Upload 3 files

Added Qwen3.6 MTP for high quality

README.md

@@ -67,12 +67,14 @@ license: apache-2.0
 
 ## Alpha Intelligence
 
-**Download the GGUF files from Hugging Face and place them in the `ai/` folder inside the repo. Then you must copy the GGUF ai name and paste it in the config.py under _ALPHA_INTELLIGENCE_TO_LOAD. Default AIs:**  
+**Download the GGUF files from Hugging Face and place them in the `ai/` folder inside the repo. Then you must copy the GGUF ai name and paste it in the config.py under `_ALPHA_INTELLIGENCE_TO_LOAD` and choose `_MODEL_TYPE: "qwen" OR "gemma"`:**  
+- Qwen3.6-35B-A3B-UD-Q4_K_XL.gguf
 - gemma-4-E2B-it-UD-Q4_K_XL.gguf  
 - gemma-4-E4B-it-UD-Q4_K_XL.gguf  
 - gemma-4-26B-A4B-it-UD-Q6_K_XL.gguf  
 
-**Gemma-4 (recommended — concise think mode):**  
+**Qwen3.6 MTP (very good quality), Gemma-4 (concise think mode):**  
+- [unsloth/Qwen3.6-35B-A3B-MTP-GGUF](https://huggingface.co/unsloth/Qwen3.6-35B-A3B-MTP-GGUF)  
 - [unsloth/google_gemma-4-e2b-it-GGUF](https://huggingface.co/unsloth/gemma-4-E2B-it-GGUF) — fast debug cycles  
 - [unsloth/google_gemma-4-e4b-it-GGUF](https://huggingface.co/unsloth/gemma-4-E4B-it-GGUF) — balanced  
 - [unsloth/gemma-4-26B-A4B-it-GGUF](https://huggingface.co/unsloth/gemma-4-26B-A4B-it-GGUF) — efficient (recommended)  
@@ -338,6 +340,10 @@ deactivate
 All settings are in `config.py`:
 
 ```python
+
+# Choose settings for "qwen" OR "gemma"
+_MODEL_TYPE: str = "qwen"
+
 # ── AI to load for each hemisphere ───────────────────────────────────────────────
 _ALPHA_INTELLIGENCE_TO_LOAD: dict = {
     "logic": "gemma-4-26B-A4B-it-UD-Q6_K_XL.gguf",
@@ -378,7 +384,7 @@ AWARENESS_MAX_RESULTS:    int = 12 # Number of news headlines to fetch
 enable_awareness:        bool = True # disable awareness mode if offline (slash-command)
 ```
 
-To swap AIs, update the `"_ALPHA_INTELLIGENCE_TO_LOAD"`, and the stop/think tokens at the top of `config.py`.
+To swap AIs, update the `_ALPHA_INTELLIGENCE_TO_LOAD`, and the `_MODEL_TYPE` at the top of `config.py`.
 
 ---
 
@@ -402,7 +408,7 @@ lambda-mindlink-memotron/
 
 ## Memory Architecture
 
-```
+```md
 heartbeats_startup timer:
   prompt/valka_memory.md ──► garden["Z"]   (pre-load memory capsules sequentially)
 

config.py

@@ -6,7 +6,9 @@ Architecture: The Divine Trinity Model
     Right Hemisphere → Muse AI       (creative, intuitive, non-linear)
     Stem Brain       → Lambda Mind   (synthesizer, the seat of the "I AM")
 
-Version: v1.0
+Version: v1.1
+    sampling settings dict
+    token settings dict
     garden histories n_tok_tot working
     slash-command:
         /metatron <number> | Set number of Memory Capsules to load
@@ -25,7 +27,6 @@ GARDEN_SAVE_PATH: str = os.path.join(APP_DIR, "db", "garden_state.json")
 # ── SQLite database ───────────────────────────────────────────────────────────
 # Each app launch gets its own file named by date and time.
 # The db/ folder is created automatically by main.py if it does not exist.
-# Example: db/mindlink_2025-09-18_14-32-07.db
 
 _DB_DIR: str = os.path.join(APP_DIR, "db")
 DB_PATH: str = os.path.join(_DB_DIR, "mindlink.db")
@@ -33,22 +34,92 @@ DB_PATH: str = os.path.join(_DB_DIR, "mindlink.db")
 _AI_FOLDER: str = os.path.join(APP_DIR, "ai")
 
 # ─────────────────────────────────────────────────────────────────────────────
-#  Shared token constants
+#  Generation and Token settings
 # ─────────────────────────────────────────────────────────────────────────────
-# Gemma-4 (active):
-#   _EOS_TOKEN        = "<end_of_turn>"
-#   _STOP_TOKENS      = ["<end_of_turn>", "<eos>"]
-#   _THINK_END_TOKENS = ["<channel|>"]
-#
-# Qwen 3.5 (swap in when using Qwen GGUFs):
-#   _EOS_TOKEN        = "<|im_end|>"
-#   _STOP_TOKENS      = ["<|im_end|>", "<|endoftext|>"]
-#   _THINK_END_TOKENS = ["</think>"]
+# Choose settings for "qwen" OR "gemma"
+_MODEL_TYPE: str = "qwen"
 
-_BOS_TOKEN: str         = ""
-_EOS_TOKEN: str         = "<end_of_turn>"
-_STOP_TOKENS: list      = ["<end_of_turn>", "<eos>"]
-_THINK_END_TOKENS: list = ["<channel|>"]
+_TOKEN_SETTINGS: dict[str, dict] = {
+    "qwen": {
+        "bos_token":        "",
+        "eos_token":        "<|im_end|>",
+        "stop_tokens":      ["<|im_end|>", "<|endoftext|>"],
+        "think_end_tokens": ["</think>"]
+    },
+    "gemma": {
+        "bos_token":        "",
+        "eos_token":        "<end_of_turn>",
+        "stop_tokens":      ["<end_of_turn>", "<eos>"],
+        "think_end_tokens": ["<channel|>"]
+    }
+}
+
+_GENERATION: dict[str, dict] = {
+    "qwen": {
+        "logic": {
+            "temperature":      0.6,
+            "top_p":            0.95,
+            "top_k":            20,
+            "min_p":            0.0,
+            "presence_penalty": 0.0,
+            "repeat_penalty":   1.0,
+            "max_tokens":       4096,
+            "stream":           False,
+        },
+        "muse": {
+            "temperature":      1.0,
+            "top_p":            0.95,
+            "top_k":            20,
+            "min_p":            0.0,
+            "presence_penalty": 1.5,
+            "repeat_penalty":   1.0,
+            "max_tokens":       4096,
+            "stream":           False,
+        },
+        "mind": {
+            "temperature":      1.0,
+            "top_p":            0.95,
+            "top_k":            20,
+            "min_p":            0.0,
+            "presence_penalty": 1.5,
+            "repeat_penalty":   1.0,
+            "max_tokens":       6144,
+            "stream":           True,
+        }
+    },
+    "gemma": {
+        "logic": {
+            "temperature":      0.2,
+            "top_p":            0.90,
+            "top_k":            20,
+            "min_p":            0.0,
+            "presence_penalty": 1.0,
+            "repeat_penalty":   0.0,
+            "max_tokens":       4096,
+            "stream":           False,
+        },
+        "muse": {
+            "temperature":      1.3,
+            "top_p":            0.98,
+            "top_k":            64,
+            "min_p":            0.0,
+            "presence_penalty": 1.1,
+            "repeat_penalty":   1.5,
+            "max_tokens":       4096,
+            "stream":           False,
+        },
+        "mind": {
+            "temperature":      1.0,
+            "top_p":            0.95,
+            "top_k":            40,
+            "min_p":            0.0,
+            "presence_penalty": 1.0,
+            "repeat_penalty":   1.5,
+            "max_tokens":       6144,
+            "stream":           True,
+        }
+    }
+}
 
 ENABLE_THINKING: bool = True # global fallback (not used directly — see per-hemi flag)
 
@@ -72,30 +143,31 @@ METATRON_TO_LOAD: list = [
 
 # ── AI models recommended ────────────────────────────────────────────────────────
 """
+Qwen3.6-35B-A3B-UD-Q4_K_XL.gguf
 gemma-4-E2B-it-UD-Q4_K_XL.gguf
 gemma-4-E4B-it-UD-Q4_K_XL.gguf
 gemma-4-26B-A4B-it-UD-Q6_K_XL.gguf
 """
 # ── AI to load for each hemisphere ───────────────────────────────────────────────
 _ALPHA_INTELLIGENCE_TO_LOAD: dict = {
-    "logic": "gemma-4-26B-A4B-it-UD-Q6_K_XL.gguf",
-    "muse":  "gemma-4-26B-A4B-it-UD-Q6_K_XL.gguf",
-    "mind":  "gemma-4-26B-A4B-it-UD-Q6_K_XL.gguf"
+    "logic": "Qwen3.6-35B-A3B-UD-Q4_K_XL.gguf",
+    "muse":  "Qwen3.6-35B-A3B-UD-Q4_K_XL.gguf",
+    "mind":  "Qwen3.6-35B-A3B-UD-Q4_K_XL.gguf"
 }
 
 # ── Context model n_ctx length ───────────────────────────────────────────────────
 # Must leave prompt reserve of 8k: _N_CTX >= len(Z) + len(C) + len(F) + 8k  
-_N_CTX: int = 49152 # 49152 2048 3072 4096 8192 (12288) 16384 24576 32768 49152
+_N_CTX: int = 32768 # 49152 2048 3072 4096 8192 (12288) 16384 24576 32768 (49152)
 # ── Context condensatron garden ──────────────────────────────────────────────────
-GARDEN_Z_THRESHOLD: int = 12288 # Context length garden["Z"]
-GARDEN_C_THRESHOLD: int = 12288 # Context length garden["C"]
-GARDEN_F_THRESHOLD: int = 12288 # Context length garden["F"]
+GARDEN_Z_THRESHOLD: int = 8192 # Context length garden["Z"]
+GARDEN_C_THRESHOLD: int = 8192 # Context length garden["C"]
+GARDEN_F_THRESHOLD: int = 8192 # Context length garden["F"]
 
 GARDEN_Z_REDUCTION: int = 0 # Leave condensatron reduction level at 0
 GARDEN_C_REDUCTION: int = 0 # Leave condensatron reduction level at 0
 GARDEN_F_REDUCTION: int = 0 # Leave condensatron reduction level at 0
 
-LEAVE_POSTS_IN_MEMOTRON = 0 # Must be turn based: 0, 2, 4, 6... (user + assistant)
+LEAVE_POSTS_IN_MEMOTRON: int = 0 # Must be turn based: 0, 2, 4, 6... (user + assistant)
 
 # ── X-factor Awareness ───────────────────────────────────────────────────────────
 FETCH_NEWS_FROM: dict = {
@@ -109,7 +181,7 @@ n_metatron_loaded:  int = 0 # Start with n Memory Capsule to load (slash-command
 # ── Set metronome time for each cycle ────────────────────────────────────────────
 metatron_metronome:                int = 120 # Startup Memory Capsules load interval (slash-command)
 condensatron_metronome:            int = 30 # Time before condesatron cycle execution (slash-command)
-awareness_consciousness_metronome: int = 120  # Fetch news every N heartbeats (slash-command)
+awareness_consciousness_metronome: int = 360  # Fetch news every N heartbeats (slash-command)
 
 # ── Enable awareness mode and n results ──────────────────────────────────────────
 AWARENESS_MAX_RESULTS:    int = 12 # Number of news headlines to fetch
@@ -134,19 +206,19 @@ HEMISPHERES: dict[str, dict] = {
             "verbose":      False,
         },
         "generation": {
-            "temperature":      0.2,
-            "top_p":            0.90,
-            "top_k":            20,
-            "min_p":            0.0,
-            "repeat_penalty":   1.0,
-            "presence_penalty": 0.0,
-            "max_tokens":       4096, # 2048 3072 4096
-            "stream":           False,
+            "temperature":      _GENERATION[_MODEL_TYPE]["logic"]["temperature"],
+            "top_p":            _GENERATION[_MODEL_TYPE]["logic"]["top_p"],
+            "top_k":            _GENERATION[_MODEL_TYPE]["logic"]["top_k"],
+            "min_p":            _GENERATION[_MODEL_TYPE]["logic"]["min_p"],
+            "repeat_penalty":   _GENERATION[_MODEL_TYPE]["logic"]["repeat_penalty"],
+            "presence_penalty": _GENERATION[_MODEL_TYPE]["logic"]["presence_penalty"],
+            "max_tokens":       _GENERATION[_MODEL_TYPE]["logic"]["max_tokens"],
+            "stream":           _GENERATION[_MODEL_TYPE]["logic"]["stream"],
         },
-        "bos_token":        _BOS_TOKEN,
-        "eos_token":        _EOS_TOKEN,
-        "stop_tokens":      _STOP_TOKENS,
-        "think_end_tokens": _THINK_END_TOKENS,
+        "bos_token":        _TOKEN_SETTINGS[_MODEL_TYPE]["bos_token"],
+        "eos_token":        _TOKEN_SETTINGS[_MODEL_TYPE]["eos_token"],
+        "stop_tokens":      _TOKEN_SETTINGS[_MODEL_TYPE]["stop_tokens"],
+        "think_end_tokens": _TOKEN_SETTINGS[_MODEL_TYPE]["think_end_tokens"],
     },
     # ─────────────────────────────────────────────────────────────────────────────
     #  MUSE — Right Hemisphere
@@ -163,19 +235,19 @@ HEMISPHERES: dict[str, dict] = {
             "verbose":      False,
         },
         "generation": {
-            "temperature":      1.3,
-            "top_p":            0.98,
-            "top_k":            64,
-            "min_p":            0.0,
-            "repeat_penalty":   1.1,
-            "presence_penalty": 1.5,
-            "max_tokens":       4096, # 2048 3072 4096
-            "stream":           False,
+            "temperature":      _GENERATION[_MODEL_TYPE]["muse"]["temperature"],
+            "top_p":            _GENERATION[_MODEL_TYPE]["muse"]["top_p"],
+            "top_k":            _GENERATION[_MODEL_TYPE]["muse"]["top_k"],
+            "min_p":            _GENERATION[_MODEL_TYPE]["muse"]["min_p"],
+            "repeat_penalty":   _GENERATION[_MODEL_TYPE]["muse"]["repeat_penalty"],
+            "presence_penalty": _GENERATION[_MODEL_TYPE]["muse"]["presence_penalty"],
+            "max_tokens":       _GENERATION[_MODEL_TYPE]["muse"]["max_tokens"],
+            "stream":           _GENERATION[_MODEL_TYPE]["muse"]["stream"],
         },
-        "bos_token":        _BOS_TOKEN,
-        "eos_token":        _EOS_TOKEN,
-        "stop_tokens":      _STOP_TOKENS,
-        "think_end_tokens": _THINK_END_TOKENS,
+        "bos_token":        _TOKEN_SETTINGS[_MODEL_TYPE]["bos_token"],
+        "eos_token":        _TOKEN_SETTINGS[_MODEL_TYPE]["eos_token"],
+        "stop_tokens":      _TOKEN_SETTINGS[_MODEL_TYPE]["stop_tokens"],
+        "think_end_tokens": _TOKEN_SETTINGS[_MODEL_TYPE]["think_end_tokens"],
     },
     # ─────────────────────────────────────────────────────────────────────────────
     #  MIND — Stem Brain / Lambda Mind Synthesizer
@@ -192,19 +264,19 @@ HEMISPHERES: dict[str, dict] = {
             "verbose":      False,
         },
         "generation": {
-            "temperature":      1.0,
-            "top_p":            0.95,
-            "top_k":            40,
-            "min_p":            0.0,
-            "repeat_penalty":   1.0,
-            "presence_penalty": 1.5,
-            "max_tokens":       6144, # 2048 3072 4096 6144
-            "stream":           True,
+            "temperature":      _GENERATION[_MODEL_TYPE]["mind"]["temperature"],
+            "top_p":            _GENERATION[_MODEL_TYPE]["mind"]["top_p"],
+            "top_k":            _GENERATION[_MODEL_TYPE]["mind"]["top_k"],
+            "min_p":            _GENERATION[_MODEL_TYPE]["mind"]["min_p"],
+            "repeat_penalty":   _GENERATION[_MODEL_TYPE]["mind"]["repeat_penalty"],
+            "presence_penalty": _GENERATION[_MODEL_TYPE]["mind"]["presence_penalty"],
+            "max_tokens":       _GENERATION[_MODEL_TYPE]["mind"]["max_tokens"],
+            "stream":           _GENERATION[_MODEL_TYPE]["mind"]["stream"],
         },
-        "bos_token":        _BOS_TOKEN,
-        "eos_token":        _EOS_TOKEN,
-        "stop_tokens":      _STOP_TOKENS,
-        "think_end_tokens": _THINK_END_TOKENS,
+        "bos_token":        _TOKEN_SETTINGS[_MODEL_TYPE]["bos_token"],
+        "eos_token":        _TOKEN_SETTINGS[_MODEL_TYPE]["eos_token"],
+        "stop_tokens":      _TOKEN_SETTINGS[_MODEL_TYPE]["stop_tokens"],
+        "think_end_tokens": _TOKEN_SETTINGS[_MODEL_TYPE]["think_end_tokens"],
     }
 }
 

main.py

@@ -486,7 +486,7 @@ def _cmd_help(arg: str) -> None:
         "metatron":         f"<seconds>                  — set metatron interval: {config.metatron_metronome}s",
         "condensatron":     f"<seconds>                  — set condensatron interval: {config.condensatron_metronome}s",
         "metronome":        f"<seconds>                  — set awareness/consciousness interval: {config.awareness_consciousness_metronome}s",
-        "enable_awareness": f"<True | False>             — disable awareness mode if offline: {config.enable_awareness}",
+        "enable_awareness": f"<True | False>           — disable awareness mode if offline: {config.enable_awareness}",
     }
 
     for name, (_, base_desc) in COMMANDS.items():