模型:
TheBloke/koala-7B-GPTQ-4bit-128g
Chat & support: my new Discord server
Want to contribute? TheBloke's Patreon page
这些文件是用于 Young Geng's Koala 7B 的GPTQ模型文件。
提供了多个GPTQ参数排列方式;有关所提供选项、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部分。
这些模型使用由 Latitude.sh 慷慨提供的硬件进行量化。
BEGINNING OF CONVERSATION: USER: {prompt} GPT:
提供了多个量化参数,以便您可以选择适合您的硬件和需求的最佳参数。
每个单独的量化参数在不同的分支中。请参阅下面关于从不同分支获取的说明。
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/koala-7B-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 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/koala-7B-GPTQ" model_basename = "koala-7b-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'''BEGINNING OF CONVERSATION: USER: {prompt} GPT: ''' 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已经过测试)和Occ4m的GPTQ-for-LLaMa分支一起使用。
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。
如需进一步支持和讨论这些模型和人工智能问题,请加入:
感谢 chirper.ai 团队!
很多人问我是否可以做贡献。我喜欢提供模型和帮助他人,并且很乐意可以花更多的时间进行提供,并扩展到新的项目,如微调/训练。
如果您有能力和意愿进行贡献,我将非常感激,并且这将帮助我继续提供更多的模型,并开始进行新的人工智能项目。
捐赠者将获得对所有人工智能/LLM/模型问题和请求的优先支持,访问私人Discord房间,以及其他好处。
特别感谢: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,特伦顿·丹布罗维茨,Eugene Pentland,Johann-Peter Hartmann,Femi Adebogun,Illia Dulskyi,senxiiz,Daniel P. Andersen,Sean Connelly,Artur Olbinski,罗A,Mano Prime,Derek Yates,Raven Klaugh,David Flickinger,Willem Michiel,皮特,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!
该存储库包含Koala模型相对于基本LLaMA的权重差异。请查看以下链接以开始使用:
该模型权重仅供学术研究使用,受 model License of LLaMA , Terms of Use of the data generated by OpenAI 和 Privacy Practices of ShareGPT 的约束。严禁将模型权重用于任何其他用途,包括但不限于商业用途。如有发现任何潜在违规行为,请与我们联系。我们的训练和推断代码采用Apache License 2.0发布。