Updated.

README.md

@@ -1,5 +1,5 @@
 ---
-title: Llama Manipuri Chatbot
+title: Llama Ask
 emoji: 💬
 colorFrom: yellow
 colorTo: purple
@@ -8,7 +8,7 @@ sdk_version: 5.0.1
 app_file: app.py
 pinned: false
 license: mit
-short_description: This is a Meitei mayek chatbot.
+short_description: Testing context-na
 ---
 
 An example chatbot using [Gradio](https://gradio.app), [`huggingface_hub`](https://huggingface.co/docs/huggingface_hub/v0.22.2/en/index), and the [Hugging Face Inference API](https://huggingface.co/docs/api-inference/index).

app.py

@@ -1,32 +1,81 @@
+import os
+
 import gradio as gr
 from huggingface_hub import InferenceClient
+import transformers
+import torch
+
+from google.cloud import translate_v2 as translate
+# Load the credentials from the secret
+credentials = os.getenv("GOOGLE_APPLICATION_CREDENTIALS_JSON")
+
+# Write the credentials to a temporary file
+credentials_path = "google_credentials.json"
+
+with open(credentials_path, "w") as f:
+    f.write(credentials)
+
+os.environ["GOOGLE_APPLICATION_CREDENTIALS"] = credentials_path
+
+def translate_text(source:str, target: str, text: str) -> dict:
+    """Translates text into the target language.
+
+    Target must be an ISO 639-1 language code.
+    See https://g.co/cloud/translate/v2/translate-reference#supported_languages
+    """
+
+    translate_client = translate.Client()
 
+    if isinstance(text, bytes):
+        text = text.decode("utf-8")
+
+    # Text can also be a sequence of strings, in which case this method
+    # will return a sequence of results for each text.
+    result = translate_client.translate(text, source_language=source,target_language=target)
+    # print(result)
+    # print("Text: {}".format(result["input"]))
+    # print("Translation: {}".format(result["translatedText"]))
+    # # print("Detected source language: {}".format(result["detectedSourceLanguage"]))
+
+    return result
 """
 For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
 """
-client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
+model_id="chuanli11/Llama-3.2-3B-Instruct-uncensored"
+client = InferenceClient(model_id)
 
+pipeline = transformers.pipeline(
+    "text-generation",
+    model=model_id,
+    model_kwargs={"torch_dtype": torch.bfloat16},
+    device_map="auto",
+)
 
 def respond(
     message,
     history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
+    system_message="You are a friendly Chatbot.",
+    max_tokens=2048,
+    temperature=0.7,
+    top_p=0.95
 ):
+    print(f"Input...{message}")
+    tmp_english_out_text = translate_text("mni-Mtei","en",message)["translatedText"]
+
+    print(f"Translated to English...{tmp_english_out_text}")
+
     messages = [{"role": "system", "content": system_message}]
 
     for val in history:
         if val[0]:
-            messages.append({"role": "user", "content": val[0]})
+            messages.append({"role": "user", "content": translate_text("mni-Mtei","en",val[0])["translatedText"]})
         if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
+            messages.append({"role": "assistant", "content": translate_text("mni-Mtei","en",val[1])["translatedText"]})
 
-    messages.append({"role": "user", "content": message})
+    messages.append({"role": "user", "content": tmp_english_out_text})
 
     response = ""
-
+    print(f"Running inference...{messages}")
     for message in client.chat_completion(
         messages,
         max_tokens=max_tokens,
@@ -37,26 +86,33 @@ def respond(
         token = message.choices[0].delta.content
 
         response += token
-        yield response
+        print(f"Response...{response}")
+        print(f"Yield {translate_text('en','mni-Mtei',response)}")
+        yield translate_text("en","mni-Mtei",response)["translatedText"]
 
 
 """
 For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
 """
+# demo = gr.ChatInterface(
+#     respond,
+#     additional_inputs=[
+#         gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
+#         gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
+#         gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
+#         gr.Slider(
+#             minimum=0.1,
+#             maximum=1.0,
+#             value=0.95,
+#             step=0.05,
+#             label="Top-p (nucleus sampling)",
+#         ),
+#     ],
+# )
+
+
 demo = gr.ChatInterface(
-    respond,
-    additional_inputs=[
-        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
-        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
-        gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
-        gr.Slider(
-            minimum=0.1,
-            maximum=1.0,
-            value=0.95,
-            step=0.05,
-            label="Top-p (nucleus sampling)",
-        ),
-    ],
+    respond
 )
 
 

requirements.txt

@@ -1 +1,75 @@
-huggingface_hub==0.25.2
+huggingface_hub==0.25.2
+accelerate==1.2.1
+aiofiles==23.2.1
+annotated-types==0.7.0
+anyio==4.7.0
+cachetools==4.2.4
+certifi==2024.12.14
+charset-normalizer==3.4.0
+click==8.1.7
+fastapi==0.115.6
+ffmpy==0.5.0
+filelock==3.16.1
+fsspec==2024.12.0
+google-api-core==1.34.1
+google-auth==1.35.0
+google-cloud-core==1.7.3
+google-cloud-translate==2.0.1
+googleapis-common-protos==1.66.0
+gradio==5.9.1
+gradio_client==1.5.2
+grpcio==1.68.1
+grpcio-status==1.48.2
+h11==0.14.0
+httpcore==1.0.7
+httpx==0.28.1
+huggingface-hub==0.25.2
+idna==3.10
+Jinja2==3.1.4
+markdown-it-py==3.0.0
+MarkupSafe==2.1.5
+mdurl==0.1.2
+mpmath==1.3.0
+networkx==3.4.2
+numpy==2.2.0
+orjson==3.10.12
+packaging==24.2
+pandas==2.2.3
+pillow==11.0.0
+protobuf==3.20.3
+psutil==6.1.1
+pyasn1==0.6.1
+pyasn1_modules==0.4.1
+pydantic==2.10.4
+pydantic_core==2.27.2
+pydub==0.25.1
+Pygments==2.18.0
+python-dateutil==2.9.0.post0
+python-multipart==0.0.20
+pytz==2024.2
+PyYAML==6.0.2
+regex==2024.11.6
+requests==2.32.3
+rich==13.9.4
+rsa==4.9
+ruff==0.8.4
+safehttpx==0.1.6
+safetensors==0.4.5
+semantic-version==2.10.0
+setuptools==75.6.0
+shellingham==1.5.4
+six==1.17.0
+sniffio==1.3.1
+starlette==0.41.3
+sympy==1.13.1
+tokenizers==0.21.0
+tomlkit==0.13.2
+torch==2.5.1
+tqdm==4.67.1
+transformers==4.47.1
+typer==0.15.1
+typing_extensions==4.12.2
+tzdata==2024.2
+urllib3==2.2.3
+uvicorn==0.34.0
+websockets==14.1