Update README.md

README.md

@@ -1,25 +1,55 @@
 ---
 license: apache-2.0
+language:
+- en
+- de
+- es
+- fr
+tags:
+- sft
+inference: false
+datasets:
+- OpenAssistant/oasst1
+- databricks/databricks-dolly-15k
 ---
 
-Supervised fine-tuning of falcon40b with a mix of OASST top-2 threads and synthetic instruction datasets. Exported at end of 2nd epoch.
+# Open-Assistant Falcon 40B SFT MIX Model
 
+This model is a fine-tuning of TII's [Falcon 40B](https://huggingface.co/tiiuae/falcon-40b) LLM. 
+It was trained on a mixture of OASST top-2 threads (exported on July 2, 2023), Dolly-15k and synthetic instruction datasets (see dataset configuration below).
 
-- base model: [tiiuae/falcon-40b](https://huggingface.co/tiiuae/falcon-40b)
-- [sampling report](https://open-assistant.github.io/oasst-model-eval/?f=https%3A%2F%2Fraw.githubusercontent.com%2FOpen-Assistant%2Foasst-model-eval%2Fmain%2Fsampling_reports%2Fchat-gpt%2F2023-04-11_gpt-3.5-turbo_lottery.json%0Ahttps%3A%2F%2Fraw.githubusercontent.com%2FOpen-Assistant%2Foasst-model-eval%2Fmain%2Fsampling_reports%2Foasst-sft%2F2023-06-05_OpenAssistant_falcon-40b-sft-mix-1226_sampling_noprefix2.json), [multiligual-60](https://open-assistant.github.io/oasst-model-eval/?f=https%3A%2F%2Fraw.githubusercontent.com%2FOpen-Assistant%2Foasst-model-eval%2Fmain%2Fsampling_reports%2Foasst-sft%2F2023-06-05_OpenAssistant_falcon-40b-sft-mix-1226_multilingual_noprefix2.json)
-- wandb: https://wandb.ai/open-assistant/public-sft/runs/feplc450
-- checkpoint: 1226 steps
+## Model Details
 
+- **Finetuned from:** [tiiuae/falcon-40b]((https://huggingface.co/tiiuae/falcon-40b)
+- **Model type:** Causal decoder-only transformer language model
+- **Language:** English, German, Spanish, French (and limited capabilities in Italian, Portuguese, Polish, Dutch, Romanian, Czech, Swedish);
+- **Demo:** [Continuations for 250 random prompts](https://open-assistant.github.io/oasst-model-eval/?f=https%3A%2F%2Fraw.githubusercontent.com%2FOpen-Assistant%2Foasst-model-eval%2Fmain%2Fsampling_reports%2Fchat-gpt%2F2023-04-11_gpt-3.5-turbo_lottery.json%0Ahttps%3A%2F%2Fraw.githubusercontent.com%2FOpen-Assistant%2Foasst-model-eval%2Fmain%2Fsampling_reports%2Foasst-sft%2F2023-06-05_OpenAssistant_falcon-40b-sft-mix-1226_sampling_noprefix2.json), [multiligual-60](https://open-assistant.github.io/oasst-model-eval/?f=https%3A%2F%2Fraw.githubusercontent.com%2FOpen-Assistant%2Foasst-model-eval%2Fmain%2Fsampling_reports%2Foasst-sft%2F2023-06-05_OpenAssistant_falcon-40b-sft-mix-1226_multilingual_noprefix2.json)
+- **Eval results:** [ilm-eval](https://tju01.github.io/ilm-eval/)
+- **Weights & Biases**: [Training log](https://wandb.ai/open-assistant/public-sft/runs/feplc450) (checkpoint: 1226 steps)
+- **License:** Apache 2.0
+- **Contact:** [Open-Assistant Discord](https://ykilcher.com/open-assistant-discord)
+
+## 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.
+
+## Configuration Details
 
 Model:
 ```
 falcon-40b:
   dtype: bf16
-  log_dir: "falcon_log_40b"
   learning_rate: 1e-5
   model_name: "tiiuae/falcon-40b"
   deepspeed_config: configs/zero3_config_falcon.json
-  output_dir: falcon
   weight_decay: 0.0
   max_length: 2048
   warmup_steps: 20
@@ -28,14 +58,13 @@ falcon-40b:
   per_device_train_batch_size: 18
   per_device_eval_batch_size: 10
   eval_steps: 120
-  #save_steps: 80
+  save_strategy: steps
+  save_steps: 613
   num_train_epochs: 8
   save_total_limit: 4
   use_flash_attention: false
   residual_dropout: 0.3
   residual_dropout_lima: true
-  sort_by_length: false
-  save_strategy: steps
 ```
 
 
@@ -49,8 +78,6 @@ sft9-stage2:
   # grade_school_math_instructions: 100.00% (8351)
   # dolly15k: 100.00% (14250)
 
-  save_strategy: steps # epoch seems not to work, gets stuck with DS 0.9.1
-  save_steps: 613
   use_custom_sampler: true
   datasets:
     - oasst_export: