模型:
TheBloke/llama-deus-7b-v3-GPTQ
Chat & support: my new Discord server
Want to contribute? TheBloke's Patreon page
这些文件是 Teknium's LLaMa Deus 7B v3 的 GPTQ 模型文件。
提供了多个 GPTQ 参数的排列组合;有关提供的选项、其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。
这些模型使用 Latitude.sh 提供的硬件进行量化。
Below is an instruction that describes a task. Write a response that appropriately completes the request. ### Instruction: {prompt} ### Response:
提供了多个量化参数,以便您选择最适合您的硬件和要求的参数。
每个不同的分支都有不同的量化。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. |
gptq-8bit-128g-actorder_True | 8 | 128 | True | 7.16 GB | False | AutoGPTQ | 8-bit, with group size 128g for higher inference quality and with Act Order for even higher accuracy. Poor AutoGPTQ CUDA speed. |
gptq-8bit-64g-actorder_True | 8 | 64 | True | 7.31 GB | False | AutoGPTQ | 8-bit, with group size 64g and Act Order for maximum inference quality. Poor AutoGPTQ CUDA speed. |
git clone --branch gptq-4bit-32g-actorder_True https://huggingface.co/TheBloke/llama-deus-7b-v3-GPTQ`
请确保您正在使用最新版本的 text-generation-webui 。
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。
首先确保您已安装 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/llama-deus-7b-v3-GPTQ" model_basename = "llama-deus-7b-v3-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'''Below is an instruction that describes a task. Write a response that appropriately completes the request. ### Instruction: {prompt} ### Response: ''' 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'])
提供的文件可与 AutoGPTQ(CUDA 和 Triton 模式)、GPTQ-for-LLaMa(仅 CUDA 经过测试)和 Occ4m 的 GPTQ-for-LLaMa 分支一起使用。
ExLlama 可以处理 4 位的 Llama 模型。有关每个文件的兼容性,请参见上面的提供的文件表。
如需进一步支持和讨论这些模型和 AI,请加入我们的 Discord:
感谢 chirper.ai 团队!
我有很多人询问是否可以做出贡献。我乐于提供模型并帮助人们,并希望能够有更多时间从事这些工作,以及扩展到新的项目,如微调/训练。
如果您可以并且愿意做出贡献,我将非常感激,并将帮助我继续提供更多模型,并开始新的 AI 项目。
捐助者将在任何与 AI/LLM/模型相关的问题和请求上获得优先支持,可以进入私人 Discord 房间,并享受其他福利。
特别感谢:来自 CarbonQuill 的 Luke、Aemon Algiz。
Patreon 特别感谢: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者和捐助者!
基本模式:Llama 7BLoRA 完全合并了 llama7b,因此您无需合并它即可加载模型。
Llama DEUS v3 是我迄今为止训练的最大数据集,包括:
GPTeacher - 通用指导 - 编码指导 - 角色扮演指导 我未发布的 Roleplay V2 指导 GPT4-LLM 未经审查+不自然指令 WizardLM 未经审查 CamelAI 的 20k 生物学、20k 物理学、20k 化学和 50k 数学 GPT4 数据集 CodeAlpaca
该模型经过 4 个周期的训练,共计训练了 1 天,是一个针对注意力头、LM_Head 和 MLP 层的第 128 级 LORA 模型
提示格式:
### Instruction: <prompt> ### Response:
或者
### Instruction: <prompt> ### Input: <input> ### Response: