Create README.md

README.md

@@ -0,0 +1,187 @@
+---
+base_model:
+- meta-llama/Meta-Llama-3-70B-Instruct
+license: llama3
+language:
+- en
+pipeline_tag: text-generation
+tags:
+- merge
+- frankenmerge
+- 96b
+---
+# BigWeave v29 96b
+
+<img src="https://cdn-uploads.huggingface.co/production/uploads/65a6db055c58475cf9e6def1/4CbbAN-X7ZWj702JrcCGH.png" width=600>
+
+The BigWeave models aim to experimentally identify merge settings for increasing model performance. The version number merely tracks various attempts and is not a quality indicator. Only results demonstrating good performance are retained and shared.
+
+# Prompting Format
+llamav3
+
+# Merge process
+This is a self-merge of meta-llama/Meta-Llama-3-70B-Instruct. Middle layers are duplicated and various matrices are scaled according to the template by jukofyork as shown here: https://github.com/arcee-ai/mergekit/issues/198#issuecomment-2079950009
+
+Merge configuration:
+```
+const_tag: &MODEL meta-llama/Meta-Llama-3-70B-Instruct
+
+const_tag: &RESIDUAL_SCALE_FACTOR 0.5
+const_tag: &QK_ATTENUATION_FACTOR 0.7071067812
+const_tag: &OUT_FACTOR 0.9
+
+scale-filter-env: &scale_filter_env
+  parameters:
+    scale:
+      - filter: o_proj
+        value: *RESIDUAL_SCALE_FACTOR
+      - filter: down_proj
+        value: *RESIDUAL_SCALE_FACTOR
+      - filter: q_proj
+        value: *QK_ATTENUATION_FACTOR
+      - filter: k_proj
+        value: *QK_ATTENUATION_FACTOR
+      - filter: v_proj
+        value: *OUT_FACTOR
+      - filter: up_proj
+        value: *OUT_FACTOR
+      - value: 1.0
+
+slices:
+  - sources:
+    - model: *MODEL
+      layer_range: [0, 25]
+
+  - sources:
+    - model: *MODEL
+      layer_range: [25, 26]
+      <<: *scale_filter_env
+
+  - sources:
+    - model: *MODEL
+      layer_range: [25, 27]
+      <<: *scale_filter_env
+  - sources:
+    - model: *MODEL
+      layer_range: [26, 28]
+      <<: *scale_filter_env
+  - sources:
+    - model: *MODEL
+      layer_range: [27, 29]
+      <<: *scale_filter_env
+  - sources:
+    - model: *MODEL
+      layer_range: [28, 30]
+      <<: *scale_filter_env
+  - sources:
+    - model: *MODEL
+      layer_range: [29, 31]
+      <<: *scale_filter_env
+  - sources:
+    - model: *MODEL
+      layer_range: [30, 32]
+      <<: *scale_filter_env
+  - sources:
+    - model: *MODEL
+      layer_range: [31, 33]
+      <<: *scale_filter_env
+  - sources:
+    - model: *MODEL
+      layer_range: [32, 34]
+      <<: *scale_filter_env
+  - sources:
+    - model: *MODEL
+      layer_range: [33, 35]
+      <<: *scale_filter_env
+  - sources:
+    - model: *MODEL
+      layer_range: [34, 36]
+      <<: *scale_filter_env
+  - sources:
+    - model: *MODEL
+      layer_range: [35, 37]
+      <<: *scale_filter_env
+  - sources:
+    - model: *MODEL
+      layer_range: [36, 38]
+      <<: *scale_filter_env
+  - sources:
+    - model: *MODEL
+      layer_range: [37, 39]
+      <<: *scale_filter_env
+  - sources:
+    - model: *MODEL
+      layer_range: [38, 40]
+      <<: *scale_filter_env
+  - sources:
+    - model: *MODEL
+      layer_range: [39, 41]
+      <<: *scale_filter_env
+  - sources:
+    - model: *MODEL
+      layer_range: [40, 42]
+      <<: *scale_filter_env
+  - sources:
+    - model: *MODEL
+      layer_range: [41, 43]
+      <<: *scale_filter_env
+  - sources:
+    - model: *MODEL
+      layer_range: [42, 44]
+      <<: *scale_filter_env
+  - sources:
+    - model: *MODEL
+      layer_range: [43, 45]
+      <<: *scale_filter_env
+  - sources:
+    - model: *MODEL
+      layer_range: [44, 46]
+      <<: *scale_filter_env
+  - sources:
+    - model: *MODEL
+      layer_range: [45, 47]
+      <<: *scale_filter_env
+  - sources:
+    - model: *MODEL
+      layer_range: [46, 48]
+      <<: *scale_filter_env
+  - sources:
+    - model: *MODEL
+      layer_range: [47, 49]
+      <<: *scale_filter_env
+  - sources:
+    - model: *MODEL
+      layer_range: [48, 50]
+      <<: *scale_filter_env
+  - sources:
+    - model: *MODEL
+      layer_range: [49, 51]
+      <<: *scale_filter_env
+  - sources:
+    - model: *MODEL
+      layer_range: [50, 52]
+      <<: *scale_filter_env
+  - sources:
+    - model: *MODEL
+      layer_range: [51, 53]
+      <<: *scale_filter_env
+  - sources:
+    - model: *MODEL
+      layer_range: [52, 54]
+      <<: *scale_filter_env
+  - sources:
+    - model: *MODEL
+      layer_range: [53, 55]
+      <<: *scale_filter_env
+
+  - sources:
+    - model: *MODEL
+      layer_range: [54, 55]
+      <<: *scale_filter_env
+  - sources:
+    - model: *MODEL
+      layer_range: [55, 80]
+
+merge_method: passthrough
+dtype: float16
+```