inference from automodelforcausallm

.gitignore

@@ -0,0 +1 @@
+.venv/

app.py

@@ -1,3 +1,29 @@
+# import gradio as gr
+
+# gr.load("models/Artigenz/Artigenz-Coder-DS-6.7B").launch()
 import gradio as gr
+import transformers
+
+# Load the model and tokenizer
+model_name = "Artigenz/Artigenz-Coder-DS-6.7B"
+tokenizer = transformers.AutoTokenizer.from_pretrained(model_name)
+model = transformers.AutoModelForCausalLM.from_pretrained(model_name, device_map="auto")
+
+# Function to generate responses from the model
+def generate_response(input_text):
+    inputs = tokenizer(input_text, return_tensors="pt")
+    outputs = model.generate(**inputs, max_new_tokens=512)
+    response = tokenizer.decode(outputs[0], skip_special_tokens=True)
+    return response
+
+# Define the Gradio interface
+iface = gr.Interface(
+    fn=generate_response, 
+    inputs="text", 
+    outputs="text",
+    title="Artigenz Coder - 6.7B Model",
+    description="A code-generation model from Artigenz. Enter a prompt to get code suggestions or completions."
+)
 
-gr.load("models/Artigenz/Artigenz-Coder-DS-6.7B").launch()
+# Launch the interface
+iface.launch()

requirements.txt

@@ -1 +1,17 @@
-huggingface_hub==0.25.2
+certifi==2024.8.30
+charset-normalizer==3.4.0
+filelock==3.16.1
+fsspec==2024.10.0
+huggingface-hub==0.25.2
+idna==3.10
+numpy==2.1.3
+packaging==24.1
+PyYAML==6.0.2
+regex==2024.11.6
+requests==2.32.3
+safetensors==0.4.5
+tokenizers==0.20.3
+tqdm==4.67.0
+transformers==4.46.2
+typing_extensions==4.12.2
+urllib3==2.2.3