Update README.md

README.md

@@ -1,152 +1,45 @@
 ---
 library_name: transformers
-license: llama3.1
-base_model: Epiculous/NovaSpark-Instruct
+license: apache-2.0
+base_model:
+- grimjim/Llama-3.1-SuperNova-Lite-lorabilterated-8B
 tags:
 - generated_from_trainer
+datasets:
+- Epiculous/SynthRP-Gens-v1.1-Filtered-n-Cleaned
+- anthracite-org/stheno-filtered-v1.1
+- PJMixers/hieunguyenminh_roleplay-deduped-ShareGPT
+- Gryphe/Sonnet3.5-Charcard-Roleplay
+- Epiculous/Synthstruct-Gens-v1.1-Filtered-n-Cleaned
+- anthracite-org/kalo-opus-instruct-22k-no-refusal
+- anthracite-org/nopm_claude_writing_fixed
+- anthracite-org/kalo_opus_misc_240827
 model-index:
-- name: outputs/NovaSpark_RP/5e-6_WD0.05_Waup8
+- name: Epiculous/NovaSpark
   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. -->
-
-[<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: `0.4.1`
-```yaml
-base_model: Epiculous/NovaSpark-Instruct
-model_type: AutoModelForCausalLM
-tokenizer_type: AutoTokenizer
-
-plugins:
-  - axolotl.integrations.liger.LigerPlugin
-liger_rope: true
-liger_rms_norm: true
-liger_swiglu: true
-liger_fused_linear_cross_entropy: true
-
-load_in_8bit: false
-load_in_4bit: false
-strict: false
-
-datasets:
-  - path: datasets/Crimson_Dawn-v0.2/RP/SynthRP-Gens_processed_09-25-2024_converted_filtered-deduplicated_deslopped-classified.jsonl
-    type: sharegpt
-    conversation: llama3
-  - path: datasets/Crimson_Dawn-v0.2/RP/stheno_data_filtered_v1.1_instruct_killed_processed_converted_filtered-deduplicated_deslopped-classified.jsonl
-    type: sharegpt
-    conversation: llama3
-  - path: datasets/Crimson_Dawn-v0.2/RP/sonnet35-charcard-roleplay-sharegpt_processed_converted_filtered-deduplicated_deslopped-classified.jsonl
-    type: sharegpt
-    conversation: llama3
-  - path: datasets/Crimson_Dawn-v0.2/RP/roleplay-deduped_processed_converted_filtered-deduplicated_deslopped-classified.jsonl
-    type: sharegpt
-    conversation: llama3
-dataset_prepared_path: last_run_prepared
-val_set_size: 0.01
-output_dir: ./outputs/NovaSpark_RP/5e-6_WD0.05_Waup8
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/64adfd277b5ff762771e4571/pnFt8anKzuycrmIuB-tew.png)
 
-chat_template: llama3
-default_system_message: "You will will take whatever role the user gives you and act accordingly."
+# Quants!
+<strong>full</strong> / [exl2]() / [gguf]()
 
-sequence_len: 16384
-sample_packing: true
-eval_sample_packing: false
-shuffle_merged_datasets: true
-pad_to_sequence_len: false
+## Prompting
+This model is trained on llama instruct template, the prompting structure goes a little something like this:
 
-wandb_project: NovaSpark_RP
-wandb_name: 5e-6_WD0.05_Waup8
-
-gradient_accumulation_steps: 16
-micro_batch_size: 1
-num_epochs: 2
-optimizer: paged_adamw_8bit
-lr_scheduler: cosine
-learning_rate: 5e-6
-
-train_on_inputs: false
-group_by_length: false
-bf16: auto
-tf32: false
-
-gradient_checkpointing: unsloth
-gradient_checkpointing_kwargs:
-  use_reentrant: false
-logging_steps: 1
-flash_attention: true
-eager_attention: false
-
-warmup_steps: 8
-evals_per_epoch: 4
-saves_per_epoch: 1
-debug: true 
-weight_decay: 0.05
-
-special_tokens:
-  pad_token: <|finetune_right_pad_id|>
-  eos_token: <|eot_id|>
 ```
+<|begin_of_text|><|start_header_id|>system<|end_header_id|>
 
-</details><br>
-
-# outputs/NovaSpark_RP/5e-6_WD0.05_Waup8
-
-This model is a fine-tuned version of [Epiculous/NovaSpark-Instruct](https://huggingface.co/Epiculous/NovaSpark-Instruct) on the None dataset.
-It achieves the following results on the evaluation set:
-- Loss: 1.1786
-
-## 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: 5e-06
-- train_batch_size: 1
-- eval_batch_size: 1
-- seed: 42
-- distributed_type: multi-GPU
-- num_devices: 2
-- gradient_accumulation_steps: 16
-- total_train_batch_size: 32
-- total_eval_batch_size: 2
-- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
-- lr_scheduler_type: cosine
-- lr_scheduler_warmup_steps: 8
-- num_epochs: 2
-
-### Training results
-
-| Training Loss | Epoch  | Step | Validation Loss |
-|:-------------:|:------:|:----:|:---------------:|
-| 1.3967        | 0.0194 | 1    | 1.3736          |
-| 1.3798        | 0.2518 | 13   | 1.3047          |
-| 1.2887        | 0.5036 | 26   | 1.2358          |
-| 1.2515        | 0.7554 | 39   | 1.2067          |
-| 1.2042        | 1.0048 | 52   | 1.1901          |
-| 1.0871        | 1.2560 | 65   | 1.1849          |
-| 1.1356        | 1.5072 | 78   | 1.1802          |
-| 1.139         | 1.7585 | 91   | 1.1786          |
+{system_prompt}<|eot_id|><|start_header_id|>user<|end_header_id|>
 
+{prompt}<|eot_id|><|start_header_id|>assistant<|end_header_id|>
+```
 
-### Framework versions
+### Context and Instruct
+This model is trained on llama-instruct, please use that Context and Instruct template.
 
-- Transformers 4.45.1
-- Pytorch 2.3.0+cu121
-- Datasets 2.21.0
-- Tokenizers 0.20.0
+### Current Top Sampler Settings
+[Smooth Creativity](https://files.catbox.moe/0ihfir.json): Credit to Juelsman for researching this one!<br/>
+[Variant Chimera](https://files.catbox.moe/h7vd45.json): Credit to Numbra!<br/>
+[Spicy_Temp](https://files.catbox.moe/9npj0z.json) <br/>
+[Violet_Twilight-Nitral-Special](https://files.catbox.moe/ot54u3.json) <br/>