Merge remote-tracking branch 'origin/main'

.github/ISSUE_TEMPLATE/bug_report.yaml

@@ -0,0 +1,63 @@
+name: 🐞 Bug/Help
+description: File a bug/issue
+title: "[BUG/Help] <title>"
+labels: []
+body:
+- type: checkboxes
+  attributes:
+    label: Is there an existing issue for this?
+    description: Please search to see if an issue already exists for the bug you encountered.
+    options:
+    - label: I have searched the existing issues
+      required: true
+- type: textarea
+  attributes:
+    label: Current Behavior
+    description: | 
+      A concise description of what you're experiencing, with screenshot attached if possible.
+      Tip: You can attach images or log files by clicking this area to highlight it and then dragging files in.
+  validations:
+    required: true
+- type: textarea
+  attributes:
+    label: Expected Behavior
+    description: A concise description of what you expected to happen.
+  validations:
+    required: false
+- type: textarea
+  attributes:
+    label: Steps To Reproduce
+    description: Steps to reproduce the behavior.
+    placeholder: |
+      1. In this environment...
+      2. With this config...
+      3. Run '...'
+      4. See error...
+  validations:
+    required: true
+- type: textarea
+  attributes:
+    label: Environment
+    description: |
+      examples:
+        - **OS**: Ubuntu 20.04
+        - **Python**: 3.8
+        - **Transformers**: 4.26.1
+        - **PyTorch**: 1.12
+        - **CUDA Support**: True
+    value: |
+        - OS:
+        - Python:
+        - Transformers:
+        - PyTorch:
+        - CUDA Support (`python -c "import torch; print(torch.cuda.is_available())"`) :
+    render: markdown
+  validations:
+    required: true
+- type: textarea
+  attributes:
+    label: Anything else?
+    description: |
+      Links? References? Anything that will give us more context about the issue you are encountering!
+  validations:
+    required: false

.github/ISSUE_TEMPLATE/config.yml

@@ -0,0 +1 @@
+blank_issues_enabled: false

.github/ISSUE_TEMPLATE/feature_request.yml

@@ -0,0 +1,26 @@
+name: Feature request
+description: Suggest an idea for this project
+title: "[Feature] <title>"
+labels: []
+body:
+- type: textarea
+  attributes:
+    label: Is your feature request related to a problem? Please describe.
+    description: | 
+      A clear and concise description of what the problem is. Ex. I'm always frustrated when [...]
+  validations:
+    required: false
+- type: textarea
+  attributes:
+    label: Solutions
+    description: |
+      Describe the solution you'd like
+      A clear and concise description of what you want to happen.
+  validations:
+    required: true
+- type: textarea
+  attributes:
+    label: Additional context
+    description: Add any other context or screenshots about the feature request here.
+  validations:
+    required: false

api.py

@@ -0,0 +1,56 @@
+from fastapi import FastAPI, Request
+from transformers import AutoTokenizer, AutoModel
+import uvicorn, json, datetime
+import torch
+
+DEVICE = "cuda"
+DEVICE_ID = "0"
+CUDA_DEVICE = f"{DEVICE}:{DEVICE_ID}" if DEVICE_ID else DEVICE
+
+
+def torch_gc():
+    if torch.cuda.is_available():
+        with torch.cuda.device(CUDA_DEVICE):
+            torch.cuda.empty_cache()
+            torch.cuda.ipc_collect()
+
+
+app = FastAPI()
+
+
+@app.post("/")
+async def create_item(request: Request):
+    global model, tokenizer
+    json_post_raw = await request.json()
+    json_post = json.dumps(json_post_raw)
+    json_post_list = json.loads(json_post)
+    prompt = json_post_list.get('prompt')
+    history = json_post_list.get('history')
+    max_length = json_post_list.get('max_length')
+    top_p = json_post_list.get('top_p')
+    temperature = json_post_list.get('temperature')
+    response, history = model.chat(tokenizer,
+                                   prompt,
+                                   history=history,
+                                   max_length=max_length if max_length else 2048,
+                                   top_p=top_p if top_p else 0.7,
+                                   temperature=temperature if temperature else 0.95)
+    now = datetime.datetime.now()
+    time = now.strftime("%Y-%m-%d %H:%M:%S")
+    answer = {
+        "response": response,
+        "history": history,
+        "status": 200,
+        "time": time
+    }
+    log = "[" + time + "] " + '", prompt:"' + prompt + '", response:"' + repr(response) + '"'
+    print(log)
+    torch_gc()
+    return answer
+
+
+if __name__ == '__main__':
+    tokenizer = AutoTokenizer.from_pretrained("THUDM/chatglm2-6b", trust_remote_code=True)
+    model = AutoModel.from_pretrained("THUDM/chatglm2-6b", trust_remote_code=True, device='cuda')
+    model.eval()
+    uvicorn.run(app, host='0.0.0.0', port=8000, workers=1)

requirements.txt

@@ -0,0 +1,8 @@
+protobuf
+transformers==4.27.1
+cpm_kernels
+torch>=2.0
+gradio
+mdtex2html
+sentencepiece
+accelerate