Manually update README.md

README.md

@@ -15,26 +15,48 @@ model-index:
   results: []
 ---
 
-<!-- This model card has been generated automatically according to the information the Trainer had access to. You
-should probably proofread and complete it, then remove this comment. -->
-
 # zephyr-7b-sft-qlora
 
-This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the HuggingFaceH4/ultrachat_200k dataset.
+This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mist\
+ral-7B-v0.1) on the HuggingFaceH4/ultrachat_200k dataset.
 It achieves the following results on the evaluation set:
 - Loss: 0.9523
 
 ## Model description
 
-More information needed
+QLoRA SFT via
+```
+# Step 1 - SFT
+ACCELERATE_LOG_LEVEL=info accelerate launch --config_file recipes/accelerate_configs/multi_gpu.yaml --n\
+um_processes=1 scripts/run_sft.py recipes/zephyr-7b-beta/sft/config_qlora.yaml --load_in_4bit=true
+```
+see https://github.com/huggingface/alignment-handbook/blob/main/recipes/zephyr-7b-beta/README.md
 
 ## Intended uses & limitations
 
-More information needed
+```
+chat_template: "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + me\
+ssage['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['c\
+ontent'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n'  + message['co\
+ntent'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }\
+}\n{% endif %}\n{% endfor %}"
+```
+
+see https://github.com/huggingface/alignment-handbook/blob/main/recipes/zephyr-7b-beta/sft/config_qlora\
+.yaml
 
 ## Training and evaluation data
 
-More information needed
+```
+dataset_mixer:
+  HuggingFaceH4/ultrachat_200k: 1.0
+dataset_splits:
+- train_sft
+- test_sft
+```
+
+see https://github.com/huggingface/alignment-handbook/blob/main/recipes/zephyr-7b-beta/sft/config_qlora\
+.yaml
 
 ## Training procedure