Skip to content

Actions: hiyouga/LLaMA-Factory

Actions

All workflows

Actions

Loading...

Showing runs from all workflows
849 workflow runs
849 workflow runs
Event

Filter by event
Status

Filter by status
Branch
Actor

Filter by actor
Dockerfile is missing unsloth label_issue #60: Issue #4232 opened by sammcj
June 12, 2024 05:02 12s
June 12, 2024 05:02 12s
How to get logit during prediction label_issue #59: Issue #4231 opened by may012345
June 12, 2024 03:30 12s
June 12, 2024 03:30 12s
加载数据时，如果存在cache，debug用参数max_samples将失效 label_issue #58: Issue #4230 opened by zyh3826
June 12, 2024 03:30 11s
June 12, 2024 03:30 11s
qwen2 awq 微调一直报错 auto-awq kernels没有安装 label_issue #57: Issue #4229 opened by hi909hi
June 12, 2024 03:09 17s
June 12, 2024 03:09 17s
[NPU] inference ZhipuAI/glm-4-9b-chat POST /v1/chat/completions ERROR: Exception in ASGI application label_issue #56: Issue #4228 opened by hunterhome
June 12, 2024 02:37 12s
June 12, 2024 02:37 12s
使用llamafactory-cli api启动Qwen/Qwen2-7B-Instruct回答乱码 label_issue #55: Issue #4226 opened by derrickcyt
June 12, 2024 02:31 13s
June 12, 2024 02:31 13s
Lora方式对Qwen1.5-7B进行增量预训练，loss值下降幅度很小 label_issue #54: Issue #4225 opened by xd-Nanan
June 12, 2024 01:34 13s
June 12, 2024 01:34 13s
使用 qwen2 7b int8 在 webui 中 chat 时所有的回答都是乱码 label_issue #53: Issue #4223 opened by onlyjokers
June 11, 2024 17:50 12s
June 11, 2024 17:50 12s
Qwen-1.5-14b-chat多卡推理时加载权重速度很慢 label_issue #52: Issue #4222 opened by orbit-clown
June 11, 2024 15:58 10s
June 11, 2024 15:58 10s
预训练 Running tokenizer on dataset 执行了两遍 label_issue #51: Issue #4221 opened by CanvaChen
June 11, 2024 15:56 11s
June 11, 2024 15:56 11s
Qwen2 7B SFT 无法启动训练 label_issue #50: Issue #4220 opened by rantianhua
June 11, 2024 14:16 12s
June 11, 2024 14:16 12s
qwen1.5-7b 预训练lora不收敛 label_issue #49: Issue #4219 opened by Liufeiran123
June 11, 2024 13:28 10s
June 11, 2024 13:28 10s
无法进行推理，可以微调以及加载模型。 label_issue #48: Issue #4218 opened by GaoHZ1
June 11, 2024 12:50 15s
June 11, 2024 12:50 15s
ValueError: Unrecognized configuration class <class 'transformers.models.llava.configuration_llava.LlavaConfig'> for this kind of AutoModel: AutoModelForCausalLM. label_issue #47: Issue #4217 opened by Hassaan68
June 11, 2024 12:49 12s
June 11, 2024 12:49 12s
SFT yi-34B 保存断点时候报错 label_issue #46: Issue #4216 opened by CXLiang123
June 11, 2024 12:31 13s
June 11, 2024 12:31 13s
BAdam能支持多GPU训练吗？ label_issue #45: Issue #4215 opened by Zheng-Jay
June 11, 2024 12:30 12s
June 11, 2024 12:30 12s
推理的时候出现错误：RuntimeError: CUDA error: device-side assert triggered label_issue #44: Issue #4214 opened by GaoHZ1
June 11, 2024 12:20 14s
June 11, 2024 12:20 14s
CUDA显存不足 label_issue #43: Issue #4213 opened by 970602
June 11, 2024 12:09 15s
June 11, 2024 12:09 15s
AttributeError: 'PreTrainedTokenizerFast' object has no attribute 'image_processor' label_issue #42: Issue #4212 opened by Hassaan68
June 11, 2024 11:51 12s
June 11, 2024 11:51 12s
使用qwen7b对训练好的sft权重合并之后，进行chat，出现keyerror错误 label_issue #41: Issue #4211 opened by cove1011
June 11, 2024 11:37 11s
June 11, 2024 11:37 11s
单卡deepspeed & lora对glm4-9b进行sft微调报错：RuntimeError: 'weight' must be 2-D label_issue #40: Issue #4210 opened by GoldenSeS
June 11, 2024 11:04 13s
June 11, 2024 11:04 13s
0.8.1版本DeepSpeed 的 zero stage3报错 label_issue #39: Issue #4209 opened by xinyubai1209
June 11, 2024 10:40 13s
June 11, 2024 10:40 13s
How to supervised fine tuning Qwen2-7b using Llama2 template? label_issue #38: Issue #4208 opened by NguyenNhoTrung
June 11, 2024 10:27 13s
June 11, 2024 10:27 13s
使用 chatglm2 的 template 对chatglm2 进行微调，出现 INFO-Cannot add this chat template to tokenizer label_issue #37: Issue #4207 opened by dontnet-wuenze
June 11, 2024 09:13 9s
June 11, 2024 09:13 9s
Merge pull request #4204 from dignfei/main tests #860: Commit 9049aab pushed by hiyouga
June 11, 2024 09:06 3m 9s main
main
June 11, 2024 09:06 3m 9s