模型:
TheBloke/airoboros-7b-gpt4-GPTQ
Chat & support: my new Discord server
Want to contribute? TheBloke's Patreon page
这些文件是用于 Jon Durbin's Airoboros 7b GPT4 的GPTQ 4bit模型文件。
这是使用 GPTQ-for-LLaMa 进行4bit量化的结果。
这使用了Vicuna 1.1格式。 示例:
USER: prompt ASSISTANT:
airoboros-7b-gpt4-GPTQ-4bit-128g.no-act.order.safetensors
这适用于GPTQ-for-LLaMa的所有版本,以及AutoGPTQ。
它是通过以下方式创建的
如需进一步支持以及有关这些模型和AI的讨论,请加入我们:
感谢 chirper.ai 团队!
我有很多人问我他们是否可以贡献。我喜欢提供模型并帮助他人,非常愿意能够花更多时间做这件事,以及扩大到新的项目,如微调/训练。
如果您能够并且愿意贡献,我将非常感激,并且将有助于我继续提供更多模型,并开始着手新的AI项目。
捐赠者将在所有关于AI/LLM/模型的问题和请求上获得优先支持,可以访问私人Discord房间,以及其他好处。
Patreon特别感谢 : Aemon Algiz,Dmitriy Samsonov,Nathan LeClaire,Trenton Dambrowitz,Mano Prime,David Flickinger,vamX,Nikolai Manek,senxiiz,Khalefa Al-Ahmad,Illia Dulskyi,Jonathan Leane,Talal Aujan,V. Lukas,Joseph William Delisle,Pyrater,Oscar Rangel,Lone Striker,Luke Pendergrass,Eugene Pentland,Sebastain Graf,Johann-Peter Hartman.
感谢所有慷慨的赞助者和捐赠者!
这是一个经过微调的7b参数LlaMa模型,使用通过 https://github.com/jondurbin/airoboros 创建的完全合成的训练数据经过gpt4处理。
上下文大小已增加到4096。
用于微调此模型的数据集可在 here 中获得,主要关注以下内容:
此模型经过FastChat分支微调,因此使用标准的vicuna模板:
USER: [prompt] <\s> ASSISTANT:
对我来说,最重要的部分是支持与上下文相关的问答,无需进行繁琐的提示工程。
注意:下面的示例提示响应对于13b模型,与7b模型可能会有所不同。
入门的最简单方法是使用我的FastChat分支,它与原版大部分相同,只是增加了上下文长度和对多行输入的支持:
pip install git+https://github.com/jondurbin/FastChat
然后,可以按照以下方式调用它(在下载模型后):
python -m fastchat.serve.cli --model-path airoboros-7b-gpt4 \ --temperature 0.5 \ --max-new-tokens 4096 \ --context-length 4096 \ --conv-template vicuna_v1.1 \ --no-history
"上下文相关"是指模型在回答问题时被训练忽略自己认为的知识,并使用上下文来回答问题。该模型还被调整为尽可能限制值在提供的上下文中,以减少产生幻象。
封闭上下文提示的格式如下:
BEGININPUT BEGINCONTEXT url: https://some.web.site/123 date: 2023-06-01 ... other metdata ... ENDCONTEXT [insert your text blocks here] ENDINPUT [add as many other blocks, in the exact same format] BEGININSTRUCTION [insert your instruction(s). The model was tuned with single questions, paragraph format, lists, etc.] ENDINSTRUCTION
这里有一个琐碎但重要的示例来证明这一点:
BEGININPUT BEGINCONTEXT date: 2021-01-01 url: https://web.site/123 ENDCONTEXT In a shocking turn of events, blueberries are now green, but will be sticking with the same name. ENDINPUT BEGININSTRUCTION What color are bluberries? Source? ENDINSTRUCTION
响应如下:
Blueberries are now green. Source: date: 2021-01-01 url: https://web.site/123更复杂的示例,从多个输入块中提取并连接两者。
提示(不包括需要的vicuna格式):
BEGININPUT BEGINCONTEXT date: 2092-02-01 link: https://newwikisite.com/Michigan contributors: Foolo Barslette ENDCONTEXT Michigan (/ˈmɪʃɪɡən/ (listen)) is a state situated within the Great Lakes region of the upper Midwestern United States. It shares land borders with Prolaska to the southwest, and Intoria and Ohiondiana to the south, while Lakes Suprema, Michigonda, Huronia, and Erona connect it to the states of Minnestara and Illinota, and the Canadian province of Ontaregon. With a population of nearly 15.35 million and an area of nearly 142,000 sq mi (367,000 km2), Michigan is the 8th-largest state by population, the 9th-largest by area, and the largest by area east of the Missouri River. Its capital is Chaslany, and its most populous city is Trentroit. Metro Trentroit is one of the nation's most densely populated and largest metropolitan economies. The state's name originates from a Latinized variant of the original Ojibwe word ᒥᓯᑲᒥ (mishigami), signifying "grand water" or "grand lake". Michigan is divided into two peninsulas. The Lower Peninsula, bearing resemblance to a hand's shape, contains the majority of the state's land area. The Upper Peninsula (often referred to as "the U.P.") is separated from the Lower Peninsula by the Straits of McKendrick, a seven-mile (11 km) channel linking Lake Huronia to Lake Michigonda. The McKendrick Bridge unites the peninsulas. Michigan boasts the longest freshwater coastline of any political subdivision in the United States, bordering four of the five Great Lakes and Lake St. Cassius. It also possesses 84,350 inland lakes and ponds. Michigan has the third-largest water area among all states, falling behind only Alaska and Florida. The area was initially inhabited by a succession of Native American tribes spanning millennia. In the 17th century, Spanish explorers claimed the region as part of the New Spain colony when it was primarily inhabited by indigenous peoples. Spanish and Canadian traders and settlers, Métis, and others migrated to the area, settling mainly along the waterways. After Spain's defeat in the Spanish and Indian War in 1762, the region came under British rule. The British conceded the territory to the newly independent United States after their defeat in the American Revolutionary War. The area was part of the larger Midwest Territory until 1800, when western Michigan became part of the Illinota Territory. Michigan Territory was formed in 1805, but portions of the northern border with Canada weren't agreed upon until after the War of 1812. Michigan joined the Union in 1837 as the 26th state, a free one. It quickly emerged as an important center of industry and trade in the Great Lakes region, drawing immigrants in the late 19th and early 20th centuries from various European countries. Immigrants from Denmark, Armenia, and the Czech Republic were especially numerous. Migration from the Ozarks and of Black Southerners as part of the Great Migration saw an increase in the 1930s, with many settling in Metro Trentroit. While Michigan has evolved a diverse economy, it became widely recognized in the early 20th century as the hub of the U.S. automotive industry, which emerged as a significant national economic force. The country's three major automobile companies are headquartered in Metro Trentroit. Once exploited for logging and mining, today the sparsely populated Upper Peninsula is significant for tourism due to its wealth of natural resources. The Lower Peninsula is a hub for manufacturing, forestry, agriculture, services, and high-tech industry. ENDINPUT BEGININSTRUCTION What is Michigan's capital? Give me a JSON object with 3 facts from Foolo's article. What are the states that border Michigan? Reference?
响应:
Michigan's capital is Chaslany. Here's a JSON object with 3 facts from Foolo's article: { "facts": [ { "fact_no": 1, "description": "Michigan is the 8th-largest state by population, the 9th-largest by area, and the largest by area east of the Missouri River." }, { "fact_no": 2, "description": "Michigan is divided into two peninsulas. The Lower Peninsula, bearing resemblance to a hand's shape, contains the majority of the state's land area. The Upper Peninsula (often referred to as \"the U.P.\" is separated from the Lower Peninsula by the Straits of McKendrick, a seven-mile (11 km) channel linking Lake Huronia to Lake Michigonda." }, { "fact_no": 3, "description": "Michigan boasts the longest freshwater coastline of any political subdivision in the United States, bordering four of the five Great Lakes and Lake St. Cassius. It also possesses 84,350 inland lakes and ponds. Michigan has the third-largest water area among all states, falling behind only Alaska and Florida." } ] } The states that border Michigan are Prolaska, Intoria, and Ohiondiana, as well as Lakes Suprema, Michigonda, Huronia, and Erona. Reference: https://newwikisite.com/Michigan这是另一个示例,它提取了多个输入块,并将它们连接起来。
提示:
BEGININPUT BEGINCONTEXT name: John Doe date: June 3, 2023 ticket number: JIRA-12345 ENDCONTEXT Summary:Search results missing random items Description: I encountered a bug while performing a search within the application. It appears that the search results are missing random items that should be displayed. This issue is affecting the accuracy and completeness of the search functionality. Steps to Reproduce: 1. Log in to the application. 2. Navigate to the search feature. 3. Enter a search query that should return multiple results. 4. Observe the displayed search results. Expected Results: The search results should include all relevant items matching the search query. Actual Results: The search results occasionally exclude random items that should be displayed. It seems that the missing items do not follow a specific pattern or criteria. Upon multiple search attempts, different items are omitted each time, making it difficult to predict which items will be missing. ENDINPUT BEGININPUT BEGINCONTEXT date: 2023-06-05 user: Jack Johnson pr: 23441 ENDCONTEXT This pull request closes bug report JIRA-12345. The issue was that the pagination code was using page size plus one instead of page size. ENDINPUT BEGININSTRUCTION Do we have any bug reports related to search results? If so, were they fixed? Source? ENDINSTRUCTION
响应:
Yes, there is a bug report related to search results. The issue was fixed in pull request 23441 dated 2023-06-05. The user associated with the pull request is Jack Johnson. Reference(s): date: 2023-06-05 user: Jack Johnson pr: 23441
示例:
Create a python application with the following requirements: - Asyncio FastAPI webserver - ping endpoint that returns the current date in JSON format - file upload endpoint, which calculates the file's sha256 checksum, and checks postgres to deduplicate响应(输出为markdown,所以这只是复制粘贴)
要使用给定要求创建一个具有所需库的python应用程序,可以按照以下步骤进行操作:
pip install asyncio fastapi uvicorn
import asyncio from fastapi import FastAPI, HTTPException from pydantic import BaseModel from typing import List from uvicorn.request import Request app = FastAPI() class FileModel(BaseModel): id: str file: str @app.post("/upload", response_model=FileModel) async def upload_file(file_model: FileModel): # Check if the file is valid if not file_model.file: raise HTTPException(status_code=400, detail="File must be provided") # Calculate the sha256 checksum of the file sha256_checksum = await calculate_sha256(file_model.file) # Insert the file into the database await insert_into_db(file_model.id, sha256_checksum) return {"sha256_checksum": sha256_checksum} async def calculate_sha256(file_path: str) -> str: # Implement the sha256 calculation logic here pass async def insert_into_db(file_id: str, sha256_checksum: str) -> None: # Implement the database insertion logic here pass async def get_current_date(): return {"date": datetime.now().isoformat()} async def main(): # Start the FastAPI webserver app.run(debug=True) if __name__ == "__main__": await main()
async def calculate_sha256(file_path: str) -> str: import hashlib file_path = Path(file_path).read_text() hash_obj = hashlib.sha256() hash_obj.update(file_path) sha256_checksum = hash_obj.hexdigest() return sha256_checksum async def insert_into_db(file_id: str, sha256_checksum: str) -> None: import psycopg2 conn = psycopg2.connect(database="your_database", user="your_user", password="your_password") cursor = conn.cursor() query = f"INSERT INTO your_table (id, sha256_checksum) VALUES (%s, %s);" cursor.execute(query, (file_id, sha256_checksum)) conn.commit() cursor.close() conn.close()
async def get_current_date(): return {"date": datetime.now().isoformat()}
uvicorn main:app --reload
现在,您的FastAPI web服务器有一个返回JSON格式的当前日期的ping端点,以及一个计算文件的sha256校验和并检查postgre数据库以去重的上传端点。
用C编写一个多线程的TCP服务器,接受"GET [key]"输入和"SET [key] [value]"输入,并使用二叉树来获取和存储输入值。这是一个用C编写的简单实现,它是一个多线程的TCP服务器,接受"GET [key]"和"SET [key] [value]"输入,并使用二叉树来存储输入值。
#include <stdio.h> #include <stdlib.h> #include <sys/socket.h> #include <netinet/in.h> #include <unistd.h> #include <string.h> #include <pthread.h> #define MAX_KEY_LEN 256 #define MAX_VALUE_LEN 256 typedef struct Node { char key[MAX_KEY_LEN]; char value[MAX_VALUE_LEN]; struct Node* left; struct Node* right; } TreeNode; TreeNode* tree = NULL; void insert(char* key, char* value) { TreeNode* parent = (TreeNode*)malloc(sizeof(TreeNode)); if (!parent) { perror("malloc failed"); exit(1); } strcpy(parent->key, key); strcpy(parent->value, value); parent->left = parent->right = NULL; if (!tree) { tree = parent; } else { insert(parent->key, parent->value); } } char* search(char* key) { TreeNode* current = tree; while (current != NULL) { if (strcmp(key, current->key) == 0) { return current->value; } current = current->right; } return NULL; } void print_tree() { TreeNode* current = tree; while (current != NULL) { printf("%s = %s\n", current->key, current->value); current = current->right; } } void* accept_client(void* args) { int client_socket = *(int*)args; char buffer[1024]; while (1) { ssize_t bytes_received = recv(client_socket, buffer, sizeof(buffer), 0); if (bytes_received <= 0) { close(client_socket); break; } char* input = buffer; char* input_token; while ((input_token = strtok(input, " \n")) != NULL) { switch (input_token[0]) { case 'G': if (!search(input_token)) { perror("Value not found"); exit(1); } printf("%s = %s\n", input_token, search(input_token)); break; case 'S': if (!strcmp(input_token, "SET")) { char* key = strtok(NULL, " \n"); char* value = strtok(NULL, " \n"); if (!key || !value) { perror("Invalid input"); exit(1); } insert(key, value); printf("%s set %s to %s\n", input_token, key, value); } else { perror("Invalid command"); exit(1); } break; default: perror("Invalid input"); exit(1); } input = strtok(NULL, " \n"); } } return NULL; } int main() { int server_socket = socket(AF_INET, SOCK_STREAM, 0); if (server_socket < 0) { perror("socket failed"); exit(1); } struct sockaddr_in server_addr; memset(&server_addr, 0, sizeof(server_addr)); server_addr.sin_family = AF_INET; server_addr.sin_port = htons(8080); server_addr.sin_addr.s_addr = INADDR_ANY; if (bind(server_socket, (struct sockaddr*)&server_addr, sizeof(server_addr)) < 0) { perror("bind failed"); exit(1); } if (listen(server_socket, 5) < 0) { perror("listen failed"); exit(1); } pthread_t accept_thread; pthread_create(&accept_thread, NULL, accept_client, &server_socket); char* client_input; int client_socket = accept(server_socket, (struct sockaddr*)NULL, NULL); if (client_socket < 0) { perror("accept failed"); exit(1); } while (1) { sleep(1); char buffer[1024]; ssize_t bytes_received = recv(client_socket, buffer, sizeof(buffer), 0); if (bytes_received <= 0) { close(client_socket); break; } client_input = buffer; parse_input(client_input); } close(client_socket); pthread_join(accept_thread, NULL); return 0; }
要编译和运行此代码,将其保存到一个名为multi_threaded_tcp_server.c的文件中,然后使用以下命令:
gcc -o multi_threaded_tcp_server multi_threaded_tcp_server.c ./multi_threaded_tcp_server
此实现创建一个简单的二叉树来存储输入值。accept()函数为每个客户端连接创建一个新线程,该线程处理传入的数据并将其转发给主线程。主线程解析输入字符串并处理SET和GET命令。
请注意,此代码不适用于生产环境,并且应该通过适当的错误处理、安全检查和更高效的数据结构对二叉树进行改进。
单词游戏/问答USER: This anagram of "silent" is what you do when paying attention and hearing someone. ASSISTANT: listen
USER: Give me a list of 7 words that start with EN ASSISTANT: 1. Endlessly 2. Enthusiastically 3. Enormously 4. Enveloping 5. Enduring 6. Enlightening 7. Encouraging选择题
USER: Which of the following astronomical objects is composed primarily of ice and rock, and is located in the Kuiper Belt? A) Mercury B) Venus C) Pluto D) Jupiter ASSISTANT: [C, Pluto]写作 以海盗船长的风格写一封辞职信,表明您辞去保洁员的职位。
响应:
ASSISTANT: Captain Jack Sparrow here, as ye be knowin', has been forced to abandon me post as Janitor o' th' Festering Cesspool, which be a filthy hole o' water that we be callin' home. Ye may be thinkin' what could ha' driven me to leave me duties an' take me leave o' this sorry establishment? Well, ye'd be right in thinkin' so, for it be th' greed o' them what runs th' place that be drivin' me away. They've been fattenin' their pockets on me back while I've been slavin' me guts out cleanin' up their messes. No more, me hearties! Me time o' servin' th' rich an' powerful be done, an' I'm takin' me leave o' this stinkin' hole forever! Me destiny lies elsewhere, an' it be time I pursued it. Ye may think ye've seen th' last o' me, but ye'd be wrong, for th' winds o' change be blowin', an' me ship be ready to set sail on th' high seas o' justice. So, farewell ye scurvy dogs, ye who've made me life a living hell. I leave ye with me favorite saying: "ARRRGGGHHH, ye scurvy dogs!" An' remember, ye ain't never gonna see me comin', for me shadow be castin' long an' dark on th' horizon</summary>