微调模型的相关问题
#2024
Replies: 4 comments 2 replies
-
使用的是什么微调框架 |
Beta Was this translation helpful? Give feedback.
0 replies
-
chatglm2+lora微调 |
Beta Was this translation helpful? Give feedback.
0 replies
-
使用的如果是llama-efficient-turning/ llama-factory的话你导出成单个模型看能不能跑, |
Beta Was this translation helpful? Give feedback.
0 replies
-
请问 llama-factory 能否导出统一的微调模型? 该模型能否适配chatchat?? |
Beta Was this translation helpful? Give feedback.
2 replies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
-
问题描述 / Problem Description
我用ChatGLM-Efficient-Tuning进行lora微调后的模型,在本项目中启动报错
复现问题的步骤 / Steps to Reproduce
我按照Wiki的p-tuning类提供的方式进行操作
预期的结果 / Expected Result
成功运行
实际结果 / Actual Result
报错
环境信息 / Environment Information
附加信息 / Additional Information
adapt_config.json内容如下
{
"_name_or_path": "D:/Langchain-Chatchat-master/Langchain-Chatchat/chatglm2-6b",
"add_bias_linear": false,
"add_qkv_bias": true,
"apply_query_key_layer_scaling": true,
"apply_residual_connection_post_layernorm": false,
"architectures": [
"ChatGLMForConditionalGeneration"
],
"attention_dropout": 0.0,
"attention_softmax_in_fp32": true,
"auto_map": {
"AutoConfig": "configuration_chatglm.ChatGLMConfig",
"AutoModel": "modeling_chatglm.ChatGLMForConditionalGeneration",
"AutoModelForCausalLM": "THUDM/chatglm2-6b--modeling_chatglm.ChatGLMForConditionalGeneration",
"AutoModelForSeq2SeqLM": "THUDM/chatglm2-6b--modeling_chatglm.ChatGLMForConditionalGeneration",
"AutoModelForSequenceClassification": "THUDM/chatglm2-6b--modeling_chatglm.ChatGLMForSequenceClassification"
},
"bias_dropout_fusion": true,
"classifier_dropout": null,
"eos_token_id": 2,
"ffn_hidden_size": 13696,
"fp32_residual_connection": false,
"hidden_dropout": 0.0,
"hidden_size": 4096,
"kv_channels": 128,
"layernorm_epsilon": 1e-05,
"model_type": "chatglm",
"multi_query_attention": true,
"multi_query_group_num": 2,
"num_attention_heads": 32,
"num_layers": 28,
"original_rope": true,
"pad_token_id": 0,
"padded_vocab_size": 65024,
"post_layer_norm": true,
"pre_seq_len": null,
"prefix_projection": false,
"quantization_bit": 0,
"rmsnorm": true,
"seq_length": 32768,
"tie_word_embeddings": false,
"torch_dtype": "float16",
"transformers_version": "4.34.1",
"use_cache": true,
"vocab_size": 65024,
"base_model_name_or_path": "D:/Langchain-Chatchat-master/Langchain-Chatchat/chatglm2-6b",
"task_type": "CAUSAL_LM",
"peft_type": "LORA",
"inference_mode": true,
"revision": "main",
"num_virtual_tokens": 16
}
Beta Was this translation helpful? Give feedback.
All reactions