update plot with new naming & reformat the code

README.md

@@ -42,19 +42,23 @@ from transformers import AutoModelForCausalLM, AutoTokenizer
 
 tokenizer = AutoTokenizer.from_pretrained('stabilityai/stablelm-zephyr-3b')
 model = AutoModelForCausalLM.from_pretrained(
-  'stabilityai/stablelm-zephyr-3b',
-  trust_remote_code=True,
-  device_map="auto"
+    'stabilityai/stablelm-zephyr-3b',
+    trust_remote_code=True,
+    device_map="auto"
 )
 
 prompt = [{'role': 'user', 'content': 'List 3 synonyms for the word "tiny"'}]
-inputs = tokenizer.apply_chat_template(prompt, add_generation_prompt=True, return_tensors='pt')
+inputs = tokenizer.apply_chat_template(
+    prompt,
+    add_generation_prompt=True,
+    return_tensors='pt'
+)
 
 tokens = model.generate(
-  inputs.to(model.device),
-  max_new_tokens=1024,
-  temperature=0.8,
-  do_sample=True
+    inputs.to(model.device),
+    max_new_tokens=1024,
+    temperature=0.8,
+    do_sample=True
 )
 
 print(tokenizer.decode(tokens[0], skip_special_tokens=False))
@@ -87,14 +91,15 @@ The dataset is comprised of a mixture of open datasets large-scale datasets avai
 
 ## Performance
 
-### MT Bench and Alpaca Bench
+### MT-Bench and Alpaca Bench
 
-<img src="https://cdn-uploads.huggingface.co/production/uploads/6310474ca119d49bc1eb0d80/LXOYt_ulqXSneMENUjI1O.png" alt="mt_bench_plot" width="600"/>
+<img src="https://cdn-uploads.huggingface.co/production/uploads/6310474ca119d49bc1eb0d80/jwpbBHzdCkHm0rMvPUVxC.png" alt="mt_bench_plot" width="600"/>
 
 | Model | Size | Alignment | MT-Bench (score) | AlpacaEval (win rate %) |
 |-------------|-----|----|---------------|--------------|
 | **StableLM Zephyr 3B** 🪁 | 3B | DPO | 6.64 | 76.00 |
 | Stable Zephyr (SFT only) | 3B | SFT | 6.04 | 71.15 | 
+| Capybara v1.9 | 3B | dSFT | 5.94 | - |
 | MPT-Chat |  7B |dSFT |5.42| -|
 | Xwin-LMv0.1 | 7B| dPPO| 6.19| 87.83|
 | Mistral-Instructv0.1 | 7B|  - | 6.84 |-|