Create README.md

README.md

@@ -0,0 +1,160 @@
+---
+library_name: transformers
+license: other
+license_name: qwen
+license_link: https://huggingface.co/Qwen/Qwen2.5-14B/blob/main/LICENSE
+base_model: Qwen/Qwen2.5-14B
+tags:
+- generated_from_trainer
+model-index:
+- name: 14B-Qwen2.5-Freya-x1
+  results: []
+---
+
+![Kunou](https://huggingface.co/Sao10K/72B-Qwen2.5-Kunou-v1/resolve/main/knn.png)
+
+**Sister Versions for Lightweight and Heavyweight Use!**
+
+# 14B-Qwen2.5-Freya-v1
+
+I decided to mess around with training methods, considering the re-emegence of no longer used methods like multi-step training. Some people began doing it again, and so, why not? Inspired by LimaRP's methology but done it my way.
+
+
+Freya-S1
+- LoRA Trained on ~1.1GB of literature and raw text over Qwen 2.5's base model.
+- Cleaned text and literature as best as I could, still, may have had issues here and there.
+
+Freya-S2
+- The first LoRA was applied over Qwen 2.5 Instruct, then I trained on top of that.
+- Reduced LoRA rank because it's mainly instruct and other details I won't get into.
+
+Recommended Model Settings | *Look, I just use these, they work fine enough. I don't even know how DRY or other meme samplers work. Your system prompt matters more anyway.*
+```
+Prompt Format: ChatML
+Temperature: 1.1
+min_p: 0.1
+```
+
+Training time in total was ~10 Hours on a 8xH100 Node, sponsored by the Government of Singapore or something. Thanks for the national service allowance, MHA.
+
+https://sao10k.carrd.co/ for contact.
+
+---
+
+[<img src="https://raw.githubusercontent.com/axolotl-ai-cloud/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/axolotl-ai-cloud/axolotl)
+<details><summary>See axolotl config</summary>
+
+axolotl version: `0.6.0`
+```yaml
+base_model:
+- s1: Qwen/Qwen2.5-14B
+- s2: Qwen/Qwen2.5-14B-Instruct
+model_type: AutoModelForCausalLM
+tokenizer_type: AutoTokenizer
+
+load_in_8bit: false
+load_in_4bit: false
+strict: false
+sequence_len: 16384
+bf16: auto
+fp16:
+tf32: false
+flash_attention: true
+special_tokens:
+  
+adapter: lora
+lora_r:
+- s1: 64
+- s2: 32
+lora_alpha: 64
+lora_dropout: 0.2
+lora_fan_in_fan_out:
+peft_use_rslora: true
+lora_target_linear: true
+  
+# Data
+dataset_prepared_path: dataset_rUn_freya
+datasets:
+# S1 - Writing / Completion
+  - path: datasets/eBooks-cleaned-75K
+    type: completion
+  - path: datasets/novels-clean-dedupe-10K
+    type: completion
+# S2 - Instruct
+  - path: datasets/10k-amoral-full-fixed-sys.json
+    type: chat_template
+    chat_template: chatml
+    roles_to_train: ["gpt"]
+    field_messages: conversations
+    message_field_role: from
+    message_field_content: value
+    train_on_eos: turn
+  - path: datasets/44k-hespera-smartshuffle.json
+    type: chat_template
+    chat_template: chatml
+    roles_to_train: ["gpt"]
+    field_messages: conversations
+    message_field_role: from
+    message_field_content: value
+    train_on_eos: turn
+  - path: datasets/5k_rpg_adventure_instruct-sys.json
+    type: chat_template
+    chat_template: chatml
+    roles_to_train: ["gpt"]
+    field_messages: conversations
+    message_field_role: from
+    message_field_content: value
+    train_on_eos: turn
+shuffle_merged_datasets: true
+warmup_ratio: 0.1
+
+plugins:
+  - axolotl.integrations.liger.LigerPlugin
+liger_rope: true
+liger_rms_norm: true
+liger_layer_norm: true
+liger_glu_activation: true
+liger_fused_linear_cross_entropy: true
+
+# Iterations
+num_epochs:
+- s1: 2
+- s2: 2
+
+# Sampling
+sample_packing: true
+pad_to_sequence_len: true
+train_on_inputs: false
+group_by_length: false
+
+# Batching
+gradient_accumulation_steps: 4
+micro_batch_size: 2
+gradient_checkpointing: unsloth
+
+# Evaluation
+val_set_size: 0.025
+evals_per_epoch: 5
+eval_table_size:
+eval_max_new_tokens: 256
+eval_sample_packing: false
+eval_batch_size: 1
+
+# Optimizer
+optimizer: paged_ademamix_8bit
+lr_scheduler: cosine
+learning_rate:
+- s1: 0.000002
+- s2: 0.000004
+weight_decay: 0.2
+max_grad_norm: 10.0
+
+# Garbage Collection
+gc_steps: 10
+
+# Misc
+deepspeed: ./deepspeed_configs/zero2.json
+
+```
+
+</details><br>