:fire: revert manual chat templating for reflection now that it's working in featherless backend.

This reverts commit ae83cd880af013682c84eb953bb9954683ae5607.

app.py

@@ -2,12 +2,6 @@ from openai import OpenAI
 import gradio as gr
 import os
 import json
-import functools
-import random
-import datetime
-from transformers import AutoTokenizer
-
-reflection_tokenizer = AutoTokenizer.from_pretrained("mattshumer/Reflection-Llama-3.1-70B")
 
 api_key = os.environ.get('FEATHERLESS_API_KEY')
 client = OpenAI(
@@ -24,51 +18,23 @@ def respond(message, history, model):
         history_openai_format.append({"role": "assistant", "content":assistant})
     history_openai_format.append({"role": "user", "content": message})
 
+    response = client.chat.completions.create(
+        model=model,
+        messages= history_openai_format,
+        temperature=1.0,
+        stream=True,
+        max_tokens=2000,
+        extra_headers={
+            'HTTP-Referer': 'https://huggingface.co/spaces/featherless-ai/try-this-model',
+            'X-Title': "HF's missing inference widget"
+        }
+    )
 
-    if model == "mattshumer/Reflection-Llama-3.1-70B":
-        # chat/completions not working for this model;
-        # apply chat template locally
-        response = client.completions.create(
-            model=model,
-            prompt=reflection_tokenizer.apply_chat_template(history_openai_format, tokenize=False),
-            temperature=1.0,
-            stream=True,
-            max_tokens=2000,
-            extra_headers={
-                'HTTP-Referer': 'https://huggingface.co/spaces/featherless-ai/try-this-model',
-                'X-Title': "HF's missing inference widget"
-            }
-        )
-
-        # debugger_ran = False
-        partial_message = ""
-        for chunk in response:
-            # if not debugger_ran:
-            #     import code
-            #     code.InteractiveConsole(locals=locals()).interact()
-            #     debugger_ran = True
-            if chunk.choices[0].text is not None:
-                partial_message = partial_message + chunk.choices[0].text
-                prefix_to_strip = "<|start_header_id|>assistant<|end_header_id|>\n\n"
-                yield partial_message[len(prefix_to_strip):]
-    else:
-        response = client.chat.completions.create(
-            model=model,
-            messages= history_openai_format,
-            temperature=1.0,
-            stream=True,
-            max_tokens=2000,
-            extra_headers={
-                'HTTP-Referer': 'https://huggingface.co/spaces/featherless-ai/try-this-model',
-                'X-Title': "HF's missing inference widget"
-            }
-        )
-
-        partial_message = ""
-        for chunk in response:
-            if chunk.choices[0].delta.content is not None:
-                  partial_message = partial_message + chunk.choices[0].delta.content
-                  yield partial_message
+    partial_message = ""
+    for chunk in response:
+        if chunk.choices[0].delta.content is not None:
+              partial_message = partial_message + chunk.choices[0].delta.content
+              yield partial_message
 
 logo = open('./logo.svg').read()
 

requirements.txt

@@ -1,205 +1 @@
-accelerate==0.32.1
-aiofiles==23.2.1
-aiohttp==3.9.5
-aiosignal==1.3.1
-altair==5.3.0
-annotated-types==0.7.0
-anyio==4.4.0
-appnope==0.1.4
-argon2-cffi==23.1.0
-argon2-cffi-bindings==21.2.0
-arrow==1.3.0
-asttokens==2.4.1
-async-lru==2.0.4
-attrs==23.2.0
-Babel==2.15.0
-beautifulsoup4==4.12.3
-bleach==6.1.0
-certifi==2024.6.2
-cffi==1.16.0
-charset-normalizer==3.3.2
-click==8.1.7
-click-default-group==1.2.4
-comm==0.2.2
-contourpy==1.2.1
-cycler==0.12.1
-dataclasses-json==0.6.7
-debugpy==1.8.2
-decorator==5.1.1
-defusedxml==0.7.1
-distro==1.9.0
-dnspython==2.6.1
-email_validator==2.2.0
-executing==2.0.1
-fastapi==0.111.0
-fastapi-cli==0.0.4
-fastjsonschema==2.20.0
-ffmpy==0.3.2
-filelock==3.15.4
-fonttools==4.53.1
-fqdn==1.5.1
-frozenlist==1.4.1
-fschat==0.2.36
-fsspec==2024.6.1
-gradio==4.37.2
-gradio_client==1.0.2
-greenlet==3.0.3
-h11==0.14.0
-httpcore==1.0.5
-httptools==0.6.1
-httpx==0.27.0
-huggingface-hub==0.23.4
-idna==3.7
-importlib_resources==6.4.0
-ipykernel==6.29.5
-ipython==8.26.0
-ipywidgets==8.1.3
-isoduration==20.11.0
-jedi==0.19.1
-Jinja2==3.1.4
-json5==0.9.25
-jsonpatch==1.33
-jsonpointer==3.0.0
-jsonschema==4.22.0
-jsonschema-specifications==2023.12.1
-jupyter==1.0.0
-jupyter-console==6.6.3
-jupyter-events==0.10.0
-jupyter-lsp==2.2.5
-jupyter_client==8.6.2
-jupyter_core==5.7.2
-jupyter_server==2.14.1
-jupyter_server_terminals==0.5.3
-jupyterlab==4.2.3
-jupyterlab_pygments==0.3.0
-jupyterlab_server==2.27.2
-jupyterlab_widgets==3.0.11
-kiwisolver==1.4.5
-langchain==0.2.5
-langchain-community==0.2.5
-langchain-core==0.2.9
-langchain-openai==0.1.8
-langchain-text-splitters==0.2.1
-langsmith==0.1.81
-latex2mathml==3.77.0
-llm==0.14
-llm-openrouter==0.2
-markdown-it-py==3.0.0
-markdown2==2.5.0
-MarkupSafe==2.1.5
-marshmallow==3.21.3
-matplotlib==3.9.1
-matplotlib-inline==0.1.7
-mdurl==0.1.2
-mistune==3.0.2
-mpmath==1.3.0
-multidict==6.0.5
-mypy-extensions==1.0.0
-nbclient==0.10.0
-nbconvert==7.16.4
-nbformat==5.10.4
-nest-asyncio==1.6.0
-networkx==3.3
-nh3==0.2.18
-notebook==7.2.1
-notebook_shim==0.2.4
-numpy==1.26.4
-openai==1.35.2
-orjson==3.10.5
-overrides==7.7.0
-packaging==24.1
-pandas==2.2.2
-pandocfilters==1.5.1
-parso==0.8.4
-peft==0.11.1
-pexpect==4.9.0
-pillow==10.4.0
-platformdirs==4.2.2
-plotly==5.22.0
-pluggy==1.5.0
-prometheus_client==0.20.0
-prompt_toolkit==3.0.47
-protobuf==5.27.2
-psutil==6.0.0
-psycopg==3.2.1
-ptyprocess==0.7.0
-pure-eval==0.2.2
-pycparser==2.22
-pydantic==2.7.4
-pydantic-settings==2.3.4
-pydantic_core==2.18.4
-pydub==0.25.1
-Pygments==2.18.0
-pymongo==4.8.0
-pyparsing==3.1.2
-python-dateutil==2.9.0.post0
-python-dotenv==1.0.1
-python-json-logger==2.0.7
-python-multipart==0.0.9
-python-ulid==2.7.0
-pytz==2024.1
-PyYAML==6.0.1
-pyzmq==26.0.3
-qtconsole==5.5.2
-QtPy==2.4.1
-referencing==0.35.1
-regex==2024.5.15
-requests==2.32.3
-rfc3339-validator==0.1.4
-rfc3986-validator==0.1.1
-rich==13.7.1
-rpds-py==0.18.1
-ruff==0.5.1
-safetensors==0.4.3
-semantic-version==2.10.0
-Send2Trash==1.8.3
-sentencepiece==0.2.0
-setuptools==70.1.1
-shellingham==1.5.4
-shortuuid==1.0.13
-six==1.16.0
-sniffio==1.3.1
-soupsieve==2.5
-SQLAlchemy==2.0.31
-sqlite-fts4==1.0.3
-sqlite-migrate==0.1b0
-sqlite-utils==3.36
-sseclient==0.0.27
-sseclient-py==1.8.0
-stack-data==0.6.3
-starlette==0.37.2
-stripe==10.8.0
-svgwrite==1.4.3
-sympy==1.13.0
-tabulate==0.9.0
-tenacity==8.4.1
-terminado==0.18.1
-tiktoken==0.7.0
-tinycss2==1.3.0
-tokenizers==0.19.1
-tomlkit==0.12.0
-toolz==0.12.1
-torch==2.2.2
-tornado==6.4.1
-tqdm==4.66.4
-traitlets==5.14.3
-transformers==4.42.4
-typer==0.12.3
-types-python-dateutil==2.9.0.20240316
-typing-inspect==0.9.0
-typing_extensions==4.12.2
-tzdata==2024.1
-ujson==5.10.0
-uri-template==1.3.0
-urllib3==2.2.2
-uvicorn==0.30.1
-uvloop==0.19.0
-watchfiles==0.22.0
-wavedrom==2.0.3.post3
-wcwidth==0.2.13
-webcolors==24.6.0
-webencodings==0.5.1
-websocket-client==1.8.0
-websockets==11.0.3
-widgetsnbextension==4.0.11
-yarl==1.9.4
+openai