Update README.md

README.md

@@ -9,108 +9,34 @@ model-index:
   results: []
 ---
 
-<!-- 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. -->
+Was torn between calling it MiLLM and Mistrillitary. *Sigh* naming is one of the two great problems in computer science...
 
-[<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>
+This is a domain-expert finetune based on the US Army field manuals (the ones that are published and available for civvies like me). It's focused on factual question answer only, but seems to be able to answer slightly deeper questions in a pinch.
+
+## Model Quirks
+
+- I had to focus on the army field manuals because the armed forces publishes a truly massive amount of text.
+- No generalist assistant data was included, which means this is very very very focused on QA, and may be inflexible.
+- Experimental change: data was mostly generated by a smaller model, Mistral NeMo. Quality seems unaffected, costs are much lower. Had problems with the open-ended questions not being in the right format.
+- Low temperture recommended. Screenshots use 0.
+- ChatML
+- No special tokens added.
+
+Examples:
+
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/64825ebceb4befee377cf8ac/KakWvjSMwSHkISPGoB0RH.png))
+
+
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/64825ebceb4befee377cf8ac/7rlJxcjGECqFuEFmYC3aV.png)
 
-axolotl version: `0.4.1`
-```yaml
-base_model: Heralax/army-pretrain-1
-tokenizer_type: AutoTokenizer
-is_mistral_derived_model: true
-load_in_8bit: false
-load_in_4bit: false
-strict: false
-
-datasets:
-  - path: json
-    data_files: us_army_plain_qa_list_open.jsonl
-    ds_type: json
-    type: sharegpt
-    conversation: chatml
-  - path: json
-    data_files: us_army_plain_qa_list_vanilla.jsonl
-    ds_type: json
-    type: sharegpt
-    conversation: chatml
-  - path: json
-    data_files: us_army_plain_qa_list_negative.jsonl
-    ds_type: json
-    type: sharegpt
-    conversation: chatml
-
-dataset_prepared_path: last_run_prepared
-output_dir: ./us-army-finetune-1
-
-sequence_len: 4096
-sample_packing: true
-pad_to_sequence_len: true
-shuffle_merged_datasets: true
-
-wandb_project: mistral-usarmy
-wandb_entity:
-wandb_watch:
-wandb_run_id:
-wandb_log_model:
-
-gradient_accumulation_steps: 6
-micro_batch_size: 2
-eval_batch_size: 1
-num_epochs: 6
-optimizer: paged_adamw_8bit
-lr_scheduler: cosine
-learning_rate: 0.000020
-weight_decay: 0
-# Gradient clipping max norm
-max_grad_norm: 1.0
-noisy_embedding_alpha: 0
-train_on_inputs: false
-group_by_length: false
-bf16: true
-fp16: false
-tf32: false
-
-gradient_checkpointing: unsloth
-early_stopping_patience:
-resume_from_checkpoint: 
-logging_steps: 1
-xformers_attention:
-flash_attention: true
-
-chat_template: chatml
-
-warmup_ratio: 0.5
-auto_resume_from_checkpoints: false
-#warmup_ratio: 0.5
-eval_steps: 10
-saves_per_epoch: 1
-eval_sample_packing: false
-save_total_limit: 3
-debug:
-deepspeed: deepspeed_configs/zero2.json
-special_tokens:
-  pad_token: "<|end_of_text|>"
-```
-
-</details><br>
-
-# us-army-finetune-1
-
-This model is a fine-tuned version of [Heralax/army-pretrain-1](https://huggingface.co/Heralax/army-pretrain-1) on the None dataset.
-
-## Model description
-
-More information needed
-
-## Intended uses & limitations
-
-More information needed
-
-## Training and evaluation data
-
-More information needed
+
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/64825ebceb4befee377cf8ac/mzxk9Qa9cveFx7PArnAmB.png)
+
+
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/64825ebceb4befee377cf8ac/2KtpGhqReVPj4Wh3fles5.png)
+
+
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/64825ebceb4befee377cf8ac/Pz70D922utg5ZZCqYiGpT.png)
 
 ## Training procedure
 
@@ -133,7 +59,7 @@ The following hyperparameters were used during training:
 
 ### Training results
 
-
+It answers questions alright.
 
 ### Framework versions