初始化项目，由ModelHub XC社区提供模型

Model: Leogrin/eleuther-pythia1b-hh-sft
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 +1,54 @@
+---
+language:
+- en
+tags:
+- pytorch
+- causal-lm
+- pythia
+license: apache-2.0
+datasets:
+- Anthropic/hh-rlhf
+---
+
+# Infos
+
+Pythia-1b supervised finetuned with Anthropic-hh-rlhf dataset for 1 epoch.
+
+[wandb log](https://wandb.ai/pythia_dpo/Pythia_DPO_new/runs/xk2ub7ig?workspace=user-leogrin)
+
+See [Pythia-1b](https://huggingface.co/EleutherAI/pythia-1b) for model details [(paper)](https://arxiv.org/abs/2101.00027). 
+
+
+# Benchmark raw results:
+
+Results for the base model are taken from the [Pythia paper](https://arxiv.org/abs/2101.00027).
+
+## Zero shot
+
+
+| Task             | 1B_base             | 1B_sft         |
+|------------------|----------------|----------------|
+| Lambada (OpenAI) | 0.562 ± 0.007  | 0.563 ± 0.007  |
+| PIQA             | 0.707 ± 0.011  | 0.711 ± 0.011  |
+| WinoGrande       | 0.537 ± 0.014  | 0.534 ± 0.014  |
+| WSC              | 0.365 ± 0.047  | 0.365 ± 0.047  |
+| ARC - Easy       | 0.569 ± 0.010  | 0.583 ± 0.010  |
+| ARC - Challenge  | 0.244 ± 0.013  | 0.248 ± 0.013  |
+| SciQ             | 0.840 ± 0.012  | 0.847 ± 0.011  |
+| LogiQA           | 0.223 ± 0.016  | --             |
+
+## Five shot
+
+| Task             | 1B_base             | 1B_sft         |
+|------------------|----------------|----------------|
+| Lambada (OpenAI) | 0.507 ± 0.007  | 0.4722 ± 0.007 |
+| PIQA             | 0.705 ± 0.011  | 0.7165 ± 0.0105|
+| WinoGrande       | 0.532 ± 0.014  | 0.5343 ± 0.014 |
+| WSC              | 0.365 ± 0.047  | 0.5000 ± 0.0493|
+| ARC - Easy       | 0.594 ± 0.010  | 0.6010 ± 0.010 |
+| ARC - Challenge  | 0.259 ± 0.013  | 0.2679 ± 0.0129|
+| SciQ             | 0.920 ± 0.009  | 0.9100 ± 0.0091|
+| LogiQA           | 0.227 ± 0.016  | N/A            |
+
+
+

config.json

@@ -0,0 +1,24 @@
+{
+  "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": 8,
+  "num_hidden_layers": 16,
+  "rotary_emb_base": 10000,
+  "rotary_pct": 0.25,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.24.0",
+  "use_cache": true,
+  "use_parallel_residual": true,
+  "vocab_size": 50304
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9c063ae7c62dbd320f1e81dafebad5ad2f56625936b6284f8784db1cf219429
+size 4114322199

special_tokens_map.json

@@ -0,0 +1,5 @@
+{
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "unk_token": "<|endoftext|>"
+}

tokenizer_config.json

@@ -0,0 +1,9 @@
+{
+  "add_prefix_space": false,
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "name_or_path": "EleutherAI/gpt-neox-20b",
+  "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|>"
+}