模型:
TheBloke/WizardLM-13B-V1.0-Uncensored-GPTQ
Chat & support: my new Discord server
Want to contribute? TheBloke's Patreon page
这些文件是用于 Eric Hartford's WizardLM-13b-V1.0-Uncensored 的GPTQ模型文件。
提供了多个GPTQ参数的排列方式;有关所提供选项、参数和创建它们的软件的详细信息,请参阅下面的提供的文件。
这些模型是使用 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,以便您根据硬件和需求选择最佳参数。
每个独立的量化存在于不同的分支中。请参阅下面的说明以获取不同分支的下载方法。
Branch | Bits | Group Size | Act Order (desc_act) | File Size | ExLlama Compatible? | Made With | Description |
---|---|---|---|---|---|---|---|
main | 4 | 128 | False | 7.45 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 | 8.00 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 | 7.51 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 | 7.26 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 | 13.36 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 | 13.65 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/WizardLM-13B-V1.0-Uncensored-GPTQ`
请确保您正在使用最新版本的 text-generation-webui 。
强烈推荐使用text-generation-webui的一键安装程序,除非您知道如何进行手动安装。
首先确保您已安装了 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/WizardLM-13B-V1.0-Uncensored-GPTQ" model_basename = "wizardlm-13b-v1.0-uncensored-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'])
提供的文件适用于AutoGPTQ(CUDA和Triton模式)、GPTQ-for-LLaMa(仅测试了CUDA版本)和Occ4m的GPTQ-for-LLaMa分支。
ExLlama适用于4位Llama模型。有关每个文件的兼容性,请参见上面提供的文件表格。
如需进一步支持以及有关这些模型和人工智能的讨论,请加入我们:
感谢 chirper.ai 团队的支持!
有很多人问我他们是否可以做出贡献。我喜欢提供模型并帮助人们,也愿意能够花更多的时间在这上面,以及扩展到新的项目,如精细调整/训练。
如果您能够并愿意做出贡献,我将非常感激,并将有助于我继续提供更多的模型,并开始新的人工智能项目。
捐赠者将在任何与人工智能/LLM/模型相关的问题和请求上获得优先支持,可以访问私人Discord房间,以及其他福利。
特别感谢:来自CarbonQuill的Luke,Aemon Algiz。
Patreon特别提到: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人和捐赠者!
这是使用 https://huggingface.co/WizardLM/WizardLM-13B-V1.0 经过筛选的数据集进行重新训练的模型,旨在减少拒绝、回避和偏见。
请注意,LLaMA本身具有固有的伦理信念,因此不存在“真正无审查”的模型。但是,该模型将比WizardLM/WizardLM-7B-V1.0更合规。
向开源AI/ML社区和帮助过我的所有人致以敬意。
注意:无审查的模型没有任何防护措施。您对模型的任何行为负有责任,就像对刀具、枪支、打火机或汽车等危险物品负责一样。将模型生成的任何内容发布与您自己发布它没有任何区别。您对所发布的内容负有责任,无论是对模型还是对刀具、枪支、打火机或汽车负有责任。
与WizardLM/WizardLM-13B-V1.0一样,该模型是使用Vicuna-1.1风格的提示进行训练的。
You are a helpful AI assistant. USER: <prompt> ASSISTANT:
感谢 chirper.ai 赞助部分计算资源!