uploading model

Signed-off-by: Jacob Renn <jacob.renn@squared.ai>

added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "### End": 50257,
+  "### Instruction:": 50258,
+  "### Response:\n": 50259
+}

config.json

@@ -0,0 +1,54 @@
+{
+  "_name_or_path": "/dbfs/FileStore/dais-model-large",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+    "custom_pipelines": {
+	"text-generation": {
+	    "impl": "instruct_pipeline.InstructionTextGenerationPipeline",
+	    "pt": "AutoModelForCausalLM",
+	    "tf": "TFAutoModelForCausalLM"
+	}
+    },
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "custom_pipelines": {
+    "text-generation": {
+      "impl": "instruct_pipeline.InstructionTextGenerationPipeline",
+      "pt": "AutoModelForCausalLM",
+      "tf": "TFAutoModelForCausalLM"
+    }
+  },
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 1600,
+  "n_head": 25,
+  "n_inner": null,
+  "n_layer": 48,
+  "n_positions": 1024,
+  "output_past": true,
+  "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0.1,
+  "scale_attn_by_inverse_layer_idx": false,
+  "scale_attn_weights": true,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "task_specific_params": {
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 50
+    }
+  },
+  "torch_dtype": "float16",
+  "transformers_version": "4.25.1",
+  "use_cache": false,
+  "vocab_size": 50260
+}

config.json~

@@ -0,0 +1,47 @@
+{
+  "_name_or_path": "/dbfs/FileStore/dais-model-large",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "custom_pipelines": {
+    "text-generation": {
+      "impl": "instruct_pipeline.InstructionTextGenerationPipeline",
+      "pt": "AutoModelForCausalLM",
+      "tf": "TFAutoModelForCausalLM"
+    }
+  },
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 1600,
+  "n_head": 25,
+  "n_inner": null,
+  "n_layer": 48,
+  "n_positions": 1024,
+  "output_past": true,
+  "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0.1,
+  "scale_attn_by_inverse_layer_idx": false,
+  "scale_attn_weights": true,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "task_specific_params": {
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 50
+    }
+  },
+  "torch_dtype": "float16",
+  "transformers_version": "4.25.1",
+  "use_cache": false,
+  "vocab_size": 50260
+}

instruct_pipeline.py

@@ -0,0 +1,160 @@
+import re
+
+import numpy as np
+from transformers import Pipeline, PreTrainedTokenizer
+
+
+INSTRUCTION_KEY = "### Instruction:"
+RESPONSE_KEY = "### Response:"
+END_KEY = "### End"
+INTRO_BLURB = (
+    "Below is an instruction that describes a task, along with any additional context. Write a response that appropriately completes the request."
+)
+
+# This is the prompt that is used for generating responses using an already trained model.  It ends with the response
+# key, where the job of the model is to provide the completion that follows it (i.e. the response itself).
+PROMPT_FOR_GENERATION_FORMAT = """{intro}
+
+{instruction_key}
+{instruction}
+
+{response_key}
+""".format(
+    intro=INTRO_BLURB,
+    instruction_key=INSTRUCTION_KEY,
+    instruction="{instruction}",
+    response_key=RESPONSE_KEY,
+)
+
+
+def get_special_token_id(tokenizer: PreTrainedTokenizer, key: str) -> int:
+    """Gets the token ID for a given string that has been added to the tokenizer as a special token.
+
+    When training, we configure the tokenizer so that the sequences like "### Instruction:" and "### End" are
+    treated specially and converted to a single, new token.  This retrieves the token ID each of these keys map to.
+
+    Args:
+        tokenizer (PreTrainedTokenizer): the tokenizer
+        key (str): the key to convert to a single token
+
+    Raises:
+        RuntimeError: if more than one ID was generated
+
+    Returns:
+        int: the token ID for the given key
+    """
+    token_ids = tokenizer.encode(key)
+    if len(token_ids) > 1:
+        raise ValueError(f"Expected only a single token for '{key}' but found {token_ids}")
+    return token_ids[0]
+
+
+class InstructionTextGenerationPipeline(Pipeline):
+    def __init__(
+        self, *args, do_sample: bool = True, max_new_tokens: int = 256, top_p: float = 0.92, top_k: int = 0, **kwargs
+    ):
+        super().__init__(*args, do_sample=do_sample, max_new_tokens=max_new_tokens, top_p=top_p, top_k=top_k, **kwargs)
+
+    def _sanitize_parameters(self, return_instruction_text=False, **generate_kwargs):
+        preprocess_params = {}
+
+        # newer versions of the tokenizer configure the response key as a special token.  newer versions still may
+        # append a newline to yield a single token.  find whatever token is configured for the response key.
+        tokenizer_response_key = next(
+            (token for token in self.tokenizer.additional_special_tokens if token.startswith(RESPONSE_KEY)), None
+        )
+
+        response_key_token_id = None
+        end_key_token_id = None
+        if tokenizer_response_key:
+            try:
+                response_key_token_id = get_special_token_id(self.tokenizer, tokenizer_response_key)
+                end_key_token_id = get_special_token_id(self.tokenizer, END_KEY)
+
+                # Ensure generation stops once it generates "### End"
+                generate_kwargs["eos_token_id"] = end_key_token_id
+            except ValueError:
+                pass
+
+        forward_params = generate_kwargs
+        postprocess_params = {
+            "response_key_token_id": response_key_token_id,
+            "end_key_token_id": end_key_token_id,
+            "return_instruction_text": return_instruction_text,
+        }
+
+        return preprocess_params, forward_params, postprocess_params
+
+    def preprocess(self, instruction_text, **generate_kwargs):
+        prompt_text = PROMPT_FOR_GENERATION_FORMAT.format(instruction=instruction_text)
+        inputs = self.tokenizer(
+            prompt_text,
+            return_tensors="pt",
+        )
+        inputs["prompt_text"] = prompt_text
+        inputs["instruction_text"] = instruction_text
+        return inputs
+
+    def _forward(self, model_inputs, **generate_kwargs):
+        input_ids = model_inputs["input_ids"]
+        attention_mask = model_inputs.get("attention_mask", None)
+        generated_sequence = self.model.generate(
+            input_ids=input_ids.to(self.model.device),
+            attention_mask=attention_mask,
+            pad_token_id=self.tokenizer.pad_token_id,
+            **generate_kwargs,
+        )[0].cpu()
+        instruction_text = model_inputs.pop("instruction_text")
+        return {"generated_sequence": generated_sequence, "input_ids": input_ids, "instruction_text": instruction_text}
+
+    def postprocess(self, model_outputs, response_key_token_id, end_key_token_id, return_instruction_text):
+        sequence = model_outputs["generated_sequence"]
+        instruction_text = model_outputs["instruction_text"]
+
+        # The response will be set to this variable if we can identify it.
+        decoded = None
+
+        # If we have token IDs for the response and end, then we can find the tokens and only decode between them.
+        if response_key_token_id and end_key_token_id:
+            # Find where "### Response:" is first found in the generated tokens.  Considering this is part of the
+            # prompt, we should definitely find it.  We will return the tokens found after this token.
+            response_pos = None
+            response_positions = np.where(sequence == response_key_token_id)[0]
+            if len(response_positions) == 0:
+                pass
+            else:
+                response_pos = response_positions[0]
+
+            if response_pos:
+                # Next find where "### End" is located.  The model has been trained to end its responses with this
+                # sequence (or actually, the token ID it maps to, since it is a special token).  We may not find
+                # this token, as the response could be truncated.  If we don't find it then just return everything
+                # to the end.  Note that even though we set eos_token_id, we still see the this token at the end.
+                end_pos = None
+                end_positions = np.where(sequence == end_key_token_id)[0]
+                if len(end_positions) > 0:
+                    end_pos = end_positions[0]
+
+                decoded = self.tokenizer.decode(sequence[response_pos + 1 : end_pos]).strip()
+        else:
+            # Otherwise we'll decode everything and use a regex to find the response and end.
+
+            fully_decoded = self.tokenizer.decode(sequence)
+
+            # The response appears after "### Response:".  The model has been trained to append "### End" at the
+            # end.
+            m = re.search(r"#+\s*Response:\s*(.+?)#+\s*End", fully_decoded, flags=re.DOTALL)
+
+            if m:
+                decoded = m.group(1).strip()
+            else:
+                # The model might not generate the "### End" sequence before reaching the max tokens.  In this case,
+                # return everything after "### Response:".
+                m = re.search(r"#+\s*Response:\s*(.+)", fully_decoded, flags=re.DOTALL)
+                if m:
+                    decoded = m.group(1).strip()
+
+        if return_instruction_text:
+            return {"instruction_text": instruction_text, "generated_text": decoded}
+
+        return decoded

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30a271cb3f0d38bbc53d2e86f933f3af9502818308bc6846707cdf7070966db4
+size 3165775133

special_tokens_map.json

@@ -0,0 +1,11 @@
+{
+  "additional_special_tokens": [
+    "### End",
+    "### Instruction:",
+    "### Response:\n"
+  ],
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "pad_token": "<|endoftext|>",
+  "unk_token": "<|endoftext|>"
+}

tokenizer_config.json

@@ -0,0 +1,34 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "errors": "replace",
+  "model_max_length": 1024,
+  "name_or_path": "/dbfs/FileStore/dais-model-large",
+  "pad_token": null,
+  "special_tokens_map_file": null,
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b0b3f10c8b1c6eb7e6085ee8166b3eedc44b8b9255e92da9797f51d5648462c5
+size 4603