{} {} '
- imgs = [valid_tools_info[tool]['avatar'] for tool in tools_chosen if valid_tools_info[tool]['avatar'] != None]
- imgs = ' '.join([img_template.format(img, img, tool) for img, tool in zip(imgs, tools_chosen)])
- return [gr.update(value='' + imgs + '', visible=True), gr.update(visible=True)]
-
-def answer_by_tools(question, tools_chosen, model_chosen):
- global return_msg
- return_msg += [(question, None), (None, '...')]
- yield [gr.update(visible=True, value=return_msg), gr.update(), gr.update()]
- OPENAI_API_KEY = os.environ.get('OPENAI_API_KEY', '')
-
- if len(tools_chosen) == 0: # if there is no tools chosen, we use all todo (TODO: What if the pool is too large.)
- tools_chosen = list(valid_tools_info.keys())
-
- if len(tools_chosen) == 1:
- answerer = STQuestionAnswerer(OPENAI_API_KEY.strip(), stream_output=True, llm=model_chosen)
- agent_executor = answerer.load_tools(tools_chosen[0], valid_tools_info[tools_chosen[0]],
- prompt_type="react-with-tool-description", return_intermediate_steps=True)
- else:
- answerer = MTQuestionAnswerer(OPENAI_API_KEY.strip(),
- load_valid_tools({k: tools_mappings[k] for k in tools_chosen}),
- stream_output=True, llm=model_chosen)
-
- agent_executor = answerer.build_runner()
-
- global chat_history
- chat_history += "Question: " + question + "\n"
- question = chat_history
- for inter in agent_executor(question):
- if isinstance(inter, AgentFinish): continue
- result_str = []
- return_msg.pop()
- if isinstance(inter, dict):
- result_str.append("Answer: {}".format(inter['output']))
- chat_history += "Answer:" + inter['output'] + "\n"
- result_str.append("...")
- else:
- try:
- not_observation = inter[0].log
- except:
- print(inter[0])
- not_observation = inter[0]
- if not not_observation.startswith('Thought:'):
- not_observation = "Thought: " + not_observation
- chat_history += not_observation
- not_observation = not_observation.replace('Thought:', 'Thought: ')
- not_observation = not_observation.replace('Action:', 'Action: ')
- not_observation = not_observation.replace('Action Input:', 'Action Input: ')
- result_str.append("{}".format(not_observation))
- result_str.append("Action output:\n{}".format(inter[1]))
- chat_history += "\nAction output:" + inter[1] + "\n"
- result_str.append("...")
- return_msg += [(None, result) for result in result_str]
- yield [gr.update(visible=True, value=return_msg), gr.update(), gr.update()]
- return_msg.pop()
- if return_msg[-1][1].startswith("Answer: "):
- return_msg[-1] = (return_msg[-1][0], return_msg[-1][1].replace("Answer: ",
- "Final Answer: "))
- yield [gr.update(visible=True, value=return_msg), gr.update(visible=True), gr.update(visible=False)]
-
-
-def retrieve(tools_search):
- if tools_search == "":
- return gr.update(choices=all_tools_list)
- else:
- url = "http://127.0.0.1:8079/retrieve"
- param = {
- "query": tools_search
- }
- response = requests.post(url, json=param)
- result = response.json()
- retrieved_tools = result["tools"]
- return gr.update(choices=retrieved_tools)
-
-
-def clear_retrieve():
- return [gr.update(value=""), gr.update(choices=all_tools_list)]
-
-
-def clear_history():
- global return_msg
- global chat_history
- return_msg = []
- chat_history = ""
- yield gr.update(visible=True, value=return_msg)
-
-def create_interface():
-
- title = 'Swarm Models'
-
- # Password authentication
- auth = []
- if shared.args.gradio_auth:
- auth.extend(x.strip() for x in shared.args.gradio_auth.strip('"').replace('\n', '').split(',') if x.strip())
- if shared.args.gradio_auth_path:
- with open(shared.args.gradio_auth_path, 'r', encoding="utf8") as file:
- auth.extend(x.strip() for line in file for x in line.split(',') if x.strip())
- auth = [tuple(cred.split(':')) for cred in auth]
-
- # Import the extensions and execute their setup() functions
- if shared.args.extensions is not None and len(shared.args.extensions) > 0:
- extensions_module.load_extensions()
-
- # Force some events to be triggered on page load
- shared.persistent_interface_state.update({
- 'loader': shared.args.loader or 'Transformers',
- 'mode': shared.settings['mode'],
- 'character_menu': shared.args.character or shared.settings['character'],
- 'instruction_template': shared.settings['instruction_template'],
- 'prompt_menu-default': shared.settings['prompt-default'],
- 'prompt_menu-notebook': shared.settings['prompt-notebook'],
- 'filter_by_loader': shared.args.loader or 'All'
- })
-
- if Path("cache/pfp_character.png").exists():
- Path("cache/pfp_character.png").unlink()
-
- # css/js strings
- css = ui.css
- js = ui.js
- css += apply_extensions('css')
- js += apply_extensions('js')
-
- # Interface state elements
- shared.input_elements = ui.list_interface_input_elements()
-
-
-
- # with gr.Blocks() as demo:
- with gr.Blocks(css=css, analytics_enabled=False, title=title, theme=ui.theme) as shared.gradio['interface']:
- with gr.Row():
- with gr.Column(scale=14):
- gr.Markdown("")
- with gr.Column(scale=1):
- gr.Image(show_label=False, show_download_button=False, value="images/swarmslogobanner.png")
-
- with gr.Tab("Models"):
- create_interface()
-
- with gr.Tab("Key setting"):
- OPENAI_API_KEY = gr.Textbox(label="OpenAI API KEY:", placeholder="sk-...", type="text")
- WOLFRAMALPH_APP_ID = gr.Textbox(label="Wolframalpha app id:", placeholder="Key to use wlframalpha", type="text")
- WEATHER_API_KEYS = gr.Textbox(label="Weather api key:", placeholder="Key to use weather api", type="text")
- BING_SUBSCRIPT_KEY = gr.Textbox(label="Bing subscript key:", placeholder="Key to use bing search", type="text")
- ALPHA_VANTAGE_KEY = gr.Textbox(label="Stock api key:", placeholder="Key to use stock api", type="text")
- BING_MAP_KEY = gr.Textbox(label="Bing map key:", placeholder="Key to use bing map", type="text")
- BAIDU_TRANSLATE_KEY = gr.Textbox(label="Baidu translation key:", placeholder="Key to use baidu translation", type="text")
- RAPIDAPI_KEY = gr.Textbox(label="Rapidapi key:", placeholder="Key to use zillow, airbnb and job search", type="text")
- SERPER_API_KEY = gr.Textbox(label="Serper key:", placeholder="Key to use google serper and google scholar", type="text")
- GPLACES_API_KEY = gr.Textbox(label="Google places key:", placeholder="Key to use google places", type="text")
- SCENEX_API_KEY = gr.Textbox(label="Scenex api key:", placeholder="Key to use sceneXplain", type="text")
- STEAMSHIP_API_KEY = gr.Textbox(label="Steamship api key:", placeholder="Key to use image generation", type="text")
- HUGGINGFACE_API_KEY = gr.Textbox(label="Huggingface api key:", placeholder="Key to use models in huggingface hub", type="text")
- AMADEUS_ID = gr.Textbox(label="Amadeus id:", placeholder="Id to use Amadeus", type="text")
- AMADEUS_KEY = gr.Textbox(label="Amadeus key:", placeholder="Key to use Amadeus", type="text")
- key_set_btn = gr.Button(value="Set keys!")
-
-
- with gr.Tab("Chat with Tool"):
- with gr.Row():
- with gr.Column(scale=4):
- with gr.Row():
- with gr.Column(scale=0.85):
- txt = gr.Textbox(show_label=False, placeholder="Question here. Use Shift+Enter to add new line.",
- lines=1).style(container=False)
- with gr.Column(scale=0.15, min_width=0):
- buttonChat = gr.Button("Chat")
-
- chatbot = gr.Chatbot(show_label=False, visible=True).style(height=600)
- buttonClear = gr.Button("Clear History")
- buttonStop = gr.Button("Stop", visible=False)
-
- with gr.Column(scale=1):
- model_chosen = gr.Dropdown(
- list(available_models), value=DEFAULTMODEL, multiselect=False, label="Model provided",
- info="Choose the model to solve your question, Default means ChatGPT."
- )
- with gr.Row():
- tools_search = gr.Textbox(
- lines=1,
- label="Tools Search",
- placeholder="Please input some text to search tools.",
- )
- buttonSearch = gr.Button("Reset search condition")
- tools_chosen = gr.CheckboxGroup(
- choices=all_tools_list,
- value=["chemical-prop"],
- label="Tools provided",
- info="Choose the tools to solve your question.",
- )
-
- key_set_btn.click(fn=set_environ, inputs=[
- OPENAI_API_KEY,
- WOLFRAMALPH_APP_ID,
- WEATHER_API_KEYS,
- BING_SUBSCRIPT_KEY,
- ALPHA_VANTAGE_KEY,
- BING_MAP_KEY,
- BAIDU_TRANSLATE_KEY,
- RAPIDAPI_KEY,
- SERPER_API_KEY,
- GPLACES_API_KEY,
- SCENEX_API_KEY,
- STEAMSHIP_API_KEY,
- HUGGINGFACE_API_KEY,
- AMADEUS_ID,
- AMADEUS_KEY,
- ], outputs=key_set_btn)
- key_set_btn.click(fn=load_tools, outputs=tools_chosen)
-
- tools_search.change(retrieve, tools_search, tools_chosen)
- buttonSearch.click(clear_retrieve, [], [tools_search, tools_chosen])
-
- txt.submit(lambda: [gr.update(value=''), gr.update(visible=False), gr.update(visible=True)], [],
- [txt, buttonClear, buttonStop])
- inference_event = txt.submit(answer_by_tools, [txt, tools_chosen, model_chosen], [chatbot, buttonClear, buttonStop])
- buttonChat.click(answer_by_tools, [txt, tools_chosen, model_chosen], [chatbot, buttonClear, buttonStop])
- buttonStop.click(lambda: [gr.update(visible=True), gr.update(visible=False)], [], [buttonClear, buttonStop],
- cancels=[inference_event])
- buttonClear.click(clear_history, [], chatbot)
-
- # Interface state
- shared.gradio['interface_state'] = gr.State({k: None for k in shared.input_elements})
-
- # Audio notification
- if Path("notification.mp3").exists():
- shared.gradio['audio_notification'] = gr.Audio(interactive=False, value="notification.mp3", elem_id="audio_notification", visible=False)
-
- # Floating menus for saving/deleting files
- ui_file_saving.create_ui()
-
- # Temporary clipboard for saving files
- shared.gradio['temporary_text'] = gr.Textbox(visible=False)
-
- # Text Generation tab
- ui_chat.create_ui()
- ui_default.create_ui()
- ui_notebook.create_ui()
-
- ui_parameters.create_ui(shared.settings['preset']) # Parameters tab
- ui_model_menu.create_ui() # Model tab
- training.create_ui() # Training tab
- ui_session.create_ui() # Session tab
-
- # Generation events
- ui_chat.create_event_handlers()
- ui_default.create_event_handlers()
- ui_notebook.create_event_handlers()
-
- # Other events
- ui_file_saving.create_event_handlers()
- ui_parameters.create_event_handlers()
- ui_model_menu.create_event_handlers()
-
- # Interface launch events
- if shared.settings['dark_theme']:
- shared.gradio['interface'].load(lambda: None, None, None, _js="() => document.getElementsByTagName('body')[0].classList.add('dark')")
-
- shared.gradio['interface'].load(lambda: None, None, None, _js=f"() => {{{js}}}")
- shared.gradio['interface'].load(None, gradio('show_controls'), None, _js=f'(x) => {{{ui.show_controls_js}; toggle_controls(x)}}')
- shared.gradio['interface'].load(partial(ui.apply_interface_values, {}, use_persistent=True), None, gradio(ui.list_interface_input_elements()), show_progress=False)
- shared.gradio['interface'].load(chat.redraw_html, gradio(ui_chat.reload_arr), gradio('display'))
-
- extensions_module.create_extensions_tabs() # Extensions tabs
- extensions_module.create_extensions_block() # Extensions block
-
- # Launch the interface
- shared.gradio['interface'].queue(concurrency_count=64)
- with OpenMonkeyPatch():
- shared.gradio['interface'].launch(
- prevent_thread_lock=True,
- share=shared.args.share,
- server_name=None if not shared.args.listen else (shared.args.listen_host or '0.0.0.0'),
- server_port=shared.args.listen_port,
- inbrowser=shared.args.auto_launch,
- auth=auth or None,
- ssl_verify=False if (shared.args.ssl_keyfile or shared.args.ssl_certfile) else True,
- ssl_keyfile=shared.args.ssl_keyfile,
- ssl_certfile=shared.args.ssl_certfile
- )
-
-
-if __name__ == "__main__":
-
- # Load custom settings
- settings_file = None
- if shared.args.settings is not None and Path(shared.args.settings).exists():
- settings_file = Path(shared.args.settings)
- elif Path('settings.yaml').exists():
- settings_file = Path('settings.yaml')
- elif Path('settings.json').exists():
- settings_file = Path('settings.json')
-
- if settings_file is not None:
- logger.info(f"Loading settings from {settings_file}...")
- file_contents = open(settings_file, 'r', encoding='utf-8').read()
- new_settings = json.loads(file_contents) if settings_file.suffix == "json" else yaml.safe_load(file_contents)
- shared.settings.update(new_settings)
-
- # Fallback settings for models
- shared.model_config['.*'] = get_fallback_settings()
- shared.model_config.move_to_end('.*', last=False) # Move to the beginning
-
- # Activate the extensions listed on settings.yaml
- extensions_module.available_extensions = utils.get_available_extensions()
- for extension in shared.settings['default_extensions']:
- shared.args.extensions = shared.args.extensions or []
- if extension not in shared.args.extensions:
- shared.args.extensions.append(extension)
-
- available_models = utils.get_available_models()
-
- # Model defined through --model
- if shared.args.model is not None:
- shared.model_name = shared.args.model
-
- # Select the model from a command-line menu
- elif shared.args.model_menu:
- if len(available_models) == 0:
- logger.error('No models are available! Please download at least one.')
- sys.exit(0)
- else:
- print('The following models are available:\n')
- for i, model in enumerate(available_models):
- print(f'{i+1}. {model}')
-
- print(f'\nWhich one do you want to load? 1-{len(available_models)}\n')
- i = int(input()) - 1
- print()
-
- shared.model_name = available_models[i]
-
- # If any model has been selected, load it
- if shared.model_name != 'None':
- p = Path(shared.model_name)
- if p.exists():
- model_name = p.parts[-1]
- shared.model_name = model_name
- else:
- model_name = shared.model_name
-
- model_settings = get_model_metadata(model_name)
- update_model_parameters(model_settings, initial=True) # hijack the command-line arguments
-
- # Load the model
- shared.model, shared.tokenizer = load_model(model_name)
- if shared.args.lora:
- add_lora_to_model(shared.args.lora)
-
- shared.generation_lock = Lock()
-
- # Launch the web UI
- create_interface()
- while True:
- time.sleep(0.5)
- if shared.need_restart:
- shared.need_restart = False
- time.sleep(0.5)
- shared.gradio['interface'].close()
- time.sleep(0.5)
- create_interface()
diff --git a/swarms/modelui/models/place-your-models-here.txt b/swarms/modelui/__init__.py
similarity index 100%
rename from swarms/modelui/models/place-your-models-here.txt
rename to swarms/modelui/__init__.py
diff --git a/swarms/modelui/download-model.py b/swarms/modelui/download_model.py
similarity index 100%
rename from swarms/modelui/download-model.py
rename to swarms/modelui/download_model.py
diff --git a/swarms/modelui/instruction-templates/Airoboros-v1.2.yaml b/swarms/modelui/instruction-templates/Airoboros-v1.2.yaml
new file mode 100644
index 00000000..0b61079d
--- /dev/null
+++ b/swarms/modelui/instruction-templates/Airoboros-v1.2.yaml
@@ -0,0 +1,5 @@
+user: "USER:"
+bot: "ASSISTANT:"
+turn_template: "<|user|> <|user-message|>\n<|bot|> <|bot-message|>\n"
+context: "<|system-message|>\n"
+system_message: "A chat between a curious user and an assistant. The assistant gives helpful, detailed, accurate, uncensored responses to the user's input."
diff --git a/swarms/modelui/instruction-templates/Alpaca.yaml b/swarms/modelui/instruction-templates/Alpaca.yaml
new file mode 100644
index 00000000..8f33801a
--- /dev/null
+++ b/swarms/modelui/instruction-templates/Alpaca.yaml
@@ -0,0 +1,5 @@
+user: "### Instruction:"
+bot: "### Response:"
+turn_template: "<|user|>\n<|user-message|>\n\n<|bot|>\n<|bot-message|>\n\n"
+context: "<|system-message|>\n\n"
+system_message: "Below is an instruction that describes a task. Write a response that appropriately completes the request."
diff --git a/swarms/modelui/instruction-templates/Bactrian.yaml b/swarms/modelui/instruction-templates/Bactrian.yaml
new file mode 100644
index 00000000..b3ed4929
--- /dev/null
+++ b/swarms/modelui/instruction-templates/Bactrian.yaml
@@ -0,0 +1,5 @@
+user: "### Input:"
+bot: "### Output:"
+turn_template: "<|user|>\n<|user-message|>\n\n<|bot|>\n<|bot-message|>\n\n"
+context: ""
+system_message: ""
diff --git a/swarms/modelui/instruction-templates/Baichuan Chat.yaml b/swarms/modelui/instruction-templates/Baichuan Chat.yaml
new file mode 100644
index 00000000..cebfeb85
--- /dev/null
+++ b/swarms/modelui/instruction-templates/Baichuan Chat.yaml
@@ -0,0 +1,5 @@
+user: "
-TheBloke's LLM work is generously supported by a grant from andreessen horowitz (a16z)
](https://github.com/OpenAccess-AI-Collective/axolotl)
-
-
-# OpenOrca - Mistral - 7B - 8k
-
-We have used our own [OpenOrca dataset](https://huggingface.co/datasets/Open-Orca/OpenOrca) to fine-tune on top of [Mistral 7B](https://huggingface.co/mistralai/Mistral-7B-v0.1).
-This dataset is our attempt to reproduce the dataset generated for Microsoft Research's [Orca Paper](https://arxiv.org/abs/2306.02707).
-We use [OpenChat](https://huggingface.co/openchat) packing, trained with [Axolotl](https://github.com/OpenAccess-AI-Collective/axolotl).
-
-This release is trained on a curated filtered subset of most of our GPT-4 augmented data.
-It is the same subset of our data as was used in our [OpenOrcaxOpenChat-Preview2-13B model](https://huggingface.co/Open-Orca/OpenOrcaxOpenChat-Preview2-13B).
-
-**HF Leaderboard evals place this model as #2 for all models smaller than 30B at release time, outperforming all but one 13B model.**
-
-This release provides a first: a fully open model with class-breaking performance, capable of running fully accelerated on even moderate consumer GPUs.
-Our thanks to the Mistral team for leading the way here.
-
-We affectionately codename this model: "*MistralOrca*"
-
-If you'd like to try the model now, we have it running on fast GPUs unquantized: https://huggingface.co/spaces/Open-Orca/Mistral-7B-OpenOrca
-
-Want to visualize our full (pre-filtering) dataset? Check out our [Nomic Atlas Map](https://atlas.nomic.ai/map/c1b88b47-2d9b-47e0-9002-b80766792582/2560fd25-52fe-42f1-a58f-ff5eccc890d2).
-
-[
](https://atlas.nomic.ai/map/c1b88b47-2d9b-47e0-9002-b80766792582/2560fd25-52fe-42f1-a58f-ff5eccc890d2)
-
-
-We are in-process with training more models, so keep a look out on our org for releases coming soon with exciting partners.
-
-We will also give sneak-peak announcements on our Discord, which you can find here:
-
-https://AlignmentLab.ai
-
-or check the OpenAccess AI Collective Discord for more information about Axolotl trainer here:
-
-https://discord.gg/5y8STgB3P3
-
-
-# Quantized Models
-
-Quantized versions of this model are generously made available by [TheBloke](https://huggingface.co/TheBloke).
-
-- AWQ: https://huggingface.co/TheBloke/Mistral-7B-OpenOrca-AWQ
-- GPTQ: https://huggingface.co/TheBloke/Mistral-7B-OpenOrca-GPTQ
-- GGUF: https://huggingface.co/TheBloke/Mistral-7B-OpenOrca-GGUF
-
-
-# Prompt Template
-
-We used [OpenAI's Chat Markup Language (ChatML)](https://github.com/openai/openai-python/blob/main/chatml.md) format, with `<|im_start|>` and `<|im_end|>` tokens added to support this.
-
-## Example Prompt Exchange
-
-```
-<|im_start|>system
-You are MistralOrca, a large language model trained by Alignment Lab AI. Write out your reasoning step-by-step to be sure you get the right answers!
-<|im_end|>
-<|im_start|>user
-How are you?<|im_end|>
-<|im_start|>assistant
-I am doing well!<|im_end|>
-<|im_start|>user
-Please tell me about how mistral winds have attracted super-orcas.<|im_end|>
-```
-
-
-# Evaluation
-
-## HuggingFace Leaderboard Performance
-
-We have evaluated using the methodology and tools for the HuggingFace Leaderboard, and find that we have dramatically improved upon the base model.
-We find **105%** of the base model's performance on HF Leaderboard evals, averaging **65.33**.
-
-At release time, this beats all 7B models, and all but one 13B.
-
-
-
-
-| Metric | Value |
-|-----------------------|-------|
-| MMLU (5-shot) | 61.73 |
-| ARC (25-shot) | 63.57 |
-| HellaSwag (10-shot) | 83.79 |
-| TruthfulQA (0-shot) | 52.24 |
-| Avg. | 65.33 |
-
-We use [Language Model Evaluation Harness](https://github.com/EleutherAI/lm-evaluation-harness) to run the benchmark tests above, using the same version as the HuggingFace LLM Leaderboard.
-
-
-## AGIEval Performance
-
-We compare our results to the base Mistral-7B model (using LM Evaluation Harness).
-
-We find **129%** of the base model's performance on AGI Eval, averaging **0.397**.
-As well, we significantly improve upon the official `mistralai/Mistral-7B-Instruct-v0.1` finetuning, achieving **119%** of their performance.
-
-
-
-## BigBench-Hard Performance
-
-We find **119%** of the base model's performance on BigBench-Hard, averaging **0.416**.
-
-
-
-
-# Dataset
-
-We used a curated, filtered selection of most of the GPT-4 augmented data from our OpenOrca dataset, which aims to reproduce the Orca Research Paper dataset.
-
-
-# Training
-
-We trained with 8x A6000 GPUs for 62 hours, completing 4 epochs of full fine tuning on our dataset in one training run.
-Commodity cost was ~$400.
-
-
-# Citation
-
-```bibtex
-@software{lian2023mistralorca1
- title = {MistralOrca: Mistral-7B Model Instruct-tuned on Filtered OpenOrcaV1 GPT-4 Dataset},
- author = {Wing Lian and Bleys Goodson and Guan Wang and Eugene Pentland and Austin Cook and Chanvichet Vong and "Teknium"},
- year = {2023},
- publisher = {HuggingFace},
- journal = {HuggingFace repository},
- howpublished = {\url{https://huggingface.co/Open-Orca/Mistral-7B-OpenOrca},
-}
-@misc{mukherjee2023orca,
- title={Orca: Progressive Learning from Complex Explanation Traces of GPT-4},
- author={Subhabrata Mukherjee and Arindam Mitra and Ganesh Jawahar and Sahaj Agarwal and Hamid Palangi and Ahmed Awadallah},
- year={2023},
- eprint={2306.02707},
- archivePrefix={arXiv},
- primaryClass={cs.CL}
-}
-@misc{longpre2023flan,
- title={The Flan Collection: Designing Data and Methods for Effective Instruction Tuning},
- author={Shayne Longpre and Le Hou and Tu Vu and Albert Webson and Hyung Won Chung and Yi Tay and Denny Zhou and Quoc V. Le and Barret Zoph and Jason Wei and Adam Roberts},
- year={2023},
- eprint={2301.13688},
- archivePrefix={arXiv},
- primaryClass={cs.AI}
-}
-```
-
-
diff --git a/swarms/modelui/models/config.json b/swarms/modelui/models/config.json
deleted file mode 100644
index 9f0f76f8..00000000
--- a/swarms/modelui/models/config.json
+++ /dev/null
@@ -1,3 +0,0 @@
-{
- "model_type": "mistral"
-}
\ No newline at end of file
diff --git a/swarms/modelui/models/config.yaml b/swarms/modelui/models/config.yaml
deleted file mode 100644
index 00db01d1..00000000
--- a/swarms/modelui/models/config.yaml
+++ /dev/null
@@ -1,182 +0,0 @@
-.*(llama|alpac|vicuna|guanaco|koala|llava|wizardlm|metharme|pygmalion-7b|pygmalion-2|mythalion|wizard-mega|openbuddy|vigogne|h2ogpt-research|manticore):
- model_type: 'llama'
-.*(opt-|opt_|opt1|opt3|optfor|galactica|galpaca|pygmalion-350m):
- model_type: 'opt'
-.*(gpt-j|gptj|gpt4all-j|malion-6b|pygway|pygmalion-6b|dolly-v1):
- model_type: 'gptj'
-.*(gpt-neox|koalpaca-polyglot|polyglot.*koalpaca|polyglot-ko|polyglot_ko|pythia|stablelm|incite|dolly-v2|polycoder|h2ogpt-oig|h2ogpt-oasst1|h2ogpt-gm):
- model_type: 'gptneox'
-.*bloom:
- model_type: 'bloom'
-.*gpt2:
- model_type: 'gpt2'
-.*falcon:
- model_type: 'falcon'
-.*mpt:
- model_type: 'mpt'
-.*(starcoder|starchat):
- model_type: 'starcoder'
-.*dolly-v2:
- model_type: 'dollyv2'
-.*replit:
- model_type: 'replit'
-.*(oasst|openassistant-|stablelm-7b-sft-v7-epoch-3):
- instruction_template: 'Open Assistant'
- skip_special_tokens: false
-(?!.*galactica)(?!.*reward).*openassistant:
- instruction_template: 'Open Assistant'
- skip_special_tokens: false
-.*galactica:
- skip_special_tokens: false
-.*dolly-v[0-9]-[0-9]*b:
- instruction_template: 'Alpaca'
- skip_special_tokens: false
-.*alpaca-native-4bit:
- instruction_template: 'Alpaca'
- custom_stopping_strings: '"### End"'
-.*llava:
- instruction_template: 'LLaVA'
- custom_stopping_strings: '"\n###"'
-.*llava.*1.5:
- instruction_template: 'LLaVA-v1'
-.*wizard.*mega:
- instruction_template: 'Wizard-Mega'
- custom_stopping_strings: '""'
-.*starchat-beta:
- instruction_template: 'Starchat-Beta'
- custom_stopping_strings: '"<|end|>"'
-(?!.*v0)(?!.*1.1)(?!.*1_1)(?!.*stable)(?!.*chinese).*vicuna:
- instruction_template: 'Vicuna-v0'
-.*vicuna.*v0:
- instruction_template: 'Vicuna-v0'
-.*vicuna.*(1.1|1_1|1.3|1_3):
- instruction_template: 'Vicuna-v1.1'
-.*vicuna.*(1.5|1_5):
- instruction_template: 'Vicuna-v1.1'
-.*stable.*vicuna:
- instruction_template: 'StableVicuna'
-(?!.*chat).*chinese-vicuna:
- instruction_template: 'Alpaca'
-.*chinese-vicuna.*chat:
- instruction_template: 'Chinese-Vicuna-Chat'
-.*alpaca:
- instruction_template: 'Alpaca'
-.*koala:
- instruction_template: 'Koala'
-.*chatglm:
- instruction_template: 'ChatGLM'
-.*(metharme|pygmalion|mythalion):
- instruction_template: 'Metharme'
-.*raven:
- instruction_template: 'RWKV-Raven'
-.*moss-moon.*sft:
- instruction_template: 'MOSS'
-.*stablelm-tuned:
- instruction_template: 'StableLM'
-.*galactica.*finetuned:
- instruction_template: 'Galactica Finetuned'
-.*galactica.*-v2:
- instruction_template: 'Galactica v2'
-(?!.*finetuned)(?!.*-v2).*galactica:
- instruction_template: 'Galactica'
-.*guanaco:
- instruction_template: 'Guanaco non-chat'
-.*baize:
- instruction_template: 'Baize'
-.*mpt-.*instruct:
- instruction_template: 'Alpaca'
-.*mpt-.*chat:
- instruction_template: 'ChatML'
-(?!.*-flan-)(?!.*-t5-).*lamini-:
- instruction_template: 'Alpaca'
-.*incite.*chat:
- instruction_template: 'INCITE-Chat'
-.*incite.*instruct:
- instruction_template: 'INCITE-Instruct'
-.*ziya-:
- instruction_template: 'Ziya'
-.*koalpaca:
- instruction_template: 'KoAlpaca'
-.*openbuddy:
- instruction_template: 'OpenBuddy'
-(?!.*chat).*vigogne:
- instruction_template: 'Vigogne-Instruct'
-.*vigogne.*chat:
- instruction_template: 'Vigogne-Chat'
-.*(llama-deus|supercot|llama-natural-instructions|open-llama-0.3t-7b-instruct-dolly-hhrlhf|open-llama-0.3t-7b-open-instruct):
- instruction_template: 'Alpaca'
-.*bactrian:
- instruction_template: 'Bactrian'
-.*(h2ogpt-oig-|h2ogpt-oasst1-|h2ogpt-research-oasst1-):
- instruction_template: 'H2O-human_bot'
-.*h2ogpt-gm-:
- instruction_template: 'H2O-prompt_answer'
-.*manticore:
- instruction_template: 'Manticore Chat'
-.*bluemoonrp-(30|13)b:
- instruction_template: 'Bluemoon'
-.*Nous-Hermes-13b:
- instruction_template: 'Alpaca'
-.*airoboros:
- instruction_template: 'Vicuna-v1.1'
-.*airoboros.*1.2:
- instruction_template: 'Airoboros-v1.2'
-.*alpa(cino|sta):
- instruction_template: 'Alpaca'
-.*hippogriff:
- instruction_template: 'Hippogriff'
-.*lazarus:
- instruction_template: 'Alpaca'
-.*guanaco-.*(7|13|33|65)b:
- instruction_template: 'Guanaco'
-.*hypermantis:
- instruction_template: 'Alpaca'
-.*open-llama-.*-open-instruct:
- instruction_template: 'Alpaca'
-.*starcoder-gpteacher-code-instruct:
- instruction_template: 'Alpaca'
-.*tulu:
- instruction_template: 'Tulu'
-.*chronos:
- instruction_template: 'Alpaca'
-.*samantha:
- instruction_template: 'Samantha'
-.*wizardcoder:
- instruction_template: 'Alpaca'
-.*minotaur:
- instruction_template: 'Minotaur'
-.*orca_mini:
- instruction_template: 'Orca Mini'
-.*(platypus|gplatty|superplatty):
- instruction_template: 'Alpaca'
-.*(openorca-platypus2):
- instruction_template: 'OpenOrca-Platypus2'
- custom_stopping_strings: '"### Instruction:", "### Response:"'
-.*longchat:
- instruction_template: 'Vicuna-v1.1'
-.*vicuna-33b:
- instruction_template: 'Vicuna-v1.1'
-.*redmond-hermes-coder:
- instruction_template: 'Alpaca'
-.*wizardcoder-15b:
- instruction_template: 'Alpaca'
-.*wizardlm:
- instruction_template: 'Vicuna-v1.1'
-.*godzilla:
- instruction_template: 'Alpaca'
-.*llama(-?)(2|v2).*chat:
- instruction_template: 'Llama-v2'
-.*newhope:
- instruction_template: 'NewHope'
-.*stablebeluga2:
- instruction_template: 'StableBeluga2'
-.*openchat:
- instruction_template: 'OpenChat'
-.*codellama.*instruct:
- instruction_template: 'Llama-v2'
-.*mistral.*instruct:
- instruction_template: 'Mistral'
-.*mistral.*openorca:
- instruction_template: 'ChatML'
-.*(WizardCoder-Python-34B-V1.0|Phind-CodeLlama-34B-v2|CodeBooga-34B-v0.1):
- instruction_template: 'Alpaca'
diff --git a/swarms/modelui/modules/ui_model_menu.py b/swarms/modelui/modules/ui_model_menu.py
index f78bc603..2b38dafd 100644
--- a/swarms/modelui/modules/ui_model_menu.py
+++ b/swarms/modelui/modules/ui_model_menu.py
@@ -235,7 +235,7 @@ def load_lora_wrapper(selected_loras):
def download_model_wrapper(repo_id, specific_file, progress=gr.Progress(), return_links=False, check=False):
try:
progress(0.0)
- downloader = importlib.import_module("download-model").ModelDownloader()
+ downloader = importlib.import_module("swarms.modelui.download_model").ModelDownloader()
model, branch = downloader.sanitize_model_and_branch_names(repo_id, None)
yield ("Getting the download links from Hugging Face")
links, sha256, is_lora, is_llamacpp = downloader.get_download_links_from_huggingface(model, branch, text_only=False, specific_file=specific_file)