Ecosyste.ms: Issues
An open API service for providing issue and pull request metadata for open source projects.
GitHub / lyogavin/airllm issues and pull requests
#182 - B70 need
Issue -
State: open - Opened by ayttop 6 days ago
#181 - How to set system prompt
Issue -
State: open - Opened by OKHand-Zy 17 days ago
- 1 comment
#180 - unsloth/Meta-Llama-3.1-405B-Instruct-bnb-4bit
Issue -
State: open - Opened by kendiyang 19 days ago
- 2 comments
#179 - delete_original
Issue -
State: open - Opened by ayttop 20 days ago
- 4 comments
#178 - RuntimeError: shape '[1, 5, 8, 128]' is invalid for input of size 10240 LLama 405B 4-bit on Layer 1
Issue -
State: open - Opened by TitleOS 20 days ago
- 3 comments
#177 - Compression does not work with MLX / Apple Silicon
Issue -
State: open - Opened by sammcj 23 days ago
#176 - Fix pip not found when install in Jupyter
Pull Request -
State: closed - Opened by chinkan 24 days ago
#175 - CUDA Out of memory RTX 4060TI 16G
Issue -
State: open - Opened by 1272870698 27 days ago
#174 - Fixing mlx model load
Pull Request -
State: closed - Opened by Razikus about 1 month ago
- 1 comment
#173 - added delete_original support for single modelfiles
Pull Request -
State: closed - Opened by NavodPeiris about 1 month ago
#172 - RuntimeError: shape '[1, 13, 8, 128]' is invalid for input of size 26624
Issue -
State: open - Opened by zhuojun1024 about 1 month ago
- 6 comments
#170 - #169: fixed error when running on cpu and added post install command to upgrade transformers
Pull Request -
State: closed - Opened by NavodPeiris about 1 month ago
#169 - Error when running on CPU device and rope_scaling error when using old version of transformers
Issue -
State: closed - Opened by NavodPeiris about 1 month ago
- 1 comment
#168 - mlx Linear weight arrays were loaded with a dict of arrays
Issue -
State: closed - Opened by shiwanlin about 1 month ago
- 1 comment
#167 - mlx embedding indexing failure - ValueError: Cannot index mlx array using the given type.
Issue -
State: closed - Opened by shiwanlin about 1 month ago
- 2 comments
#166 - how to increase speed of inference
Issue -
State: open - Opened by Tdrinker about 1 month ago
- 1 comment
#165 - Position Embedding with Seq > 512
Issue -
State: open - Opened by Codys12 about 2 months ago
- 1 comment
#164 - Data Parallel across multiple GPUs?
Issue -
State: open - Opened by Codys12 about 2 months ago
#163 - name 'dynamically_import_QuantLinear' is not defined
Issue -
State: open - Opened by gyyixr about 2 months ago
- 1 comment
Labels: enhancement, future work
#162 - layer_name 在使用前没有被定义
Issue -
State: open - Opened by yjleo17 about 2 months ago
- 4 comments
#161 - Circular import error in importing partially initialised module airllm
Issue -
State: closed - Opened by samarthpusalkar about 2 months ago
- 1 comment
#160 - AssertionError: model.safetensors.index.json should exist
Issue -
State: open - Opened by huangyifu about 2 months ago
#159 - I can’t run llama-3.1-405B-Instruct-bnb-4bit because of a ValueError: rope_scaling must be a dictionary with two fields.
Issue -
State: open - Opened by LCG22 about 2 months ago
- 1 comment
#158 - can not run llama 3.1 405B
Issue -
State: open - Opened by taozhiyuai about 2 months ago
- 2 comments
#157 - docs: add Japanese README
Pull Request -
State: closed - Opened by eltociear about 2 months ago
#156 - AttributeError: 'AirLLMLlama2' object has no attribute '_supports_cache_class'
Issue -
State: open - Opened by Source61 2 months ago
- 2 comments
#155 - Ramdisk
Issue -
State: open - Opened by HennethAnnun 2 months ago
#154 - how to use Qwen2-72B-instuct
Issue -
State: open - Opened by shenhai-ran 2 months ago
- 2 comments
#153 - AssertionError: Torch not compiled with CUDA enabled
Issue -
State: open - Opened by smartdawg 3 months ago
- 1 comment
#152 - Some grammar suggested fixes in README.md
Pull Request -
State: closed - Opened by TheTechOddBug 3 months ago
#151 - No english readme for rlhf
Issue -
State: open - Opened by drawnwren 3 months ago
#150 - How?
Issue -
State: closed - Opened by nonetrix 3 months ago
- 1 comment
#149 - AttributeError: 'list' object has no attribute 'absmax' when I load Qwen-72B-Chat with 8-bit compression with AirLLMQWen
Issue -
State: open - Opened by Yang-bug-star 3 months ago
#146 - Add support for Mistral model inference
Issue -
State: open - Opened by kunling-cxk 3 months ago
#145 - ImportError: cannot import name 'AutoModel' from partially initialized module 'airllm' (most likely due to a circular import)
Issue -
State: closed - Opened by leobilocastro 3 months ago
#144 - Linear(in_features=28672, out_features=8192, bias=False) does not have a parameter or a buffer named qweight.
Issue -
State: open - Opened by luzacao 4 months ago
#143 - WeChat QR Code out of date
Issue -
State: open - Opened by zixianwang2022 4 months ago
#142 - air_llm: README fix MacOS typo
Pull Request -
State: closed - Opened by hiemal 4 months ago
#137 - safetensors_rust.SafetensorError: Error while deserializing header: MetadataIncompleteBuffer
Issue -
State: open - Opened by chuangzhidan 5 months ago
#136 - Insuficient disk space
Issue -
State: open - Opened by ulisesbussi 5 months ago
- 3 comments
#135 - CPU ram offload
Issue -
State: open - Opened by NicolasMejiaPetit 5 months ago
#134 - error in apple mac m3
Issue -
State: open - Opened by mustangs0786 5 months ago
- 5 comments
#133 - Does airllm support quantized gguf/gptq/awq models ?
Issue -
State: open - Opened by robik72 5 months ago
#132 - COMPILED_WITH_CUDA error requires libcuda.so
Issue -
State: open - Opened by nickums 5 months ago
#131 - Error with Llama3: ValueError: Trying to set a tensor of shape torch.Size([1024, 8192]) in "weight" (which has shape torch.Size([8192, 8192])), this look incorrect.
Issue -
State: closed - Opened by Cangshanqingshi 5 months ago
#130 - 跑不通chatglm3,请大佬指教。
Issue -
State: open - Opened by ZiQiangXie 5 months ago
- 2 comments
#129 - segmentation fault python3 airllm2.py
Issue -
State: open - Opened by taozhiyuai 5 months ago
- 3 comments
#128 - to run llama3-70b,but fail to import. why?
Issue -
State: closed - Opened by taozhiyuai 5 months ago
#127 - Any CoreML implementation plans?
Issue -
State: open - Opened by Proryanator 5 months ago
#126 - Mac 'str' object has no attribute 'sequences
Issue -
State: open - Opened by gr3enarr0w 5 months ago
#125 - "src" directory name is conflicted
Issue -
State: open - Opened by Rambo55555 5 months ago
#124 - how to delete the original download model after it has been downloaded
Issue -
State: open - Opened by ruiguo-bio 5 months ago
- 1 comment
#123 - Running on Mac get traceback error
Issue -
State: closed - Opened by gr3enarr0w 5 months ago
- 3 comments
#122 - 通过Ollama下载了的模型,如何在airllm中直接使用呢
Issue -
State: open - Opened by w1005444804 5 months ago
- 2 comments
#121 - 请求支持llama3
Issue -
State: closed - Opened by CrazyBoyM 5 months ago
- 2 comments
Labels: enhancement
#120 - The following error is encountered when running the sample code
Issue -
State: open - Opened by Nuclear6 6 months ago
#119 - compression parameter on mac.dosent work.
Issue -
State: open - Opened by dnvs 6 months ago
#118 - Support for OPT Architecture
Issue -
State: open - Opened by varunlmxd 6 months ago
#117 - Is it possible to use AirLLM with a quantized input model?
Issue -
State: open - Opened by Verdagon 6 months ago
- 3 comments
Labels: enhancement
#116 - mac m2 run air llm garage-bAInd/Platypus2-7B get error Input must be a file-like object opened in binary mode, or string
Issue -
State: open - Opened by wuxiongwei 7 months ago
- 6 comments
#115 - 似乎只能产生很少的字符
Issue -
State: closed - Opened by andeyeluguo 7 months ago
- 2 comments
#114 - Add UI like AUTOMATIC1111 for stable-diffusion-webui
Issue -
State: open - Opened by janmartin 7 months ago
#112 - Which 70B model does macOS support?
Issue -
State: open - Opened by ruifengma 7 months ago
#111 - Generation takes forever
Issue -
State: closed - Opened by Kira-Pgr 8 months ago
- 4 comments
#109 - Optimize for consumer GPU, eg 11GB or 16GB
Issue -
State: open - Opened by profintegra 8 months ago
#108 - AirLLM: Support for DirectML
Issue -
State: open - Opened by vegax87 8 months ago
- 1 comment
#107 - attn impl to sdpa...
Issue -
State: open - Opened by saa1028 8 months ago
- 4 comments
#106 - AMD gpu support
Issue -
State: open - Opened by hanq-moreh 8 months ago
- 1 comment
#105 - For me this model is extremely underperforming
Issue -
State: open - Opened by SadafShafi 8 months ago
- 1 comment
#104 - Macbook "Torch not compiled with CUDA enabled" Error
Issue -
State: closed - Opened by LanLanBoom 8 months ago
- 2 comments
#103 - 用airllm运行Yi-34B-chat模型,分层之后报这个错误
Issue -
State: open - Opened by peiyanyang 8 months ago
- 1 comment
#102 - Will the airllm framework be adapted for the streaming output functionality of different models in the future?
Issue -
State: open - Opened by wangqn1 8 months ago
Labels: future work
#101 - ValueError: LlamaForCausalLM does not support an attention implementation through torch.nn.functional.scaled_dot_product_attention yet.
Issue -
State: open - Opened by sleeper1023 8 months ago
- 1 comment
Labels: bug
#100 - AirLLMLlamaMlx fails to load model with mlx==0.0.7
Issue -
State: open - Opened by jakule 9 months ago
Labels: bug
#99 - 关于对话模型是否能使用airllm
Issue -
State: open - Opened by wzz981 9 months ago
- 1 comment
Labels: question
#98 - how to infer on multiple gpus?
Issue -
State: closed - Opened by yuxx0218 9 months ago
- 1 comment
Labels: wontfix
#97 - Fix TYPO
Pull Request -
State: closed - Opened by Naozumi520 9 months ago
#96 - Finetune 70B on 24GB 4090?
Issue -
State: open - Opened by Naozumi520 9 months ago
- 1 comment
Labels: future work
#95 - microsoft-phi2:max() arg is an empty sequence
Issue -
State: open - Opened by zazaji 9 months ago
- 1 comment
Labels: future work
#94 - ImportError: cannot import name AutoMode
Issue -
State: closed - Opened by zazaji 9 months ago
- 1 comment
#93 - safetensors_rust.SafetensorError: Error while deserializing header: HeaderTooLarge
Issue -
State: open - Opened by fudp 9 months ago
- 1 comment
Labels: bug
#91 - ValueError: max() arg is an empty sequence(Apple M2 Max, macOS 14.2.1)
Issue -
State: open - Opened by tvsj 9 months ago
- 6 comments
Labels: future work
#90 - Discord Invite Expired in the readme
Issue -
State: open - Opened by birdup000 9 months ago
- 1 comment
Labels: help wanted
#89 - Would adding Parallelism speed up AirLLM?
Issue -
State: open - Opened by birdup000 9 months ago
Labels: question
#88 - Mac quantization
Issue -
State: open - Opened by ageorgios 9 months ago
Labels: question
#87 - Mac Airllm Inference tigerbot-70b-chat-v2
Issue -
State: open - Opened by ageorgios 9 months ago
Labels: bug
#86 - configure the chunk split size
Issue -
State: open - Opened by ageorgios 9 months ago
Labels: question
#85 - Does Airllm support sqlcoder-34b which was fine-tuned on codellama?
Issue -
State: closed - Opened by mw-hv 9 months ago
- 1 comment
#84 - Mixtral models seem to run forever
Issue -
State: closed - Opened by Josh-XT 9 months ago
- 1 comment
#83 - mistral模型无限加载中
Issue -
State: closed - Opened by fenglui 9 months ago
- 2 comments
Labels: help wanted
#82 - Mistral Mixtral model support
Issue -
State: closed - Opened by birdup000 9 months ago
#81 - RuntimeError: cannot pin 'torch.cuda.HalfTensor' only dense CPU tensors can be pinned
Issue -
State: closed - Opened by birdup000 9 months ago
- 2 comments
Labels: bug
#80 - what's the difference or advantage of airllm vs flexgen?
Issue -
State: open - Opened by showkeyjar 9 months ago
- 1 comment
Labels: enhancement
#79 - [Feature Request] Mixtral Model Support
Issue -
State: closed - Opened by birdup000 9 months ago
- 11 comments
Labels: bug
#78 - airllm是否支持ptunig、lora等微调模型的加载?
Issue -
State: open - Opened by estuday 9 months ago
Labels: enhancement
#77 - Mistral Model ValueError: Asking to pad but the tokenizer does not have a padding token
Issue -
State: closed - Opened by birdup000 9 months ago
- 2 comments
#76 - fix unbound error
Pull Request -
State: closed - Opened by birdup000 9 months ago
- 2 comments
#75 - Running the example inference code and I get error
Issue -
State: closed - Opened by birdup000 9 months ago
- 3 comments