Attempted to run a small llm

Dockerfile

@@ -42,8 +42,8 @@ RUN --mount=type=cache,target=/root/.cache/pip \
 # COPY requirements.txt .
 # RUN python -m pip install --no-cache-dir -r requirements.txt
 
-# Install ollama
-RUN curl -fsSL https://ollama.com/install.sh | sh
+# # Install ollama
+# RUN curl -fsSL https://ollama.com/install.sh | sh
 
 # # Switch to the non-privileged user to run the application.
 # USER appuser

examples/phi3.py

@@ -0,0 +1,35 @@
+import torch 
+from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline 
+
+torch.random.manual_seed(0) 
+model = AutoModelForCausalLM.from_pretrained( 
+    "microsoft/Phi-3-mini-4k-instruct",  
+    # device_map="auto",  
+    torch_dtype="auto",  
+    trust_remote_code=True,  
+) 
+
+tokenizer = AutoTokenizer.from_pretrained("microsoft/Phi-3-mini-4k-instruct") 
+
+messages = [ 
+    {"role": "system", "content": "You are a helpful AI assistant."}, 
+    {"role": "user", "content": "Can you provide ways to eat combinations of bananas and dragonfruits?"}, 
+    {"role": "assistant", "content": "Sure! Here are some ways to eat bananas and dragonfruits together: 1. Banana and dragonfruit smoothie: Blend bananas and dragonfruits together with some milk and honey. 2. Banana and dragonfruit salad: Mix sliced bananas and dragonfruits together with some lemon juice and honey."}, 
+    {"role": "user", "content": "What about solving an 2x + 3 = 7 equation?"}, 
+] 
+
+pipe = pipeline( 
+    "text-generation", 
+    model=model, 
+    tokenizer=tokenizer, 
+) 
+
+generation_args = { 
+    "max_new_tokens": 500, 
+    "return_full_text": False, 
+    "temperature": 0.0, 
+    "do_sample": False, 
+} 
+
+output = pipe(messages, **generation_args) 
+print(output[0]['generated_text'])

requirements.txt

@@ -2,4 +2,4 @@ chromadb==0.5.5
 pymupdf==1.24.9
 streamlit==1.38.0
 transformers
-torch
+torch