Update README.md

README.md

@@ -29,7 +29,8 @@ model-index:
       value: 63.57
       name: normalized accuracy
     source:
-      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=rxavier/Taurus-7B-1.0
+      url: >-
+        https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=rxavier/Taurus-7B-1.0
       name: Open LLM Leaderboard
   - task:
       type: text-generation
@@ -45,7 +46,8 @@ model-index:
       value: 83.64
       name: normalized accuracy
     source:
-      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=rxavier/Taurus-7B-1.0
+      url: >-
+        https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=rxavier/Taurus-7B-1.0
       name: Open LLM Leaderboard
   - task:
       type: text-generation
@@ -62,7 +64,8 @@ model-index:
       value: 63.5
       name: accuracy
     source:
-      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=rxavier/Taurus-7B-1.0
+      url: >-
+        https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=rxavier/Taurus-7B-1.0
       name: Open LLM Leaderboard
   - task:
       type: text-generation
@@ -78,7 +81,8 @@ model-index:
     - type: mc2
       value: 50.21
     source:
-      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=rxavier/Taurus-7B-1.0
+      url: >-
+        https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=rxavier/Taurus-7B-1.0
       name: Open LLM Leaderboard
   - task:
       type: text-generation
@@ -95,7 +99,8 @@ model-index:
       value: 78.14
       name: accuracy
     source:
-      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=rxavier/Taurus-7B-1.0
+      url: >-
+        https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=rxavier/Taurus-7B-1.0
       name: Open LLM Leaderboard
   - task:
       type: text-generation
@@ -112,8 +117,10 @@ model-index:
       value: 59.36
       name: accuracy
     source:
-      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=rxavier/Taurus-7B-1.0
+      url: >-
+        https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=rxavier/Taurus-7B-1.0
       name: Open LLM Leaderboard
+library_name: transformers
 ---
 
 # Taurus 7B 1.0
@@ -155,23 +162,24 @@ User message<|im_end|>
 
 ```python
 import torch
-from transformers import AutoModelForCausalLM, AutoTokenizer, GeneratorConfig
+from transformers import AutoModelForCausalLM, AutoTokenizer, GenerationConfig
 
 
 model_id = "rxavier/Taurus-7B-1.0"
 model = AutoModelForCausalLM.from_pretrained(
-    model_path,
-    torch_dtype=torch.bfloat16,
+    model_id,
+    torch_dtype=torch.bfloat16, #torch.float16 for older GPUs
+    device_map="auto", # Requires having accelerate installed, useful in places like Colab with limited VRAM
 )
-tokenizer = AutoTokenizer.from_pretrained(model_path)
+tokenizer = AutoTokenizer.from_pretrained(model_id)
 generation_config = GenerationConfig(
-                bos_token_id=tok.bos_token_id,
-                eos_token_id=tok.eos_token_id,
-                pad_token_id=tok.pad_token_id,
+                bos_token_id=tokenizer.bos_token_id,
+                eos_token_id=tokenizer.eos_token_id,
+                pad_token_id=tokenizer.pad_token_id,
             )
 
-prompt = "Give me latex formulas for extended euler equations"
 system_message = "You are an expert in economics with PhD level knowledge. You are helpful, give thorough and clear explanations, and use equations and formulas where needed."
+prompt = "Give me latex formulas for extended euler equations"
 
 messages = [{"role": "system",
              "content": system_message},
@@ -180,7 +188,7 @@ messages = [{"role": "system",
 tokens = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt").to("cuda")
 
 with torch.no_grad():
-    outputs = model.generate(inputs=tokens, generation_config=generation_config)
+    outputs = model.generate(inputs=tokens, generation_config=generation_config, max_length=512)
 print(tokenizer.decode(outputs["sequences"].cpu().tolist()[0]))
 ```