Duplicate from netist/slim

Co-authored-by: zheng fu Liu <netist@users.noreply.huggingface.co>

.gitattributes

@@ -0,0 +1,34 @@
+*.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
+*.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 +1,13 @@
+---
+title: Slim
+emoji: 🏢
+colorFrom: gray
+colorTo: purple
+sdk: gradio
+sdk_version: 3.23.0
+app_file: app.py
+pinned: false
+duplicated_from: netist/slim
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,34 @@
+#from transformers import AutoModel, AutoTokenizer
+import gradio as gr
+
+from transformers import AutoModelForSeq2SeqLM
+
+model = AutoModelForSeq2SeqLM.from_pretrained("silver/chatglm-6b-int4-qe-slim")
+
+#tokenizer = AutoTokenizer.from_pretrained("THUDM/chatglm-6b", trust_remote_code=True)
+#model = AutoModel.from_pretrained("THUDM/chatglm-6b", trust_remote_code=True).half().cuda()
+#tokenizer = AutoTokenizer.from_pretrained("silver/chatglm-6b-slim", trust_remote_code=True)
+#model = AutoModel.from_pretrained("silver/chatglm-6b-slim", trust_remote_code=True).half().cuda()
+
+
+model = model.eval()
+
+def predict(input, history=None):
+    if history is None:
+        history = []
+    response, history = model.chat(tokenizer, input, history)
+    return history, history
+
+
+with gr.Blocks() as demo:
+    
+    state = gr.State([])
+    chatbot = gr.Chatbot([], elem_id="chatbot").style(height=400)
+    with gr.Row():
+        with gr.Column(scale=4):
+            txt = gr.Textbox(show_label=False, placeholder="Enter text and press enter").style(container=False)
+        with gr.Column(scale=1):
+            button = gr.Button("Generate")
+    txt.submit(predict, [txt, state], [chatbot, state])
+    button.click(predict, [txt, state], [chatbot, state])
+demo.queue().launch()

requirements.txt

@@ -0,0 +1,4 @@
+torch
+transformers>=4.26.1
+cpm_kernels
+icetk