added a note on SSL access to app.py

app.py

@@ -32,66 +32,6 @@ PROMPT_FOR_GENERATION_FORMAT = """{intro}
 )
 
 
-#class InstructionTextGenerationPipeline:
-#    def __init__(
-#        self,
-#        model_name,
-#        torch_dtype=torch.bfloat16,
-#        trust_remote_code=True,
-#        use_auth_token=None,
-#    ) -> None:
-#        self.model = AutoModelForCausalLM.from_pretrained(
-#            model_name,
-#            torch_dtype=torch_dtype,
-#            trust_remote_code=trust_remote_code,
-#            use_auth_token=use_auth_token,
-#        )
-#
-#        tokenizer = AutoTokenizer.from_pretrained(
-#            model_name,
-#            trust_remote_code=trust_remote_code,
-#            use_auth_token=use_auth_token,
-#        )
-#        if tokenizer.pad_token_id is None:
-#            warnings.warn(
-#                "pad_token_id is not set for the tokenizer. Using eos_token_id as pad_token_id."
-#            )
-#            tokenizer.pad_token = tokenizer.eos_token
-#        tokenizer.padding_side = "left"
-#        self.tokenizer = tokenizer
-#
-#        device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
-#        self.model.eval()
-#        self.model.to(device=device, dtype=torch_dtype)
-#
-#        self.generate_kwargs = {
-#            "temperature": 0.5,
-#            "top_p": 0.92,
-#            "top_k": 0,
-#            "max_new_tokens": 512,
-#            "use_cache": True,
-#            "do_sample": True,
-#            "eos_token_id": self.tokenizer.eos_token_id,
-#            "pad_token_id": self.tokenizer.pad_token_id,
-#            "repetition_penalty": 1.1,  # 1.0 means no penalty, > 1.0 means penalty, 1.2 from CTRL paper
-#        }
-#
-#    def format_instruction(self, instruction):
-#        return PROMPT_FOR_GENERATION_FORMAT.format(instruction=instruction)
-#
-#    def __call__(
-#        self, instruction: str, **generate_kwargs: Dict[str, Any]
-#    ) -> Tuple[str, str, float]:
-#        s = PROMPT_FOR_GENERATION_FORMAT.format(instruction=instruction)
-#        input_ids = self.tokenizer(s, return_tensors="pt").input_ids
-#        input_ids = input_ids.to(self.model.device)
-#        gkw = {**self.generate_kwargs, **generate_kwargs}
-#        with torch.no_grad():
-#            output_ids = self.model.generate(input_ids, **gkw)
-#        # Slice the output_ids tensor to get only new tokens
-#        new_tokens = output_ids[0, len(input_ids[0]) :]
-#        output_text = self.tokenizer.decode(new_tokens, skip_special_tokens=True)
-#        return output_text
 ##
 from InstructionTextGenerationPipeline    import *
 from timeit import default_timer as timer
@@ -200,7 +140,7 @@ demo = gr.Interface(
             gr.Slider(256, 3072,value=1024, step=256, label="Tokens" ),
             gr.Slider(0.0, 1.0, value=0.1, step=0.1, label='temperature:'),
             gr.Slider(0, 1,  value=0, step=1, label='top_k:'),
-            gr.Slider(0.0, 1.0, value=0.0, step=0.05, label='top_p:')
+            gr.Slider(0.0, 1.0, value=0.05, step=0.05, label='top_p:')
            
            ],
     outputs=["text"],
@@ -209,3 +149,8 @@ demo.launch(share=True,
     server_name="0.0.0.0",
     server_port=7860
             )
+# Note on how we can run on SSL
+# See:https://github.com/gradio-app/gradio/issues/563 
+# a = gr.Interface(lambda x:x, "image", "image", examples=["lion.jpg"]).launch(
+#    share=False, ssl_keyfile="key.pem", ssl_certfile="cert.pem")
+# seems like we need an appropriate NON SELF SIGNED cert that the customer will accept on their net

nohup.out

@@ -0,0 +1,56 @@
+sys.path : ['/home/ec2-user/Gradio/MPT7BTest', '/usr/lib64/python37.zip', '/usr/lib64/python3.7', '/usr/lib64/python3.7/lib-dynload', '/home/ec2-user/.local/lib/python3.7/site-packages', '/usr/lib64/python3.7/site-packages', '/usr/lib/python3.7/site-packages', '/home/ec2-user/workspace/Notebooks/lib']
+
+Cell imports done
+
+Cell start generate
+You are using config.init_device='cpu', but you can also use config.init_device="meta" with Composer + FSDP for fast initialization.
+Traceback (most recent call last):
+  File "app.py", line 68, in <module>
+    trust_remote_code=True,
+  File "/home/ec2-user/Gradio/MPT7BTest/InstructionTextGenerationPipeline.py", line 44, in __init__
+    use_auth_token=use_auth_token,
+  File "/home/ec2-user/.local/lib/python3.7/site-packages/transformers/models/auto/auto_factory.py", line 463, in from_pretrained
+    pretrained_model_name_or_path, *model_args, config=config, **hub_kwargs, **kwargs
+  File "/home/ec2-user/.local/lib/python3.7/site-packages/transformers/modeling_utils.py", line 2611, in from_pretrained
+    model = cls(config, *model_args, **model_kwargs)
+  File "/home/ec2-user/.cache/huggingface/modules/transformers_modules/mosaicml/mpt-7b-instruct/ff5f3989b2585668930aeba501e83dfb306fc78d/modeling_mpt.py", line 222, in __init__
+    self.transformer = MPTModel(config)
+  File "/home/ec2-user/.cache/huggingface/modules/transformers_modules/mosaicml/mpt-7b-instruct/ff5f3989b2585668930aeba501e83dfb306fc78d/modeling_mpt.py", line 55, in __init__
+    self.apply(self.param_init_fn)
+  File "/home/ec2-user/.local/lib/python3.7/site-packages/torch/nn/modules/module.py", line 728, in apply
+    module.apply(fn)
+  File "/home/ec2-user/.local/lib/python3.7/site-packages/torch/nn/modules/module.py", line 728, in apply
+    module.apply(fn)
+  File "/home/ec2-user/.local/lib/python3.7/site-packages/torch/nn/modules/module.py", line 728, in apply
+    module.apply(fn)
+  [Previous line repeated 1 more time]
+  File "/home/ec2-user/.local/lib/python3.7/site-packages/torch/nn/modules/module.py", line 729, in apply
+    fn(self)
+  File "/home/ec2-user/.cache/huggingface/modules/transformers_modules/mosaicml/mpt-7b-instruct/ff5f3989b2585668930aeba501e83dfb306fc78d/modeling_mpt.py", line 208, in param_init_fn
+    MODEL_INIT_REGISTRY[init_fn_name](module=module, n_layers=self.config.n_layers, d_model=self.config.d_model, **self.config.init_config)
+  File "/home/ec2-user/.cache/huggingface/modules/transformers_modules/mosaicml/mpt-7b-instruct/ff5f3989b2585668930aeba501e83dfb306fc78d/param_init_fns.py", line 167, in kaiming_normal_param_init_fn_
+    generic_param_init_fn_(module=module, init_fn_=kaiming_normal_, d_model=d_model, n_layers=n_layers, init_div_is_residual=init_div_is_residual, emb_init_std=emb_init_std, emb_init_uniform_lim=emb_init_uniform_lim, verbose=verbose)
+  File "/home/ec2-user/.cache/huggingface/modules/transformers_modules/mosaicml/mpt-7b-instruct/ff5f3989b2585668930aeba501e83dfb306fc78d/param_init_fns.py", line 51, in generic_param_init_fn_
+    init_fn_(module.weight)
+  File "/home/ec2-user/.local/lib/python3.7/site-packages/torch/nn/init.py", line 451, in kaiming_normal_
+    return tensor.normal_(0, std)
+KeyboardInterrupt
+sys.path : ['/home/ec2-user/Gradio/MPT7BTest', '/usr/lib64/python37.zip', '/usr/lib64/python3.7', '/usr/lib64/python3.7/lib-dynload', '/home/ec2-user/.local/lib/python3.7/site-packages', '/usr/lib64/python3.7/site-packages', '/usr/lib/python3.7/site-packages', '/home/ec2-user/workspace/Notebooks/lib']
+
+Cell imports done
+
+Cell start generate
+
+
+During handling of the above exception, another exception occurred:
+
+Traceback (most recent call last):
+  File "app.py", line 68, in <module>
+    trust_remote_code=True,
+  File "/home/ec2-user/Gradio/MPT7BTest/InstructionTextGenerationPipeline.py", line 44, in __init__
+    use_auth_token=use_auth_token,
+  File "/home/ec2-user/.local/lib/python3.7/site-packages/transformers/models/auto/auto_factory.py", line 463, in from_pretrained
+    pretrained_model_name_or_path, *model_args, config=config, **hub_kwargs, **kwargs
+  File "/home/ec2-user/.local/lib/python3.7/site-packages/transformers/modeling_utils.py", line 2611, in from_pretrained
+    model = cls(config, *model_args, **model_kwargs)
+KeyboardInterrupt