Update README.md

README.md

@@ -20,7 +20,7 @@ General instruction-following llm finetuned from [mistralai/Mistral-7B-v0.1](htt
 
 ### Model Description
 
-This instruction-following llm was built via parameter-efficient QLoRA finetuning of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the first 200k rows of [ehartford/dolphin](https://huggingface.co/datasets/ehartford/dolphin). Finetuning was executed on 1x A100 (40 GB SXM) for roughly 20 hours on Google Colab. **Only** the `peft` adapter weights are included in this model repo, alonside the tokenizer.
+This instruction-following llm was built via parameter-efficient QLoRA finetuning of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the first 5k rows of [ehartford/dolphin](https://huggingface.co/datasets/ehartford/dolphin). Finetuning was executed on 1x A100 (40 GB SXM) for roughly 1 hour on Google Colab. **Only** the `peft` adapter weights are included in this model repo, alonside the tokenizer.
 
 - **Developed by:** Daniel Furman
 - **Model type:** Decoder-only
@@ -32,7 +32,7 @@ This instruction-following llm was built via parameter-efficient QLoRA finetunin
 
 - **Repository:** [github.com/daniel-furman/sft-demos](https://github.com/daniel-furman/sft-demos/blob/main/src/sft/one_gpu/mistral/sft-mistral-7b-instruct-peft.ipynb)
 
-### Evaluation Results
+### Evaluation
 
 | Metric                | Value |
 |-----------------------|-------|
@@ -44,64 +44,21 @@ This instruction-following llm was built via parameter-efficient QLoRA finetunin
 
 We use Eleuther.AI's [Language Model Evaluation Harness](https://github.com/EleutherAI/lm-evaluation-harness) to run the benchmark tests above, the same version as Hugging Face's [Open LLM Leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard).
 
+## Training
 
-## Uses
-
-<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
-
-### Direct Use
-
-<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
-
-[More Information Needed]
-
-### Downstream Use 
-
-<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
-
-[More Information Needed]
-
-### Out-of-Scope Use
-
-<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
-
-[More Information Needed]
-
-## Bias, Risks, and Limitations
-
-<!-- This section is meant to convey both technical and sociotechnical limitations. -->
-
-[More Information Needed]
-
-### Recommendations
-
-<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
-
-Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
-
-## How to Get Started with the Model
-
-Use the code below to get started with the model.
-
-[More Information Needed]
-
-## Training Details
-
-### Training Data
-
-<!-- This should link to a Data Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
-
-[More Information Needed]
-
-
-### Preprocessing 
-
-[More Information Needed]
-
+It took ~1 hour to train 1 epoch on 1x A100.
 
+Prompt format:
+This model (and all my future releases) use [ChatML](https://huggingface.co/docs/transformers/chat_templating#what-template-should-i-use) prompt format.
+```
+<|im_start|>system
+You are a helpful assistant.<|im_end|>
+<|im_start|>user
+{prompt}<|im_end|>
+<|im_start|>assistant
 ### Training Hyperparameters
 
-We used the [`SFTTrainer` from TRL library](https://huggingface.co/docs/trl/main/en/sft_trainer) that gives a wrapper around transformers `Trainer` to easily fine-tune models on instruction based datasets.
+We use the [`SFTTrainer`] (https://huggingface.co/docs/trl/main/en/sft_trainer) from 🤗's TRL package to easily fine-tune llms on instruction-following datasets.
 
 The following `TrainingArguments` config was used:
 
@@ -130,6 +87,12 @@ The following `bitsandbytes` quantization config was used:
 - bnb_4bit_use_double_quant: False
 - bnb_4bit_compute_dtype: bfloat16
 
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
 ### Speeds, Sizes, Times 
 
 | runtime / 50 tokens (sec) | GPU             | attn | torch dtype | VRAM (GB) |