Duplicate from vasilee/flan-t5

.gitattributes

@@ -0,0 +1,35 @@
+*.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
+multilingual-e5-base/tokenizer.json filter=lfs diff=lfs merge=lfs -text

Dockerfile

@@ -0,0 +1,20 @@
+FROM python:3.9
+
+WORKDIR /code
+
+COPY ./* /code
+
+RUN pip install --no-cache-dir --upgrade -r /code/requirements.txt
+
+RUN useradd -m -u 1000 user
+
+USER user
+
+ENV HOME=/home/user \
+	PATH=/home/user/.local/bin:$PATH
+
+WORKDIR $HOME/app
+
+COPY --chown=user . $HOME/app
+
+CMD ["uvicorn", "main:app", "--host", "0.0.0.0", "--port", "7860"]

README.md

@@ -0,0 +1,12 @@
+---
+title: Difussion
+emoji: 💻
+colorFrom: yellow
+colorTo: yellow
+sdk: docker
+pinned: false
+app_port: 7860
+duplicated_from: vasilee/flan-t5
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

ct2fast-flan-alpaca-xl/.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

ct2fast-flan-alpaca-xl/README.md

@@ -0,0 +1,41 @@
+---
+license: apache-2.0
+tags:
+- ctranslate2
+- t5
+---
+# Fast-Inference with Ctranslate2
+Speedup inference by 2x-8x using int8 inference in C++
+
+quantized version of [declare-lab/flan-alpaca-xl](https://huggingface.co/declare-lab/flan-alpaca-xl)
+```bash
+pip install hf_hub_ctranslate2>=1.0.0 ctranslate2>=3.13.0
+```
+
+
+Checkpoint compatible to [ctranslate2](https://github.com/OpenNMT/CTranslate2) and [hf-hub-ctranslate2](https://github.com/michaelfeil/hf-hub-ctranslate2)
+- `compute_type=int8_float16` for `device="cuda"` 
+- `compute_type=int8`  for `device="cpu"`
+
+```python
+from hf_hub_ctranslate2 import TranslatorCT2fromHfHub, GeneratorCT2fromHfHub
+
+model_name = "michaelfeil/ct2fast-flan-alpaca-xl"
+model = TranslatorCT2fromHfHub(
+        # load in int8 on CUDA
+        model_name_or_path=model_name, 
+        device="cuda",
+        compute_type="int8_float16"
+)
+outputs = model.generate(
+    text=["How do you call a fast Flan-ingo?", "Translate to german: How are you doing?"],
+    min_decoding_length=24,
+    max_decoding_length=32,
+    max_input_length=512,
+    beam_size=5
+)
+print(outputs)
+```
+
+# Licence and other remarks:
+This is just a quantized version. Licence conditions are intended to be idential to original huggingface repo.

ct2fast-flan-alpaca-xl/config.json

@@ -0,0 +1,8 @@
+{
+  "add_source_bos": false,
+  "add_source_eos": false,
+  "bos_token": "<pad>",
+  "decoder_start_token": "<pad>",
+  "eos_token": "</s>",
+  "unk_token": "<unk>"
+}

ct2fast-flan-alpaca-xl/model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25ec76282de12f1112ab018bcad38720ba4ffab251c2306189611f744dacd2f2
+size 2855042120

ct2fast-flan-alpaca-xl/model.binZone.Identifier

@@ -0,0 +1,4 @@
+[ZoneTransfer]
+ZoneId=3
+ReferrerUrl=https://huggingface.co/
+HostUrl=https://cdn-lfs.huggingface.co/repos/8a/63/8a63edf3c9d3d772c9237477d38cb19c1a2b7cb517f4b603333bf71596dcb871/25ec76282de12f1112ab018bcad38720ba4ffab251c2306189611f744dacd2f2?response-content-disposition=attachment%3B+filename*%3DUTF-8%27%27model.bin%3B+filename%3D%22model.bin%22%3B&response-content-type=application%2Foctet-stream&Expires=1686473535&Policy=eyJTdGF0ZW1lbnQiOlt7IlJlc291cmNlIjoiaHR0cHM6Ly9jZG4tbGZzLmh1Z2dpbmdmYWNlLmNvL3JlcG9zLzhhLzYzLzhhNjNlZGYzYzlkM2Q3NzJjOTIzNzQ3N2QzOGNiMTljMWEyYjdjYjUxN2Y0YjYwMzMzM2JmNzE1OTZkY2I4NzEvMjVlYzc2MjgyZGUxMmYxMTEyYWIwMThiY2FkMzg3MjBiYTRmZmFiMjUxYzIzMDYxODk2MTFmNzQ0ZGFjZDJmMj9yZXNwb25zZS1jb250ZW50LWRpc3Bvc2l0aW9uPSomcmVzcG9uc2UtY29udGVudC10eXBlPSoiLCJDb25kaXRpb24iOnsiRGF0ZUxlc3NUaGFuIjp7IkFXUzpFcG9jaFRpbWUiOjE2ODY0NzM1MzV9fX1dfQ__&Signature=g%7EwPP6k9jIshth2rOqXNkxa0ZECt%7EpGz5aYLQdsgRLKzEhLGU6yra8hQREUsy-FLXFhUvDi0AFEGG-CyRKLPMVpATb6oxOalBoDr%7ENxMa2cIfbUImF4Mhg-apUCs09y%7Elk16h9Vw5AAoTAbFO-B11%7Ed8V68rPZiylFNuGYSQSK7VSona123gSbeOmMogKpan2LHpyoJCXjvV8S15IPSfEJbXhE8wQoxEitt1NbKcKlH0ViyLfQcn2IoDc1DEWPQr1zuFqhWZug4V0ptN7TxkK8hL1wwUAfm9Bf6o1xZq7xASToKkFsi2N%7EoJ-XikUC-cwUi5UvFy5DQS7VmCTEcohw__&Key-Pair-Id=KVTP0A1DKRTAX

ct2fast-flan-alpaca-xl/tokenizer_config.json

@@ -0,0 +1,112 @@
+{
+    "additional_special_tokens": [
+        "<extra_id_0>",
+        "<extra_id_1>",
+        "<extra_id_2>",
+        "<extra_id_3>",
+        "<extra_id_4>",
+        "<extra_id_5>",
+        "<extra_id_6>",
+        "<extra_id_7>",
+        "<extra_id_8>",
+        "<extra_id_9>",
+        "<extra_id_10>",
+        "<extra_id_11>",
+        "<extra_id_12>",
+        "<extra_id_13>",
+        "<extra_id_14>",
+        "<extra_id_15>",
+        "<extra_id_16>",
+        "<extra_id_17>",
+        "<extra_id_18>",
+        "<extra_id_19>",
+        "<extra_id_20>",
+        "<extra_id_21>",
+        "<extra_id_22>",
+        "<extra_id_23>",
+        "<extra_id_24>",
+        "<extra_id_25>",
+        "<extra_id_26>",
+        "<extra_id_27>",
+        "<extra_id_28>",
+        "<extra_id_29>",
+        "<extra_id_30>",
+        "<extra_id_31>",
+        "<extra_id_32>",
+        "<extra_id_33>",
+        "<extra_id_34>",
+        "<extra_id_35>",
+        "<extra_id_36>",
+        "<extra_id_37>",
+        "<extra_id_38>",
+        "<extra_id_39>",
+        "<extra_id_40>",
+        "<extra_id_41>",
+        "<extra_id_42>",
+        "<extra_id_43>",
+        "<extra_id_44>",
+        "<extra_id_45>",
+        "<extra_id_46>",
+        "<extra_id_47>",
+        "<extra_id_48>",
+        "<extra_id_49>",
+        "<extra_id_50>",
+        "<extra_id_51>",
+        "<extra_id_52>",
+        "<extra_id_53>",
+        "<extra_id_54>",
+        "<extra_id_55>",
+        "<extra_id_56>",
+        "<extra_id_57>",
+        "<extra_id_58>",
+        "<extra_id_59>",
+        "<extra_id_60>",
+        "<extra_id_61>",
+        "<extra_id_62>",
+        "<extra_id_63>",
+        "<extra_id_64>",
+        "<extra_id_65>",
+        "<extra_id_66>",
+        "<extra_id_67>",
+        "<extra_id_68>",
+        "<extra_id_69>",
+        "<extra_id_70>",
+        "<extra_id_71>",
+        "<extra_id_72>",
+        "<extra_id_73>",
+        "<extra_id_74>",
+        "<extra_id_75>",
+        "<extra_id_76>",
+        "<extra_id_77>",
+        "<extra_id_78>",
+        "<extra_id_79>",
+        "<extra_id_80>",
+        "<extra_id_81>",
+        "<extra_id_82>",
+        "<extra_id_83>",
+        "<extra_id_84>",
+        "<extra_id_85>",
+        "<extra_id_86>",
+        "<extra_id_87>",
+        "<extra_id_88>",
+        "<extra_id_89>",
+        "<extra_id_90>",
+        "<extra_id_91>",
+        "<extra_id_92>",
+        "<extra_id_93>",
+        "<extra_id_94>",
+        "<extra_id_95>",
+        "<extra_id_96>",
+        "<extra_id_97>",
+        "<extra_id_98>",
+        "<extra_id_99>"
+    ],
+    "eos_token": "</s>",
+    "extra_ids": 100,
+    "model_max_length": 512,
+    "pad_token": "<pad>",
+    "sp_model_kwargs": {},
+    "special_tokens_map_file": "/home/arthur_huggingface_co/.cache/huggingface/hub/models--google--t5-v1_1-small/snapshots/fb7e6cba609f7bab11c614294bc04f82f613c7b1/special_tokens_map.json",
+    "tokenizer_class": "T5Tokenizer",
+    "unk_token": "<unk>"
+}

ct2fast-flan-alpaca-xxl/.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

ct2fast-flan-alpaca-xxl/README.md

@@ -0,0 +1,38 @@
+---
+license: apache-2.0
+---
+# Fast-Inference with Ctranslate2
+Speedup inference by 2x-8x using int8 inference in C++
+
+quantized version of [declare-lab/flan-alpaca-xxl](https://huggingface.co/declare-lab/flan-alpaca-xxl)
+```bash
+pip install hf_hub_ctranslate2>=1.0.0 ctranslate2>=3.13.0
+```
+
+
+Checkpoint compatible to [ctranslate2](https://github.com/OpenNMT/CTranslate2) and [hf-hub-ctranslate2](https://github.com/michaelfeil/hf-hub-ctranslate2)
+- `compute_type=int8_float16` for `device="cuda"` 
+- `compute_type=int8`  for `device="cpu"`
+
+```python
+from hf_hub_ctranslate2 import TranslatorCT2fromHfHub, GeneratorCT2fromHfHub
+
+model_name = "michaelfeil/ct2fast-flan-alpaca-xxl"
+model = TranslatorCT2fromHfHub(
+        # load in int8 on CUDA
+        model_name_or_path=model_name, 
+        device="cuda",
+        compute_type="int8_float16"
+)
+outputs = model.generate(
+    text=["How do you call a fast Flan-ingo?", "Translate to german: How are you doing?"],
+    min_decoding_length=24,
+    max_decoding_length=32,
+    max_input_length=512,
+    beam_size=5
+)
+print(outputs)
+```
+
+# Licence and other remarks:
+This is just a quantized version. Licence conditions are intended to be idential to original huggingface repo.

ct2fast-flan-alpaca-xxl/config.json

@@ -0,0 +1,8 @@
+{
+  "add_source_bos": false,
+  "add_source_eos": false,
+  "bos_token": "<pad>",
+  "decoder_start_token": "<pad>",
+  "eos_token": "</s>",
+  "unk_token": "<unk>"
+}

ct2fast-flan-alpaca-xxl/model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35c0fd62b8f7b49175264ca887ade36a77587b86fb40ea23bb372fd7c20e4ed9
+size 11145587784

ct2fast-flan-alpaca-xxl/model.binZone.Identifier

@@ -0,0 +1,4 @@
+[ZoneTransfer]
+ZoneId=3
+ReferrerUrl=https://huggingface.co/
+HostUrl=https://cdn-lfs.huggingface.co/repos/0c/e1/0ce18c05aa8fb558cfacca62a2d6625c9eb548ec37d26f2cfaa611e3bf1d1c5b/35c0fd62b8f7b49175264ca887ade36a77587b86fb40ea23bb372fd7c20e4ed9?response-content-disposition=attachment%3B+filename*%3DUTF-8%27%27model.bin%3B+filename%3D%22model.bin%22%3B&response-content-type=application%2Foctet-stream&Expires=1686601840&Policy=eyJTdGF0ZW1lbnQiOlt7IlJlc291cmNlIjoiaHR0cHM6Ly9jZG4tbGZzLmh1Z2dpbmdmYWNlLmNvL3JlcG9zLzBjL2UxLzBjZTE4YzA1YWE4ZmI1NThjZmFjY2E2MmEyZDY2MjVjOWViNTQ4ZWMzN2QyNmYyY2ZhYTYxMWUzYmYxZDFjNWIvMzVjMGZkNjJiOGY3YjQ5MTc1MjY0Y2E4ODdhZGUzNmE3NzU4N2I4NmZiNDBlYTIzYmIzNzJmZDdjMjBlNGVkOT9yZXNwb25zZS1jb250ZW50LWRpc3Bvc2l0aW9uPSomcmVzcG9uc2UtY29udGVudC10eXBlPSoiLCJDb25kaXRpb24iOnsiRGF0ZUxlc3NUaGFuIjp7IkFXUzpFcG9jaFRpbWUiOjE2ODY2MDE4NDB9fX1dfQ__&Signature=QG7QwbKOOe-4aiyQP1tzsZ2rEcmkls8%7EYrccmU5GNJ3Coc1%7ERzfmAvpjUiuFCqNrmEQaBgE8iVwlMW8xmc%7ExViykk9Xcd8riioauLemZ4X792KTeT8tAeraCpWIvqxhW%7E6PIX-eMBEDJfi38b8eD7cINlY71FruKrATpVFlrOXQOKbpkT2KETNop4efmGlmF11MDh5r31yYP-jAsG8P71dfsYSGGLk2bJqOea07RBG0O6DpRojnLfEvbxe8yN65XzEhygJ9ffehjRqlDTmD8F67eWzyZUpvEl69869JMbLkfy7EdPiYfROAH4R%7EMhdYzK6NyzoOVj18ErX83MEEobg__&Key-Pair-Id=KVTP0A1DKRTAX

ct2fast-flan-alpaca-xxl/tokenizer_config.json

@@ -0,0 +1,112 @@
+{
+    "additional_special_tokens": [
+        "<extra_id_0>",
+        "<extra_id_1>",
+        "<extra_id_2>",
+        "<extra_id_3>",
+        "<extra_id_4>",
+        "<extra_id_5>",
+        "<extra_id_6>",
+        "<extra_id_7>",
+        "<extra_id_8>",
+        "<extra_id_9>",
+        "<extra_id_10>",
+        "<extra_id_11>",
+        "<extra_id_12>",
+        "<extra_id_13>",
+        "<extra_id_14>",
+        "<extra_id_15>",
+        "<extra_id_16>",
+        "<extra_id_17>",
+        "<extra_id_18>",
+        "<extra_id_19>",
+        "<extra_id_20>",
+        "<extra_id_21>",
+        "<extra_id_22>",
+        "<extra_id_23>",
+        "<extra_id_24>",
+        "<extra_id_25>",
+        "<extra_id_26>",
+        "<extra_id_27>",
+        "<extra_id_28>",
+        "<extra_id_29>",
+        "<extra_id_30>",
+        "<extra_id_31>",
+        "<extra_id_32>",
+        "<extra_id_33>",
+        "<extra_id_34>",
+        "<extra_id_35>",
+        "<extra_id_36>",
+        "<extra_id_37>",
+        "<extra_id_38>",
+        "<extra_id_39>",
+        "<extra_id_40>",
+        "<extra_id_41>",
+        "<extra_id_42>",
+        "<extra_id_43>",
+        "<extra_id_44>",
+        "<extra_id_45>",
+        "<extra_id_46>",
+        "<extra_id_47>",
+        "<extra_id_48>",
+        "<extra_id_49>",
+        "<extra_id_50>",
+        "<extra_id_51>",
+        "<extra_id_52>",
+        "<extra_id_53>",
+        "<extra_id_54>",
+        "<extra_id_55>",
+        "<extra_id_56>",
+        "<extra_id_57>",
+        "<extra_id_58>",
+        "<extra_id_59>",
+        "<extra_id_60>",
+        "<extra_id_61>",
+        "<extra_id_62>",
+        "<extra_id_63>",
+        "<extra_id_64>",
+        "<extra_id_65>",
+        "<extra_id_66>",
+        "<extra_id_67>",
+        "<extra_id_68>",
+        "<extra_id_69>",
+        "<extra_id_70>",
+        "<extra_id_71>",
+        "<extra_id_72>",
+        "<extra_id_73>",
+        "<extra_id_74>",
+        "<extra_id_75>",
+        "<extra_id_76>",
+        "<extra_id_77>",
+        "<extra_id_78>",
+        "<extra_id_79>",
+        "<extra_id_80>",
+        "<extra_id_81>",
+        "<extra_id_82>",
+        "<extra_id_83>",
+        "<extra_id_84>",
+        "<extra_id_85>",
+        "<extra_id_86>",
+        "<extra_id_87>",
+        "<extra_id_88>",
+        "<extra_id_89>",
+        "<extra_id_90>",
+        "<extra_id_91>",
+        "<extra_id_92>",
+        "<extra_id_93>",
+        "<extra_id_94>",
+        "<extra_id_95>",
+        "<extra_id_96>",
+        "<extra_id_97>",
+        "<extra_id_98>",
+        "<extra_id_99>"
+    ],
+    "eos_token": "</s>",
+    "extra_ids": 100,
+    "model_max_length": 512,
+    "pad_token": "<pad>",
+    "sp_model_kwargs": {},
+    "special_tokens_map_file": "/home/arthur_huggingface_co/.cache/huggingface/hub/models--google--t5-v1_1-small/snapshots/fb7e6cba609f7bab11c614294bc04f82f613c7b1/special_tokens_map.json",
+    "tokenizer_class": "T5Tokenizer",
+    "unk_token": "<unk>"
+}

main.py

@@ -0,0 +1,105 @@
+from torch import Tensor
+from transformers import AutoTokenizer, AutoModel
+from ctranslate2 import Translator
+from typing import Union
+
+from fastapi import FastAPI
+from pydantic import BaseModel
+
+
+def average_pool(last_hidden_states: Tensor,
+                 attention_mask: Tensor) -> Tensor:
+    last_hidden = last_hidden_states.masked_fill(
+        ~attention_mask[..., None].bool(), 0.0)
+    return last_hidden.sum(dim=1) / attention_mask.sum(dim=1)[..., None]
+
+
+# text-ada replacement
+embeddingTokenizer = AutoTokenizer.from_pretrained(
+    './multilingual-e5-base')
+embeddingModel = AutoModel.from_pretrained('./multilingual-e5-base')
+
+# chatGpt replacement
+inferenceTokenizer = AutoTokenizer.from_pretrained(
+    "./ct2fast-flan-alpaca-xl")
+inferenceTranslator = Translator(
+    "./ct2fast-flan-alpaca-xl", compute_type="int8", device="cpu")
+
+
+class EmbeddingRequest(BaseModel):
+    input: Union[str, None] = None
+
+
+class TokensCountRequest(BaseModel):
+    input: Union[str, None] = None
+
+
+class InferenceRequest(BaseModel):
+    input: Union[str, None] = None
+    max_length: Union[int, None] = 0
+
+
+app = FastAPI()
+
+
+@app.get("/")
+async def root():
+    return {"message": "Hello World"}
+
+
+@app.post("/text-embedding")
+async def text_embedding(request: EmbeddingRequest):
+    input = request.input
+
+    # Process the input data
+    batch_dict = embeddingTokenizer([input], max_length=512,
+                                    padding=True, truncation=True, return_tensors='pt')
+    outputs = embeddingModel(**batch_dict)
+    embeddings = average_pool(outputs.last_hidden_state,
+                              batch_dict['attention_mask'])
+
+    # create response
+    return {
+        'embedding': embeddings[0].tolist()
+    }
+
+
+@app.post('/inference')
+async def inference(request: InferenceRequest):
+    input_text = request.input
+    max_length = 256
+    try:
+        max_length = int(request.max_length)
+        max_length = min(1024, max_length)
+    except:
+        pass
+
+    # process request
+    input_tokens = inferenceTokenizer.convert_ids_to_tokens(
+        inferenceTokenizer.encode(input_text))
+
+    results = inferenceTranslator.translate_batch(
+        [input_tokens], beam_size=1, max_input_length=0, max_decoding_length=max_length, num_hypotheses=1, repetition_penalty=1.3, sampling_topk=40, sampling_temperature=0.7, use_vmap=False)
+
+    output_tokens = results[0].hypotheses[0]
+    output_text = inferenceTokenizer.decode(
+        inferenceTokenizer.convert_tokens_to_ids(output_tokens))
+
+    # create response
+    return {
+        'generated_text': output_text
+    }
+
+
+@app.post('/tokens-count')
+async def tokens_count(request: TokensCountRequest):
+    input_text = request.input
+
+    tokens = inferenceTokenizer.convert_ids_to_tokens(
+        inferenceTokenizer.encode(input_text))
+
+    # create response
+    return {
+        'tokens': tokens,
+        'total': len(tokens)
+    }

multilingual-e5-base/config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "intfloat/multilingual-e5-base",
+  "architectures": ["XLMRobertaModel"],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-5,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.29.2",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

multilingual-e5-base/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f061cb7641880f52895cbacab7c4ab39b0844e2e6b73794f2798de460d9fa418
+size 1112242989

multilingual-e5-base/special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

multilingual-e5-base/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62c24cdc13d4c9952d63718d6c9fa4c287974249e16b7ade6d5a85e7bbb75626
+size 17082660

multilingual-e5-base/tokenizer_config.json

@@ -0,0 +1,19 @@
+{
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "__type": "AddedToken",
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}

requirements.txt

@@ -0,0 +1,6 @@
+ctranslate2==3.14.0
+fastapi==0.96.0
+pydantic==1.10.8
+torch==2.0.1
+transformers==4.29.2
+uvicorn[standard]==0.17.*

static/index.html

@@ -0,0 +1,36 @@
+<!DOCTYPE html>
+<html lang="en">
+  <head>
+    <meta charset="UTF-8" />
+    <meta name="viewport" content="width=device-width, initial-scale=1.0" />
+    <title>Fast API 🤗 Space served with Uvicorn</title>
+    <link rel="stylesheet" href="style.css" />
+    <script type="module" src="script.js"></script>
+  </head>
+  <body>
+    <main>
+      <section id="text-gen">
+        <h1>Text generation using Flan T5</h1>
+        <p>
+          Model:
+          <a
+              href="https://huggingface.co/google/flan-t5-small"
+              rel="noreferrer"
+              target="_blank"
+            >google/flan-t5-small</a
+          >
+        </p>
+        <form class="text-gen-form">
+          <label for="text-gen-input">Text prompt</label>
+          <input
+            id="text-gen-input"
+            type="text"
+            value="English: Translate There are many ducks. German:"
+          />
+          <button id="text-gen-submit">Submit</button>
+          <p class="text-gen-output"></p>
+        </form>
+      </section>
+    </main>
+  </body>
+</html>

static/script.js

@@ -0,0 +1,21 @@
+const textGenForm = document.querySelector('.text-gen-form');
+
+const translateText = async (text) => {
+    const inferResponse = await fetch(`infer_t5?input=${text}`);
+    const inferJson = await inferResponse.json();
+
+    return inferJson.output;
+};
+
+textGenForm.addEventListener('submit', async (event) => {
+  event.preventDefault();
+
+  const textGenInput = document.getElementById('text-gen-input');
+  const textGenParagraph = document.querySelector('.text-gen-output');
+
+  try {
+    textGenParagraph.textContent = await translateText(textGenInput.value);
+  } catch (err) {
+    console.error(err);
+  }
+});

static/style.css

@@ -0,0 +1,45 @@
+body {
+  --text: hsl(0 0% 15%);
+  padding: 2.5rem;
+  font-family: sans-serif;
+  color: var(--text);
+}
+
+body.dark-theme {
+  --text: hsl(0 0% 90%);
+  background-color: hsl(223 39% 7%);
+}
+
+main {
+  max-width: 80rem;
+  text-align: center;
+}
+
+section {
+  display: flex;
+  flex-direction: column;
+  align-items: center;
+}
+
+a {
+  color: var(--text);
+}
+
+form {
+  width: 30rem;
+  margin: 0 auto;
+}
+
+input {
+  width: 100%;
+}
+
+button {
+  cursor: pointer;
+}
+
+.text-gen-output {
+  min-height: 1.2rem;
+  margin: 1rem;
+  border: 0.5px solid grey;
+}