Update README.md

README.md

@@ -17,9 +17,13 @@ datasets:
 - anthracite-org/kalo_misc_part2
 tags:
 - chat
+language:
+- en
+base_model:
+- nvidia/Mistral-NeMo-Minitron-8B-Base
 ---
 
-
+An earlier checkpoint of [Darkens-8B] using the same configuration, Finetuned ontop of the Prune/Distill NeMo 8B done by Nvidia, This model aims to have generally good prose and writing. 
 
 
 # Quants 
@@ -52,7 +56,6 @@ I would highly recommend using Sao10k's Euryale System prompt, But the "Roleplay
 Currently, your role is {{char}}, described in detail below. As {{char}}, continue the narrative exchange with {{user}}.
 
 <Guidelines>
-• Write upto 200 words. 
 • Maintain the character persona but allow it to evolve with the story.
 • Be creative and proactive. Drive the story forward, introducing plotlines and events when relevant.
 • All types of outputs are encouraged; respond accordingly to the narrative.
@@ -66,7 +69,6 @@ Currently, your role is {{char}}, described in detail below. As {{char}}, contin
 </Guidelines>
 
 <Forbidden>
-• Writing more then 200 words. 
 • Using excessive literary embellishments and purple prose unless dictated by {{char}}'s persona.
 • Writing for, speaking, thinking, acting, or replying as {{user}} in your response.
 • Repetitive and monotonous outputs.
@@ -102,7 +104,7 @@ load_in_4bit: false
 strict: false
 
 datasets:
-  - path: anthracite-core/c2_logs_16k_llama_v1.1
+  - path: PRIVATE CLAUDE LOG FILTER
     type: sharegpt
     conversation: chatml
   - path: anthracite-org/kalo-opus-instruct-22k-no-refusal
@@ -201,21 +203,10 @@ special_tokens:
 - [Epiculous/Synthstruct-Gens-v1.1-Filtered-n-Cleaned](https://huggingface.co/datasets/Epiculous/Synthstruct-Gens-v1.1-Filtered-n-Cleaned)
 - [anthracite-org/kalo_opus_misc_240827](https://huggingface.co/datasets/anthracite-org/kalo_opus_misc_240827)
 - [anthracite-org/kalo_misc_part2](https://huggingface.co/datasets/anthracite-org/kalo_misc_part2)
-- [anthracite-core/c2_logs_16k_llama_v1.1](https://huggingface.co/datasets/anthracite-core/c2_logs_16k_llama_v1.1)
+- [Private Claude Log filter](https://google.com)
 
 
 ## Training
-The training was done for 2 epochs. We used  10 x [A40s](https://www.nvidia.com/en-us/data-center/a40/) GPUs graciously provided by [Kalomaze](https://huggingface.co/kalomaze) for the full-parameter fine-tuning of the model. 
-
-[<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)
-
-## Safety
-
-Avoid misusing this model, or you’ll need a ‘clicker’ to reset reality. ;)
-
-## Musings
-
-One of the members of Anthracite had quite an interesting idea, to finetune a smaller model for 4 epochs at a lower Learning rate as quote "Smaller models learn slower" - [Kalomaze](https://huggingface.co/kalomaze) provided access to 10 X A40s and We finetuned what now is [Tor-8B]() for 2.5 epochs (and it's 4 Epoch version released as [Darkens-8B]()) and the result was quite impressive and the same configuration being used to train [Magnum=9B-V4] & [Odin-9B]. We also finetuned the model at above the 8192 context length to see if the model could "heal" in a way to a context length of 16384 with Needle tests coming soon ;)
-
-
+The training was done for 4 epochs. (This model is the 2 epoch checkpoint), I used  10 x [A40s](https://www.nvidia.com/en-us/data-center/a40/) GPUs graciously provided by [Kalomaze](https://huggingface.co/kalomaze) for the full-parameter fine-tuning of the model. 
 
+[<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)