Duplicate from duxb/chatglm-6b-int4

Co-authored-by: xb <[email protected]>

.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 +1,14 @@
+---
+title: Chatglm 6b
+emoji: 🌖
+colorFrom: blue
+colorTo: yellow
+sdk: gradio
+sdk_version: 3.24.1
+app_file: app.py
+pinned: false
+license: mit
+duplicated_from: duxb/chatglm-6b-int4
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,52 @@
+from transformers import AutoModel, AutoTokenizer
+import gradio as gr
+import json
+model_path = 'THUDM/chatglm-6b-int4-qe'
+tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)
+model = AutoModel.from_pretrained(model_path, trust_remote_code=True).half().float()
+model = model.eval()
+
+MAX_TURNS = 20
+MAX_BOXES = MAX_TURNS * 2
+
+
+def predict(input, max_length, top_p, temperature, history=None, state=None):
+    if state is None:
+        state = []
+    if history is None or history == "":
+        history = state
+    else:
+        history = json.loads(history)
+
+    for response, history in model.stream_chat(tokenizer, input, history, max_length=max_length, top_p=top_p,
+                                               temperature=temperature):
+        updates = []
+        for query, response in history:
+            updates.append(gr.update(visible=True, value=query))
+            updates.append(gr.update(visible=True, value=response))
+        if len(updates) < MAX_BOXES:
+            updates = updates + [gr.Textbox.update(visible=False)] * (MAX_BOXES - len(updates))
+        yield [history] + updates
+
+
+with gr.Blocks() as demo:
+    state = gr.State([])
+    text_boxes = []
+    for i in range(MAX_BOXES):
+        if i % 2 == 0:
+            text_boxes.append(gr.Text(visible=False, label="提问："))
+        else:
+            text_boxes.append(gr.Text(visible=False, label="回复："))
+
+    with gr.Row():
+        with gr.Column(scale=4):
+            txt = gr.Textbox(show_label=False, placeholder="Enter text and press enter", lines=11).style(
+                container=False)
+        with gr.Column(scale=1):
+            max_length = gr.Slider(0, 4096, value=2048, step=1.0, label="Maximum length", interactive=True)
+            top_p = gr.Slider(0, 1, value=0.7, step=0.01, label="Top P", interactive=True)
+            temperature = gr.Slider(0, 1, value=0.95, step=0.01, label="Temperature", interactive=True)
+            history = gr.TextArea(visible=False)
+            button = gr.Button("Generate")
+    button.click(predict, [txt, max_length, top_p, temperature, history, state], [state] + text_boxes, queue=True)
+demo.queue(concurrency_count=10).launch(enable_queue=True, max_threads=2)

requirements.txt

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