初始化项目，由ModelHub XC社区提供模型

Model: AtAndDev/ShortKing-1.4b-v0.1
Source: Original Platform

.gitattributes

@@ -0,0 +1,35 @@
+*.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
+*.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 +1,39 @@
+---
+license: cc-by-nc-4.0
+datasets:
+- vicgalle/alpaca-gpt4
+language:
+- en
+---
+
+## Model Overview
+Model license: cc-by-nc-4.0<br>
+This model is trained based on [EleutherAI/pythia-1.4b-deduped](https://huggingface.co/EleutherAI/pythia-1.4b-deduped) model that is LoRA finetuned on [vicgalle/alpaca-gpt4](https://huggingface.co/datasets/vicgalle/alpaca-gpt4) dataset.<br>
+
+## Prompt Template: `Alpaca`
+```
+<system_prompt>
+
+### Instruction:
+<user_message>
+
+### Response:
+<assistant_response>
+```
+
+## Intended Use
+THIS IS A TEST MODEL, IT IS NOT INTENDED FOR REAL APPLICATIONS BY ANY MEANS. HOWEVER, A NEW MODEL IS COMING IN THE SAME TOPIC.<br>
+This model series will be used for small but intense applications.
+
+## Training Details
+This model took `2:31:23` to train in QLoRA on a single  `T4`  GPU.<br>
+ - *epochs*:  `1`
+ - *train batch size*:  `12`
+ - *eval batch size*:  `12`
+ - *gradient accumulation steps*:  `1`
+ - *maximum gradient normal*:  `0.3`
+ - *learning rate*:  `2e-4`
+ - *weight decay*:  `0.001`
+ - *optimizer*:  `paged_adamw_32bit`
+ - *learning rate schedule*:  `cosine`
+ - *warmup ratio (linear)*:  `0.03`

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "EleutherAI/pythia-1.4b-deduped",
+  "architectures": [
+    "GPTNeoXForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "classifier_dropout": 0.1,
+  "eos_token_id": 0,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.0,
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 2048,
+  "model_type": "gpt_neox",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "rope_scaling": null,
+  "rotary_emb_base": 10000,
+  "rotary_pct": 0.25,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.31.0",
+  "use_cache": true,
+  "use_parallel_residual": true,
+  "vocab_size": 50304
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": 0,
+  "transformers_version": "4.31.0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e8e4261da7e7f3d0f207e472fc5aa7140834305c72b0288eb97f5e7f6cf827b
+size 2829333984

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:89651eb227cb6240fb084d29462474b93c3768f3900220a9177c4635c0d6b6ca
+size 2829404093

special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "pad_token": "<|endoftext|>",
+  "unk_token": "<|endoftext|>"
+}

tokenizer_config.json

@@ -0,0 +1,9 @@
+{
+  "add_prefix_space": false,
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 1000000000000000019884624838656,
+  "tokenizer_class": "GPTNeoXTokenizer",
+  "unk_token": "<|endoftext|>"
+}