runtime error

gface_inference_endpoints data = fn(*data) # type: ignore File "/usr/local/lib/python3.10/site-packages/gradio/external_utils.py", line 115, in text_generation_inner return input + client.text_generation(input) File "/usr/local/lib/python3.10/site-packages/huggingface_hub/inference/_client.py", line 1841, in text_generation raise_text_generation_error(e) File "/usr/local/lib/python3.10/site-packages/huggingface_hub/inference/_common.py", line 470, in raise_text_generation_error raise http_error File "/usr/local/lib/python3.10/site-packages/huggingface_hub/inference/_client.py", line 1817, in text_generation bytes_output = self.post(json=payload, model=model, task="text-generation", stream=stream) # type: ignore File "/usr/local/lib/python3.10/site-packages/huggingface_hub/inference/_client.py", line 267, in post hf_raise_for_status(response) File "/usr/local/lib/python3.10/site-packages/huggingface_hub/utils/_errors.py", line 371, in hf_raise_for_status raise HfHubHTTPError(str(e), response=response) from e huggingface_hub.utils._errors.HfHubHTTPError: 500 Server Error: Internal Server Error for url: https://api-inference.huggingface.co/models/YanaS/llama-2-7b-langchain-chat-GGUF (Request ID: rNUpCUh5uAkkMh_tX--w1) Could not load model YanaS/llama-2-7b-langchain-chat-GGUF with any of the following classes: (<class 'transformers.models.llama.modeling_llama.LlamaForCausalLM'>,). See the original errors: while loading with LlamaForCausalLM, an error is thrown: Traceback (most recent call last): File "/src/transformers/src/transformers/pipelines/base.py", line 279, in infer_framework_load_model model = model_class.from_pretrained(model, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/src/transformers/src/transformers/modeling_utils.py", line 3236, in from_pretrained raise EnvironmentError( OSError: YanaS/llama-2-7b-langchain-chat-GGUF does not appear to have a file named pytorch_model.bin, tf_model.h5, model.ckpt or flax_model.msgpack.

Container logs: