Duplicate from awinml/api_vicuna-openblas-3

.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: Api Vicuna -2 (OpenBlas)
+emoji: 👩‍💻
+colorFrom: blue
+colorTo: green
+sdk: gradio
+sdk_version: 3.33.1
+python_version: 3.9.13
+app_file: app.py
+pinned: false
+license: mit
+duplicated_from: awinml/api_vicuna-openblas-3
+---

app.py

@@ -0,0 +1,29 @@
+import os
+os.system('CMAKE_ARGS="-DLLAMA_OPENBLAS=on" FORCE_CMAKE=1 pip install llama-cpp-python==0.1.50')
+
+import gradio as gr
+from llama_cpp import Llama
+
+
+llm = Llama(model_path="eachadea_ggml-vic7b-q4_0.bin", n_ctx=2048, n_batch=126)
+
+def generate_text(prompt):
+    output = llm(prompt, max_tokens=468, temperature=0.1, top_p=0.5, echo=False, stop=["#"])
+    output_text = output['choices'][0]['text']
+    return output_text
+
+description = "Vicuna-7B-GPTQ-4bit-128g.GGML, max_tokens=468, temperature=0.1, top_p=0.5"
+
+examples = [
+    ["What is the capital of France? ", "The capital of France is Paris."],
+    ["Who wrote the novel 'Pride and Prejudice'?", "The novel 'Pride and Prejudice' was written by Jane Austen."],
+    ["What is the square root of 64?", "The square root of 64 is 8."]
+]
+
+gradio_interface = gr.Interface(
+  fn=generate_text,
+  inputs="text",
+  outputs="text",
+  title="Vicuna API",
+)
+gradio_interface.launch()

eachadea_ggml-vic7b-q4_0.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67efec973a81151a55e55f8e747b455354979492978b2f9f22a342c6d841e6b7
+size 4212859520

eachadea_ggml-vic7b-q5_1.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:377c40e9a5d9efc933e8530930c863737637b5e13a7c2ab55334e96564deea54
+size 5055128192

requirements.txt

@@ -0,0 +1 @@
+#llama-cpp-python==0.1.50

vicuna-AlekseyKorshuk-7B-GPTQ-4bit-128g.GGML.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9015f602eecad368ad8b2765006b9825b22630a6119fdd374a828f964045e31
+size 5382824576