init

.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,12 @@
+---
+title: harpertoken llama3.1-8b
+emoji: 👋
+colorFrom: gray
+colorTo: indigo
+sdk: gradio
+sdk_version: 6.14.0
+app_file: app.py
+pinned: true
+license: mit
+short_description: llama3.1-8b chat with cerebras inference
+---

app.py

@@ -0,0 +1,76 @@
+import gradio as gr
+import os
+import re
+from dotenv import load_dotenv
+from cerebras.cloud.sdk import Cerebras
+
+# Load environment variables
+load_dotenv()
+
+client = Cerebras(
+    api_key=os.environ.get("CEREBRAS_API_KEY")
+)
+
+def clean_response(text):
+    lines = []
+    for line in text.splitlines():
+        # Remove bullets (*, #, •, -) at line start
+        line = re.sub(r"^\s*[*#•\-]+\s*", "", line)
+        # Remove markdown bold
+        line = re.sub(r"\*\*(.*?)\*\*", r"\1", line)
+        line = re.sub(r"__(.*?)__", r"\1", line)
+        lines.append(line)
+    return "\n".join(lines)
+
+def chat(user_message, history):
+    try:
+        stream = client.chat.completions.create(
+            messages=[
+                {"role": "system", "content": "You are a helpful assistant."},
+                {"role": "user", "content": user_message}
+            ],
+            model="llama3.1-8b",
+            stream=True,
+            max_completion_tokens=65536,
+            temperature=1,
+            top_p=1
+        )
+
+        response_text = ""
+        for chunk in stream:
+            if chunk.choices[0].delta.content:
+                response_text += chunk.choices[0].delta.content
+
+        response_text = clean_response(response_text)
+
+        history = history or []
+        history.append({"role": "user", "content": user_message})
+        history.append({"role": "assistant", "content": response_text})
+        return history
+
+    except Exception as e:
+        history = history or []
+        history.append({"role": "user", "content": user_message})
+        history.append({"role": "assistant", "content": f"Error: {str(e)}"})
+        return history
+
+with gr.Blocks() as demo:
+    gr.Markdown("## Chat")
+
+    chatbot = gr.Chatbot(
+        label="Conversation",
+        height=600
+    )
+
+    with gr.Row():
+        msg = gr.Textbox(
+            label="Ask something",
+            placeholder="Type your prompt and press Enter",
+            scale=4
+        )
+        clear = gr.Button("Clear")
+
+    msg.submit(chat, [msg, chatbot], chatbot)
+    clear.click(lambda: [], None, chatbot)
+
+demo.launch()

requirements.txt

@@ -0,0 +1,3 @@
+gradio[oauth,mcp]==6.14.0
+cerebras-cloud-sdk
+python-dotenv