FreedomIntelligence / LLMZoo

⚡LLM Zoo is a project that provides data, models, and evaluation benchmark for large language models.⚡

FreedomIntelligence/LLMZoo Issues

Evaluation benchmark
Updated 9 months ago
Can't run the train phoenix-script
Updated 10 months ago4
lora训练出错
Updated 10 months ago1
ModuleNotFoundError: No module named 'auto_gptq'
Updated a year ago3
对安装环境有要求吗？
Updated a year ago5
Phoenix-chat-7b 支持商用吗?
Updated a year ago1
How can I get word_embeddings in weight？
Closed a year ago2
Challenge on the training details of Phoenix
Updated a year ago
Load checkpoint in inference
Updated a year ago5
How to load from the checkpoints for models trained with lora?
Updated a year ago
关于显存爆炸 - OutOfMemoryError: CUDA out of memory
Updated a year ago
支持transformers 直接加载模型使用吗？
Updated a year ago
Cannot resume trainer from checkpoint
Updated a year ago2
Have you extended the vocabulary size of the tokenizer?
Updated a year ago1
一张A100-SXM4-40GB 能够用来finetuning phoenix-inst-chat-7b-int4 吗
Updated a year ago1
How to fix this issues "Failed to build flash-attn ERROR: Could not build wheels for flash-attn, which is required to install pyproject.toml-based projects"
Updated a year ago1
LLaMA and Alpace are not open-source.
Updated a year ago
The streaming output contains garbled characters.
Closed a year ago1
token = int(torch.multinomial(probs, num_samples=1)) 不加这个生成效果很烂
Closed a year ago1
Join the competition! https://lmsys.org/blog/2023-05-03-arena/
Closed a year ago1
BloomTokenizer does not exist
Updated a year ago1
No such file or directory: ”eval/questions/roleplay-questions-zh.jsonl“
Updated a year ago
Is is possible to run the pre-trained model with rtx 2060 6g?
Updated a year ago3
ask tuning details, like lr
Closed a year ago2
When will the chat data release? Thanks!
Closed a year ago2
Evaluating RWKV "Raven" (ChatGPT-tuned models)
Closed a year ago1
Can you kindly provide the training code ? Thanks !
Closed a year ago1
detailed supported languages for the new model "Phoenix"
Closed a year ago2
有预训练的代码么
Closed a year ago2
Released merged weight & GPTQ quant weight
Closed a year ago2
How to eval and rank model outputs?
Updated a year ago
我使用chimera-inst-chat-13b-delta模型回答的是乱码使用Torch.fload16
Closed a year ago2
phoenix-inst-chat-7b对prompt的理解有些bug
Updated a year ago
Would you provide some details of model training process?
Closed a year ago5
[ask]training code?
Closed a year ago9
Is it possible the have the Web API inteface just like 'llmzoo.deploy.cli'
Updated a year ago4
Cannot launch web app properly
Updated a year ago1
About the tokenizer
Closed a year ago4
running model with 8-bit, too slow!
Updated a year ago2
Request for Information on Dialogue Model Training and Format Guidelines
Closed a year ago1
Is phoenix or chimera better for german?
Closed a year ago4
Is it planned to train Phoenix-13B?
Closed a year ago2
chat with chimera-inst-chat-13b report error
Closed a year ago1
is there a llama.cpp version?
Updated a year ago2
Regarding Baize's training data
Closed a year ago2
Running issue
Closed a year ago2
Please add a license to this repo
Closed a year ago1
Huatuogpt API KEY
Closed a year ago3
chat with phoenix-inst-chat-7b report error
Closed a year ago1