Update README.md

README.md

@@ -1,3 +1,166 @@
 ---
 license: cc-by-nc-2.0
+language:
+- en
+- zh
+- ja
+tags:
+- sft
+pipeline_tag: text-generation
+widget:
+- text: >-
+    <|prompter|>What is a meme, and what's the history behind this
+    word?<|endoftext|><|assistant|>
+- text: <|prompter|>What's the Earth total population<|endoftext|><|assistant|>
+- text: >-
+    <|prompter|>Write a story about future of AI
+    development<|endoftext|><|assistant|>
 ---
+
+# Redpajama-3B SFT model
+
+It is based on a RedPajama's 3B that was fine-tuned on human demonstrations 
+of assistant conversations collected through the 
+[https://open-assistant.io/](https://open-assistant.io/) human feedback web 
+app before April 12, 2023. 
+
+## Model Details
+
+- **Developed by:** [Open-Assistant Contributors](https://open-assistant.io/) and [iKala](https://ikala.ai/)
+- **Model type:** Transformer-based Language Model
+- **Language:** English, Chinese, Japanese
+- **Finetuned from:** [togethercomputer/RedPajama-INCITE-Base-3B-v1](https://huggingface.co/togethercomputer/RedPajama-INCITE-Base-3B-v1)
+- **Code:** [Open-Assistant/model/model_training](https://github.com/LAION-AI/Open-Assistant/tree/main/model/model_training)
+
+## Prompting
+
+Two special tokens are used to mark the beginning of user and assistant turns:
+`<|prompter|>` and `<|assistant|>`. Each turn ends with a `<|endoftext|>` token.
+
+Input prompt example:
+```
+<|prompter|>What is a meme, and what's the history behind this word?<|endoftext|><|assistant|>
+```
+The input ends with the `<|assistant|>` token to signal that the model should 
+start generating the assistant reply.
+
+## Benchmark
+
+
+| model  | MMLU  | BBH  | Humaneval @10  |
+|---|---|---|---|
+| ikala/redpajama-3b-chat  |  24.6 | 29.3  |  4.76 |
+| ikala/bloom-zh-chat-3b  | 31.4  | 30.18  | 0.0  |
+| llama-7b (reference)  | 30.9  |  27.6 |  10.3 |
+
+## Dev Details
+
+- base model: [togethercomputer/RedPajama-INCITE-Base-3B-v1](https://huggingface.co/togethercomputer/RedPajama-INCITE-Base-3B-v1)
+- checkpoint: 1 epoch (6000 steps)
+
+command: `deepspeed trainer_sft.py --configs defaults stablelm-7b oasst-mix --cache_dir /home/ubuntu/data_cache --output_dir .saved/stable-lm-7b-1 --num_train_epochs 4 --deepspeed`
+
+data:
+```
+datasets:
+  - wmt2019_zh-en:
+      max_val_set: 1000
+      max_train_set: 20000
+  - ted_trans_en-ja:
+      max_val_set: 1000
+      max_train_set: 20000
+  - ted_trans_zh-ja:
+      max_val_set: 1000
+      max_train_set: 20000
+  - ikala:
+      input_file_path: export_conversation_v4.4.jsonl
+      val_split: 0.05
+  - dolly15k:
+      val_split: 0.05
+  - oasst_export:
+      lang: "bg,ca,cs,da,de,en,es,fr,hr,hu,it,nl,pl,pt,ro,ru,sl,sr,sv,uk,zh,ja,th,ko"
+      input_file_path: 2023-04-12_oasst_release_ready_synth.jsonl.gz
+      val_split: 0.05
+  - joke
+  - gsm8k
+  - webgpt
+```
+
+with internal datasets `ikala` so if you try to reproduce please remove the dataset
+
+redpajama-3b:
+```
+redpajama-3b:
+  dtype: fp16
+  log_dir: "redpajama_3b"
+  learning_rate: 1e-5
+  model_name: saved_models/RedPajama-INCITE-Base-3B-v1
+  output_dir: ikala_v4_3b
+  weight_decay: 0.0
+  max_length: 8196
+  warmup_steps: 2000
+  gradient_checkpointing: true
+  gradient_accumulation_steps: 32
+  per_device_train_batch_size: 1
+  per_device_eval_batch_size: 2
+  eval_steps: 500
+  save_steps: 1000
+  num_train_epochs: 8
+  save_total_limit: 2
+  deepspeed_config: configs/zero3_config_sft.json
+```
+
+zero config:
+```
+{
+  "fp16": {
+    "enabled": "auto",
+    "loss_scale": 0,
+    "loss_scale_window": 1000,
+    "initial_scale_power": 16,
+    "hysteresis": 2,
+    "min_loss_scale": 1
+  },
+  "bf16": {
+    "enabled": "auto"
+  },
+  "optimizer": {
+    "type": "AdamW",
+    "params": {
+      "lr": "auto",
+      "betas": "auto",
+      "eps": "auto",
+      "weight_decay": "auto"
+    }
+  },
+  "scheduler": {
+    "type": "WarmupDecayLR",
+    "params": {
+      "warmup_min_lr": "auto",
+      "warmup_max_lr": "auto",
+      "warmup_num_steps": "auto",
+      "warmup_type": "linear",
+      "total_num_steps": "auto"
+    }
+  },
+  "zero_optimization": {
+    "stage": 3,
+    "overlap_comm": true,
+    "contiguous_gradients": true,
+    "sub_group_size": 1e9,
+    "reduce_bucket_size": "auto",
+    "stage3_prefetch_bucket_size": "auto",
+    "stage3_param_persistence_threshold": "auto",
+    "stage3_max_live_parameters": 1e9,
+    "stage3_max_reuse_distance": 1e9,
+    "stage3_gather_16bit_weights_on_model_save": true
+  },
+  "gradient_accumulation_steps": "auto",
+  "gradient_clipping": "auto",
+  "steps_per_print": 2000,
+  "train_batch_size": "auto",
+  "train_micro_batch_size_per_gpu": "auto",
+  "wall_clock_breakdown": false
+}
+
+```