel-ubuntu22.04 as pytorch-install

ARG PYTORCH_VERSION=2.1.1
ARG PYTHON_VERSION=3.10
# Keep in sync with `server/pyproject.toml
ARG CUDA_VERSION=12.1
ARG MAMBA_VERSION=23.3.1-1
ARG CUDA_CHANNEL=nvidia
ARG INSTALL_CHANNEL=pytorch
# Automatically set by buildx
ARG TARGETPLATFORM

Is this version outdated?

OlivierDehaene · 2024-03-05T10:27:49Z

The driver version is related to your host running the container, not the docker image.

HitSakhavala · 2024-03-05T12:06:09Z

I'm facing the same issue but I do not have any error/warning related to GPU(except FlashAttantion).
here the logs, can you help me why it is failing?

Docker Image: ghcr.io/huggingface/text-generation-inference
model: bigcode/starcoder2-15b
also i'm quantizing the model using --quantize bitsandbytes-fp4 .

2024-03-05T11:55:52.160985Z INFO download: text_generation_launcher: Starting download process.
2024-03-05T11:55:59.440544Z INFO text_generation_launcher: Files are already present on the host. Skipping download.

2024-03-05T11:56:00.071391Z  INFO download: text_generation_launcher: Successfully downloaded weights.
2024-03-05T11:56:00.071643Z  INFO shard-manager: text_generation_launcher: Starting shard rank=0
2024-03-05T11:56:08.165844Z  WARN text_generation_launcher: Unable to use Flash Attention V2: GPU with CUDA capability 7 5 is not supported for Flash Attention V2

2024-03-05T11:56:09.068702Z ERROR text_generation_launcher: Error when initializing model
Traceback (most recent call last):
File "/opt/conda/lib/python3.10/site-packages/transformers/models/auto/configuration_auto.py", line 1117, in from_pretrained
    config_class = CONFIG_MAPPING[config_dict["model_type"]]
File "/opt/conda/lib/python3.10/site-packages/transformers/models/auto/configuration_auto.py", line 813, in __getitem__
    raise KeyError(key)
KeyError: 'starcoder2'

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "/opt/conda/bin/text-generation-server", line 8, in <module>
    sys.exit(app())
File "/opt/conda/lib/python3.10/site-packages/typer/main.py", line 311, in __call__
    return get_command(self)(*args, **kwargs)
File "/opt/conda/lib/python3.10/site-packages/click/core.py", line 1157, in __call__
    return self.main(*args, **kwargs)
File "/opt/conda/lib/python3.10/site-packages/typer/core.py", line 778, in main
    return _main(
File "/opt/conda/lib/python3.10/site-packages/typer/core.py", line 216, in _main
    rv = self.invoke(ctx)
File "/opt/conda/lib/python3.10/site-packages/click/core.py", line 1688, in invoke
    return _process_result(sub_ctx.command.invoke(sub_ctx))
File "/opt/conda/lib/python3.10/site-packages/click/core.py", line 1434, in invoke
    return ctx.invoke(self.callback, **ctx.params)
File "/opt/conda/lib/python3.10/site-packages/click/core.py", line 783, in invoke
    return __callback(*args, **kwargs)
File "/opt/conda/lib/python3.10/site-packages/typer/main.py", line 683, in wrapper
    return callback(**use_params)  # type: ignore
File "/opt/conda/lib/python3.10/site-packages/text_generation_server/cli.py", line 89, in serve
    server.serve(
File "/opt/conda/lib/python3.10/site-packages/text_generation_server/server.py", line 235, in serve
    asyncio.run(
File "/opt/conda/lib/python3.10/asyncio/runners.py", line 44, in run
    return loop.run_until_complete(main)
File "/opt/conda/lib/python3.10/asyncio/base_events.py", line 636, in run_until_complete
    self.run_forever()
File "/opt/conda/lib/python3.10/asyncio/base_events.py", line 603, in run_forever
    self._run_once()
File "/opt/conda/lib/python3.10/asyncio/base_events.py", line 1909, in _run_once
    handle._run()
File "/opt/conda/lib/python3.10/asyncio/events.py", line 80, in _run
    self._context.run(self._callback, *self._args)
> File "/opt/conda/lib/python3.10/site-packages/text_generation_server/server.py", line 196, in serve_inner
    model = get_model(
File "/opt/conda/lib/python3.10/site-packages/text_generation_server/models/__init__.py", line 458, in get_model
    return CausalLM(
File "/opt/conda/lib/python3.10/site-packages/text_generation_server/models/causal_lm.py", line 509, in __init__
    model = AutoModelForCausalLM.from_pretrained(
File "/opt/conda/lib/python3.10/site-packages/transformers/models/auto/auto_factory.py", line 526, in from_pretrained
    config, kwargs = AutoConfig.from_pretrained(
File "/opt/conda/lib/python3.10/site-packages/transformers/models/auto/configuration_auto.py", line 1119, in from_pretrained
    raise ValueError(
ValueError: The checkpoint you are trying to load has model type `starcoder2` but Transformers does not recognize this architecture. This could be because of an issue with the checkpoint, or because your version of Transformers is out of date.

2024-03-05T11:56:09.984085Z ERROR shard-manager: text_generation_launcher: Shard complete standard error output:

Traceback (most recent call last):

File "/opt/conda/lib/python3.10/site-packages/transformers/models/auto/configuration_auto.py", line 1117, in from_pretrained
    config_class = CONFIG_MAPPING[config_dict["model_type"]]

File "/opt/conda/lib/python3.10/site-packages/transformers/models/auto/configuration_auto.py", line 813, in __getitem__
    raise KeyError(key)

KeyError: 'starcoder2'


During handling of the above exception, another exception occurred:


Traceback (most recent call last):

File "/opt/conda/bin/text-generation-server", line 8, in <module>
    sys.exit(app())

File "/opt/conda/lib/python3.10/site-packages/text_generation_server/cli.py", line 89, in serve
    server.serve(

File "/opt/conda/lib/python3.10/site-packages/text_generation_server/server.py", line 235, in serve
    asyncio.run(

File "/opt/conda/lib/python3.10/asyncio/runners.py", line 44, in run
    return loop.run_until_complete(main)

File "/opt/conda/lib/python3.10/asyncio/base_events.py", line 649, in run_until_complete
    return future.result()

File "/opt/conda/lib/python3.10/site-packages/text_generation_server/server.py", line 196, in serve_inner
    model = get_model(

File "/opt/conda/lib/python3.10/site-packages/text_generation_server/models/__init__.py", line 458, in get_model
    return CausalLM(

File "/opt/conda/lib/python3.10/site-packages/text_generation_server/models/causal_lm.py", line 509, in __init__
    model = AutoModelForCausalLM.from_pretrained(

File "/opt/conda/lib/python3.10/site-packages/transformers/models/auto/auto_factory.py", line 526, in from_pretrained
    config, kwargs = AutoConfig.from_pretrained(

File "/opt/conda/lib/python3.10/site-packages/transformers/models/auto/configuration_auto.py", line 1119, in from_pretrained
    raise ValueError(

ValueError: The checkpoint you are trying to load has model type `starcoder2` but Transformers does not recognize this architecture. This could be because of an issue with the checkpoint, or because your version of Transformers is out of date.
rank=0
2024-03-05T11:56:10.083000Z ERROR text_generation_launcher: Shard 0 failed to start
2024-03-05T11:56:10.083033Z  INFO text_generation_launcher: Shutting down shards

coder-xieshijie · 2024-03-06T07:17:06Z

The driver version is related to your host running the container, not the docker image.

Thank you for your opinion, I will give it a try and will get back to you with the results.

BinBrent · 2024-03-07T01:33:35Z

@coder-xieshijie Uninstall the current version of the transformer and reinstall it from the source. i.e. pip install git+https://github.com/huggingface/transformers.git

It worked. "Successfully installed transformers-4.39.0.dev0", the transformers version matters

github-actions · 2024-04-06T01:44:23Z

This issue is stale because it has been open 30 days with no activity. Remove stale label or comment or this will be closed in 5 days.

NanoCode012 mentioned this issue Mar 13, 2024

Running bigcode/starcoder2-3b model usingexamples/starcoder2/qlora.yml config failed axolotl-ai-cloud/axolotl#1398

Closed

8 tasks

github-actions bot added the Stale label Apr 6, 2024

github-actions bot closed this as not planned Won't fix, can't repro, duplicate, stale Apr 11, 2024

yakazimir mentioned this issue May 13, 2024

Evaluate: jetmoe/jetmoe-8b | -8b-sft | -8b-chat logikon-ai/cot-eval#47

Open

7 tasks

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

ValueError: The checkpoint you are trying to load has model type `starcoder2` but Transformers does not recognize this architecture. This could be because of an issue with the checkpoint, or because your version of Transformers is out of date. #1620

ValueError: The checkpoint you are trying to load has model type `starcoder2` but Transformers does not recognize this architecture. This could be because of an issue with the checkpoint, or because your version of Transformers is out of date. #1620

coder-xieshijie commented Mar 4, 2024

coder-xieshijie commented Mar 4, 2024

suyashhchougule commented Mar 4, 2024

OlivierDehaene commented Mar 4, 2024

coder-xieshijie commented Mar 5, 2024

OlivierDehaene commented Mar 5, 2024

HitSakhavala commented Mar 5, 2024

coder-xieshijie commented Mar 6, 2024

BinBrent commented Mar 7, 2024

github-actions bot commented Apr 6, 2024

ValueError: The checkpoint you are trying to load has model type starcoder2 but Transformers does not recognize this architecture. This could be because of an issue with the checkpoint, or because your version of Transformers is out of date. #1620

ValueError: The checkpoint you are trying to load has model type starcoder2 but Transformers does not recognize this architecture. This could be because of an issue with the checkpoint, or because your version of Transformers is out of date. #1620

Comments

coder-xieshijie commented Mar 4, 2024

System Info

Information

Tasks

Reproduction

Expected behavior

coder-xieshijie commented Mar 4, 2024

suyashhchougule commented Mar 4, 2024

OlivierDehaene commented Mar 4, 2024

coder-xieshijie commented Mar 5, 2024

OlivierDehaene commented Mar 5, 2024

HitSakhavala commented Mar 5, 2024

coder-xieshijie commented Mar 6, 2024

BinBrent commented Mar 7, 2024

github-actions bot commented Apr 6, 2024

ValueError: The checkpoint you are trying to load has model type `starcoder2` but Transformers does not recognize this architecture. This could be because of an issue with the checkpoint, or because your version of Transformers is out of date. #1620

ValueError: The checkpoint you are trying to load has model type `starcoder2` but Transformers does not recognize this architecture. This could be because of an issue with the checkpoint, or because your version of Transformers is out of date. #1620