模型:
TheBloke/vicuna-7B-v1.3-GPTQ
Chat & support: my new Discord server
Want to contribute? TheBloke's Patreon page
这些文件是用于 LmSys' Vicuna 7B v1.3 的 GPTQ 模型文件。
提供了多种 GPTQ 参数排列,有关所提供选项、它们的参数和用于创建它们的软件的详细信息,请参见下面的提供的文件。
这些模型是使用由 Latitude.sh 提供的硬件进行量化的。
A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions. USER: {prompt} ASSISTANT:
提供了多个量化参数,以便您可以选择最适合您的硬件和要求的参数。
每个单独的量化都在一个不同的分支中。有关从不同分支获取的说明,请参见下面的说明。
Branch | Bits | Group Size | Act Order (desc_act) | File Size | ExLlama Compatible? | Made With | Description |
---|---|---|---|---|---|---|---|
main | 4 | 128 | False | 4.00 GB | True | GPTQ-for-LLaMa | Most compatible option. Good inference speed in AutoGPTQ and GPTQ-for-LLaMa. Lower inference quality than other options. |
gptq-4bit-32g-actorder_True | 4 | 32 | True | 4.28 GB | True | AutoGPTQ | 4-bit, with Act Order and group size. 32g gives highest possible inference quality, with maximum VRAM usage. Poor AutoGPTQ CUDA speed. |
gptq-4bit-64g-actorder_True | 4 | 64 | True | 4.02 GB | True | AutoGPTQ | 4-bit, with Act Order and group size. 64g uses less VRAM than 32g, but with slightly lower accuracy. Poor AutoGPTQ CUDA speed. |
gptq-4bit-128g-actorder_True | 4 | 128 | True | 3.90 GB | True | AutoGPTQ | 4-bit, with Act Order and group size. 128g uses even less VRAM, but with slightly lower accuracy. Poor AutoGPTQ CUDA speed. |
gptq-8bit--1g-actorder_True | 8 | None | True | 7.01 GB | False | AutoGPTQ | 8-bit, with Act Order. No group size, to lower VRAM requirements and to improve AutoGPTQ speed. |
gptq-8bit-128g-actorder_False | 8 | 128 | False | 7.16 GB | False | AutoGPTQ | 8-bit, with group size 128g for higher inference quality and without Act Order to improve AutoGPTQ speed. |
git clone --branch gptq-4bit-32g-actorder_True https://huggingface.co/TheBloke/vicuna-7B-v1.3-GPTQ`
请确保您使用的是 text-generation-webui 的最新版本。
强烈建议使用text-generation-webui的一键安装程序,除非您知道如何进行手动安装。
首先确保您安装了 AutoGPTQ :
GITHUB_ACTIONS=true pip install auto-gptq
然后尝试以下示例代码:
from transformers import AutoTokenizer, pipeline, logging from auto_gptq import AutoGPTQForCausalLM, BaseQuantizeConfig model_name_or_path = "TheBloke/vicuna-7B-v1.3-GPTQ" model_basename = "vicuna-7b-v1.3-GPTQ-4bit-128g.no-act.order" use_triton = False tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, use_fast=True) model = AutoGPTQForCausalLM.from_quantized(model_name_or_path, model_basename=model_basename use_safetensors=True, trust_remote_code=True, device="cuda:0", use_triton=use_triton, quantize_config=None) """ To download from a specific branch, use the revision parameter, as in this example: model = AutoGPTQForCausalLM.from_quantized(model_name_or_path, revision="gptq-4bit-32g-actorder_True", model_basename=model_basename, use_safetensors=True, trust_remote_code=True, device="cuda:0", quantize_config=None) """ prompt = "Tell me about AI" prompt_template=f'''A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions. USER: {prompt} ASSISTANT: ''' print("\n\n*** Generate:") input_ids = tokenizer(prompt_template, return_tensors='pt').input_ids.cuda() output = model.generate(inputs=input_ids, temperature=0.7, max_new_tokens=512) print(tokenizer.decode(output[0])) # Inference can also be done using transformers' pipeline # Prevent printing spurious transformers error when using pipeline with AutoGPTQ logging.set_verbosity(logging.CRITICAL) print("*** Pipeline:") pipe = pipeline( "text-generation", model=model, tokenizer=tokenizer, max_new_tokens=512, temperature=0.7, top_p=0.95, repetition_penalty=1.15 ) print(pipe(prompt_template)[0]['generated_text'])
提供的文件可用于AutoGPTQ(CUDA和Triton模式)、GPTQ-for-LLaMa(仅CUDA已经测试过)和Occ4m的GPTQ-for-LLaMa分支。
ExLlama与4位Llama模型兼容。有关每个文件的兼容性,请参见上面提供的文件表。
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: TheBloke AI's Discord server
感谢 chirper.ai 团队!
我有很多人问我是否可以做出贡献。我喜欢提供模型并帮助人们,希望能有更多时间做这些,并且扩展到新的项目,如微调/训练。
如果您有能力和意愿贡献,我将非常感激,并将帮助我继续提供更多模型,并开始进行新的AI项目。
捐助者将优先获得有关所有AI/LLM/模型相关问题和请求的支持,可以访问私人Discord房间,以及其他福利。
特别感谢:CarbonQuill的Luke,Aemon Algiz。
Patreon特别提及:Space Cruiser,Nikolai Manek,Sam,Chris McCloskey,Rishabh Srivastava,Kalila,Spiking Neurons AB,Khalefa Al-Ahmad,WelcomeToTheClub,Chadd,Lone Striker,Viktor Bowallius,Edmond Seymore,Ai Maven,Chris Smitley,Dave,Alexandros Triantafyllidis,Luke @flexchar,Elle,ya boyyy,Talal Aujan,Alex,Jonathan Leane,Deep Realms,Randy H,subjectnull,Preetika Verma,Joseph William Delisle,Michael Levine,chris gileta,K,Oscar Rangel,LangChain4j,Trenton Dambrowitz,Eugene Pentland,Johann-Peter Hartmann,Femi Adebogun,Illia Dulskyi,senxiiz,Daniel P. Andersen,Sean Connelly,Artur Olbinski,RoA,Mano Prime,Derek Yates,Raven Klaugh,David Flickinger,Willem Michiel,Pieter,Willian Hasse,vamX,Luke Pendergrass,webtim,Ghost,Rainer Wilmers,Nathan LeClaire,Will Dee,Cory Kujawski,John Detwiler,Fred von Graf,biorpg,Iucharbius,Imad Khwaja,Pierre Kircher,terasurfer,Asp the Wyvern,John Villwock,theTransient,zynix,Gabriel Tamborski,Fen Risland,Gabriel Puliatti,Matthew Berman,Pyrater,SuperWojo,Stephen Murray,Karl Bernard,Ajan Kanaga,Greatston Gnanesh,Junyu Yang。
感谢所有慷慨的赞助商和捐赠者!
Vicuna 是一个通过基于转换器架构的 LLaMA 进行细调的聊天助手,使用 ShareGPT 上共享的对话进行训练。
Vicuna 的主要用途是进行大型语言模型和聊天机器人研究。模型的主要目标用户是自然语言处理、机器学习和人工智能领域的研究人员和爱好者。
命令行界面: https://github.com/lm-sys/FastChat#vicuna-weights 。API(OpenAI API,Huggingface API): https://github.com/lm-sys/FastChat/tree/main#api 。
Vicuna v1.3 是通过使用受监督指令微调的方式从 LLaMA 进行微调的。训练数据来自于 ShareGPT.com 上收集的约140K个对话。有关更多详细信息,请参阅本 paper 的附录中的“Vicuna 模型的训练详情”部分。
Vicuna 使用标准基准、人类偏好和 LLM 作为评判进行评估。有关更多详细信息,请参阅本 paper 和 leaderboard 。