Merge branch 'main' of https://github.com/nomic-ai/gpt4all-ui

backends/gpt4all/json2yaml.py

@@ -0,0 +1,27 @@
+import json
+import yaml
+from pathlib import Path
+import argparse
+
+def json_to_yaml(json_file):
+    # Read JSON file
+    with open(json_file, 'r') as file:
+        json_data = json.load(file)
+
+    # Create YAML file path
+    yaml_file = Path(json_file).with_suffix('.yaml')
+
+    # Convert JSON to YAML
+    with open(yaml_file, 'w') as file:
+        yaml.dump(json_data, file)
+
+    print(f"Conversion complete. YAML file saved as: {yaml_file}")
+
+if __name__ == "__main__":
+    # Parse command-line arguments
+    parser = argparse.ArgumentParser(description='Convert JSON file to YAML.')
+    parser.add_argument('json_file', help='Path to the JSON file')
+    args = parser.parse_args()
+
+    # Convert JSON to YAML
+    json_to_yaml(args.json_file)

backends/gpt4all/models.json

@@ -0,0 +1,101 @@
+[
+    {
+      "md5sum": "81a09a0ddf89690372fc296ff7f625af",
+      "filename": "ggml-gpt4all-j-v1.3-groovy.bin",
+      "server":"https://gpt4all.io/models/",
+      "filesize": "3785248281",
+      "isDefault": "true",
+      "bestGPTJ": "true",
+      "description": "Current best commercially licensable model based on GPT-J and trained by Nomic AI on the latest curated GPT4All dataset."
+    },
+    {
+      "md5sum": "91f886b68fbce697e9a3cd501951e455",
+      "filename": "ggml-gpt4all-l13b-snoozy.bin",
+      "server":"https://gpt4all.io/models/",
+      "filesize": "8136770688",
+      "bestLlama": "true",
+      "description": "Current best non-commercially licensable model based on Llama 13b and trained by Nomic AI on the latest curated GPT4All dataset."
+    },
+    {
+      "md5sum": "756249d3d6abe23bde3b1ae272628640",
+      "filename": "ggml-mpt-7b-chat.bin",
+      "server":"https://gpt4all.io/models/",
+      "filesize": "4854401050",
+      "isDefault": "true",
+      "bestMPT": "true",
+      "requires": "2.4.1",
+      "description": "Current best non-commercially licensable chat model based on MPT and trained by Mosaic ML."
+    },
+    {
+      "md5sum": "879344aaa9d62fdccbda0be7a09e7976",
+      "filename": "ggml-gpt4all-j-v1.2-jazzy.bin",
+      "server":"https://gpt4all.io/models/",
+      "filesize": "3785248281",
+      "description": "A commercially licensable model based on GPT-J and trained by Nomic AI on the v2 GPT4All dataset."
+    },
+    {
+      "md5sum": "61d48a82cb188cceb14ebb8082bfec37",
+      "filename": "ggml-gpt4all-j-v1.1-breezy.bin",
+      "server":"https://gpt4all.io/models/",
+      "filesize": "3785248281",
+      "description": "A commercially licensable model based on GPT-J and trained by Nomic AI on the v1 GPT4All dataset."
+    },
+    {
+      "md5sum": "5b5a3f9b858d33b29b52b89692415595",
+      "filename": "ggml-gpt4all-j.bin",
+      "server":"https://gpt4all.io/models/",
+      "filesize": "3785248281",
+      "description": "A commercially licensable model based on GPT-J and trained by Nomic AI on the v0 GPT4All dataset."
+    },
+    {
+      "md5sum": "29119f8fa11712704c6b22ac5ab792ea",
+      "filename": "ggml-vicuna-7b-1.1-q4_2.bin",
+      "server":"https://gpt4all.io/models/",
+      "filesize": "4212859520",
+      "description": "A non-commercially licensable model based on Llama 7b and trained by teams from UC Berkeley, CMU, Stanford, MBZUAI, and UC San Diego."
+    },
+    {
+      "md5sum": "95999b7b0699e2070af63bf5d34101a8",
+      "filename": "ggml-vicuna-13b-1.1-q4_2.bin",
+      "server":"https://gpt4all.io/models/",
+      "filesize": "8136770688",
+      "description": "A non-commercially licensable model based on Llama 13b and trained by teams from UC Berkeley, CMU, Stanford, MBZUAI, and UC San Diego."
+    },
+    {
+      "md5sum": "99e6d129745a3f1fb1121abed747b05a",
+      "filename": "ggml-wizardLM-7B.q4_2.bin",
+      "server":"https://gpt4all.io/models/",
+      "filesize": "4212864640",
+      "description": "A non-commercially licensable model based on Llama 7b and trained by Microsoft and Peking University."
+    },
+    {
+      "md5sum": "6cb4ee297537c9133bddab9692879de0",
+      "filename": "ggml-stable-vicuna-13B.q4_2.bin",
+      "server":"https://gpt4all.io/models/",
+      "filesize": "8136777088",
+      "description": "A non-commercially licensable model based on Llama 13b and RLHF trained by Stable AI."
+    },
+    {
+      "md5sum": "120c32a51d020066288df045ef5d52b9",
+      "filename": "ggml-mpt-7b-base.bin",
+      "server":"https://gpt4all.io/models/",
+      "filesize": "4854401028",
+      "requires": "2.4.1",
+      "description": "A commercially licensable model base pre-trained by Mosaic ML."
+    },
+    {
+      "md5sum": "d5eafd5b0bd0d615cfd5fd763f642dfe",
+      "filename": "ggml-nous-gpt4-vicuna-13b.bin",
+      "server":"https://gpt4all.io/models/",
+      "filesize": "8136777088",
+      "description": "A non-commercially licensable model based on Vicuna 13b, fine-tuned on ~180,000 instructions, trained by Nous Research."
+    },
+    {
+      "md5sum": "1cfa4958f489f0a0d1ffdf6b37322809",
+      "filename": "ggml-mpt-7b-instruct.bin",
+      "server":"https://gpt4all.io/models/",
+      "filesize": "4854401028",
+      "requires": "2.4.1",
+      "description": "A commericially licensable instruct model based on MPT and trained by Mosaic ML."
+    }
+  ]

backends/gpt4all/models.yaml

@@ -0,0 +1,85 @@
+- bestGPTJ: 'true'
+  description: Current best commercially licensable model based on GPT-J and trained
+    by Nomic AI on the latest curated GPT4All dataset.
+  filename: ggml-gpt4all-j-v1.3-groovy.bin
+  filesize: '3785248281'
+  isDefault: 'true'
+  md5sum: 81a09a0ddf89690372fc296ff7f625af
+  server: https://gpt4all.io/models/
+- bestLlama: 'true'
+  description: Current best non-commercially licensable model based on Llama 13b and
+    trained by Nomic AI on the latest curated GPT4All dataset.
+  filename: ggml-gpt4all-l13b-snoozy.bin
+  filesize: '8136770688'
+  md5sum: 91f886b68fbce697e9a3cd501951e455
+  server: https://gpt4all.io/models/
+- bestMPT: 'true'
+  description: Current best non-commercially licensable chat model based on MPT and
+    trained by Mosaic ML.
+  filename: ggml-mpt-7b-chat.bin
+  filesize: '4854401050'
+  isDefault: 'true'
+  md5sum: 756249d3d6abe23bde3b1ae272628640
+  requires: 2.4.1
+  server: https://gpt4all.io/models/
+- description: A commercially licensable model based on GPT-J and trained by Nomic
+    AI on the v2 GPT4All dataset.
+  filename: ggml-gpt4all-j-v1.2-jazzy.bin
+  filesize: '3785248281'
+  md5sum: 879344aaa9d62fdccbda0be7a09e7976
+  server: https://gpt4all.io/models/
+- description: A commercially licensable model based on GPT-J and trained by Nomic
+    AI on the v1 GPT4All dataset.
+  filename: ggml-gpt4all-j-v1.1-breezy.bin
+  filesize: '3785248281'
+  md5sum: 61d48a82cb188cceb14ebb8082bfec37
+  server: https://gpt4all.io/models/
+- description: A commercially licensable model based on GPT-J and trained by Nomic
+    AI on the v0 GPT4All dataset.
+  filename: ggml-gpt4all-j.bin
+  filesize: '3785248281'
+  md5sum: 5b5a3f9b858d33b29b52b89692415595
+  server: https://gpt4all.io/models/
+- description: A non-commercially licensable model based on Llama 7b and trained by
+    teams from UC Berkeley, CMU, Stanford, MBZUAI, and UC San Diego.
+  filename: ggml-vicuna-7b-1.1-q4_2.bin
+  filesize: '4212859520'
+  md5sum: 29119f8fa11712704c6b22ac5ab792ea
+  server: https://gpt4all.io/models/
+- description: A non-commercially licensable model based on Llama 13b and trained
+    by teams from UC Berkeley, CMU, Stanford, MBZUAI, and UC San Diego.
+  filename: ggml-vicuna-13b-1.1-q4_2.bin
+  filesize: '8136770688'
+  md5sum: 95999b7b0699e2070af63bf5d34101a8
+  server: https://gpt4all.io/models/
+- description: A non-commercially licensable model based on Llama 7b and trained by
+    Microsoft and Peking University.
+  filename: ggml-wizardLM-7B.q4_2.bin
+  filesize: '4212864640'
+  md5sum: 99e6d129745a3f1fb1121abed747b05a
+  server: https://gpt4all.io/models/
+- description: A non-commercially licensable model based on Llama 13b and RLHF trained
+    by Stable AI.
+  filename: ggml-stable-vicuna-13B.q4_2.bin
+  filesize: '8136777088'
+  md5sum: 6cb4ee297537c9133bddab9692879de0
+  server: https://gpt4all.io/models/
+- description: A commercially licensable model base pre-trained by Mosaic ML.
+  filename: ggml-mpt-7b-base.bin
+  filesize: '4854401028'
+  md5sum: 120c32a51d020066288df045ef5d52b9
+  requires: 2.4.1
+  server: https://gpt4all.io/models/
+- description: A non-commercially licensable model based on Vicuna 13b, fine-tuned
+    on ~180,000 instructions, trained by Nous Research.
+  filename: ggml-nous-gpt4-vicuna-13b.bin
+  filesize: '8136777088'
+  md5sum: d5eafd5b0bd0d615cfd5fd763f642dfe
+  server: https://gpt4all.io/models/
+- description: A commericially licensable instruct model based on MPT and trained
+    by Mosaic ML.
+  filename: ggml-mpt-7b-instruct.bin
+  filesize: '4854401028'
+  md5sum: 1cfa4958f489f0a0d1ffdf6b37322809
+  requires: 2.4.1
+  server: https://gpt4all.io/models/

backends/gptj/__init__.py

@@ -0,0 +1,82 @@
+######
+# Project       : GPT4ALL-UI
+# File          : backend.py
+# Author        : ParisNeo with the help of the community
+# Supported by Nomic-AI
+# Licence       : Apache 2.0
+# Description   : 
+# This is an interface class for GPT4All-ui backends.
+######
+from pathlib import Path
+from typing import Callable
+from gpt4allj import Model
+from pyGpt4All.backend import GPTBackend
+import yaml
+
+__author__ = "parisneo"
+__github__ = "https://github.com/nomic-ai/gpt4all-ui"
+__copyright__ = "Copyright 2023, "
+__license__ = "Apache 2.0"
+
+backend_name = "GPTJ"
+
+class GPTJ(GPTBackend):
+    file_extension='*.bin'
+    def __init__(self, config:dict) -> None:
+        """Builds a LLAMACPP backend
+
+        Args:
+            config (dict): The configuration file
+        """
+        super().__init__(config, False)
+        
+        self.model = Model(
+                model=f"./models/llama_cpp/{self.config['model']}", avx2 = self.config["use_avx2"]
+                )
+
+    def stop_generation(self):
+        self.model._grab_text_callback()
+
+    def generate(self, 
+                 prompt:str,                  
+                 n_predict: int = 128,
+                 new_text_callback: Callable[[str], None] = bool,
+                 verbose: bool = False,
+                 **gpt_params ):
+        """Generates text out of a prompt
+
+        Args:
+            prompt (str): The prompt to use for generation
+            n_predict (int, optional): Number of tokens to prodict. Defaults to 128.
+            new_text_callback (Callable[[str], None], optional): A callback function that is called everytime a new text element is generated. Defaults to None.
+            verbose (bool, optional): If true, the code will spit many informations about the generation process. Defaults to False.
+        """
+        try:
+            self.model.reset()
+            for tok in self.model.generate(
+                                            prompt, 
+                                            seed=self.config['seed'],
+                                            n_threads=self.config['n_threads'],
+                                            n_predict=n_predict,
+                                            top_k=self.config['top_k'],
+                                            top_p=self.config['top_p'],
+                                            temp=self.config['temperature'],
+                                            repeat_penalty=self.config['repeat_penalty'],
+                                            repeat_last_n=self.config['repeat_last_n'],
+                                            n_batch=8,
+                                            reset=True,
+                                           ):
+                if not new_text_callback(tok):
+                    return
+        except Exception as ex:
+            print(ex)
+    @staticmethod
+    def get_available_models():
+        # Create the file path relative to the child class's directory
+        backend_path = Path(__file__).parent
+        file_path = backend_path/"models.yaml"
+
+        with open(file_path, 'r') as file:
+            yaml_data = yaml.safe_load(file)
+        
+        return yaml_data

backends/gptj/models.yaml

@@ -0,0 +1,72 @@
+- bestGPTJ: 'true'
+  description: Current best commercially licensable model based on GPT-J and trained
+    by Nomic AI on the latest curated GPT4All dataset.
+  filename: ggml-gpt4all-j-v1.3-groovy.bin
+  filesize: '3785248281'
+  isDefault: 'true'
+  md5sum: 81a09a0ddf89690372fc296ff7f625af
+- bestLlama: 'true'
+  description: Current best non-commercially licensable model based on Llama 13b and
+    trained by Nomic AI on the latest curated GPT4All dataset.
+  filename: ggml-gpt4all-l13b-snoozy.bin
+  filesize: '8136770688'
+  md5sum: 91f886b68fbce697e9a3cd501951e455
+- bestMPT: 'true'
+  description: Current best non-commercially licensable chat model based on MPT and
+    trained by Mosaic ML.
+  filename: ggml-mpt-7b-chat.bin
+  filesize: '4854401050'
+  isDefault: 'true'
+  md5sum: 756249d3d6abe23bde3b1ae272628640
+  requires: 2.4.1
+- description: A commercially licensable model based on GPT-J and trained by Nomic
+    AI on the v2 GPT4All dataset.
+  filename: ggml-gpt4all-j-v1.2-jazzy.bin
+  filesize: '3785248281'
+  md5sum: 879344aaa9d62fdccbda0be7a09e7976
+- description: A commercially licensable model based on GPT-J and trained by Nomic
+    AI on the v1 GPT4All dataset.
+  filename: ggml-gpt4all-j-v1.1-breezy.bin
+  filesize: '3785248281'
+  md5sum: 61d48a82cb188cceb14ebb8082bfec37
+- description: A commercially licensable model based on GPT-J and trained by Nomic
+    AI on the v0 GPT4All dataset.
+  filename: ggml-gpt4all-j.bin
+  filesize: '3785248281'
+  md5sum: 5b5a3f9b858d33b29b52b89692415595
+- description: A non-commercially licensable model based on Llama 7b and trained by
+    teams from UC Berkeley, CMU, Stanford, MBZUAI, and UC San Diego.
+  filename: ggml-vicuna-7b-1.1-q4_2.bin
+  filesize: '4212859520'
+  md5sum: 29119f8fa11712704c6b22ac5ab792ea
+- description: A non-commercially licensable model based on Llama 13b and trained
+    by teams from UC Berkeley, CMU, Stanford, MBZUAI, and UC San Diego.
+  filename: ggml-vicuna-13b-1.1-q4_2.bin
+  filesize: '8136770688'
+  md5sum: 95999b7b0699e2070af63bf5d34101a8
+- description: A non-commercially licensable model based on Llama 7b and trained by
+    Microsoft and Peking University.
+  filename: ggml-wizardLM-7B.q4_2.bin
+  filesize: '4212864640'
+  md5sum: 99e6d129745a3f1fb1121abed747b05a
+- description: A non-commercially licensable model based on Llama 13b and RLHF trained
+    by Stable AI.
+  filename: ggml-stable-vicuna-13B.q4_2.bin
+  filesize: '8136777088'
+  md5sum: 6cb4ee297537c9133bddab9692879de0
+- description: A commercially licensable model base pre-trained by Mosaic ML.
+  filename: ggml-mpt-7b-base.bin
+  filesize: '4854401028'
+  md5sum: 120c32a51d020066288df045ef5d52b9
+  requires: 2.4.1
+- description: A non-commercially licensable model based on Vicuna 13b, fine-tuned
+    on ~180,000 instructions, trained by Nous Research.
+  filename: ggml-nous-gpt4-vicuna-13b.bin
+  filesize: '8136777088'
+  md5sum: d5eafd5b0bd0d615cfd5fd763f642dfe
+- description: A commericially licensable instruct model based on MPT and trained
+    by Mosaic ML.
+  filename: ggml-mpt-7b-instruct.bin
+  filesize: '4854401028'
+  md5sum: 1cfa4958f489f0a0d1ffdf6b37322809
+  requires: 2.4.1

backends/llama_cpp/models.yaml

@@ -0,0 +1,85 @@
+- bestGPTJ: 'true'
+  description: Current best commercially licensable model based on GPT-J and trained
+    by Nomic AI on the latest curated GPT4All dataset.
+  filename: ggml-gpt4all-j-v1.3-groovy.bin
+  filesize: '3785248281'
+  isDefault: 'true'
+  md5sum: 81a09a0ddf89690372fc296ff7f625af
+  server: https://gpt4all.io/models/
+- bestLlama: 'true'
+  description: Current best non-commercially licensable model based on Llama 13b and
+    trained by Nomic AI on the latest curated GPT4All dataset.
+  filename: ggml-gpt4all-l13b-snoozy.bin
+  filesize: '8136770688'
+  md5sum: 91f886b68fbce697e9a3cd501951e455
+  server: https://gpt4all.io/models/
+- bestMPT: 'true'
+  description: Current best non-commercially licensable chat model based on MPT and
+    trained by Mosaic ML.
+  filename: ggml-mpt-7b-chat.bin
+  filesize: '4854401050'
+  isDefault: 'true'
+  md5sum: 756249d3d6abe23bde3b1ae272628640
+  requires: 2.4.1
+  server: https://gpt4all.io/models/
+- description: A commercially licensable model based on GPT-J and trained by Nomic
+    AI on the v2 GPT4All dataset.
+  filename: ggml-gpt4all-j-v1.2-jazzy.bin
+  filesize: '3785248281'
+  md5sum: 879344aaa9d62fdccbda0be7a09e7976
+  server: https://gpt4all.io/models/
+- description: A commercially licensable model based on GPT-J and trained by Nomic
+    AI on the v1 GPT4All dataset.
+  filename: ggml-gpt4all-j-v1.1-breezy.bin
+  filesize: '3785248281'
+  md5sum: 61d48a82cb188cceb14ebb8082bfec37
+  server: https://gpt4all.io/models/
+- description: A commercially licensable model based on GPT-J and trained by Nomic
+    AI on the v0 GPT4All dataset.
+  filename: ggml-gpt4all-j.bin
+  filesize: '3785248281'
+  md5sum: 5b5a3f9b858d33b29b52b89692415595
+  server: https://gpt4all.io/models/
+- description: A non-commercially licensable model based on Llama 7b and trained by
+    teams from UC Berkeley, CMU, Stanford, MBZUAI, and UC San Diego.
+  filename: ggml-vicuna-7b-1.1-q4_2.bin
+  filesize: '4212859520'
+  md5sum: 29119f8fa11712704c6b22ac5ab792ea
+  server: https://gpt4all.io/models/
+- description: A non-commercially licensable model based on Llama 13b and trained
+    by teams from UC Berkeley, CMU, Stanford, MBZUAI, and UC San Diego.
+  filename: ggml-vicuna-13b-1.1-q4_2.bin
+  filesize: '8136770688'
+  md5sum: 95999b7b0699e2070af63bf5d34101a8
+  server: https://gpt4all.io/models/
+- description: A non-commercially licensable model based on Llama 7b and trained by
+    Microsoft and Peking University.
+  filename: ggml-wizardLM-7B.q4_2.bin
+  filesize: '4212864640'
+  md5sum: 99e6d129745a3f1fb1121abed747b05a
+  server: https://gpt4all.io/models/
+- description: A non-commercially licensable model based on Llama 13b and RLHF trained
+    by Stable AI.
+  filename: ggml-stable-vicuna-13B.q4_2.bin
+  filesize: '8136777088'
+  md5sum: 6cb4ee297537c9133bddab9692879de0
+  server: https://gpt4all.io/models/
+- description: A commercially licensable model base pre-trained by Mosaic ML.
+  filename: ggml-mpt-7b-base.bin
+  filesize: '4854401028'
+  md5sum: 120c32a51d020066288df045ef5d52b9
+  requires: 2.4.1
+  server: https://gpt4all.io/models/
+- description: A non-commercially licensable model based on Vicuna 13b, fine-tuned
+    on ~180,000 instructions, trained by Nous Research.
+  filename: ggml-nous-gpt4-vicuna-13b.bin
+  filesize: '8136777088'
+  md5sum: d5eafd5b0bd0d615cfd5fd763f642dfe
+  server: https://gpt4all.io/models/
+- description: A commericially licensable instruct model based on MPT and trained
+    by Mosaic ML.
+  filename: ggml-mpt-7b-instruct.bin
+  filesize: '4854401028'
+  md5sum: 1cfa4958f489f0a0d1ffdf6b37322809
+  requires: 2.4.1
+  server: https://gpt4all.io/models/