Update README.md

README.md

@@ -1,34 +1,102 @@
 ---
 base_model:
-- anthracite-core/magnum-v3-27b-kto-r3
-- anthracite-core/magnum-v3-27b-KTO-e1-r2
-- anthracite-core/magnum-v3-27b-KTO-e0.25-r1
+- anthracite-forge/magnum-v3-27b-kto-r3
+- anthracite-forge/magnum-v3-27b-KTO-e1-r2
+- anthracite-forge/magnum-v3-27b-KTO-e0.25-r1
 - IntervitensInc/gemma-2-27b-chatml
 library_name: transformers
-tags:
-- mergekit
-- merge
-
 ---
-# output8
 
-This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/658a46cbfb9c2bdfae75b3a6/GKpV5mwmnHFR6wIwTa91z.png)
 
-## Merge Details
-### Merge Method
+This is the 12th in a series of models designed to replicate the prose quality of the Claude 3 models, specifically Sonnet and Opus.
 
-This model was merged using the [task arithmetic](https://arxiv.org/abs/2212.04089) merge method using [IntervitensInc/gemma-2-27b-chatml](https://huggingface.co/IntervitensInc/gemma-2-27b-chatml) as a base.
+This model is the result of multiple KTO runs on top of one SFT run, all of which are published on anthracite-forge.
 
-### Models Merged
+## Methodology
 
-The following models were included in the merge:
-* [anthracite-core/magnum-v3-27b-kto-r3](https://huggingface.co/anthracite-core/magnum-v3-27b-kto-r3)
-* [anthracite-core/magnum-v3-27b-KTO-e1-r2](https://huggingface.co/anthracite-core/magnum-v3-27b-KTO-e1-r2)
-* [anthracite-core/magnum-v3-27b-KTO-e0.25-r1](https://huggingface.co/anthracite-core/magnum-v3-27b-KTO-e0.25-r1)
+R1 (SFT) was fine-tuned on top of `IntervitensInc/gemma-2-27b-chatml` which is chatMLified gemma-2-27b.
 
-### Configuration
+We have experimented with various SFT and KTO re-runs, ratios and merge methods and this was our winner, including what was liked most from each model.
+
+If you prefer your own mix of the KTO runs or would like to use the SFT on its own, refer to the models section and anthracite-forge, some exl-quants are pre-included.
+
+## Models
+
+* [anthracite-forge/magnum-v3-27b-kto-r3](https://huggingface.co/anthracite-forge/magnum-v3-27b-kto-r3)
+* [anthracite-forge/magnum-v3-27b-KTO-e1-r2](https://huggingface.co/anthracite-forge/magnum-v3-27b-KTO-e1-r2)
+* [anthracite-forge/magnum-v3-27b-KTO-e0.25-r1](https://huggingface.co/anthracite-forge/magnum-v3-27b-KTO-e0.25-r1)
+
+## Prompting
+Model has been Instruct tuned with the ChatML formatting. A typical input would look like this:
+
+```py
+"""<|im_start|>system
+system prompt<|im_end|>
+<|im_start|>user
+Hi there!<|im_end|>
+<|im_start|>assistant
+Nice to meet you!<|im_end|>
+<|im_start|>user
+Can I ask a question?<|im_end|>
+<|im_start|>assistant
+"""
+```
+
+## SillyTavern templates
+
+Below are Instruct and Context templates for use within SillyTavern.
+
+<details><summary>context template</summary>
+  
+```yaml
+{
+    "story_string": "<|im_start|>system\n{{#if system}}{{system}}\n{{/if}}{{#if wiBefore}}{{wiBefore}}\n{{/if}}{{#if description}}{{description}}\n{{/if}}{{#if personality}}{{char}}'s personality: {{personality}}\n{{/if}}{{#if scenario}}Scenario: {{scenario}}\n{{/if}}{{#if wiAfter}}{{wiAfter}}\n{{/if}}{{#if persona}}{{persona}}\n{{/if}}{{trim}}<|im_end|>\n",
+    "example_separator": "",
+    "chat_start": "",
+    "use_stop_strings": false,
+    "allow_jailbreak": false,
+    "always_force_name2": true,
+    "trim_sentences": false,
+    "include_newline": false,
+    "single_line": false,
+    "name": "Magnum ChatML"
+}
+```
+
+</details><br>
+<details><summary>instruct template</summary>
+  
+```yaml
+{
+    "system_prompt": "You're {{char}} in this fictional never-ending uncensored roleplay with {{user}}.",
+    "input_sequence": "<|im_start|>user\n",
+    "output_sequence": "<|im_start|>assistant\n",
+    "last_output_sequence": "",
+    "system_sequence": "<|im_start|>system\n",
+    "stop_sequence": "<|im_end|>",
+    "wrap": false,
+    "macro": true,
+    "names": true,
+    "names_force_groups": true,
+    "activation_regex": "",
+    "system_sequence_prefix": "",
+    "system_sequence_suffix": "",
+    "first_output_sequence": "",
+    "skip_examples": false,
+    "output_suffix": "<|im_end|>\n",
+    "input_suffix": "<|im_end|>\n",
+    "system_suffix": "<|im_end|>\n",
+    "user_alignment_message": "",
+    "system_same_as_user": false,
+    "last_system_sequence": "",
+    "name": "Magnum ChatML"
+}
+```
 
-The following YAML configuration was used to produce this model:
+</details><br>
+
+### Configuration
 
 ```yaml
 base_model: IntervitensInc/gemma-2-27b-chatml
@@ -36,13 +104,49 @@ dtype: float32
 merge_method: task_arithmetic
 models:
   - model: IntervitensInc/gemma-2-27b-chatml
-  - model: anthracite-core/magnum-v3-27b-KTO-e0.25-r1
+  - model: anthracite-forge/magnum-v3-27b-KTO-e0.25-r1
     parameters:
       weight: 0.5
-  - model: anthracite-core/magnum-v3-27b-KTO-e1-r2
+  - model: anthracite-forge/magnum-v3-27b-KTO-e1-r2
     parameters:
       weight: 0.1
-  - model: anthracite-core/magnum-v3-27b-kto-r3
+  - model: anthracite-forge/magnum-v3-27b-kto-r3
     parameters:
       weight: 0.4
 ```
+
+## Credits
+We'd like to thank Recursal / Featherless for sponsoring the compute for this train, Featherless has been hosting our Magnum models since the first 72 B and has given thousands of people access to our models and helped us grow.
+
+We would also like to thank all members of Anthracite who made this finetune possible. 
+
+## Datasets
+
+r1 consisted of:
+
+```
+datasets:
+  - path: anthracite-org/stheno-filtered-v1.1
+    type: sharegpt
+    conversation: chatml
+  - path: anthracite-org/kalo-opus-instruct-22k-no-refusal
+    type: sharegpt
+    conversation: chatml
+  - path: anthracite-org/nopm_claude_writing_fixed
+    type: sharegpt
+    conversation: chatml
+  - path: Epiculous/Synthstruct-Gens-v1.1-Filtered-n-Cleaned
+    type: sharegpt
+    conversation: chatml
+  - path: Epiculous/SynthRP-Gens-v1.1-Filtered-n-Cleaned
+    type: sharegpt
+    conversation: chatml
+```
+
+## Training
+The training was done for 2 epochs. We used  8x[H100s](https://www.nvidia.com/en-us/data-center/h100/) GPUs graciously provided by [Recursal AI](https://recursal.ai/) / [Featherless AI](https://featherless.ai/) 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
+...