Upload 56 files
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- LICENSE +21 -0
- coding_problems.py +201 -0
- config.json +61 -0
- configuration_deepseek.py +210 -0
- generation_config.json +9 -0
- model-00001-of-00171.safetensors +3 -0
- model-00002-of-00171.safetensors +3 -0
- model-00003-of-00171.safetensors +3 -0
- model-00004-of-00171.safetensors +3 -0
- model-00005-of-00171.safetensors +3 -0
- model-00006-of-00171.safetensors +3 -0
- model-00007-of-00171.safetensors +3 -0
- model-00008-of-00171.safetensors +3 -0
- model-00009-of-00171.safetensors +3 -0
- model-00010-of-00171.safetensors +3 -0
- model-00011-of-00171.safetensors +3 -0
- model-00012-of-00171.safetensors +3 -0
- model-00013-of-00171.safetensors +3 -0
- model-00014-of-00171.safetensors +3 -0
- model-00015-of-00171.safetensors +3 -0
- model-00016-of-00171.safetensors +3 -0
- model-00017-of-00171.safetensors +3 -0
- model-00018-of-00171.safetensors +3 -0
- model-00019-of-00171.safetensors +3 -0
- model-00020-of-00171.safetensors +3 -0
- model-00021-of-00171.safetensors +3 -0
- model-00022-of-00171.safetensors +3 -0
- model-00023-of-00171.safetensors +3 -0
- model-00024-of-00171.safetensors +3 -0
- model-00025-of-00171.safetensors +3 -0
- model-00026-of-00171.safetensors +3 -0
- model-00027-of-00171.safetensors +3 -0
- model-00028-of-00171.safetensors +3 -0
- model-00029-of-00171.safetensors +3 -0
- model-00030-of-00171.safetensors +3 -0
- model-00031-of-00171.safetensors +3 -0
- model-00032-of-00171.safetensors +3 -0
- model-00033-of-00171.safetensors +3 -0
- model-00034-of-00171.safetensors +3 -0
- model-00035-of-00171.safetensors +3 -0
- model-00036-of-00171.safetensors +3 -0
- model-00037-of-00171.safetensors +3 -0
- model-00038-of-00171.safetensors +3 -0
- model-00039-of-00171.safetensors +3 -0
- model-00040-of-00171.safetensors +3 -0
- model-00041-of-00171.safetensors +3 -0
- model-00042-of-00171.safetensors +3 -0
- model-00043-of-00171.safetensors +3 -0
- model-00044-of-00171.safetensors +3 -0
- model-00045-of-00171.safetensors +3 -0
LICENSE
ADDED
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
MIT License
|
2 |
+
|
3 |
+
Copyright (c) 2023 DeepSeek
|
4 |
+
|
5 |
+
Permission is hereby granted, free of charge, to any person obtaining a copy
|
6 |
+
of this software and associated documentation files (the "Software"), to deal
|
7 |
+
in the Software without restriction, including without limitation the rights
|
8 |
+
to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
|
9 |
+
copies of the Software, and to permit persons to whom the Software is
|
10 |
+
furnished to do so, subject to the following conditions:
|
11 |
+
|
12 |
+
The above copyright notice and this permission notice shall be included in all
|
13 |
+
copies or substantial portions of the Software.
|
14 |
+
|
15 |
+
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
|
16 |
+
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
|
17 |
+
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
|
18 |
+
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
|
19 |
+
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
|
20 |
+
OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
|
21 |
+
SOFTWARE.
|
coding_problems.py
ADDED
@@ -0,0 +1,201 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
coding_problems = {
|
2 |
+
"Python": "In Python, write a function to reverse a string, for example, turning input 'hello' into 'olleh'.",
|
3 |
+
"Java": "In Java, implement a simple calculator class that supports addition, subtraction, multiplication, and division.",
|
4 |
+
"C++": "In C++, implement an efficient sorting algorithm (e.g., quicksort or mergesort) to sort an array of integers.",
|
5 |
+
"JavaScript": "In JavaScript, create a simple web page interaction with a button that, when clicked, displays the current time.",
|
6 |
+
"C#": "In C#, implement a simple Windows Forms application featuring a text box and a button that displays the text box content when clicked.",
|
7 |
+
"Ruby": "In Ruby, implement a simple web server using Ruby on Rails that returns 'Hello, World!'",
|
8 |
+
"PHP": "In PHP, create a dynamic web page that displays the current date and time.",
|
9 |
+
"Swift": "In Swift, implement a simple iOS app interface with a label and a button that updates the label to 'Clicked!' when pressed.",
|
10 |
+
"Go": "In Go, implement a concurrent program using goroutines to calculate the square and cube of two numbers simultaneously.",
|
11 |
+
"R": "In R, read data from a CSV file, calculate the average, and plot a bar chart.",
|
12 |
+
"SQL": "In SQL, write a query to retrieve the total number of orders for each user from 'users' and 'orders' tables.",
|
13 |
+
"Kotlin": "In Kotlin, implement a simple Android app feature with an input field and a button that displays the input content when clicked.",
|
14 |
+
"Scala": "In Scala, implement a functional programming example with a function that takes a list of integers and returns their sum.",
|
15 |
+
"Perl": "In Perl, implement a text processing script to extract all email addresses from a text file.",
|
16 |
+
"Haskell": "In Haskell, implement a pure functional program to calculate the nth Fibonacci number.",
|
17 |
+
"Lua": "In Lua, implement a game script to control a character's simple movements (e.g., up, down, left, right).",
|
18 |
+
"MATLAB": "In MATLAB, implement matrix multiplication and visualize the result.",
|
19 |
+
"Objective-C": "In Objective-C, implement a simple iOS app feature with a button that shows an alert with 'Welcome!' when clicked.",
|
20 |
+
"Rust": "In Rust, implement a safe concurrent program to calculate the sum of all elements in an array using multiple threads.",
|
21 |
+
"TypeScript": "In TypeScript, implement a type-safe function that takes an array of numbers and returns the maximum value.",
|
22 |
+
"Bash": "In Bash, write a shell script to backup a specified directory to a compressed file.",
|
23 |
+
"PowerShell": "In PowerShell, implement a system management script to list all running processes.",
|
24 |
+
"Dart": "In Dart, implement a simple Flutter app interface with a counter button.",
|
25 |
+
"Groovy": "In Groovy, implement a simple script to read and print the content of a JSON file.",
|
26 |
+
"F#": "In F#, implement a functional programming example with a function to calculate the product of all elements in an integer list.",
|
27 |
+
"Erlang": "In Erlang, implement a simple distributed chat server that supports multiple client connections.",
|
28 |
+
"COBOL": "In COBOL, implement a business calculation program to compute an employee's total salary (base salary + bonus).",
|
29 |
+
"Fortran": "In Fortran, implement a scientific computing program to calculate a definite integral (e.g., using the rectangle method).",
|
30 |
+
"Ada": "In Ada, implement an embedded system program to simulate controlling an LED light (on/off).",
|
31 |
+
"Prolog": "In Prolog, implement a logic reasoning program to solve a simple puzzle, such as 'Who is the murderer?'",
|
32 |
+
"Lisp": "In Lisp, implement a symbolic computation program to evaluate a simple mathematical expression, e.g., '(add 2 3)'.",
|
33 |
+
"Scheme": "In Scheme, implement a recursive function to calculate the factorial of n.",
|
34 |
+
"Smalltalk": "In Smalltalk, implement an object-oriented program to simulate bank account deposits and withdrawals.",
|
35 |
+
"VHDL": "In VHDL, design a simple digital circuit, such as an adder.",
|
36 |
+
"Verilog": "In Verilog, implement a hardware module for a simple sequential logic circuit, like a counter.",
|
37 |
+
"Assembly": "In Assembly, write a low-level program to compute the sum of two numbers.",
|
38 |
+
"Clojure": "In Clojure, implement a concurrent program using concurrency primitives to compute the sum of squares of an array.",
|
39 |
+
"Elixir": "In Elixir, implement a simple distributed counter.",
|
40 |
+
"Julia": "In Julia, implement a high-performance computing program for matrix multiplication and measure execution time.",
|
41 |
+
"Crystal": "In Crystal, implement a web application that returns a JSON response.",
|
42 |
+
"Nim": "In Nim, implement a command-line tool that accepts arguments and prints the content of a file.",
|
43 |
+
"D": "In D, implement a system-level program to list all files in a directory.",
|
44 |
+
"Pascal": "In Pascal, implement a teaching program demonstrating if-else and loop structures.",
|
45 |
+
"Forth": "In Forth, implement a stack-based addition calculator.",
|
46 |
+
"APL": "In APL, implement an array processing program to sort an array and calculate its average.",
|
47 |
+
"J": "In J, implement a data analysis program to compute the standard deviation of a dataset.",
|
48 |
+
"K": "In K, implement a high-performance data processing program to compute the sum of a large array.",
|
49 |
+
"Q": "In Q, implement a database query to retrieve data from a time-series database for a specific period.",
|
50 |
+
"Tcl": "In Tcl, implement a script to automate file renaming.",
|
51 |
+
"Awk": "In Awk, implement a text processing script to extract the second field from each line of a log file.",
|
52 |
+
"Sed": "In Sed, implement a text replacement script to replace 'cat' with 'dog' in a text file.",
|
53 |
+
"Grep": "In Grep, implement a pattern matching script to find lines containing 'error' in a file.",
|
54 |
+
"Makefile": "In Makefile, write a build script to compile a C program and generate an executable file.",
|
55 |
+
"CMake": "In CMake, implement a cross-platform build system configuration.",
|
56 |
+
"Dockerfile": "In Dockerfile, write a container configuration file to build a Docker image with a Python environment.",
|
57 |
+
"YAML": "In YAML, implement a configuration file for a web application, specifying port and database connection.",
|
58 |
+
"JSON": "In JSON, implement a data exchange format to represent a user's personal information.",
|
59 |
+
"XML": "In XML, implement a markup language document to describe a book's title and author.",
|
60 |
+
"HTML": "In HTML, implement a simple web page with a title and a paragraph.",
|
61 |
+
"CSS": "In CSS, implement a style sheet to add background color and font styles to an HTML page.",
|
62 |
+
"Sass": "In Sass, implement a CSS preprocessor script to generate nested style sheets.",
|
63 |
+
"Less": "In Less, implement a CSS preprocessor script using variables to define colors and generate CSS.",
|
64 |
+
"PostScript": "In PostScript, implement a print script to generate a circle graphic.",
|
65 |
+
"TeX": "In TeX, implement a typesetting document that includes mathematical formulas.",
|
66 |
+
"ABAP": "In ABAP, implement a report program to retrieve and display customer data from an SAP database.",
|
67 |
+
"ActionScript": "In ActionScript, create an interactive animation where a ball moves across the screen when a button is clicked.",
|
68 |
+
"ALGOL": "In ALGOL, implement a procedure to calculate the greatest common divisor (GCD) of two numbers.",
|
69 |
+
"Ballerina": "In Ballerina, implement a simple REST API service that returns a greeting message.",
|
70 |
+
"Basic": "In Basic, write a program to calculate and display the area of a rectangle based on user input.",
|
71 |
+
"BCPL": "In BCPL, implement a simple memory allocation function for dynamic arrays.",
|
72 |
+
"Chapel": "In Chapel, implement a parallel program to compute the dot product of two large vectors.",
|
73 |
+
"ColdFusion": "In ColdFusion, create a dynamic webpage that displays a list of products from a database.",
|
74 |
+
"Datalog": "In Datalog, write a query to determine family relationships (e.g., 'Who is the grandparent?') from a set of facts.",
|
75 |
+
"Elm": "In Elm, implement a simple counter web app with increment and decrement buttons.",
|
76 |
+
"Hack": "In Hack, implement a type-safe function to validate and process a user registration form.",
|
77 |
+
"Icon": "In Icon, write a program to generate all permutations of a given string.",
|
78 |
+
"Io": "In Io, implement a prototype-based object system to simulate a simple car with start and stop methods.",
|
79 |
+
"J#": "In J#, implement a console application to sort a list of names alphabetically.",
|
80 |
+
"LabVIEW": "In LabVIEW, create a virtual instrument to measure and display the voltage from a simulated sensor.",
|
81 |
+
"Ladder Logic": "In Ladder Logic, design a PLC program to control a traffic light sequence.",
|
82 |
+
"LiveScript": "In LiveScript, implement a functional pipeline to process and filter an array of numbers.",
|
83 |
+
"Logo": "In Logo, write a script to draw a square using turtle graphics.",
|
84 |
+
"Mercury": "In Mercury, implement a type-safe program to solve a Sudoku puzzle.",
|
85 |
+
"Modula-2": "In Modula-2, implement a module to manage a simple inventory system.",
|
86 |
+
"OCaml": "In OCaml, implement a function to balance a binary search tree.",
|
87 |
+
"PL/I": "In PL/I, write a program to calculate monthly loan payments based on principal and interest rate.",
|
88 |
+
"Processing": "In Processing, create a visual sketch where circles follow the mouse cursor.",
|
89 |
+
"Puppet": "In Puppet, write a manifest to configure a web server with specific ports and packages.",
|
90 |
+
"Racket": "In Racket, implement a simple interpreter for a custom arithmetic language.",
|
91 |
+
"REXX": "In REXX, write a script to parse and reformat a log file into a report.",
|
92 |
+
"SAS": "In SAS, implement a data analysis program to compute summary statistics from a dataset.",
|
93 |
+
"Scratch": "In Scratch, create a simple game where a sprite moves to avoid obstacles.",
|
94 |
+
"Solidity": "In Solidity, implement a smart contract for a voting system on the Ethereum blockchain.",
|
95 |
+
"SPARK": "In SPARK, implement a verified program to control an elevator��s floor selection safely.",
|
96 |
+
"Squirrel": "In Squirrel, write a script to manage a simple game character��s health and inventory.",
|
97 |
+
"Stan": "In Stan, implement a Bayesian model to fit a linear regression to sample data.",
|
98 |
+
"Vala": "In Vala, implement a GTK application with a window and a button that changes color when clicked.",
|
99 |
+
"VBA": "In VBA, automate an Excel task to sum a column and highlight cells above a threshold.",
|
100 |
+
"Zig": "In Zig, implement a memory-safe program to reverse an array without using extra space.",
|
101 |
+
"Apex": "In Apex, implement a Salesforce trigger to automatically update a contact��s status when an opportunity is closed.",
|
102 |
+
"B": "In B, write a low-level function to swap two integer values without using a temporary variable.",
|
103 |
+
"Brainfuck": "In Brainfuck, implement a program to print 'Hello, World!' using its minimalistic syntax.",
|
104 |
+
"Ceylon": "In Ceylon, implement a type-safe class hierarchy for a library system with books and borrowers.",
|
105 |
+
"CFML": "In CFML, create a dynamic page to display a user��s profile fetched from a database.",
|
106 |
+
"Chisel": "In Chisel, design a hardware module for a simple 4-bit counter.",
|
107 |
+
"Clarion": "In Clarion, implement a database application to manage customer orders and invoices.",
|
108 |
+
"Clean": "In Clean, implement a purely functional program to compute the greatest common divisor (GCD) of two numbers.",
|
109 |
+
"Clipper": "In Clipper, write a program to manage a simple inventory database with add and delete functions.",
|
110 |
+
"Common Lisp": "In Common Lisp, implement a symbolic differentiation function for basic algebraic expressions.",
|
111 |
+
"Dafny": "In Dafny, implement a verified program to sort an array with provable correctness.",
|
112 |
+
"Delphi": "In Delphi, create a desktop application with a form to calculate and display a factorial.",
|
113 |
+
"Eiffel": "In Eiffel, implement a class with design-by-contract to manage a stack with push and pop operations.",
|
114 |
+
"Elm": "In Elm, build a simple web app with a text input that displays the character count in real-time.",
|
115 |
+
"Factor": "In Factor, implement a stack-based program to calculate the sum of numbers from 1 to n.",
|
116 |
+
"Falcon": "In Falcon, write a script to process and format a CSV file into a readable report.",
|
117 |
+
"Frink": "In Frink, implement a unit conversion program to convert between miles and kilometers.",
|
118 |
+
"GAMS": "In GAMS, model an optimization problem to minimize the cost of a production process.",
|
119 |
+
"GAP": "In GAP, implement a group theory computation to find the order of a permutation group.",
|
120 |
+
"Genie": "In Genie, create a simple GTK application with a button that toggles a label��s text.",
|
121 |
+
"Haxe": "In Haxe, implement a cross-platform program to draw a animated bouncing ball.",
|
122 |
+
"Hy": "In Hy, write a Lisp-style program to filter even numbers from a list.",
|
123 |
+
"Idris": "In Idris, implement a dependently-typed function to append two lists with length preservation.",
|
124 |
+
"Inform": "In Inform, create a simple text adventure game where the player navigates a room.",
|
125 |
+
"JCL": "In JCL, write a job control script to execute a COBOL program on a mainframe.",
|
126 |
+
"Jython": "In Jython, implement a Python script to interact with a Java library and print system properties.",
|
127 |
+
"KRL": "In KRL, design a rule-based system to send a notification when a sensor value exceeds a threshold.",
|
128 |
+
"LFE": "In LFE, implement a Lisp-based concurrent program to calculate factorials using actors.",
|
129 |
+
"MQL4": "In MQL4, write a trading script for MetaTrader to calculate moving averages of stock prices.",
|
130 |
+
"Nemerle": "In Nemerle, implement a macro-based program to generate boilerplate code for a class.",
|
131 |
+
"Oberon": "In Oberon, write a modular program to simulate a simple file system.",
|
132 |
+
"Opa": "In Opa, implement a full-stack web app with a chat interface running on both client and server.",
|
133 |
+
"OpenCL": "In OpenCL, write a parallel program to perform matrix addition on a GPU.",
|
134 |
+
"Oz": "In Oz, implement a multi-paradigm program to solve a constraint satisfaction problem like Sudoku.",
|
135 |
+
"Pike": "In Pike, create a simple network server that echoes back client messages.",
|
136 |
+
"Pony": "In Pony, implement an actor-based program to simulate a bank with concurrent transactions.",
|
137 |
+
"Pure": "In Pure, write a term-rewriting program to simplify algebraic expressions.",
|
138 |
+
"Q#": "In Q#, implement a quantum algorithm to generate a random bit using superposition.",
|
139 |
+
"Red": "In Red, create a lightweight GUI app with a button that changes the window��s title.",
|
140 |
+
"Ring": "In Ring, implement a simple game loop to move a character across the screen.",
|
141 |
+
"RPG": "In RPG, write a business program to calculate employee payroll with tax deductions.",
|
142 |
+
"S-Lang": "In S-Lang, implement a script to process astronomical data and compute averages.",
|
143 |
+
"Simula": "In Simula, simulate a queueing system for customers in a bank.",
|
144 |
+
"Standard ML": "In Standard ML, implement a functional program to reverse a list using pattern matching.",
|
145 |
+
"SuperCollider": "In SuperCollider, create a synthesizer script to generate a sine wave sound.",
|
146 |
+
"Turing": "In Turing, write an educational program to draw a spiral using turtle graphics.",
|
147 |
+
"UnrealScript": "In UnrealScript, implement a simple game mechanic to spawn an enemy in Unreal Engine.",
|
148 |
+
"Wolfram Language": "In Wolfram Language, create a visualization of a 3D mathematical function.",
|
149 |
+
"X10": "In X10, implement a distributed program to compute the sum of an array across multiple nodes.",
|
150 |
+
"ZPL": "In ZPL, write a parallel program to perform a stencil computation on a 2D grid.",
|
151 |
+
"A#": "In A#, implement a simple audio processing script to generate a square wave tone.",
|
152 |
+
"ABC": "In ABC, write a program to calculate and display the first 10 numbers of the Fibonacci sequence.",
|
153 |
+
"Accent": "In Accent, implement a reactive system to update a counter based on incoming events.",
|
154 |
+
"Agora": "In Agora, create an object-oriented program to simulate a simple online auction.",
|
155 |
+
"Alef": "In Alef, implement a concurrent program to manage multiple threads printing numbers.",
|
156 |
+
"Alice": "In Alice, design a 3D animation where a character walks across a scene.",
|
157 |
+
"Amiga E": "In Amiga E, write a program to draw a colorful pattern on an Amiga-style display.",
|
158 |
+
"AngelScript": "In AngelScript, implement a game scripting function to handle player movement in a 2D game.",
|
159 |
+
"APL2": "In APL2, write an array-based program to compute the transpose of a matrix.",
|
160 |
+
"Arc": "In Arc, implement a minimal web server that serves a custom HTML page.",
|
161 |
+
"AspectJ": "In AspectJ, add logging functionality to an existing Java class using aspects.",
|
162 |
+
"Ateji PX": "In Ateji PX, implement a parallel program to compute the sum of a large array.",
|
163 |
+
"AutoHotkey": "In AutoHotkey, create a script to automate repetitive keyboard and mouse actions.",
|
164 |
+
"Befunge": "In Befunge, write a 2D program to print the numbers from 1 to 10.",
|
165 |
+
"BLISS": "In BLISS, implement a low-level routine to optimize bit manipulation in a system program.",
|
166 |
+
"Boo": "In Boo, create a simple scripting program to process and sort a list of strings.",
|
167 |
+
"C--": "In C--, implement an intermediate language function to multiply two integers.",
|
168 |
+
"Caml": "In Caml, write a functional program to compute the depth of a binary tree.",
|
169 |
+
"Charity": "In Charity, implement a purely functional program to process a stream of integers.",
|
170 |
+
"ChucK": "In ChucK, create a real-time audio program to play a repeating drum pattern.",
|
171 |
+
"Cilk": "In Cilk, implement a parallel program to compute the factorial of a number using spawn and sync.",
|
172 |
+
"COMAL": "In COMAL, write an educational program to teach loops by printing a multiplication table.",
|
173 |
+
"Curl": "In Curl, implement a rich internet application with a clickable button that changes text.",
|
174 |
+
"DASL": "In DASL, design a dataflow program to filter and transform a stream of sensor data.",
|
175 |
+
"DIBOL": "In DIBOL, write a business application to calculate total sales from a list of transactions.",
|
176 |
+
"E": "In E, implement a secure distributed system to exchange encrypted messages between two nodes.",
|
177 |
+
"Ease": "In Ease, create a visual programming script to animate a bouncing ball.",
|
178 |
+
"Euphoria": "In Euphoria, write a simple interpreter for a custom command language.",
|
179 |
+
"Fantom": "In Fantom, implement a cross-platform program to read and display a configuration file.",
|
180 |
+
"Ferite": "In Ferite, create a lightweight script to simulate a dice-rolling game.",
|
181 |
+
"FL": "In FL, implement a functional logic program to solve a simple puzzle like Towers of Hanoi.",
|
182 |
+
"Focal": "In Focal, write a scientific calculator program to compute trigonometric functions.",
|
183 |
+
"GameMaker Language": "In GameMaker Language, implement a simple platformer mechanic for jumping.",
|
184 |
+
"GML": "In GML, design a graph manipulation program to find the shortest path between nodes.",
|
185 |
+
"Hope": "In Hope, implement a lazy functional program to generate an infinite list of primes.",
|
186 |
+
"ICI": "In ICI, write a script to process and reformat a text file into a table.",
|
187 |
+
"INTERCAL": "In INTERCAL, create a humorous program to compute '2 + 2' with unnecessary complexity.",
|
188 |
+
"Joy": "In Joy, implement a stack-based program to reverse a sequence of numbers.",
|
189 |
+
"Kodu": "In Kodu, design a simple game where a character collects objects in a 3D world.",
|
190 |
+
"Leda": "In Leda, write a multi-paradigm program combining imperative and functional styles to sort a list.",
|
191 |
+
"Limbo": "In Limbo, implement a concurrent program for a distributed system running on Inferno OS.",
|
192 |
+
"Miranda": "In Miranda, create a lazy functional program to compute the sum of squares up to n.",
|
193 |
+
"MUMPS": "In MUMPS, implement a database application to store and retrieve patient records.",
|
194 |
+
"Nial": "In Nial, write an array-oriented program to compute the average of nested arrays.",
|
195 |
+
"Obliq": "In Obliq, implement a distributed GUI application with a button that updates remotely.",
|
196 |
+
"OmniMark": "In OmniMark, create a text-processing script to convert XML to HTML.",
|
197 |
+
"Opal": "In Opal, implement a functional program to manipulate algebraic data types like lists.",
|
198 |
+
"PILOT": "In PILOT, write an educational script to quiz users on basic math problems.",
|
199 |
+
"Self": "In Self, implement a prototype-based object system to model a simple car with behaviors.",
|
200 |
+
"TOM": "In TOM, create a pattern-matching program to transform a string based on rules."
|
201 |
+
}
|
config.json
ADDED
@@ -0,0 +1,61 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"architectures": [
|
3 |
+
"DeepseekV3ForCausalLM"
|
4 |
+
],
|
5 |
+
"attention_bias": false,
|
6 |
+
"attention_dropout": 0.0,
|
7 |
+
"auto_map": {
|
8 |
+
"AutoConfig": "configuration_deepseek.DeepseekV3Config",
|
9 |
+
"AutoModel": "modeling_deepseek.DeepseekV3Model",
|
10 |
+
"AutoModelForCausalLM": "modeling_deepseek.DeepseekV3ForCausalLM"
|
11 |
+
},
|
12 |
+
"aux_loss_alpha": 0.001,
|
13 |
+
"bos_token_id": 0,
|
14 |
+
"eos_token_id": 1,
|
15 |
+
"ep_size": 1,
|
16 |
+
"first_k_dense_replace": 3,
|
17 |
+
"hidden_act": "silu",
|
18 |
+
"hidden_size": 7168,
|
19 |
+
"initializer_range": 0.02,
|
20 |
+
"intermediate_size": 18432,
|
21 |
+
"kv_lora_rank": 512,
|
22 |
+
"max_position_embeddings": 163840,
|
23 |
+
"model_type": "deepseek_v3",
|
24 |
+
"moe_intermediate_size": 2048,
|
25 |
+
"moe_layer_freq": 1,
|
26 |
+
"n_group": 8,
|
27 |
+
"n_routed_experts": 160,
|
28 |
+
"n_shared_experts": 1,
|
29 |
+
"norm_topk_prob": true,
|
30 |
+
"num_attention_heads": 128,
|
31 |
+
"num_experts_per_tok": 6,
|
32 |
+
"num_hidden_layers": 61,
|
33 |
+
"num_key_value_heads": 128,
|
34 |
+
"num_nextn_predict_layers": 1,
|
35 |
+
"pretraining_tp": 1,
|
36 |
+
"q_lora_rank": 1536,
|
37 |
+
"qk_nope_head_dim": 128,
|
38 |
+
"qk_rope_head_dim": 64,
|
39 |
+
"rms_norm_eps": 1e-06,
|
40 |
+
"rope_scaling": {
|
41 |
+
"beta_fast": 32,
|
42 |
+
"beta_slow": 1,
|
43 |
+
"factor": 40,
|
44 |
+
"mscale": 1.0,
|
45 |
+
"mscale_all_dim": 1.0,
|
46 |
+
"original_max_position_embeddings": 4096,
|
47 |
+
"type": "yarn"
|
48 |
+
},
|
49 |
+
"rope_theta": 10000,
|
50 |
+
"routed_scaling_factor": 2.5,
|
51 |
+
"scoring_func": "sigmoid",
|
52 |
+
"seq_aux": true,
|
53 |
+
"tie_word_embeddings": false,
|
54 |
+
"topk_group": 4,
|
55 |
+
"topk_method": "noaux_tc",
|
56 |
+
"torch_dtype": "bfloat16",
|
57 |
+
"transformers_version": "4.46.3",
|
58 |
+
"use_cache": true,
|
59 |
+
"v_head_dim": 128,
|
60 |
+
"vocab_size": 129280
|
61 |
+
}
|
configuration_deepseek.py
ADDED
@@ -0,0 +1,210 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
from transformers.configuration_utils import PretrainedConfig
|
2 |
+
from transformers.utils import logging
|
3 |
+
|
4 |
+
logger = logging.get_logger(__name__)
|
5 |
+
|
6 |
+
DEEPSEEK_PRETRAINED_CONFIG_ARCHIVE_MAP = {}
|
7 |
+
class DeepseekV3Config(PretrainedConfig):
|
8 |
+
r"""
|
9 |
+
This is the configuration class to store the configuration of a [`DeepseekV3Model`]. It is used to instantiate an DeepSeek
|
10 |
+
model according to the specified arguments, defining the model architecture. Instantiating a configuration with the
|
11 |
+
defaults will yield a similar configuration to that of the DeepSeek-V3.
|
12 |
+
|
13 |
+
Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model outputs. Read the
|
14 |
+
documentation from [`PretrainedConfig`] for more information.
|
15 |
+
|
16 |
+
|
17 |
+
Args:
|
18 |
+
vocab_size (`int`, *optional*, defaults to 129280):
|
19 |
+
Vocabulary size of the Deep model. Defines the number of different tokens that can be represented by the
|
20 |
+
`inputs_ids` passed when calling [`DeepseekV3Model`]
|
21 |
+
hidden_size (`int`, *optional*, defaults to 4096):
|
22 |
+
Dimension of the hidden representations.
|
23 |
+
intermediate_size (`int`, *optional*, defaults to 11008):
|
24 |
+
Dimension of the MLP representations.
|
25 |
+
moe_intermediate_size (`int`, *optional*, defaults to 1407):
|
26 |
+
Dimension of the MoE representations.
|
27 |
+
num_hidden_layers (`int`, *optional*, defaults to 32):
|
28 |
+
Number of hidden layers in the Transformer decoder.
|
29 |
+
num_nextn_predict_layers (`int`, *optional*, defaults to 1):
|
30 |
+
Number of nextn predict layers in the DeepSeekV3 Model.
|
31 |
+
num_attention_heads (`int`, *optional*, defaults to 32):
|
32 |
+
Number of attention heads for each attention layer in the Transformer decoder.
|
33 |
+
n_shared_experts (`int`, *optional*, defaults to None):
|
34 |
+
Number of shared experts, None means dense model.
|
35 |
+
n_routed_experts (`int`, *optional*, defaults to None):
|
36 |
+
Number of routed experts, None means dense model.
|
37 |
+
routed_scaling_factor (`float`, *optional*, defaults to 1.0):
|
38 |
+
Scaling factor or routed experts.
|
39 |
+
topk_method (`str`, *optional*, defaults to `gready`):
|
40 |
+
Topk method used in routed gate.
|
41 |
+
n_group (`int`, *optional*, defaults to None):
|
42 |
+
Number of groups for routed experts.
|
43 |
+
topk_group (`int`, *optional*, defaults to None):
|
44 |
+
Number of selected groups for each token(for each token, ensuring the selected experts is only within `topk_group` groups).
|
45 |
+
num_experts_per_tok (`int`, *optional*, defaults to None):
|
46 |
+
Number of selected experts, None means dense model.
|
47 |
+
moe_layer_freq (`int`, *optional*, defaults to 1):
|
48 |
+
The frequency of the MoE layer: one expert layer for every `moe_layer_freq - 1` dense layers.
|
49 |
+
first_k_dense_replace (`int`, *optional*, defaults to 0):
|
50 |
+
Number of dense layers in shallow layers(embed->dense->dense->...->dense->moe->moe...->lm_head).
|
51 |
+
\--k dense layers--/
|
52 |
+
norm_topk_prob (`bool`, *optional*, defaults to False):
|
53 |
+
Whether to normalize the weights of the routed experts.
|
54 |
+
scoring_func (`str`, *optional*, defaults to 'softmax'):
|
55 |
+
Method of computing expert weights.
|
56 |
+
aux_loss_alpha (`float`, *optional*, defaults to 0.001):
|
57 |
+
Auxiliary loss weight coefficient.
|
58 |
+
seq_aux = (`bool`, *optional*, defaults to True):
|
59 |
+
Whether to compute the auxiliary loss for each individual sample.
|
60 |
+
num_key_value_heads (`int`, *optional*):
|
61 |
+
This is the number of key_value heads that should be used to implement Grouped Query Attention. If
|
62 |
+
`num_key_value_heads=num_attention_heads`, the model will use Multi Head Attention (MHA), if
|
63 |
+
`num_key_value_heads=1 the model will use Multi Query Attention (MQA) otherwise GQA is used. When
|
64 |
+
converting a multi-head checkpoint to a GQA checkpoint, each group key and value head should be constructed
|
65 |
+
by meanpooling all the original heads within that group. For more details checkout [this
|
66 |
+
paper](https://arxiv.org/pdf/2305.13245.pdf). If it is not specified, will default to
|
67 |
+
`num_attention_heads`.
|
68 |
+
hidden_act (`str` or `function`, *optional*, defaults to `"silu"`):
|
69 |
+
The non-linear activation function (function or string) in the decoder.
|
70 |
+
max_position_embeddings (`int`, *optional*, defaults to 2048):
|
71 |
+
The maximum sequence length that this model might ever be used with.
|
72 |
+
initializer_range (`float`, *optional*, defaults to 0.02):
|
73 |
+
The standard deviation of the truncated_normal_initializer for initializing all weight matrices.
|
74 |
+
rms_norm_eps (`float`, *optional*, defaults to 1e-06):
|
75 |
+
The epsilon used by the rms normalization layers.
|
76 |
+
use_cache (`bool`, *optional*, defaults to `True`):
|
77 |
+
Whether or not the model should return the last key/values attentions (not used by all models). Only
|
78 |
+
relevant if `config.is_decoder=True`.
|
79 |
+
pad_token_id (`int`, *optional*):
|
80 |
+
Padding token id.
|
81 |
+
bos_token_id (`int`, *optional*, defaults to 1):
|
82 |
+
Beginning of stream token id.
|
83 |
+
eos_token_id (`int`, *optional*, defaults to 2):
|
84 |
+
End of stream token id.
|
85 |
+
pretraining_tp (`int`, *optional*, defaults to 1):
|
86 |
+
Experimental feature. Tensor parallelism rank used during pretraining. Please refer to [this
|
87 |
+
document](https://huggingface.co/docs/transformers/parallelism) to understand more about it. This value is
|
88 |
+
necessary to ensure exact reproducibility of the pretraining results. Please refer to [this
|
89 |
+
issue](https://github.com/pytorch/pytorch/issues/76232).
|
90 |
+
tie_word_embeddings (`bool`, *optional*, defaults to `False`):
|
91 |
+
Whether to tie weight embeddings
|
92 |
+
rope_theta (`float`, *optional*, defaults to 10000.0):
|
93 |
+
The base period of the RoPE embeddings.
|
94 |
+
rope_scaling (`Dict`, *optional*):
|
95 |
+
Dictionary containing the scaling configuration for the RoPE embeddings. Currently supports two scaling
|
96 |
+
strategies: linear and dynamic. Their scaling factor must be a float greater than 1. The expected format is
|
97 |
+
`{"type": strategy name, "factor": scaling factor}`. When using this flag, don't update
|
98 |
+
`max_position_embeddings` to the expected new maximum.
|
99 |
+
attention_bias (`bool`, defaults to `False`, *optional*, defaults to `False`):
|
100 |
+
Whether to use a bias in the query, key, value and output projection layers during self-attention.
|
101 |
+
attention_dropout (`float`, *optional*, defaults to 0.0):
|
102 |
+
The dropout ratio for the attention probabilities.
|
103 |
+
|
104 |
+
```python
|
105 |
+
>>> from transformers import DeepseekV3Model, DeepseekV3Config
|
106 |
+
|
107 |
+
>>> # Initializing a Deepseek-V3 style configuration
|
108 |
+
>>> configuration = DeepseekV3Config()
|
109 |
+
|
110 |
+
>>> # Accessing the model configuration
|
111 |
+
>>> configuration = model.config
|
112 |
+
```"""
|
113 |
+
|
114 |
+
model_type = "deepseek_v3"
|
115 |
+
keys_to_ignore_at_inference = ["past_key_values"]
|
116 |
+
|
117 |
+
def __init__(
|
118 |
+
self,
|
119 |
+
vocab_size=129280,
|
120 |
+
hidden_size=7168,
|
121 |
+
intermediate_size=18432,
|
122 |
+
moe_intermediate_size = 2048,
|
123 |
+
num_hidden_layers=61,
|
124 |
+
num_nextn_predict_layers=1,
|
125 |
+
num_attention_heads=128,
|
126 |
+
num_key_value_heads=128,
|
127 |
+
n_shared_experts = 1,
|
128 |
+
n_routed_experts = 256,
|
129 |
+
ep_size = 1,
|
130 |
+
routed_scaling_factor = 2.5,
|
131 |
+
kv_lora_rank = 512,
|
132 |
+
q_lora_rank = 1536,
|
133 |
+
qk_rope_head_dim = 64,
|
134 |
+
v_head_dim = 128,
|
135 |
+
qk_nope_head_dim = 128,
|
136 |
+
topk_method = 'noaux_tc',
|
137 |
+
n_group = 8,
|
138 |
+
topk_group = 4,
|
139 |
+
num_experts_per_tok = 8,
|
140 |
+
moe_layer_freq = 1,
|
141 |
+
first_k_dense_replace = 3,
|
142 |
+
norm_topk_prob = True,
|
143 |
+
scoring_func = 'sigmoid',
|
144 |
+
aux_loss_alpha = 0.001,
|
145 |
+
seq_aux = True,
|
146 |
+
hidden_act="silu",
|
147 |
+
max_position_embeddings=4096,
|
148 |
+
initializer_range=0.02,
|
149 |
+
rms_norm_eps=1e-6,
|
150 |
+
use_cache=True,
|
151 |
+
pad_token_id=None,
|
152 |
+
bos_token_id=0,
|
153 |
+
eos_token_id=1,
|
154 |
+
pretraining_tp=1,
|
155 |
+
tie_word_embeddings=False,
|
156 |
+
rope_theta=10000.0,
|
157 |
+
rope_scaling=None,
|
158 |
+
attention_bias=False,
|
159 |
+
attention_dropout=0.0,
|
160 |
+
**kwargs,
|
161 |
+
):
|
162 |
+
self.vocab_size = vocab_size
|
163 |
+
self.max_position_embeddings = max_position_embeddings
|
164 |
+
self.hidden_size = hidden_size
|
165 |
+
self.intermediate_size = intermediate_size
|
166 |
+
self.moe_intermediate_size = moe_intermediate_size
|
167 |
+
self.num_hidden_layers = num_hidden_layers
|
168 |
+
self.num_nextn_predict_layers = num_nextn_predict_layers
|
169 |
+
self.num_attention_heads = num_attention_heads
|
170 |
+
self.n_shared_experts = n_shared_experts
|
171 |
+
self.n_routed_experts = n_routed_experts
|
172 |
+
self.ep_size = ep_size
|
173 |
+
self.routed_scaling_factor = routed_scaling_factor
|
174 |
+
self.kv_lora_rank = kv_lora_rank
|
175 |
+
self.q_lora_rank = q_lora_rank
|
176 |
+
self.qk_rope_head_dim = qk_rope_head_dim
|
177 |
+
self.v_head_dim = v_head_dim
|
178 |
+
self.qk_nope_head_dim = qk_nope_head_dim
|
179 |
+
self.topk_method = topk_method
|
180 |
+
self.n_group = n_group
|
181 |
+
self.topk_group = topk_group
|
182 |
+
self.num_experts_per_tok = num_experts_per_tok
|
183 |
+
self.moe_layer_freq = moe_layer_freq
|
184 |
+
self.first_k_dense_replace = first_k_dense_replace
|
185 |
+
self.norm_topk_prob = norm_topk_prob
|
186 |
+
self.scoring_func = scoring_func
|
187 |
+
self.aux_loss_alpha = aux_loss_alpha
|
188 |
+
self.seq_aux = seq_aux
|
189 |
+
# for backward compatibility
|
190 |
+
if num_key_value_heads is None:
|
191 |
+
num_key_value_heads = num_attention_heads
|
192 |
+
|
193 |
+
self.num_key_value_heads = num_key_value_heads
|
194 |
+
self.hidden_act = hidden_act
|
195 |
+
self.initializer_range = initializer_range
|
196 |
+
self.rms_norm_eps = rms_norm_eps
|
197 |
+
self.pretraining_tp = pretraining_tp
|
198 |
+
self.use_cache = use_cache
|
199 |
+
self.rope_theta = rope_theta
|
200 |
+
self.rope_scaling = rope_scaling
|
201 |
+
self.attention_bias = attention_bias
|
202 |
+
self.attention_dropout = attention_dropout
|
203 |
+
|
204 |
+
super().__init__(
|
205 |
+
pad_token_id=pad_token_id,
|
206 |
+
bos_token_id=bos_token_id,
|
207 |
+
eos_token_id=eos_token_id,
|
208 |
+
tie_word_embeddings=tie_word_embeddings,
|
209 |
+
**kwargs,
|
210 |
+
)
|
generation_config.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 0,
|
4 |
+
"eos_token_id": 1,
|
5 |
+
"do_sample": true,
|
6 |
+
"temperature": 0.6,
|
7 |
+
"top_p": 0.95,
|
8 |
+
"transformers_version": "4.39.3"
|
9 |
+
}
|
model-00001-of-00171.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0653dca2ed0be0caf03a5aa3db3bcbf68a0e79d2ca8765ccd207a379c803f0e9
|
3 |
+
size 4825751392
|
model-00002-of-00171.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b12e9e387abadd8c61e553ce80ab6b899492a18ff4010b4807d19c0715d0fa7c
|
3 |
+
size 4983801968
|
model-00003-of-00171.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2d770869f9adb3d3c08dc98a68055d1a7cd2810eeb095c70844689921b1cec79
|
3 |
+
size 4991242864
|
model-00004-of-00171.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d70d02a0e10f7f4f9544d90a54ad38d56188c7b77d23b2607b5f9e922d5b1d29
|
3 |
+
size 4991243024
|
model-00005-of-00171.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1bfa7281afec6686c9a7969979611eb6918c5f43f04b2297a4a55927ab1ecc02
|
3 |
+
size 4986098256
|
model-00006-of-00171.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a473e30455d15ac7839f99e44a54922c6933b433d6f36d88cc374836cee01f43
|
3 |
+
size 4991242880
|
model-00007-of-00171.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7ca0c9d13447f11ec1cf12e227dbbeffafb3d2ab0ff22c1c6475aa96da35a790
|
3 |
+
size 4839298064
|
model-00008-of-00171.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:da0dd556bdc9e8b7fc24a3ff515248ef07bd8e578ebe319da0d8ba20b7201fe7
|
3 |
+
size 4991241952
|
model-00009-of-00171.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7d476febe3c733daff48e2958af8ace6682f6aa40178d9258e765301d09d6cd3
|
3 |
+
size 4991242888
|
model-00010-of-00171.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:693db222ebe63473dc56a94aa517e702d871f0354ce40d7a64c4acd74624866d
|
3 |
+
size 4986098432
|
model-00011-of-00171.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:117161b04ff34b52fb541533291690ef34900c03c91f7d0396e6bca33f80be2d
|
3 |
+
size 4991242832
|
model-00012-of-00171.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:947b8a3bc7c47d9001d0999690e7ae636f407b4c542ec129b27539b8117875a3
|
3 |
+
size 4991242904
|
model-00013-of-00171.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d77e6b5666d981cf2a480fcdf87dfefbe4ded87e2c3634df935bd5ead0b9f488
|
3 |
+
size 4986098400
|
model-00014-of-00171.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4116e4e3e68d22978c12d02d29d038317f6fa44e64b1139529f148d8315206a5
|
3 |
+
size 4991242848
|
model-00015-of-00171.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3d7ad902f2dd4634ff2f61be94b923b3c7ad2bfed9a41a1fbb735e29c203d0d8
|
3 |
+
size 4991242920
|
model-00016-of-00171.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9b7cfd4f85368556a9ec9f247f282e8564bee0e7a5608e06ee56a9098886b4fd
|
3 |
+
size 4986098376
|
model-00017-of-00171.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:23e101bb6523fd5c2f32154a89d94e8ce4f369ae3e1287a2d79f33c4b7f05792
|
3 |
+
size 4991242856
|
model-00018-of-00171.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:349d591c992e0004edc6a3275774171fceebf900adc43d98477914dd310617f9
|
3 |
+
size 4991242928
|
model-00019-of-00171.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:47fc7f1165f136551de7de116ad1921c0f8ce9007293bb88712eec55ef7c68f5
|
3 |
+
size 4986098368
|
model-00020-of-00171.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:67e1cb0371b8dc0f2600ab064214fc554fcfedc264359c73a04dc3e21aa1ba7b
|
3 |
+
size 4991242856
|
model-00021-of-00171.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2fba0a3a0c27f317bbf2e43449e52abaf532e775ce1913a7b855f1efeacd0709
|
3 |
+
size 4991242944
|
model-00022-of-00171.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5df7fbf5ca7ddf00439cb4239830f58a5d5bd74e0800d3cadec85cc31cb563f5
|
3 |
+
size 4986098432
|
model-00023-of-00171.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2550fd76fdcd7bd8a80d8f842cde88ae593d0f8979c127e5e1b219b14ffebd0d
|
3 |
+
size 4991243032
|
model-00024-of-00171.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:13bffd9cdbaa43af4ae80145812deb072fa32cfc70dbe0cc946621fc15016d75
|
3 |
+
size 4991243128
|
model-00025-of-00171.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1cfa73b613a2b0f8a08c6164d3551caf3a1497c98ddfbee0a94bba17a6be8032
|
3 |
+
size 4986098504
|
model-00026-of-00171.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6d35733b57cdef3c6a4fe930147c189ffb0b8fc3eb312bc22664311e6e2c399c
|
3 |
+
size 4991243024
|
model-00027-of-00171.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ed3a945348444106ab6fa2b85f9c5a6fe6f87820588a37302855171fa770fa40
|
3 |
+
size 4991243144
|
model-00028-of-00171.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a0d271d12d6e70a0e0ec0ffef13ae60ed4f7b74d0f16b3d137cbfb2592c67894
|
3 |
+
size 4986098488
|
model-00029-of-00171.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:68d5762e69416fd5967ac5601e944b53d28d9307f957381f21028f965003fd82
|
3 |
+
size 4991243024
|
model-00030-of-00171.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:958b205719b0c72af1afd02e441c51f7edfbbd4aa0aa00313655a4e56610e116
|
3 |
+
size 4991243160
|
model-00031-of-00171.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:33ba538b7e8ad374b37e3a36e0b9dc5db41b5a79eb47ce4d3d90b6f00cb6c318
|
3 |
+
size 4986098472
|
model-00032-of-00171.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9baf7091733f62c75c876ed52980348b28cd42f914664e6e257779f8184a7a3e
|
3 |
+
size 4991243032
|
model-00033-of-00171.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1eb3a78913a24c21b25c36a778ff67bcccc3d69844020df3dc3887a4f45e5aa7
|
3 |
+
size 4991243168
|
model-00034-of-00171.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:273db85f6096943bb33a51efa3dbf0fedaebec5c32d3623c48661e2b0ab876fd
|
3 |
+
size 4986098464
|
model-00035-of-00171.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ee6ffb7c676fb48db8fccc4c1377c487ff7c483e60e679651e67684dc025dd5c
|
3 |
+
size 4991243024
|
model-00036-of-00171.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c6566f492e34df5a1555f52063b8155565ffbbfd6a6b61ab416405e4cf247aa3
|
3 |
+
size 4991243184
|
model-00037-of-00171.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2c5f3ddb5c31e2e525f68cfda5576e9792b8634f73d6c448aa05625b9712bb56
|
3 |
+
size 4986098448
|
model-00038-of-00171.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3f330fc60ebd66751f7cf2e2dcf0d288c9f8c02cddef96a2da1d20728dcc2cd2
|
3 |
+
size 4991243032
|
model-00039-of-00171.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8e3a58b7a64a9762df520f82bbba4bd04a2942f258250c79b4f2272234194fb8
|
3 |
+
size 4991243200
|
model-00040-of-00171.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b6a1d49c7be300879805235be24dfc63f91162be9492b171706783f4c468ac06
|
3 |
+
size 4986098432
|
model-00041-of-00171.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2f747440a56f9e0cd68f316206dc8e7ce0676d25f0115b8bb76df7f3fd7debb8
|
3 |
+
size 4991243048
|
model-00042-of-00171.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1fd1eb16be4fb04568101b8975aa11c372ca4c6af759807ba3a133ab0526d20b
|
3 |
+
size 4927509056
|
model-00043-of-00171.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e163db88c59aa4830f229aab6ba22c3450f4133148ac80752b9f117c5a605b84
|
3 |
+
size 4991112056
|
model-00044-of-00171.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2814af3a989731aff868de51dda0dbe3e08d016a42dfcbc2844136033c92b01c
|
3 |
+
size 4991243056
|
model-00045-of-00171.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a144688741be09a4ddd058453bd8cb492cf1adc5ae53fb364028840322d50c79
|
3 |
+
size 4986098608
|