Update README.md

README.md

@@ -21,10 +21,13 @@ When evaluated on a subset of AGIEval (Nous), this model compares very well with
 
 Tess-v2.5 model was initiated with the base weights of Qwen2-72B. It was then fine-tuned with the Tess-v2.5 dataset, using Axolotl as the training framework. Most of Tess models follow a common fine-tuning methodology: low learning rates, low number of epochs, and uses very high quality and diverse data. This model was fine-tuned on a 4xA100 VM on Microsoft Azure for 4 days. The model has not been aligned with RLHF or DPO.
 
-The author believes that model's capabilities seem to come primariliy from the pre-training process. This is the foundation for every fine-tune of Tess models.
+The author believes that model's capabilities seem to come primariliy from the pre-training process. This is the foundation for every fine-tune of Tess models, and preserving the entropy of the base models is of paramount to the author.
 
 # Evaluation Results
 
+Tess-v2.5 model is an overall well balanced model. Complete evaluation tables can be accessed here: [Google Spreadsheet](https://docs.google.com/spreadsheets/d/1k0BIKux_DpuoTPwFCTMBzczw17kbpxofigHF_0w2LGw/edit?usp=sharing)
+
+
 ## MMLU (Massive Multitask Language Understanding)
 ![MMLU_open](https://huggingface.co/migtissera/Tess-v2.5-Qwen2-72B/resolve/main/Figures/mmlu_open_models.png)
 
@@ -34,5 +37,72 @@ The author believes that model's capabilities seem to come primariliy from the p
 ![AGIEval](https://huggingface.co/migtissera/Tess-v2.5-Qwen2-72B/resolve/main/Figures/AGIEval.png)
 
 
-
+# Sample code to run inference
+
+```python
+import torch, json
+from transformers import AutoModelForCausalLM, AutoTokenizer
+from stop_word import StopWordCriteria
+
+model_path = "migtissera/Tess-v2.5-Qwen2-72B"
+output_file_path = "/home/migel/conversations.jsonl"
+
+model = AutoModelForCausalLM.from_pretrained(
+    model_path,
+    torch_dtype=torch.float16,
+    device_map="auto",
+    load_in_4bit=False,
+    trust_remote_code=True,
+)
+
+tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)
+
+terminators = [
+    tokenizer.convert_tokens_to_ids("<|im_end|>")
+]
+
+def generate_text(instruction):
+    tokens = tokenizer.encode(instruction)
+    tokens = torch.LongTensor(tokens).unsqueeze(0)
+    tokens = tokens.to("cuda")
+
+    instance = {
+        "input_ids": tokens,
+        "top_p": 1.0,
+        "temperature": 0.75,
+        "generate_len": 1024,
+        "top_k": 50,
+    }
+
+    length = len(tokens[0])
+    with torch.no_grad():
+        rest = model.generate(
+            input_ids=tokens,
+            max_length=length + instance["generate_len"],
+            use_cache=True,
+            do_sample=True,
+            top_p=instance["top_p"],
+            temperature=instance["temperature"],
+            top_k=instance["top_k"],
+            num_return_sequences=1,
+            pad_token_id=tokenizer.eos_token_id,
+            eos_token_id=terminators,
+        )
+    output = rest[0][length:]
+    string = tokenizer.decode(output, skip_special_tokens=True)
+    return f"{string}"
+
+conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""
+
+while True:
+    user_input = input("You: ")
+    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
+    answer = generate_text(llm_prompt)
+    print(answer)
+    conversation = f"{llm_prompt}{answer}\n"
+    json_data = {"prompt": user_input, "answer": answer}
+
+    with open(output_file_path, "a") as output_file:
+        output_file.write(json.dumps(json_data) + "\n")
+```