初始化项目，由ModelHub XC社区提供模型

Model: aisquared/dlite-v2-1_5b
Source: Original Platform

.gitattributes

@@ -0,0 +1,34 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,131 @@
+---
+license: apache-2.0
+datasets:
+- aisquared/databricks-dolly-15k
+language:
+- en
+library_name: transformers
+---
+
+
+# Model Card for `dlite-v2-1.5b`
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+AI Squared's `dlite-v2-1.5b` is a large language 
+model which is derived from OpenAI's large [GPT-2](https://huggingface.co/gpt2-large) model and fine-tuned on a corpus of 15k records
+([Databricks' "Dolly 15k" Dataset](https://huggingface.co/datasets/aisquared/databricks-dolly-15k)) to help it exhibit chat-based capabilities.
+
+Just like [Databricks' Dolly V2 models](https://www.databricks.com/blog/2023/04/12/dolly-first-open-commercially-viable-instruction-tuned-llm),
+`dlite-v2-1.5b` (and all other members of the `dlite-v2` family) is licensed for both **research and commercial use.** We are extremely grateful 
+for the work that Databricks has done to create the `databricks-dolly-15k` dataset, for without it we would not be able to create and release this
+model under such an open and permissive license.
+
+While `dlite-v2-1.5b` is **not a state-of-the-art model**, we believe that the level of interactivity that can be achieved on such a small model that is trained so cheaply
+is important to showcase, as it continues to demonstrate that creating powerful AI capabilities may be much more accessible than previously thought. 
+
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+- **Developed by:** AI Squared, Inc.
+- **Shared by:** AI Squared, Inc.
+- **Model type:** Large Language Model
+- **Language(s) (NLP):** EN
+- **License:** Apache v2.0
+- **Finetuned from model:** GPT-2
+
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+**`dlite-v2-1.5b` is not a state-of-the-art language model.** `dlite-v2-1.5b` is an experimental technology, and as with any experimental technology, 
+AI Squared urges potential users of this technology to test its capabilities thoroughly before usage.
+Furthermore, the model can sometimes exhibit undesired behaviors. Some of these behaviors include,
+but are not limited to: factual inaccuracies, biases, offensive responses, toxicity, and hallucinations.
+Just as with any other LLM, we advise users of this technology to exercise good judgment when applying this technology.
+
+
+## Usage
+
+To use the model with the `transformers` library on a machine with GPUs, first make sure you have the `transformers` and `accelerate` libraries installed.
+From your terminal, run:
+
+```python
+pip install "accelerate>=0.16.0,<1" "transformers[torch]>=4.28.1,<5" "torch>=1.13.1,<2"
+```
+
+The instruction following pipeline can be loaded using the `pipeline` function as shown below.  This loads a custom `InstructionTextGenerationPipeline` 
+found in the model repo [here](https://huggingface.co/aisquared/dlite-v2-1_5b/blob/main/instruct_pipeline.py), which is why `trust_remote_code=True` is required.
+Including `torch_dtype=torch.bfloat16` is generally recommended if this type is supported in order to reduce memory usage.  It does not appear to impact output quality.
+It is also fine to remove it if there is sufficient memory.
+
+```python
+from transformers import pipeline
+import torch
+
+generate_text = pipeline(model="aisquared/dlite-v2-1_5b", torch_dtype=torch.bfloat16, trust_remote_code=True, device_map="auto")
+```
+
+You can then use the pipeline to answer instructions:
+
+```python
+res = generate_text("Who was George Washington?")
+print(res)
+```
+
+Alternatively, if you prefer to not use `trust_remote_code=True` you can download [instruct_pipeline.py](https://huggingface.co/aisquared/dlite-v2-1_5b/blob/main/instruct_pipeline.py),
+store it alongside your notebook, and construct the pipeline yourself from the loaded model and tokenizer:
+
+```python
+from instruct_pipeline import InstructionTextGenerationPipeline
+from transformers import AutoModelForCausalLM, AutoTokenizer
+import torch
+
+tokenizer = AutoTokenizer.from_pretrained("aisquared/dlite-v2-1_5b", padding_side="left")
+model = AutoModelForCausalLM.from_pretrained("aisquared/dlite-v2-1_5b", device_map="auto", torch_dtype=torch.bfloat16)
+
+generate_text = InstructionTextGenerationPipeline(model=model, tokenizer=tokenizer)
+```
+
+### Model Performance Metrics
+
+We present the results from various model benchmarks on the EleutherAI LLM Evaluation Harness for all models in the DLite family.
+Model results are sorted by mean score, ascending, to provide an ordering. These metrics serve to further show that none of the DLite models are
+state of the art, but rather further show that chat-like behaviors in LLMs can be trained almost independent of model size.
+
+| Model         |   arc_challenge |   arc_easy |    boolq |   hellaswag |   openbookqa |     piqa |   winogrande |
+|:--------------|----------------:|-----------:|---------:|------------:|-------------:|---------:|-------------:|
+| dlite-v2-124m |        0.199659 |   0.447811 | 0.494801 |    0.291675 |        0.156 | 0.620239 |     0.487766 |
+| gpt2          |        0.190273 |   0.438131 | 0.487156 |    0.289185 |        0.164 | 0.628945 |     0.51618  |
+| dlite-v1-124m |        0.223549 |   0.462542 | 0.502446 |    0.293268 |        0.17  | 0.622416 |     0.494081 |
+| gpt2-medium   |        0.215017 |   0.490741 | 0.585933 |    0.333101 |        0.186 | 0.676279 |     0.531176 |
+| dlite-v2-355m |        0.251706 |   0.486111 | 0.547401 |    0.344354 |        0.216 | 0.671926 |     0.52723  |
+| dlite-v1-355m |        0.234642 |   0.507576 | 0.600306 |    0.338478 |        0.216 | 0.664309 |     0.496448 |
+| gpt2-large    |        0.216724 |   0.531566 | 0.604893 |    0.363971 |        0.194 | 0.703482 |     0.553275 |
+| dlite-v1-774m |        0.250853 |   0.545875 | 0.614985 |    0.375124 |        0.218 | 0.698041 |     0.562747 |
+| dlite-v2-774m |        0.269625 |   0.52904  | 0.613761 |    0.395937 |        0.256 | 0.691513 |     0.566693 |
+| gpt2-xl       |        0.25     |   0.582912 | 0.617737 |    0.400418 |        0.224 | 0.708379 |     0.583268 |
+| dlite-v1-1_5b |        0.268771 |   0.588384 | 0.624159 |    0.401414 |        0.226 | 0.708379 |     0.584846 |
+| dlite-v2-1_5b |        0.289249 |   0.565657 | 0.601223 |    0.434077 |        0.272 | 0.703482 |     0.588003 |
+
+### Limitations
+*DLite is an experimental technology and is not designed for use in any environment without significant testing and safety consideration.
+Furthermore, the model can sometimes exhibit undesired behaviors. Some of these behaviors include, but are not limited to: factual
+inaccuracies, biases, offensive responses, toxicity, and hallucinations. Just as with any other LLM, we advise users of this technology
+to exercise good judgment when applying this technology.*
+# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
+Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_aisquared__dlite-v2-1_5b)
+
+| Metric                | Value                     |
+|-----------------------|---------------------------|
+| Avg.                  | 30.03   |
+| ARC (25-shot)         | 32.59          |
+| HellaSwag (10-shot)   | 53.98    |
+| MMLU (5-shot)         | 24.93         |
+| TruthfulQA (0-shot)   | 38.77   |
+| Winogrande (5-shot)   | 54.7   |
+| GSM8K (5-shot)        | 0.23        |
+| DROP (3-shot)         | 5.04         |

added_tokens.json

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

config.json

@@ -0,0 +1,47 @@
+{
+  "_name_or_path": "gpt2-xl",
+  "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,
+  "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 sha256:5a2ba12acb87aff387e4b0c41a399acde9d210813c2a843bcc92a36ccbb053fd
+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 +1,10 @@
+{
+  "add_prefix_space": false,
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 1024,
+  "name_or_path": "gpt2-xl",
+  "special_tokens_map_file": null,
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7419979b2c153a41b2f0f96d5d6a8e1a6c584c5eef9ab0e20084ec471e6c2681
+size 4539