Update app.py

app.py

@@ -1,86 +1,14 @@
-# Copyright 2024 X.AI Corp.
-#
-# Licensed under the Apache License, Version 2.0 (the "License");
-# you may not use this file except in compliance with the License.
-# You may obtain a copy of the License at
-#
-#     http://www.apache.org/licenses/LICENSE-2.0
-#
-# Unless required by applicable law or agreed to in writing, software
-# distributed under the License is distributed on an "AS IS" BASIS,
-# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-# See the License for the specific language governing permissions and
-# limitations under the License.
-
-import logging
-import os
-
 import gradio as gr
-from huggingface_hub import snapshot_download
-
-from model import LanguageModelConfig
-from model import QuantizedWeight8bit as QW8Bit
-from model import TransformerConfig
-from runners import InferenceRunner, ModelRunner, sample_from_model
-
-CKPT_PATH = "./checkpoints/"
-
-
-def main():
-    grok_1_model = LanguageModelConfig(
-        vocab_size=128 * 1024,
-        pad_token=0,
-        eos_token=2,
-        sequence_len=8192,
-        embedding_init_scale=1.0,
-        output_multiplier_scale=0.5773502691896257,
-        embedding_multiplier_scale=78.38367176906169,
-        model=TransformerConfig(
-            emb_size=48 * 128,
-            widening_factor=8,
-            key_size=128,
-            num_q_heads=48,
-            num_kv_heads=8,
-            num_layers=64,
-            attn_output_multiplier=0.08838834764831845,
-            shard_activations=True,
-            # MoE.
-            num_experts=8,
-            num_selected_experts=2,
-            # Activation sharding.
-            data_axis="data",
-            model_axis="model",
-        ),
-    )
-    inference_runner = InferenceRunner(
-        pad_sizes=(1024,),
-        runner=ModelRunner(
-            model=grok_1_model,
-            bs_per_device=0.125,
-            checkpoint_path=CKPT_PATH,
-        ),
-        name="local",
-        load=CKPT_PATH,
-        tokenizer_path="./tokenizer.model",
-        local_mesh_config=(1, 8),
-        between_hosts_config=(1, 1),
-    )
-
-    inference_runner.initialize()
-    gen = inference_runner.run()
-
-    def chatbot_response(message, history):
-        history.append(message)
-        inp = " ".join(history)
-        output = sample_from_model(inference_runner.run(), inp, max_len=100, temperature=0.01)
-        history.append(output)
-        return output
-
-    iface = gr.ChatInterface(fn=chatbot_response, chatbot="Grok-1", history=[], title="Grok-1")
+from transformers import pipeline
 
-    iface.launch()
+pipe = pipeline("text-generation", model="keyfan/grok-1-hf", trust_remote_code=True)
 
+def chatbot_response(message, history):
+    history.append(message)
+    inp = " ".join(history)
+    output = pipe(inp, max_length=100, temperature=0.01)[0]['generated_text']  # Access generated text
+    history.append(output)
+    return output
 
-if __name__ == "__main__":
-    logging.basicConfig(level=logging.INFO)
-    main()
+iface = gr.ChatInterface(fn=chatbot_response, chatbot="Grok-1", history=[], title="Grok-1")
+iface.launch()