Update README.md

README.md

@@ -28,6 +28,202 @@ The following models were included in the merge:
 The following YAML configuration was used to produce this model:
 
 ```yaml
+# Recipe
+```yaml
+#1. Take a collection of RP and Storywriter 8b models and merge them.
+
+dtype: float32
+merge_method: linear
+      weight: 0.15
+    parameters:
+  - model: tokyotech-llm/Llama-3-Swallow-8B-v0.1
+      weight: 0.4
+    parameters:
+  - model: NeverSleep/Llama-3-Lumimaid-8B-v0.1-OAS
+      weight: 0.1
+    parameters:
+  - model: maldv/llama-3-fantasy-writer-8b
+      weight: 0.6
+    parameters:
+  - model: Nitral-AI/Hathor_Respawn-L3-8B-v0.8
+ 
+#2. Use task-arithmetic to learn the vector directions from the RP-Mix onto Llama-3-SPPO which is the smartest 8B model imo, this way we can preserve Meta's multi-bullion dollar tuning.
+
+models:
+dtype: float32
+    normalize: false
+parameters:
+base_model: UCLA-AGI/Llama-3-Instruct-8B-SPPO-Iter3
+merge_method: task_arithmetic
+      weight: 0.35
+    parameters:
+  - model: rpmix-part1
+      weight: 1.0
+    parameters:
+  - model: UCLA-AGI/Llama-3-Instruct-8B-SPPO-Iter3
+  
+#2,5. Apply abliteration to the previous model
+
+models:
+dtype: float32
+merge_method: linear
+      weight: 1.0
+    parameters:
+  - model: sppo-rpmix-part2+grimjim/Llama-3-Instruct-abliteration-LoRA-8B
+  
+#3. Create an abliterated version of Stheno3.2-8B as we will use this in the 15B frankenmerge.
+
+models:
+dtype: float32
+merge_method: linear
+      weight: 1.0
+    parameters:
+  - model: Sao10K/L3-8B-Stheno-v3.2+grimjim/Llama-3-Instruct-abliteration-LoRA-8B
+  
+#4. Make an inverted version of a Llama-3-15B Frankenmerge with the previous models.
+
+models:
+    model: v000000/L3-8B-Stheno-v3.2-abliterated
+  - layer_range: [24, 32]
+- sources:
+    model: v000000/SwallowMaid-8B-L3-SPPO-abliterated
+  - layer_range: [8, 24]
+- sources:
+    parameters:
+    model: v000000/L3-8B-Stheno-v3.2-abliterated
+  - layer_range: [8, 24]
+- sources:
+    model: v000000/SwallowMaid-8B-L3-SPPO-abliterated
+  - layer_range: [0, 24]
+- sources:
+slices:
+
+#5. Make an non-inverted version of a Llama-3-15B Frankenmerge with the previous models.
+merge_method: passthrough
+dtype: float32
+    model: v000000/SwallowMaid-8B-L3-SPPO-abliterated
+  - layer_range: [24, 32]
+- sources:
+    model: v000000/L3-8B-Stheno-v3.2-abliterated
+  - layer_range: [8, 24]
+- sources:
+    model: v000000/SwallowMaid-8B-L3-SPPO-abliterated
+  - layer_range: [8, 24]
+- sources:
+    model: v000000/L3-8B-Stheno-v3.2-abliterated
+  - layer_range: [0, 24]
+- sources:
+slices:
+
+#6. Test the previous two models and determine which is better in the output/input stage and which is best in the middle and we slerp them in a v-shape.
+
+merge_method: passthrough
+dtype: float32
+  t: [0, 0.5, 1, 0.5, 0]
+parameters:
+dtype: float32
+base_model: v000000/Sthalomaid-15B-abliterated
+merge_method: slerp
+  - model: v000000/Sthalomaid-15B-Inverted-abliterated
+  - model: v000000/Sthalomaid-15B-abliterated
+  
+#7. Apply Blackroot Lora in a model_stock merge of the different models so far
+
+models:
+dtype: float32
+merge_method: model_stock
+base_model: v000000/Sthalomaid-V-15B-abliterated
+  - model: v000000/Sthalomaid-15B-Inverted-abliterated+Blackroot/Llama-3-8B-Abomination-LORA
+  - model: v000000/Sthalomaid-15B-abliterated+Blackroot/Llama-3-8B-Abomination-LORA
+  - model: v000000/Sthalomaid-V-15B-abliterated+Blackroot/Llama-3-8B-Abomination-LORA #seems to work on 15b
+  - model: v000000/Sthalomaid-15B-Inverted-abliterated
+  - model: v000000/Sthalomaid-15B-abliterated
+  - model: v000000/Sthalomaid-V-15B-abliterated
+ 
+#7. Create another 15B frankenmerge from just SPPO and abiterate it, this is so we can merge in a smarter model.
+
+models:
+dtype: float32
+merge_method: passthrough
+slices:
+- sources:
+  - layer_range: [0, 24]
+    model: UCLA-AGI/Llama-3-Instruct-8B-SPPO-Iter3+grimjim/Llama-3-Instruct-abliteration-LoRA-8B
+- sources:
+  - layer_range: [8, 24]
+    model: UCLA-AGI/Llama-3-Instruct-8B-SPPO-Iter3+grimjim/Llama-3-Instruct-abliteration-LoRA-8B
+    parameters:
+- sources:
+  - layer_range: [8, 24]
+    model: UCLA-AGI/Llama-3-Instruct-8B-SPPO-Iter3+grimjim/Llama-3-Instruct-abliteration-LoRA-8B
+- sources:
+  - layer_range: [24, 32]
+    model: UCLA-AGI/Llama-3-Instruct-8B-SPPO-Iter3+grimjim/Llama-3-Instruct-abliteration-LoRA-8B
+
+#8. Learn vectors from our previous blackroot model_stock model to smarter SPPO-Iter model to preserve RP capabilities.
+
+models:
+  - model: v000000/HaloMaidRP-V-15B-Blackroot-v0.1
+    parameters:
+      weight: 1.3
+merge_method: task_arithmetic
+base_model: v000000/Llama-3-Instruct-15B-SPPO-Iter3-abliterated
+parameters:
+  normalize: false
+
+#9. Merge the blackroot model_stock-15B and SPPO-15B models together with a smooth gradient.
+
+dtype: float32
+slices:
+  - sources:
+      - model: v000000/HaloMaidRP-V-15B-Blackroot-v0.1
+        layer_range: [0, 64]
+      - model: v000000/HaloMaidRP-V-15B-Blackroot-v0.223
+        layer_range: [0, 64]
+merge_method: slerp
+base_model: v000000/HaloMaidRP-V-15B-Blackroot-v0.223
+parameters:
+  t:
+    - filter: self_attn
+      value: [0, 0.5, 0.3, 0.7, 1, 0.1, 0.6, 0.3, 0.8, 0.5]
+    - filter: mlp
+      value: [1, 0.5, 0.7, 0.3, 0, 0.3, 0.4, 0.7, 0.2, 0.5]
+    - value: 0.5
+dtype: bfloat16 #Oops accidentally swtich to half precision do this also very important
+
+#10. Heal the layers, o_proj and down_proj seems to be the only tensors that determine adaptation to a new architecture, so we can steal them from an already finetuned 15B, 
+#this way we don't need to finetune our new frankenmerge at all to have full performance. Why reinvent the wheel?
+#sapphire
+models:
+  - model: v000000/HaloMaidRP1_component
+merge_method: slerp
+base_model: ZeusLabs/L3-Aethora-15B-V2
+parameters:
+  t:
+    - filter: o_proj
+      value: 0
+    - filter: down_proj
+      value: 0
+    - value: 1
+dtype: bfloat16
+
+#11. Go back to an earlier checkpoint that had interesting results with being very depraved before the blackroot model_stock merge and do the same as (10.) to heal it.
+#ruby
+models:
+  - model: v000000/component____HaloMaidRP-V
+merge_method: slerp
+base_model: ZeusLabs/L3-Aethora-15B-V2
+parameters:
+  t:
+    - filter: o_proj
+      value: 0
+    - filter: down_proj
+      value: 0
+    - value: 1
+dtype: bfloat16
+
+#12. Then we merge these two together to get a semi-depraved smart model.
+#emerald
 slices:
   - sources:
       - model: v000000/HaloMaidRP-v1.32-15B-Sapphire
@@ -46,3 +242,4 @@ parameters:
 dtype: bfloat16
 
 ```
+```