TheBloke/NewHope-GPTQ · No .bin weights found

Deploying through AWS Sagemaker and running into these errors

Error #1

#033[2m2023-08-07T15:49:27.786695Z#033[0m #033[31mERROR#033[0m #033[1mshard-manager#033[0m: #033[2mtext_generation_launcher#033[0m#033[2m:#033[0m Error when initializing model

Error #2

Traceback (most recent call last):
  File "/opt/conda/bin/text-generation-server", line 8, in <module>
    sys.exit(app())
  File "/opt/conda/lib/python3.9/site-packages/typer/main.py", line 311, in __call__
    return get_command(self)(*args, **kwargs)
  File "/opt/conda/lib/python3.9/site-packages/click/core.py", line 1130, in __call__
    return self.main(*args, **kwargs)
  File "/opt/conda/lib/python3.9/site-packages/typer/core.py", line 778, in main
    return _main(
  File "/opt/conda/lib/python3.9/site-packages/typer/core.py", line 216, in _main
    rv = self.invoke(ctx)
  File "/opt/conda/lib/python3.9/site-packages/click/core.py", line 1657, in invoke
    return _process_result(sub_ctx.command.invoke(sub_ctx))
  File "/opt/conda/lib/python3.9/site-packages/click/core.py", line 1404, in invoke
    return ctx.invoke(self.callback, **ctx.params)
  File "/opt/conda/lib/python3.9/site-packages/click/core.py", line 760, in invoke
    return __callback(*args, **kwargs)
  File "/opt/conda/lib/python3.9/site-packages/typer/main.py", line 683, in wrapper
    return callback(**use_params)  # type: ignore
  File "/opt/conda/lib/python3.9/site-packages/text_generation_server/cli.py", line 67, in serve
    server.serve(model_id, revision, sharded, quantize, trust_remote_code, uds_path)
  File "/opt/conda/lib/python3.9/site-packages/text_generation_server/server.py", line 155, in serve
    asyncio.run(serve_inner(model_id, revision, sharded, quantize, trust_remote_code))
  File "/opt/conda/lib/python3.9/asyncio/runners.py", line 44, in run
    return loop.run_until_complete(main)
  File "/opt/conda/lib/python3.9/asyncio/base_events.py", line 634, in run_until_complete
    self.run_forever()
  File "/opt/conda/lib/python3.9/asyncio/base_events.py", line 601, in run_forever
    self._run_once()
  File "/opt/conda/lib/python3.9/asyncio/base_events.py", line 1905, in _run_once
    handle._run()
  File "/opt/conda/lib/python3.9/asyncio/events.py", line 80, in _run
    self._context.run(self._callback, *self._args)

Error #3

> File "/opt/conda/lib/python3.9/site-packages/text_generation_server/server.py", line 124, in serve_inner
    model = get_model(model_id, revision, sharded, quantize, trust_remote_code)
  File "/opt/conda/lib/python3.9/site-packages/text_generation_server/models/__init__.py", line 246, in get_model
    return llama_cls(
  File "/opt/conda/lib/python3.9/site-packages/text_generation_server/models/flash_llama.py", line 58, in __init__
    filenames = weight_files(model_id, revision, ".bin")
  File "/opt/conda/lib/python3.9/site-packages/text_generation_server/utils/hub.py", line 95, in weight_files
    raise e
  File "/opt/conda/lib/python3.9/site-packages/text_generation_server/utils/hub.py", line 92, in weight_files
    filenames = weight_hub_files(model_id, revision, extension)
  File "/opt/conda/lib/python3.9/site-packages/text_generation_server/utils/hub.py", line 33, in weight_hub_files
    raise EntryNotFoundError(

Error #4

huggingface_hub.utils._errors.EntryNotFoundError: No .bin weights found for model TheBloke/NewHope-GPTQ and revision None.
 #033[2m#033[3mrank#033[0m#033[2m=#033[0m0#033[0m

Sagemaker notebook

import json
import sagemaker
import boto3
from sagemaker.huggingface import HuggingFaceModel, get_huggingface_llm_image_uri

try:
    role = sagemaker.get_execution_role()
except ValueError:
    iam = boto3.client('iam')
    role = iam.get_role(RoleName='sagemaker_execution_role')['Role']['Arn']

# Hub Model configuration. https://huggingface.co/models
hub = {
    'HF_MODEL_ID':'TheBloke/NewHope-GPTQ',
    'SM_NUM_GPUS': json.dumps(1),
    'HF_API_TOKEN': '<TOKEN>'
}

# create Hugging Face Model Class
huggingface_model = HuggingFaceModel(
    image_uri=get_huggingface_llm_image_uri("huggingface",version="0.8.2"),
    env=hub,
    role=role, 
)

# deploy model to SageMaker Inference
predictor = huggingface_model.deploy(
    initial_instance_count=1,
    instance_type="ml.g5.2xlarge",
    container_startup_health_check_timeout=300,
    endpoint_name="NewHopeGPTQ",
    model_name="NewHopeGPTQ"
  )
  
# send request
predictor.predict({
    "inputs": "My name is Julien and I like to",
})