Update README.md

README.md

@@ -4,13 +4,13 @@ language:
 - en
 ---
 # Model Card
-SAM (Small Agentic Model), a 7B model that demonstrates impressive reasoning abilities despite its smaller size. SAM-7B has outperformed existing SoTA models on various reasoning benchmarks, including GSM-8K and ARC-C.
+SAM (Small Agentic Model), a 7B model that demonstrates impressive reasoning abilities despite its smaller size. SAM-7B has outperformed existing SoTA models on various reasoning benchmarks, including GSM8k and ARC-C.
 
 For full details of this model please read our [release blog post](https://superagi.com/introducing-sam-small-agentic-model/).
 
 # Key Contributions
-- SAM-7B outperforms GPT 3.5, Orca, and several other 70B models on multiple reasoning benchmarks, including ARC-C and GSM-8K.
-- Interestingly, despite being trained on a 97% smaller dataset, SAM-7B surpasses Orca-13B on GSM-8K.
+- SAM-7B outperforms GPT 3.5, Orca, and several other 70B models on multiple reasoning benchmarks, including ARC-C and GSM8k.
+- Interestingly, despite being trained on a 97% smaller dataset, SAM-7B surpasses Orca-13B on GSM8k.
 - All responses in our fine-tuning dataset are generated by open-source models without any assistance from state-of-the-art models like GPT-3.5 or GPT-4.
 
 ## Training
@@ -40,6 +40,8 @@ These benchmarks show that our model has improved reasoning as compared to orca
 Despite being smaller in size, we show better multi-hop reasoning, as shown below:
 <img src = "https://superagi.com/wp-content/uploads/2023/12/image-932.png" alt="Reasoning Benchmark Performance" width="700"> 
 
+Note: Temperature=0.3 is the suggested for optimal performance
+
 ## Run the model
 
 ```python
@@ -50,10 +52,10 @@ tokenizer = AutoTokenizer.from_pretrained(model_id)
 
 model = AutoModelForCausalLM.from_pretrained(model_id)
 
-text = "Hello my name is"
+text = "Can elephants fly?"
 inputs = tokenizer(text, return_tensors="pt")
 
-outputs = model.generate(**inputs, max_new_tokens=20)
+outputs = model.generate(**inputs, max_new_tokens=200)
 print(tokenizer.decode(outputs[0], skip_special_tokens=True))
 ```
 
@@ -61,7 +63,7 @@ print(tokenizer.decode(outputs[0], skip_special_tokens=True))
 ## Limitations
 
 SAM is a demonstration that better reasoning can be induced using less but high-quality data generated using OpenSource LLMs.
-The model is not suitable for conversations and Q&A, it performs better in task breakdown and reasoning only.
+The model is not suitable for conversations and simple Q&A, it performs better in task breakdown and reasoning only.
 It does not have any moderation mechanisms. Therefore, the model is not suitable for production usage as it doesn't have guardrails for toxicity, societal bias, and language limitations. We would love to collaborate with the community to build safer and better models.
 
 ## The SuperAGI AI Team