Update README.md

README.md

@@ -12,36 +12,44 @@ should probably proofread and complete it, then remove this comment. -->
 
 # Ruckus-PyAssi-13b
 
-This model is a fine-tuned version of [meta-llama/Llama-2-13b-hf](https://huggingface.co/meta-llama/Llama-2-13b-hf) on an unknown dataset.
+This model is a fine-tuned version of [meta-llama/Llama-2-13b-hf](https://huggingface.co/meta-llama/Llama-2-13b-hf) 
+on a 10 000 examples from flytech/llama-python-codes-30k dataset.
 
 ## Model description
 
-More information needed
+Model trained in 4-bit architecture using SFT (Supervised Fine Tuning) and LoRA (Low-Rank Adaptation) methods,
+fine-tuning further is possible.
 
 ## Intended uses & limitations
 
-More information needed
-
-## Training and evaluation data
-
-More information needed
+Code-generation, but as like all Ruckus models
+- Created to serve as an executional layer
+- Rich in Python codes and instructional tasks
+- Specially formatted for chat (see inference)
 
 ## Training procedure
 
+Model was being trained for 13 hours of A6000 single 48GB vRAM GPU
+
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
 - learning_rate: 0.0002
 - train_batch_size: 32
-- eval_batch_size: 32
+- eval_batch_size: 32 * 2
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: constant
 - num_epochs: 5
 
-### Training results
-
+## Inference
 
+- Make sure to format your prompt:
+  - <s>[INST]This is my prompt[/INST]
+ 
+  - <s>[INST]Ruckus, open google[/INST]
+  **Note that <s> is not closed, this is because
+    </s> is used to mark end of AI's answer**
 
 ### Framework versions