Update README.md

README.md

@@ -24,13 +24,13 @@ Trying to get better at medical Q & A
 
 
 - **Developed by:** [Tonic](https://huggingface.co/Tonic)
-- **Shared by [optional]:** [Tonic](https://huggingface.co/Tonic)
+- **Shared by :** [Tonic](https://huggingface.co/Tonic)
 - **Model type:** Mistral Fine-Tune
 - **Language(s) (NLP):** English
 - **License:** MIT2.0
-- **Finetuned from model [optional]:** [mistralai/Mistral-7B-v0.1](https://huggingface.com/Mistralai/Mistral-7B-v0.1)
+- **Finetuned from model :** [mistralai/Mistral-7B-v0.1](https://huggingface.com/Mistralai/Mistral-7B-v0.1)
 
-### Model Sources [optional]
+### Model Sources
 
 
 - **Repository:** [Tonic/mistralmed](https://huggingface.co/Tonic/mistralmed)
@@ -45,7 +45,7 @@ This model can be used the same way you normally use mistral
 
 This model can do better in medical question and answer scenarios.
 
-### Downstream Use [optional]
+### Downstream Use
 
 This model is intended to be further fine tuned.
 
@@ -63,18 +63,16 @@ Users (both direct and downstream) should be made aware of the risks, biases and
 
 Use the code below to get started with the model.
 
-[Tonic/MistralMED_Chat](https://huggingface.co/Tonic/MistralMED_Chat)
+[pseudolab/MistralMED_Chat](https://huggingface.co/spaces/pseudolab/MistralMED_Chat)
 
 ```python
-from transformers import AutoTokenizer, MistralForCausalLM
-import torch
-import gradio as gr
-import random
-from textwrap import wrap
 from transformers import AutoConfig, AutoTokenizer, AutoModelForSeq2SeqLM, AutoModelForCausalLM, MistralForCausalLM
 from peft import PeftModel, PeftConfig
 import torch
 import gradio as gr
+import random
+from textwrap import wrap
+
 
 # Functions to Wrap the Prompt Correctly
 def wrap_text(text, width=90):
@@ -195,14 +193,16 @@ iface.launch()
 
 ### Training Procedure 
 
+```json
 Dataset({
     features: ['qtype', 'Question', 'Answer'],
     num_rows: 16407
 })
-
+```
 
 #### Preprocessing [optional]
 
+```json
 MistralForCausalLM(
   (model): MistralModel(
     (embed_tokens): Embedding(32000, 4096)
@@ -229,11 +229,12 @@ MistralForCausalLM(
   )
   (lm_head): Linear(in_features=4096, out_features=32000, bias=False)
 )
-
+```
 
 #### Training Hyperparameters
 
 - **Training regime:** 
+```json
 config = LoraConfig(
     r=8,
     lora_alpha=16,
@@ -251,6 +252,7 @@ config = LoraConfig(
     lora_dropout=0.05,  # Conventional
     task_type="CAUSAL_LM",
 )
+```
 
 #### Speeds, Sizes, Times [optional]
 
@@ -260,7 +262,6 @@ config = LoraConfig(
 
 ## Environmental Impact
 
-<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
 
 Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
 
@@ -300,6 +301,7 @@ Carbon emissions can be estimated using the [Machine Learning Impact calculator]
 
 ### Model Architecture and Objective
 
+```json
 PeftModelForCausalLM(
   (base_model): LoraModel(
     (model): MistralForCausalLM(
@@ -434,6 +436,8 @@ PeftModelForCausalLM(
     )
   )
 )
+```
+
 #### Hardware
 
 A100