Update README.md

README.md

@@ -1,93 +1,96 @@
----
-base_model:
-- CrucibleLab/L3.3-70B-Loki-V2.0
-- meta-llama/Llama-3.1-70B
-- schonsense/Tropoplectic
-library_name: transformers
-tags:
-- mergekit
-- merge
-
----
-# Bragi3
-
-This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
-
-## Merge Details
-### Merge Method
-
-This model was merged using the NuSLERP merge method using [meta-llama/Llama-3.1-70B](https://huggingface.co/meta-llama/Llama-3.1-70B) as a base.
-
-### Models Merged
-
-The following models were included in the merge:
-* [CrucibleLab/L3.3-70B-Loki-V2.0](https://huggingface.co/CrucibleLab/L3.3-70B-Loki-V2.0)
-* [schonsense/Tropoplectic](https://huggingface.co/schonsense/Tropoplectic)
-
-### Configuration
-
-The following YAML configuration was used to produce this model:
-
-```yaml
-models:
-  - model: CrucibleLab/L3.3-70B-Loki-V2.0
-    parameters:        
-          weight:
-            - filter: q_proj
-              value: [0.80, 0.30, 0.30, 0.30, 0.8]
-            - filter: k_proj
-              value: [0.70, 0.20, 0.20, 0.20, 0.7]
-            - filter: v_proj
-              value: [0.80, 0.40, 0.40, 0.40, 0.8]
-            - filter: o_proj
-              value: [0.90, 0.80, 0.80, 0.80, 0.9] 
-            - filter: gate_proj
-              value: [0.80, 0.20, 0.20, 0.20, 0.8]
-            - filter: up_proj
-              value: [0.80, 0.30, 0.30, 0.30, 0.8]
-            - filter: down_proj
-              value: [0.90, 0.80, 0.80, 0.80, 0.9]
-            - filter: lm_head
-              value: 0.95
-            - value: 1
-
-
-
-  - model: schonsense/Tropoplectic
-    parameters:       
-          weight:
-            - filter: q_proj
-              value: [0.20, 0.70, 0.70, 0.70, 0.2]
-            - filter: k_proj
-              value: [0.30, 0.80, 0.80, 0.80, 0.3]
-            - filter: v_proj
-              value: [0.20, 0.60, 0.60, 0.60, 0.2]
-            - filter: o_proj
-              value: [0.10, 0.25, 0.25, 0.25, 0.1] 
-            - filter: gate_proj
-              value: [0.20, 0.80, 0.80, 0.80, 0.2]
-            - filter: up_proj
-              value: [0.20, 0.70, 0.70, 0.70, 0.2]
-            - filter: down_proj
-              value: [0.10, 0.25, 0.25, 0.25, 0.1]
-            - filter: lm_head
-              value: 0.05
-            - value: 0
-
-base_model: meta-llama/Llama-3.1-70B
-merge_method: nuslerp
-
-parameters:
-  normalize: false
-  int8_mask: false
-  rescale: false
-
-dtype: float32
-out_dtype: bfloat16
-
-chat_template: llama3
-tokenizer:
-  source: union
-  pad_to_multiple_of: 8
-        
-```
+---
+base_model:
+- CrucibleLab/L3.3-70B-Loki-V2.0
+- meta-llama/Llama-3.1-70B
+- schonsense/Tropoplectic
+library_name: transformers
+tags:
+- mergekit
+- merge
+
+---
+# Bragi3
+
+Too sloppy for my tastes.
+
+
+This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
+
+## Merge Details
+### Merge Method
+
+This model was merged using the NuSLERP merge method using [meta-llama/Llama-3.1-70B](https://huggingface.co/meta-llama/Llama-3.1-70B) as a base.
+
+### Models Merged
+
+The following models were included in the merge:
+* [CrucibleLab/L3.3-70B-Loki-V2.0](https://huggingface.co/CrucibleLab/L3.3-70B-Loki-V2.0)
+* [schonsense/Tropoplectic](https://huggingface.co/schonsense/Tropoplectic)
+
+### Configuration
+
+The following YAML configuration was used to produce this model:
+
+```yaml
+models:
+  - model: CrucibleLab/L3.3-70B-Loki-V2.0
+    parameters:        
+          weight:
+            - filter: q_proj
+              value: [0.80, 0.30, 0.30, 0.30, 0.8]
+            - filter: k_proj
+              value: [0.70, 0.20, 0.20, 0.20, 0.7]
+            - filter: v_proj
+              value: [0.80, 0.40, 0.40, 0.40, 0.8]
+            - filter: o_proj
+              value: [0.90, 0.80, 0.80, 0.80, 0.9] 
+            - filter: gate_proj
+              value: [0.80, 0.20, 0.20, 0.20, 0.8]
+            - filter: up_proj
+              value: [0.80, 0.30, 0.30, 0.30, 0.8]
+            - filter: down_proj
+              value: [0.90, 0.80, 0.80, 0.80, 0.9]
+            - filter: lm_head
+              value: 0.95
+            - value: 1
+
+
+
+  - model: schonsense/Tropoplectic
+    parameters:       
+          weight:
+            - filter: q_proj
+              value: [0.20, 0.70, 0.70, 0.70, 0.2]
+            - filter: k_proj
+              value: [0.30, 0.80, 0.80, 0.80, 0.3]
+            - filter: v_proj
+              value: [0.20, 0.60, 0.60, 0.60, 0.2]
+            - filter: o_proj
+              value: [0.10, 0.25, 0.25, 0.25, 0.1] 
+            - filter: gate_proj
+              value: [0.20, 0.80, 0.80, 0.80, 0.2]
+            - filter: up_proj
+              value: [0.20, 0.70, 0.70, 0.70, 0.2]
+            - filter: down_proj
+              value: [0.10, 0.25, 0.25, 0.25, 0.1]
+            - filter: lm_head
+              value: 0.05
+            - value: 0
+
+base_model: meta-llama/Llama-3.1-70B
+merge_method: nuslerp
+
+parameters:
+  normalize: false
+  int8_mask: false
+  rescale: false
+
+dtype: float32
+out_dtype: bfloat16
+
+chat_template: llama3
+tokenizer:
+  source: union
+  pad_to_multiple_of: 8
+        
+```