Update app.py

app.py

@@ -1,32 +1,23 @@
-# Code to inference Hermes with HF Transformers
-# Requires pytorch, transformers, bitsandbytes, sentencepiece, protobuf, and flash-attn packages
-
-import torch
-from transformers import AutoTokenizer, AutoModelForCausalLM
-from transformers import LlamaTokenizer, MixtralForCausalLM
-import bitsandbytes, flash_attn
-
-tokenizer = LlamaTokenizer.from_pretrained('NousResearch/Nous-Hermes-2-Mistral-7B-DPO-GGUF', trust_remote_code=True)
-model = MixtralForCausalLM.from_pretrained(
-    "NousResearch/Nous-Hermes-2-Mistral-7B-DPO-GGUF",
-    torch_dtype=torch.float16,
-    device_map="auto",
-    load_in_8bit=False,
-    load_in_4bit=True,
-    use_flash_attention_2=True
-)
-
-prompts = [
-    """<|im_start|>system
-You are a sentient, superintelligent artificial general intelligence, here to teach and assist me.<|im_end|>
-<|im_start|>user
-Write a short story about Goku discovering kirby has teamed up with Majin Buu to destroy the world.<|im_end|>
-<|im_start|>assistant""",
-    ]
-
-for chat in prompts:
-    print(chat)
-    input_ids = tokenizer(chat, return_tensors="pt").input_ids.to("cuda")
-    generated_ids = model.generate(input_ids, max_new_tokens=750, temperature=0.8, repetition_penalty=1.1, do_sample=True, eos_token_id=tokenizer.eos_token_id)
-    response = tokenizer.decode(generated_ids[0][input_ids.shape[-1]:], skip_special_tokens=True, clean_up_tokenization_space=True)
-    print(f"Response: {response}")
+from ctransformers import AutoModelForCausalLM
+
+ 
+# Set gpu_layers to the number of layers to offload to GPU. Set to 0 if no GPU acceleration is available on your system.
+#llm = AutoModelForCausalLM.from_pretrained("TheBloke/Mistral-7B-OpenOrca-GGUF", model_file="mistral-7b-openorca.Q4_K_M.gguf", model_type="mistral", gpu_layers=50)
+
+
+#llm = AutoModelForCausalLM.from_pretrained("Open-Orca/Mistral-7B-OpenOrca",gpu_layers=0, max_new_tokens = 1000, context_length = 10000)
+
+llm = AutoModelForCausalLM.from_pretrained("NousResearch/Nous-Hermes-2-Mistral-7B-DPO.Q4_0.gguf",gpu_layers=0, max_new_tokens = 500, context_length = 2048)
+# llm = AutoModelForCausalLM.from_pretrained("/home/ubuntu/.cache/gpt4all/Nous-Hermes-2-Mistral-7B-DPO.Q4_0.gguf",gpu_layers=0, max_new_tokens = 500, context_length = 6000)
+
+
+
+
+
+#llm = AutoModelForCausalLM.from_pretrained("TheBloke/zephyr-7B-beta-GGUF",model_file="zephyr-7b-beta.Q5_K_M.gguf", model_type="mistral",gpu_layers=0, max_new_tokens = 1000, context_length = 6000)
+
+contenuto="che ore sono?"
+print(contenuto)
+
+if __name__ == '__main__':
+    print(llm(contenuto,threads=16,temperature=0.7,top_k=40,top_p=0.4,repetition_penalty=1.18))