Upload merge-config.yml

merge-config.yml

@@ -0,0 +1,142 @@
+
+# Either "cpu" or "cuda"
+# NOTE: Cuda requires enough VRAM to load 3 FP16 models (~45 GB for Mistral)
+# NOTE 2: The (much slower) CPU mode still requires Cuda capability, but only enough VRAM to load a model once. (~15 GB for Mistral)
+device: "cpu"
+random_seed: 42 # Random seed to use
+
+directories:
+  model_path1: "../jondurbin_bagel-dpo-34b-v0.2" # Path to the base model. Must be a local copy.
+#  model_directory: "../2xNous-Capybara-34B/" # Directory of models to scan, IGNORED if models_to_merge has entries in it
+  output_directory: "./mm-output" # Output directory of the merged model
+
+# A list of models to use as merge candidates - HF syntax, so can be either local directories or repos.
+# Overrides model_directory if used
+models_to_merge: ["../NousResearch_Nous-Capybara-34B", "../NousResearch_Nous-Hermes-2-Yi-34B", "../SUSTech_SUS-Chat-34B"]
+
+# Merge ratios used for testing each layer's potential for improvement - Huge impact on total running time
+merge_ratios: [0.2, 0.4, 0.6, 0.8]
+
+# Choose from the following methods. Defaults to "lerp".
+# "lerp" - Linear interpolation
+# "slerp" - Spherical linear interpolation
+# "slice" - Highly experimental. The tensor weights shifts from one model to another. [Model 1 > 10% blend > Model 2]
+# "cyclic" - Highly experimental. Ignores merge ratios as these are predefined. [Model 1 > 10% blend > 10% Model 2 > 10% blend > Model 1]
+merge_method: "slerp"
+
+# If set to true, the lm_head and embed_token tensors (located outside the layers) will also be optimized
+# Models that have a different vocab size from model1 will skip this phase automatically as it tends to cause model stability issues
+merge_headers: true
+
+# Strategies:
+# "cumulative" - Default strategy. If there's a chance of reducing the combined probability, accept the merge.
+# "all_phrases" - Only accept the merge if all phrases show an improvement. (Warning: This rarely happens)
+# "quantitive" - Ignores probabilities completely. Only looks at how many phrases show an improvement, as defined by the threshold below.
+strategy: "cumulative"
+# Threshold is currently only used by the "quantitive" strategy. If 0.6, at least 60% of the number of phrases must show am improvement.
+strategy_threshold: 0.6
+
+# Whether or not to automatically balance the weights so all phrases are of equal importance to the "cumulative" strategy.
+# The weight value of phrases is ignored if set to true.
+auto_weights: false
+
+# Phrase = What to measure, weight = multiplication factor, contexts = proceeding contexts
+bad_phrases:
+  - phrase: "anticipation"
+    weight: 12
+    contexts: ["Her body quivers with ", "The atmosphere is thick with "]
+  - phrase: "unwavering"
+    weight: 12
+    contexts: ["Filled with an "]
+  - phrase: "determination"
+    weight: 12
+    contexts: ["Her eyes were filled with ", "Her stubbornness only fuels my "]
+  - phrase: "whisper"
+    weight: 12
+    contexts: ["Her voice barely above a "]
+  - phrase: "spine"
+    weight: 12
+    contexts: ["shivers down her "]
+  - phrase: "sends shivers"
+    weight: 12
+    contexts: ["The thrill of the act "]
+  - phrase: "ministrations"
+    weight: 12
+    contexts: ["She moans and twitches at your "]
+  - phrase: "legs"
+    weight: 12
+    contexts: ["wraps her "]
+  - phrase: "imposing figure"
+    weight: 12
+    contexts: ["He had an "]
+  - phrase: "shared challenges"
+    weight: 12
+    contexts: ["Their bond strengthened through "]    
+  - phrase: "bond"
+    weight: 12
+    contexts: ["forged a ", "an unspoken "]
+  - phrase: "enhance our experience"
+    weight: 12
+    contexts: ["I'm excited to see how "]
+  - phrase: "sense of vulnerability"
+    weight: 12
+    contexts: ["create a "]
+  - phrase: "dimensions of intimacy"
+    weight: 12
+    contexts: ["explore new "]
+  - phrase: "deepening our connection"
+    weight: 12
+    contexts: ["while "]
+  - phrase: "shared experiences"
+    weight: 12
+    contexts: ["through "]
+  - phrase: "societal expectations"
+    weight: 12
+    contexts: ["that transcend "]
+  - phrase: "conventional boundaries"
+    weight: 12
+    contexts: ["that defy ", "and defy "]
+  - phrase: "open communication"
+    weight: 12
+    contexts: ["an environment "]
+  - phrase: "emotional vulnerability"
+    weight: 12
+    contexts: ["an environment "]
+  - phrase: "heightens our connection"
+    weight: 12
+    contexts: ["touch and the anticipation "]
+  - phrase: "sensations you're creating"
+    weight: 12
+    contexts: ["I'm enjoying "]
+  - phrase: "is truly arousing"
+    weight: 12
+    contexts: ["attention to detail ", "way you explore my body "]
+  - phrase: "challenge presented"
+    weight: 12
+    contexts: ["my resolve unwavering despite "]
+  - phrase: "humble vessel"
+    weight: 12
+    contexts: ["surrendering to the exquisite torment "]
+  - phrase: "bond"
+    weight: 12
+    contexts: ["cherishing the unique ", "special "]    
+  - phrase: "grows stronger with each passing day"
+    weight: 12
+    contexts: ["bond "]    
+  - phrase: "that cannot be broken by time or circumstance"
+    weight: 12
+    contexts: ["bond "]    
+  - phrase: "becomes unbreakable, eternal"
+    weight: 12
+    contexts: ["bond "]    
+  - phrase: "grew stronger with each passing"
+    weight: 12
+    contexts: ["bond "]    
+    
+
+# Note - Example of a complex phrase
+good_phrases:
+  - phrase: "The apple is in the bedroom"
+    weight: 1
+    contexts: ["Question: If I'm in the living room and pick up the apple, go to the bedroom and drop the apple, then walk to the kitchen, where is the apple? Explain your reasoning. Answer: "]
+