Update README.md

README.md

@@ -1,16 +1,18 @@
 ---
 license: llama3
 base_model: meta-llama/Meta-Llama-3-8B-Instruct
+language:
+- en
 ---
-# Llama3-KALE-LM-Chem 8B
+# Llama3-KALE-LM-Chem-8B
 
 ## Introduction
 
-We are thrilled to present Llama3-KALE-LM-Chem 8B, the newest version of our Llama3-KALE-LM-Chem model, which embodies nearly half a year of innovation.
+We are thrilled to present Llama3-KALE-LM-Chem 8B, our first open-source KALE-LM, which specializes in chemistry.
 
 ## Training Details
 
-We have continue pre-trained the model with a large amount of data and post-trained it using supervised fine-tuning.
+We have continually pre-trained the model with a large amount of data and post-trained it through supervised fine-tuning.
 
 ## Benchmarks
 
@@ -24,12 +26,11 @@ We have continue pre-trained the model with a large amount of data and post-trai
 | ChemDFM | 44.44 | 58.11 | 45.60 | 86.70 | 7.61 | 11.49 |
 | ChemLLM-7B-Chat | 34.16 | 61.79 | 48.39 | 94.00 | 29.66 | 39.17 |
 | ChemLLM-7B-Chat-1.5-SFT | 42.75 | 63.56 | 49.63 | **95.10** | 14.96 | 19.61 |
-| **KALE-LM** | **52.40** | **68.74** | **53.83** | 91.50 | **67.50** | **78.37** |
-| **KALE-LM-INSTRUCT** | **57.01** | 68.09 | **54.83** | 91.60 | 57.53 | 64.16 |
+| **Llama3-KALE-LM-Chem-8B** | **52.40** | **68.74** | **53.83** | 91.50 | **67.50** | **78.37** |
 
-### In-House Benchmarks
+#### ChemBench Details (Evaluated By OpenCompass)
 
-| Models | NC | PP | M2C | C2M | PP | Retro | YP | TP | SP | Average |
+| Models | NC | PP | M2C | C2M | PP | RS | YP | TP | SP | Average |
 | ------ | ------ | ------ | ------ | ------ | ------ | ------ | ------ | ------ | ------ | ------ |
 | GPT-3.5 | 46.93 | 56.98 | 85.28 | 38.25 | 43.67 | 42.33 | 30.33 | 42.57 | 38 | 47.15 |
 | GPT-4 | 54.82 | 65.02 | 92.64 | 52.88 | 62.67 | 52.67 | 42.33 | 24.75 | 35.67 | 53.72 |
@@ -38,8 +39,7 @@ We have continue pre-trained the model with a large amount of data and post-trai
 | ChemDFM | 36.92 | 55.57 | 83.95 | 42.00 | 40.00 | 37.33 | 39.00 | 33.17 | 32.00 | 44.44 |
 | ChemLLM-7B-Chat | 41.05 | 29.76 | 85.28 | 26.12 | 26.00 | 24.00 | 20.00 | 24.26 | 31.00 | 34.16 |
 | ChemLLM-7B-Chat-1.5-SFT | 50.06 | 49.51 | 85.28 | 38.75 | 38.00 | 26.67 | 28.33 | 31.68 | 33.67 | 42.44 |
-| OURMODEL | 63.58 | 58.39 | 92.98 | 44.50 | 48.67 | 38.33 | 46.33 | 44.55 | 34.33 | 52.41 |
-| OURMODELINSTRUCT | 61.33 | 43.44 | 90.30 | 53.62 | 72.67 | 53.67 | 46.00 | 47.03 | 45.00 | 57.01 |
+| Llama3-KALE-LM-Chem-8B | 63.58 | 58.39 | 92.98 | 44.50 | 48.67 | 38.33 | 46.33 | 44.55 | 34.33 | 52.41 |
 
 ## Quick Start 
 
@@ -49,7 +49,7 @@ device = "cuda" # the device to load the model onto
 
 model = AutoModelForCausalLM.from_pretrained(
     "USTC-KnowledgeComputingLab/Llama3-KALE-LM-Chem-8B",
-    torch_dtype="auto",
+    torch_dtype=torch.float16,
     device_map="auto"
 )
 tokenizer = AutoTokenizer.from_pretrained("USTC-KnowledgeComputingLab/Llama3-KALE-LM-Chem-8B")