初始化项目，由ModelHub XC社区提供模型

Model: shisa-ai/shisa-v1-llama3-8b.neftune Source: Original Platform
2026-05-21 16:54:13 +08:00
commit 24ceeb56d2
13 changed files with 2628 additions and 0 deletions
--- a/README.md
+++ b/README.md
@@ -0,0 +1,139 @@
+---
+license: llama3
+base_model: meta-llama/Meta-Llama-3-8B-Instruct
+tags:
+- generated_from_trainer
+model-index:
+- name: outputs/neftune
+  results: []
+---
+Within MOE of scores w/o NEFTune, but slightly reduced overfitting on the embedding layer.
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+[<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl)
+<details><summary>See axolotl config</summary>
+
+axolotl version: `0.4.0`
+```yaml
+base_model: meta-llama/Meta-Llama-3-8B-Instruct
+model_type: LlamaForCausalLM
+tokenizer_type: AutoTokenizer
+
+load_in_8bit: false
+load_in_4bit: false
+strict: false
+
+chat_template: llama3
+datasets:
+  - path: augmxnt/ultra-orca-boros-en-ja-v1
+    type: sharegpt
+dataset_prepared_path: last_run_prepared
+val_set_size: 0.05
+output_dir: ./outputs/neftune
+
+sequence_len: 8192
+sample_packing: true
+pad_to_sequence_len: true
+
+use_wandb: true
+wandb_project: shisa-v2
+wandb_entity: augmxnt
+wandb_name: shisa-v1-llama3-8b.neftune
+
+neftune_noise_alpha: 5
+
+gradient_accumulation_steps: 8
+micro_batch_size: 1
+num_epochs: 3
+optimizer: paged_adamw_8bit
+lr_scheduler: linear
+learning_rate: 2e-5
+
+train_on_inputs: false
+group_by_length: false
+bf16: auto
+fp16:
+tf32: false
+
+gradient_checkpointing: true
+gradient_checkpointing_kwargs:
+  use_reentrant: false
+early_stopping_patience:
+resume_from_checkpoint:
+logging_steps: 1
+xformers_attention:
+flash_attention: true
+
+warmup_steps: 100
+evals_per_epoch: 2
+eval_table_size:
+saves_per_epoch: 1
+debug:
+deepspeed: axolotl/deepspeed_configs/zero2.json
+weight_decay: 0.0
+fsdp:
+fsdp_config:
+special_tokens:
+  pad_token: <|end_of_text|>
+
+```
+
+</details><br>
+
+# outputs/neftune
+
+This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.5048
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 2e-05
+- train_batch_size: 1
+- eval_batch_size: 1
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 8
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 64
+- total_eval_batch_size: 8
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 100
+- num_epochs: 3
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 1.3955        | 0.0064 | 1    | 0.8645          |
+| 0.8892        | 0.5020 | 79   | 0.5718          |
+| 0.8728        | 1.0040 | 158  | 0.5392          |
+| 0.7356        | 1.4853 | 237  | 0.5191          |
+| 0.7075        | 1.9873 | 316  | 0.5032          |
+| 0.6447        | 2.4694 | 395  | 0.5048          |
+
+
+### Framework versions
+
+- Transformers 4.40.2
+- Pytorch 2.3.0+cu121
+- Datasets 2.19.1
+- Tokenizers 0.19.1