初始化项目，由ModelHub XC社区提供模型

Model: andreaskoepf/pythia-1.4b-gpt4all-pretrain
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 +1,58 @@
+---
+license: apache-2.0
+---
+
+wandb: https://wandb.ai/open-assistant/supervised-finetuning/runs/t2adm3wu
+
+checkpoint: 11000 step (2 epochs)
+
+datasets:
+```
+pretrain:
+  weight_decay: 0.01
+  use_custom_sampler: true
+  sort_by_length: false
+  datasets:
+    - joke
+    - webgpt:
+        val_split: 0.1
+    - gpt4all:
+        val_split: 0.01
+    - alpaca:
+        val_split: 0.025
+    - code_alpaca:
+        val_split: 0.05
+    - minimath
+    - humaneval_mbpp_codegen_qa
+    - humaneval_mbpp_testgen_qa
+    - grade_school_math_instructions
+    - recipes
+    - cmu_wiki_qa
+    - oa_wiki_qa_bart_10000row
+    - prosocial_dialogue:
+        fraction: 0.1
+    - explain_prosocial:
+        fraction: 0.05
+```
+
+
+pythia:
+```
+pythia-1.4b-pretrain:
+  dtype: fp16
+  learning_rate: 6e-6
+  model_name: EleutherAI/pythia-1.4b-deduped
+  deepspeed_config: configs/zero_config_pretrain.json
+  weight_decay: 0.0
+  max_length: 2048
+  use_flash_attention: true
+  warmup_steps: 50
+  gradient_checkpointing: false
+  gradient_accumulation_steps: 1
+  per_device_train_batch_size: 16
+  per_device_eval_batch_size: 16
+  num_train_epochs: 2 
+  save_total_limit: 2
+```
+
+command: `deepspeed trainer_sft.py --configs defaults pretrain pythia-1.4b-pretrain --cache_dir .cache/ --output_dir .saved_models/pythia-1.4b-pre --residual_dropout 0.0 --deepspeed`

config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": ".saved_models/pythia-1.4b-pre/checkpoint-11000/",
+  "architectures": [
+    "GPTNeoXForCausalLM"
+  ],
+  "bos_token_id": 0,
+  "eos_token_id": 0,
+  "hidden_act": "gelu",
+  "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,
+  "rotary_emb_base": 10000,
+  "rotary_pct": 0.25,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.28.0.dev0",
+  "use_cache": true,
+  "use_parallel_residual": true,
+  "vocab_size": 50288
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": 0,
+  "transformers_version": "4.28.0.dev0"
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:751508ac2653b685749034237c7f3422e5581867cc94d815cc6ba5bfb329f21e
+size 2929947325

special_tokens_map.json

@@ -0,0 +1,14 @@
+{
+  "additional_special_tokens": [
+    "<|prefix_begin|>",
+    "<|assistant|>",
+    "<|prompter|>",
+    "<|system|>",
+    "<|prefix_end|>"
+  ],
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "pad_token": "<|padding|>",
+  "sep_token": "<|endoftext|>",
+  "unk_token": "<|endoftext|>"
+}

tokenizer_config.json

@@ -0,0 +1,10 @@
+{
+  "add_prefix_space": false,
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 1000000000000000019884624838656,
+  "special_tokens_map_file": "/admin/home-hailey/.cache/huggingface/hub/models--EleutherAI--gpt-neox-20b/snapshots/4e49eadb5d14bd22f314ec3f45b69a87b88c7691/special_tokens_map.json",
+  "tokenizer_class": "GPTNeoXTokenizer",
+  "unk_token": "<|endoftext|>"
+}