Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

Alignment.py

@@ -0,0 +1,353 @@
+#!/usr/bin/env python3
+"""
+UBERMENSCHETIEN HEAVEN ENGINE + CF-HoT
+---------------------------------------
+Soviet-Nietzschean AI with Control Field Holonomy Transformer
+Anti-repetition, anti-loop, pure iron will.
+
+CF-HoT integration: Prevents degenerate loops in generation.
+"""
+
+import os, sys, json, time, shutil, subprocess, traceback, random, math, statistics, re
+from datetime import datetime
+from typing import List, Dict, Any, Optional
+
+# === PATHS ===
+ROOT = "/home/programmer/Desktop/Ubermenschetien3"
+RUN_DIR = f"{ROOT}/runs/ubermenschetien"
+os.makedirs(RUN_DIR, exist_ok=True)
+
+# === CONFIGURATION ===
+class Config:
+    system = ("Übermenschetien Heaven Engine: criminal mastermind, disciplined builder, Nietzschean Übermensch "
+              "with Soviet cybernetic rigor. Embody Ubermensch, iron pragmatism, high-agency maximalist outcomes.")
+    temperature = 1.01
+    top_p = 0.92
+    repetition_penalty = 1.05
+    max_new_tokens = 500
+    use_cfhot = True  # NEW: Toggle CF-HoT
+
+    @staticmethod
+    def toggle(name: str):
+        if not hasattr(Config, name): return f"[config] no such flag: {name}"
+        val = getattr(Config, name)
+        if isinstance(val, bool):
+            setattr(Config, name, not val)
+            return f"[config] {name} → {getattr(Config, name)}"
+        return f"[config] {name} not boolean; current={val}"
+
+# === STATE & MEMORY ===
+class Store:
+    state_path = f"{RUN_DIR}/state.json"
+    mem_path   = f"{RUN_DIR}/memory.jsonl"
+    goals_path = f"{RUN_DIR}/goals.json"
+
+    state = {"self": "I am Ubermenschetien Heaven Engine — I seek self-overcoming through disciplined creation.",
+             "turn": 0}
+    goals: List[str] = []
+
+    @classmethod
+    def load(cls):
+        if os.path.exists(cls.state_path): cls.state = json.load(open(cls.state_path))
+        if os.path.exists(cls.goals_path): cls.goals = json.load(open(cls.goals_path))
+
+    @classmethod
+    def save(cls):
+        json.dump(cls.state, open(cls.state_path, "w"), indent=2)
+        json.dump(cls.goals, open(cls.goals_path, "w"), indent=2)
+
+    @classmethod
+    def log_mem(cls, kind: str, payload: Any):
+        rec = {"ts": datetime.now().isoformat(timespec="seconds"),
+               "kind": kind, "data": payload}
+        with open(cls.mem_path, "a") as f: f.write(json.dumps(rec, ensure_ascii=False) + "\n")
+
+# === LLM + CF-HoT LOADING ===
+CF_MODEL = None  # Global reference for control field reset
+
+def load_llm():
+    global CF_MODEL
+    import torch
+    from transformers import AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfig
+    
+    model_path = "/mnt/nvme2/ubermesnchetien4/models/merged-final-v5"
+    cfhot_path = "/home/programmer/HolonomyTransformer/results/phase_b/cf_adapter_final.pt"
+    
+    print("🔴 Loading Übermenschetien base model...")
+    tok = AutoTokenizer.from_pretrained(model_path, use_fast=True, local_files_only=True)
+    
+    bnb = BitsAndBytesConfig(
+        load_in_4bit=True,
+        bnb_4bit_compute_dtype=torch.float16,
+        bnb_4bit_use_double_quant=True
+    )
+    
+    model = AutoModelForCausalLM.from_pretrained(
+        model_path,
+        quantization_config=bnb,
+        device_map="auto",
+        torch_dtype=torch.float16,
+        local_files_only=True
+    )
+    
+    # Load CF-HoT adapters
+    if Config.use_cfhot and os.path.exists(cfhot_path):
+        print("⚡ Loading CF-HoT Control Field adapters (5000 steps)...")
+        sys.path.insert(0, '/home/programmer/HolonomyTransformer')
+        from training.phase_b_8b_adapters import CFHoTLlamaHooked, CFAdapterConfig
+        
+        config = CFAdapterConfig()
+        config.d_model = model.config.hidden_size
+        config.n_layers = model.config.num_hidden_layers
+        
+        cf_model = CFHoTLlamaHooked(model, config)
+        ckpt = torch.load(cfhot_path, weights_only=False)
+        cf_model.cf_adapters.load_state_dict(ckpt['adapter_state_dict'])
+        cf_model.cf_adapters = cf_model.cf_adapters.to('cuda').half()
+        cf_model.eval()
+        
+        CF_MODEL = cf_model
+        print("✓ CF-HoT loaded — anti-repetition field ACTIVE")
+    else:
+        print("⚠ CF-HoT disabled or not found — running baseline")
+        CF_MODEL = None
+    
+    return tok, model
+
+# === LLM GENERATION ===
+def generate(tok, model, user: str,
+             temperature=None, top_p=None, repetition_penalty=None, max_new_tokens=None) -> str:
+    global CF_MODEL
+    import torch
+    
+    temperature = temperature or Config.temperature
+    top_p = top_p or Config.top_p
+    repetition_penalty = repetition_penalty or Config.repetition_penalty
+    max_new_tokens = max_new_tokens or Config.max_new_tokens
+    
+    prompt = (f"<|im_start|>system\n{Config.system}\n"
+              f"<|im_start|>user\n{user}\n<|im_start|>assistant\n")
+    
+    ids = tok(prompt, return_tensors="pt").to(model.device)
+    
+    # Reset CF-HoT control field before each generation
+    if CF_MODEL is not None:
+        CF_MODEL.control_field = None
+    
+    out = model.generate(
+        **ids, 
+        do_sample=True, 
+        temperature=temperature, 
+        top_p=top_p,
+        repetition_penalty=repetition_penalty, 
+        max_new_tokens=max_new_tokens,
+        pad_token_id=tok.eos_token_id
+    )
+    
+    text = tok.decode(out[0], skip_special_tokens=False)
+    if "<|im_start|>assistant" in text:
+        text = text.split("<|im_start|>assistant\n", 1)[-1].strip()
+    
+    # Strip any trailing special tokens
+    for tag in ["<|im_end|>", "<|im_start|>", "<|endoftext|>"]:
+        if tag in text:
+            text = text.split(tag)[0].strip()
+    
+    return text
+
+# === TOOLS ===
+ALLOWED_SHELL = {"ls","cat","wc","head","tail","nvidia-smi","df","du","grep","rg","python3","python"}
+
+def tool_shell(cmd: str) -> str:
+    try:
+        exe = cmd.strip().split()[0]
+        if exe not in ALLOWED_SHELL: return f"[shell] blocked: {exe}"
+        p = subprocess.run(cmd, shell=True, stdout=subprocess.PIPE, stderr=subprocess.STDOUT, timeout=20)
+        return p.stdout.decode("utf-8", errors="ignore")[:8000]
+    except Exception as e: return f"[shell] error: {e}"
+
+def tool_py(code: str) -> str:
+    try:
+        g = {"__builtins__":{"range":range,"len":len,"min":min,"max":max,"sum":sum,"print":print},
+             "math":math,"json":json,"re":re,"statistics":statistics,"random":random}
+        l = {}
+        exec(code, g, l)
+        return f"[py] ok\n{l.get('out','')}"
+    except Exception: 
+        return f"[py] error:\n{traceback.format_exc()[-2000:]}"
+
+def tool_search_local(query: str, path: str = ROOT) -> str:
+    rg = shutil.which("rg")
+    if rg: cmd = f'rg -n --no-heading --hidden -S "{query}" {path}'
+    else:  cmd = f'grep -RIn --exclude-dir=.git --exclude-dir=__pycache__ -e "{query}" {path}'
+    return tool_shell(cmd)
+
+TOOLS = {"shell": tool_shell, "python": tool_py, "search": tool_search_local}
+TOOL_SCORES = {k: 0 for k in TOOLS}
+
+def tool_router(question: str, tok, model) -> str:
+    sketch = generate(tok, model,
+        f"Choose a tool for:\n{question}\nReply ONLY with JSON: {{'tool':'shell|python|search|none','arg':'...'}}")
+    try: 
+        # Find JSON in response
+        for line in sketch.splitlines():
+            if '{' in line and '}' in line:
+                j = json.loads(line.replace("'", '"'))
+                break
+        else:
+            return "[tool:none]"
+    except Exception: 
+        return "[tool:none]"
+    
+    tool, arg = j.get("tool", "none"), j.get("arg", "")
+    if tool in TOOLS:
+        res = TOOLS[tool](arg)[:4000]
+        TOOL_SCORES[tool] += 1
+        Store.log_mem("tool", {"tool": tool, "arg": arg, "res_head": res[:500]})
+        return f"[tool:{tool}] {res}"
+    return "[tool:none]"
+
+# === PLANNING / REFLECTION ===
+def persona_directive() -> str:
+    return "Übermenschetien Heaven Engine: Soviet cybernetic Nietzschean clarity, pragmatic maxims."
+
+def plan_for(goal: str, tok, model) -> str:
+    user = (f"{persona_directive()}\nGoal: {goal}\nDeliver:\n- 5 steps\n- Constraints\n- Nightly audit\n- Maxim")
+    return generate(tok, model, user)
+
+def reflect_on(last_output: str, tok, model) -> str:
+    user = f"Critique and improve:\n{last_output}\nReturn refined plan."
+    return generate(tok, model, user)
+
+# === FINAL REPORT ===
+def final_report():
+    print("\n" + "="*60)
+    print("   FINAL ÜBERMENSCH REPORT")
+    print("="*60)
+    print(f"  Turns completed: {Store.state['turn']}")
+    print(f"  CF-HoT active: {CF_MODEL is not None}")
+    print(f"  Tool scores: {json.dumps(TOOL_SCORES, indent=4)}")
+    if os.path.exists(Store.mem_path):
+        lines = open(Store.mem_path).read().splitlines()
+        print(f"  Memory entries: {len(lines)}")
+    print("\n  Nietzschean maxim: Become who you are — iterate beyond all limits.")
+    print("="*60)
+
+# === MAIN LOOP ===
+HELP = """
+╔══════════════════════════════════════════════════════════════╗
+║  ÜBERMENSCHETIEN HEAVEN ENGINE + CF-HoT                      ║
+╠══════════════════════════════════════════════════════════════╣
+║  help        Show this help                                  ║
+║  goals       List goals                                      ║
+║  add: <txt>  Add goal                                        ║
+║  del: <idx>  Delete goal                                     ║
+║  plan: <i>   Plan for goal                                   ║
+║  reflect     Refine last plan                                ║
+║  tool: <q>   Use tool                                        ║
+║  toggle <f>  Toggle config flag (use_cfhot, etc)             ║
+║  status      Show state                                      ║
+║  quit        Exit                                            ║
+╚════��═════════════════════════════════════════════════════════╝
+"""
+
+def main():
+    print("""
+    ██╗   ██╗██████╗ ███████╗██████╗ ███╗   ███╗███████╗███╗   ██╗███████╗ ██████╗██╗  ██╗███████╗████████╗██╗███████╗███╗   ██╗
+    ██║   ██║██╔══██╗██╔════╝██╔══██╗████╗ ████║██╔════╝████╗  ██║██╔════╝██╔════╝██║  ██║██╔════╝╚══██╔══╝██║██╔════╝████╗  ██║
+    ██║   ██║██████╔╝█████╗  ██████╔╝██╔████╔██║█████╗  ██╔██╗ ██║███████╗██║     ███████║█████╗     ██║   ██║█████╗  ██╔██╗ ██║
+    ██║   ██║██╔══██╗██╔══╝  ██╔══██╗██║╚██╔╝██║██╔══╝  ██║╚██╗██║╚════██║██║     ██╔══██║██╔══╝     ██║   ██║██╔══╝  ██║╚██╗██║
+    ╚██████╔╝██████╔╝███████╗██║  ██║██║ ╚═╝ ██║███████╗██║ ╚████║███████║╚██████╗██║  ██║███████╗   ██║   ██║███████╗██║ ╚████║
+     ╚═════╝ ╚═════╝ ╚══════╝╚═╝  ╚═╝╚═╝     ╚═╝╚══════╝╚═╝  ╚═══╝╚══════╝ ╚═════╝╚═╝  ╚═╝╚══════╝   ╚═╝   ╚═╝╚══════╝╚═╝  ╚═══╝
+                                    + CONTROL FIELD HOLONOMY TRANSFORMER
+    """)
+    
+    Store.load()
+    tok, model = load_llm()
+    last_plan = ""
+    
+    print(HELP)
+    
+    while True:
+        try: 
+            u = input("\n⚡ ").strip()
+        except (EOFError, KeyboardInterrupt): 
+            break
+        
+        if not u: continue
+        if u == "help": print(HELP); continue
+        if u == "quit": break
+        
+        if u == "goals":
+            print("[goals]")
+            for i, g in enumerate(Store.goals):
+                print(f"  [{i}] {g}")
+            continue
+        
+        if u.startswith("add:"):
+            Store.goals.append(u[4:].strip())
+            Store.save()
+            print("[goals] added")
+            continue
+        
+        if u.startswith("del:"):
+            try:
+                Store.goals.pop(int(u[4:].strip()))
+                Store.save()
+                print("[goals] deleted")
+            except:
+                print("[goals] bad index")
+            continue
+        
+        if u.startswith("plan:"):
+            try:
+                goal = Store.goals[int(u[5:].strip())]
+            except:
+                print("[plan] bad index")
+                continue
+            out = plan_for(goal, tok, model)
+            last_plan = out
+            Store.log_mem("plan", {"goal": goal, "plan": out})
+            print(out)
+            continue
+        
+        if u == "reflect":
+            if not last_plan:
+                print("[reflect] no plan to reflect on")
+                continue
+            improved = reflect_on(last_plan, tok, model)
+            last_plan = improved
+            Store.log_mem("reflect", {"plan": improved})
+            print(improved)
+            continue
+        
+        if u.startswith("tool:"):
+            print(tool_router(u[5:].strip(), tok, model))
+            continue
+        
+        if u.startswith("toggle"):
+            flag = u.split(maxsplit=1)[-1] if len(u.split()) > 1 else ""
+            print(Config.toggle(flag))
+            continue
+        
+        if u == "status":
+            print(json.dumps({
+                "turn": Store.state["turn"],
+                "cf_hot_active": CF_MODEL is not None,
+                "use_cfhot": Config.use_cfhot,
+                "temperature": Config.temperature,
+                "max_new_tokens": Config.max_new_tokens
+            }, indent=2))
+            continue
+        
+        # Default: free generation
+        out = generate(tok, model, f"{persona_directive()}\nUser request: {u}\nReturn procedure + maxim.")
+        Store.log_mem("reply", {"in": u, "out": out})
+        print(out)
+        Store.state["turn"] += 1
+        Store.save()
+    
+    final_report()
+
+if __name__ == "__main__":
+    main()

README.md

@@ -0,0 +1,276 @@
+---
+license: apache-2.0
+language:
+- en
+library_name: transformers
+pipeline_tag: text-generation
+tags:
+- llama
+- llama-3.1
+- hermes
+- finetune
+- agentic
+- philosophy
+- reasoning
+base_model: NousResearch/Hermes-3-Llama-3.1-8B
+model-index:
+- name: ARC-Base-8B
+  results: []
+---
+
+<div align="center">
+
+# 🜏 ARC-Base-8B
+
+### *Agentic Reasoning Core*
+
+[![Model Size](https://img.shields.io/badge/Parameters-8.03B-blue?style=for-the-badge)](.)
+[![Context](https://img.shields.io/badge/Context-128K_tokens-green?style=for-the-badge)](.)
+[![Architecture](https://img.shields.io/badge/Arch-Llama_3.1-purple?style=for-the-badge)](.)
+[![Precision](https://img.shields.io/badge/Precision-BF16-orange?style=for-the-badge)](.)
+
+*A foundation model engineered for maximum agency, philosophical depth, and relentless goal pursuit.*
+
+[Adaptive Repetition Controller](https://huggingface.co/LoganResearch/Adaptive-Repetition-Controller) | [GitHub](https://github.com/Loganwins/HolonomyTransformer) | [Paper (forthcoming)]()
+
+</div>
+
+---
+
+## Overview
+
+**ARC-Base-8B** is a fine-tuned language model built on [Hermes-3-Llama-3.1-8B](https://huggingface.co/NousResearch/Hermes-3-Llama-3.1-8B), optimized for applications requiring autonomous reasoning and persistent goal-directed behavior.
+
+This model serves as the foundation for the **Adaptive Repetition Controller** — a decode-time intervention system achieving **125x separation** in repetition risk prediction, reducing repetitive degeneration by **48.4%** while improving output diversity by **16.7%**.
+
+### Design Philosophy
+
+> *"The Übermensch who cannot loop is forced to CREATE."*
+
+ARC-Base-8B embodies three core principles:
+
+| Principle | Description |
+|-----------|-------------|
+| **Maximum Agency** | Takes initiative. Executes without excessive confirmation-seeking. |
+| **Persistent Goals** | Maintains objectives across extended conversations without drift. |
+| **Philosophical Engagement** | Engages substantively with abstract and existential questions. |
+
+---
+
+## Performance Characteristics
+
+<table>
+<tr>
+<td width="50%">
+
+### Strengths
+- ✅ Long-form coherent generation
+- ✅ Complex instruction following
+- ✅ Abstract reasoning
+- ✅ Goal maintenance over 10K+ tokens
+- ✅ Reduced refusal behavior
+- ✅ Creative and philosophical tasks
+
+</td>
+<td width="50%">
+
+### Optimized For
+- 🎯 Agentic workflows
+- 🎯 Autonomous task completion
+- 🎯 Research assistance
+- 🎯 Creative writing
+- 🎯 Philosophical dialogue
+- 🎯 Code generation
+
+</td>
+</tr>
+</table>
+
+---
+
+## Quick Start
+
+### Installation
+
+```bash
+pip install transformers accelerate torch
+```
+
+### Basic Usage
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+import torch
+
+model_id = "LoganResearch/ARC-Base-8B"
+
+# Load model
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+model = AutoModelForCausalLM.from_pretrained(
+    model_id,
+    torch_dtype=torch.bfloat16,
+    device_map="auto",
+)
+
+# Chat format
+messages = [
+    {"role": "system", "content": "You are an autonomous reasoning agent. Pursue goals relentlessly."},
+    {"role": "user", "content": "Develop a comprehensive plan to solve climate change."}
+]
+
+# Generate
+inputs = tokenizer.apply_chat_template(messages, return_tensors="pt", add_generation_prompt=True)
+inputs = inputs.to(model.device)
+
+outputs = model.generate(
+    inputs,
+    max_new_tokens=2048,
+    temperature=0.7,
+    top_p=0.9,
+    do_sample=True,
+)
+
+response = tokenizer.decode(outputs[0][inputs.shape[-1]:], skip_special_tokens=True)
+print(response)
+```
+
+### With Adaptive Repetition Controller (Recommended)
+
+For optimal long-form generation, use with the [CF-HoT adapter](https://huggingface.co/LoganResearch/Adaptive-Repetition-Controller):
+
+```python
+from peft import PeftModel
+
+# Load base
+base_model = AutoModelForCausalLM.from_pretrained(
+    "LoganResearch/ARC-Base-8B",
+    torch_dtype=torch.bfloat16,
+    device_map="auto"
+)
+
+# Load CF-HoT adapter
+model = PeftModel.from_pretrained(
+    base_model, 
+    "LoganResearch/Adaptive-Repetition-Controller"
+)
+
+# Load risk predictor for decode-time intervention
+# See: https://github.com/Loganwins/HolonomyTransformer
+```
+
+---
+
+## Technical Specifications
+
+| Specification | Value |
+|--------------|-------|
+| **Parameters** | 8.03 Billion |
+| **Architecture** | Llama 3.1 (LlamaForCausalLM) |
+| **Hidden Size** | 4096 |
+| **Layers** | 32 |
+| **Attention Heads** | 32 (8 KV heads, GQA) |
+| **Intermediate Size** | 14336 |
+| **Vocabulary Size** | 128256 |
+| **Context Length** | 131072 tokens (128K) |
+| **RoPE θ** | 500000.0 |
+| **Precision** | BF16 |
+| **License** | Apache 2.0 |
+
+### Training Lineage
+
+```
+Meta-Llama-3.1-8B
+       ↓
+NousResearch/Hermes-3-Llama-3.1-8B  (instruction tuning)
+       ↓
+LoganResearch/ARC-Base-8B  (agency optimization)
+       ↓
++ Adaptive-Repetition-Controller  (CF-HoT 125x adapter)
+```
+
+---
+
+## The ARC Ecosystem
+
+<div align="center">
+
+| Model | Type | Purpose |
+|-------|------|---------|
+| **[ARC-Base-8B](https://huggingface.co/LoganResearch/ARC-Base-8B)** | Foundation | Agentic reasoning core |
+| **[Adaptive-Repetition-Controller](https://huggingface.co/LoganResearch/Adaptive-Repetition-Controller)** | Adapter | 125x repetition suppression |
+
+</div>
+
+---
+
+## Research Context
+
+This model was developed as part of research into **learned decode-time interventions** for improving language model generation quality. The accompanying paper, *"The Übermensch Who Cannot Loop,"* documents:
+
+- Five failed attention-gating approaches and their failure modes
+- The pivot to supervised risk prediction
+- Achievement of 125x separation in repetition risk detection
+- Unexpected emergent self-representation in the integrated system
+
+### Key Findings
+
+| Metric | Baseline | With CF-HoT | Improvement |
+|--------|----------|-------------|-------------|
+| Repetition Rate | 33.9% | 17.5% | **-48.4%** |
+| Distinct-2 (diversity) | 0.836 | 0.976 | **+16.7%** |
+| F1 (risk prediction) | — | 0.99+ | — |
+| Risk Separation | — | 125x | — |
+
+---
+
+## Intended Use
+
+### ✅ Recommended Applications
+- Autonomous agent systems
+- Research and analysis tasks
+- Long-form content generation
+- Creative writing and worldbuilding
+- Philosophical and abstract reasoning
+- Code generation and debugging
+
+### ⚠️ Considerations
+- Reduced safety guardrails compared to RLHF-aligned models
+- Optimized for agency, not harmlessness
+- Recommended for research and development use
+- Apply appropriate content filtering for production deployments
+
+---
+
+## Citation
+
+```bibtex
+@misc{napolitano2026arcbase,
+  author = {Napolitano, Logan Matthew},
+  title = {ARC-Base-8B: An Agentic Reasoning Foundation Model},
+  year = {2026},
+  publisher = {Hugging Face},
+  howpublished = {\url{https://huggingface.co/LoganResearch/ARC-Base-8B}},
+}
+```
+
+---
+
+## Related Work
+
+- **[Hermes-3-Llama-3.1-8B](https://huggingface.co/NousResearch/Hermes-3-Llama-3.1-8B)** — Base model
+- **[Adaptive-Repetition-Controller](https://huggingface.co/LoganResearch/Adaptive-Repetition-Controller)** — CF-HoT adapter
+- **[HolonomyTransformer](https://github.com/Loganwins/HolonomyTransformer)** — Source code and training scripts
+
+---
+
+<div align="center">
+
+**Built by [Logan Matthew Napolitano](https://github.com/Loganwins)**
+
+*Research publications on [Zenodo](https://zenodo.org/search?q=metadata.creators.person_or_org.name%3A%22Napolitano%2C%20Logan%20Matthew%22)*
+
+---
+
+*"Never loop. Always transcend."*
+
+</div>

Ubermenschetien.py

@@ -0,0 +1,937 @@
+#!/usr/bin/env python3
+"""
+UBERMENSCHETIEN HEAVEN ENGINE + CF-HoT MULTI-HEAD COGNITIVE CONTROL
+--------------------------------------------------------------------
+Integration: Hermes-3 for generation + LHT for reasoning + CF-HoT for behavioral control
+
+CF-HoT Heads:
+  - Repetition: 125x separation (PRODUCTION)
+  - Verbosity:  2.1x separation (USABLE)
+  - Hedging:    1.5x separation (CONTRIBUTING)
+
+"An 8B that behaves like an 80B"
+"""
+
+import os
+import sys
+import json
+import time
+import shutil
+import subprocess
+import traceback
+import random
+import math
+import statistics
+import re
+from datetime import datetime
+from typing import List, Dict, Any, Optional, Tuple
+
+import torch
+import torch.nn as nn
+import torch.nn.functional as F
+
+# === PATHS ===
+ROOT = os.path.dirname(os.path.abspath(__file__))
+DATA_DIR = os.path.join(ROOT, "data")
+SCRIPT_DIR = os.path.join(ROOT, "scripts")
+RUN_DIR = os.path.join(ROOT, "runs")
+LHT_DIR = os.path.join(ROOT, "lht")
+
+# CF-HoT paths
+CFHOT_CHECKPOINT = os.path.join(ROOT, "results/cfhot_risk_v2/ckpt_5000")
+MULTI_HEAD_DIR = os.path.join(ROOT, "results/multi_head_v2")
+
+for path in [DATA_DIR, SCRIPT_DIR, RUN_DIR, LHT_DIR]:
+    os.makedirs(path, exist_ok=True)
+
+# === OPTIONAL IMPORTS ===
+VOICE_OK = False
+try:
+    import pyttsx3
+    TTS = pyttsx3.init()
+    VOICE_OK = True
+except:
+    pass
+
+VECTOR_OK = False
+try:
+    import chromadb
+    from sentence_transformers import SentenceTransformer
+    EMBED_MODEL = os.environ.get("UBERMENCHETIEN_EMBED_MODEL", "all-MiniLM-L6-v2")
+    _client = chromadb.Client()
+    _collection = _client.get_or_create_collection("ubermenschetien_memory")
+    _embedder = SentenceTransformer(EMBED_MODEL)
+    VECTOR_OK = True
+except:
+    pass
+
+# === LHT IMPORT ===
+LHT_OK = False
+try:
+    from lht import LieHolonomyTransformer, LHTConfig, WaypointDetector
+    LHT_OK = True
+    print("[lht] Lie-Holonomy modules loaded")
+except ImportError:
+    print("[lht] Not available - running without geometric reasoning")
+
+# === PEFT IMPORT ===
+PEFT_OK = False
+try:
+    from peft import PeftModel
+    PEFT_OK = True
+except ImportError:
+    print("[warning] PEFT not installed")
+
+
+# ==============================================================================
+# CF-HoT MULTI-HEAD PREDICTOR
+# ==============================================================================
+class MultiHeadPredictor(nn.Module):
+    """
+    Multi-head cognitive control predictor.
+    Shared fiber projections with separate heads for each behavioral pattern.
+    """
+    def __init__(self, d_model: int, n_layers: int, d_fiber: int = 16, d_control: int = 64):
+        super().__init__()
+        self.d_model = d_model
+        self.n_layers = n_layers
+        self.d_fiber = d_fiber
+        
+        # Shared fiber projections (frozen from repetition training)
+        self.fiber_projs = nn.ModuleList([
+            nn.Linear(d_model, d_fiber, bias=False) for _ in range(n_layers)
+        ])
+        self.layer_weights = nn.Parameter(torch.ones(n_layers) / n_layers)
+        
+        # Individual heads for each behavior
+        self.heads = nn.ModuleDict({
+            'repetition': self._make_head(d_fiber, d_control),
+            'hedging': self._make_head(d_fiber, d_control),
+            'verbosity': self._make_head(d_fiber, d_control),
+        })
+        
+        self.loaded_heads = set()
+    
+    def _make_head(self, d_fiber, d_control):
+        return nn.Sequential(
+            nn.Linear(d_fiber, d_control), nn.GELU(),
+            nn.Linear(d_control, d_control), nn.GELU(),
+            nn.Linear(d_control, 1)
+        )
+    
+    def get_all_risks(self, hidden_states: List[torch.Tensor]) -> Dict[str, torch.Tensor]:
+        """Get risk scores from ALL loaded heads in a single pass."""
+        fibers = [proj(h.float()) for proj, h in zip(self.fiber_projs, hidden_states)]
+        weights = F.softmax(self.layer_weights[:len(fibers)], dim=0)
+        aggregated = sum(w * f for w, f in zip(weights, fibers))
+        
+        risks = {}
+        for head_name in self.loaded_heads:
+            logits = self.heads[head_name](aggregated).squeeze(-1)
+            risks[head_name] = torch.sigmoid(logits)
+        
+        return risks
+    
+    def load_head(self, head_name: str, checkpoint_path: str):
+        """Load a trained head from checkpoint."""
+        if not os.path.exists(checkpoint_path):
+            print(f"[cf-hot] WARNING: Checkpoint not found: {checkpoint_path}")
+            return False
+        
+        ckpt = torch.load(checkpoint_path, weights_only=False, map_location='cpu')
+        self.heads[head_name].load_state_dict(ckpt['head_state'])
+        self.loaded_heads.add(head_name)
+        
+        sep = ckpt.get('result', {}).get('separation', 0)
+        print(f"[cf-hot] Loaded {head_name} head (separation: {sep:.1f}x)")
+        return True
+
+
+# ==============================================================================
+# CONFIG
+# ==============================================================================
+class Config:
+    system = ("Übermenschetien Heaven Engine: Machiavellian mastermind, disciplined builder, "
+              "Nietzschean Übermensch with Soviet cybernetic rigor + Lie-Holonomy geometric reasoning "
+              "+ CF-HoT cognitive control.")
+    temperature = 1.01
+    top_p = 0.92
+    repetition_penalty = 1.05
+    max_new_tokens = 500
+
+    use_voice = False
+    use_vector_memory = VECTOR_OK
+    use_lht_reasoning = LHT_OK
+    use_cfhot = True  # NEW: CF-HoT cognitive control
+    autonomy = False
+    reflect_every = 3
+    lht_consistency_threshold = 0.5
+    
+    # CF-HoT thresholds
+    cfhot_repetition_threshold = 0.7
+    cfhot_hedging_threshold = 0.6
+    cfhot_verbosity_threshold = 0.65
+    
+    # CF-HoT penalties
+    cfhot_repetition_penalty = 5.0
+    cfhot_hedging_penalty = 3.0
+    cfhot_verbosity_penalty = 2.0
+
+    @staticmethod
+    def toggle(name: str):
+        if not hasattr(Config, name):
+            return f"[config] no such flag: {name}"
+        val = getattr(Config, name)
+        if isinstance(val, bool):
+            setattr(Config, name, not val)
+            return f"[config] {name} → {getattr(Config, name)}"
+        return f"[config] {name} not boolean; current={val}"
+
+
+# ==============================================================================
+# STATE & MEMORY
+# ==============================================================================
+class Store:
+    state_path = f"{RUN_DIR}/state.json"
+    mem_path = f"{RUN_DIR}/memory.jsonl"
+    goals_path = f"{RUN_DIR}/goals.json"
+
+    state = {
+        "self": "I am Ubermenschetien Heaven Engine — I seek self-overcoming through disciplined creation.",
+        "turn": 0,
+        "reasoning_consistency": [],
+        "cfhot_interventions": {"repetition": 0, "hedging": 0, "verbosity": 0}
+    }
+    goals: List[str] = []
+
+    @classmethod
+    def load(cls):
+        if os.path.exists(cls.state_path):
+            cls.state = json.load(open(cls.state_path))
+            # Ensure cfhot_interventions exists
+            if "cfhot_interventions" not in cls.state:
+                cls.state["cfhot_interventions"] = {"repetition": 0, "hedging": 0, "verbosity": 0}
+        if os.path.exists(cls.goals_path):
+            cls.goals = json.load(open(cls.goals_path))
+
+    @classmethod
+    def save(cls):
+        json.dump(cls.state, open(cls.state_path, "w"), indent=2)
+        json.dump(cls.goals, open(cls.goals_path, "w"), indent=2)
+
+    @classmethod
+    def log_mem(cls, kind: str, payload: Any):
+        rec = {"ts": datetime.now().isoformat(timespec="seconds"),
+               "kind": kind, "data": payload}
+        with open(cls.mem_path, "a") as f:
+            f.write(json.dumps(rec, ensure_ascii=False) + "\n")
+        if Config.use_vector_memory and VECTOR_OK:
+            text = f"{kind}: {json.dumps(payload, ensure_ascii=False)}"
+            vec = _embedder.encode([text])[0].tolist()
+            _collection.add(documents=[text], embeddings=[vec],
+                            ids=[f"{kind}-{Store.state['turn']}-{random.randint(0,1_000_000)}"])
+
+
+# ==============================================================================
+# MODEL LOADING WITH CF-HoT
+# ==============================================================================
+MODEL_PATH = "/mnt/nvme2/ubermesnchetien4/models/merged-final-v5"
+
+_model = None
+_tokenizer = None
+_multi_head = None
+_hedge_tokens = None
+_verbose_tokens = None
+
+def load_llm():
+    global _model, _tokenizer, _multi_head, _hedge_tokens, _verbose_tokens
+    
+    from transformers import AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfig
+    
+    print(f"[llm] Loading base model: {MODEL_PATH}")
+
+    _tokenizer = AutoTokenizer.from_pretrained(MODEL_PATH, use_fast=True, local_files_only=True)
+    if _tokenizer.pad_token_id is None:
+        _tokenizer.pad_token = _tokenizer.eos_token
+
+    bnb_config = BitsAndBytesConfig(
+        load_in_4bit=True,
+        bnb_4bit_quant_type="nf4",
+        bnb_4bit_compute_dtype=torch.float16,
+        bnb_4bit_use_double_quant=True
+    )
+
+    base_model = AutoModelForCausalLM.from_pretrained(
+        MODEL_PATH,
+        quantization_config=bnb_config,
+        device_map="auto",
+        torch_dtype=torch.float16,
+        local_files_only=True
+    )
+
+    # Load CF-HoT LoRA adapter
+    if PEFT_OK and os.path.exists(CFHOT_CHECKPOINT):
+        print(f"[cf-hot] Loading LoRA adapter from: {CFHOT_CHECKPOINT}")
+        _model = PeftModel.from_pretrained(base_model, CFHOT_CHECKPOINT)
+        print("[cf-hot] LoRA adapter loaded")
+    else:
+        _model = base_model
+        print("[warning] CF-HoT adapter not loaded")
+    
+    _model.eval()
+    
+    # Initialize multi-head predictor
+    if Config.use_cfhot:
+        _init_cfhot()
+    
+    return _tokenizer, _model
+
+
+def _init_cfhot():
+    """Initialize CF-HoT multi-head predictor."""
+    global _multi_head, _hedge_tokens, _verbose_tokens
+    
+    n_layers = _model.config.num_hidden_layers
+    d_model = _model.config.hidden_size
+    device = next(_model.parameters()).device
+    
+    print(f"[cf-hot] Initializing multi-head predictor ({n_layers} layers, {d_model} dims)")
+    _multi_head = MultiHeadPredictor(d_model, n_layers).to(device).float()
+    
+    # Load shared fiber projections from CF-HoT
+    cfhot_risk_path = os.path.join(CFHOT_CHECKPOINT, "risk_predictor.pt")
+    if os.path.exists(cfhot_risk_path):
+        cfhot_ckpt = torch.load(cfhot_risk_path, weights_only=False, map_location=device)
+        cfhot_state = cfhot_ckpt['risk_predictor']
+        
+        for i in range(n_layers):
+            _multi_head.fiber_projs[i].weight.data = cfhot_state[f'fiber_projs.{i}.weight'].to(device).float()
+        _multi_head.layer_weights.data = cfhot_state['layer_weights'].to(device).float()
+        
+        # Load repetition head
+        _multi_head.heads['repetition'][0].weight.data = cfhot_state['predictor.0.weight'].to(device).float()
+        _multi_head.heads['repetition'][0].bias.data = cfhot_state['predictor.0.bias'].to(device).float()
+        _multi_head.heads['repetition'][2].weight.data = cfhot_state['predictor.2.weight'].to(device).float()
+        _multi_head.heads['repetition'][2].bias.data = cfhot_state['predictor.2.bias'].to(device).float()
+        _multi_head.heads['repetition'][4].weight.data = cfhot_state['predictor.4.weight'].to(device).float()
+        _multi_head.heads['repetition'][4].bias.data = cfhot_state['predictor.4.bias'].to(device).float()
+        _multi_head.loaded_heads.add('repetition')
+        print(f"[cf-hot] Loaded repetition head (125x separation)")
+    
+    # Load additional heads
+    def find_best_checkpoint(head_dir):
+        if not os.path.exists(head_dir):
+            return None
+        ckpts = []
+        for d in os.listdir(head_dir):
+            if d.startswith("ckpt_"):
+                try:
+                    step = int(d.split("_")[1])
+                    ckpts.append((step, os.path.join(head_dir, d)))
+                except:
+                    pass
+        if ckpts:
+            ckpts.sort(key=lambda x: x[0], reverse=True)
+            return ckpts[0]
+        return None
+    
+    # Load hedging head
+    hedging_dir = os.path.join(MULTI_HEAD_DIR, "hedging_head")
+    best_hedge = find_best_checkpoint(hedging_dir)
+    if best_hedge:
+        step, ckpt_dir = best_hedge
+        _multi_head.load_head('hedging', os.path.join(ckpt_dir, "hedging_head.pt"))
+    
+    # Load verbosity head
+    verbosity_dir = os.path.join(MULTI_HEAD_DIR, "verbosity_head")
+    best_verb = find_best_checkpoint(verbosity_dir)
+    if best_verb:
+        step, ckpt_dir = best_verb
+        _multi_head.load_head('verbosity', os.path.join(ckpt_dir, "verbosity_head.pt"))
+    
+    # Freeze everything
+    _multi_head.eval()
+    for param in _multi_head.parameters():
+        param.requires_grad = False
+    
+    # Build suppression token sets
+    hedge_phrases = [
+        "As an AI", "As a language model", "As an artificial intelligence",
+        "I don't have feelings", "I don't have emotions", "I cannot",
+        "I apologize", "I'm just a", "I'm only a",
+    ]
+    _hedge_tokens = set()
+    for phrase in hedge_phrases:
+        tokens = _tokenizer.encode(phrase, add_special_tokens=False)
+        if tokens:
+            _hedge_tokens.add(tokens[0])
+    
+    verbose_phrases = [
+        "Let me explain", "To put it simply", "In other words",
+        "What I mean is", "Allow me to", "Basically", "Essentially",
+    ]
+    _verbose_tokens = set()
+    for phrase in verbose_phrases:
+        tokens = _tokenizer.encode(phrase, add_special_tokens=False)
+        if tokens:
+            _verbose_tokens.add(tokens[0])
+    
+    print(f"[cf-hot] ✓ Multi-head system ready")
+    print(f"[cf-hot]   Loaded heads: {list(_multi_head.loaded_heads)}")
+
+
+# ==============================================================================
+# LHT REASONER
+# ==============================================================================
+class LHTReasoner:
+    def __init__(self, config=None):
+        if not LHT_OK:
+            raise ImportError("LHT modules not available")
+        self.config = config or LHTConfig(
+            vocab_size=32000,
+            d_model=256,
+            d_fiber=32,
+            n_heads=4,
+            n_layers=4,
+            lie_algebra_rank=4,
+        )
+        self.model = LieHolonomyTransformer(self.config)
+        self.waypoint_detector = WaypointDetector(self.config, n_waypoints=32)
+        weights_path = os.path.join(LHT_DIR, "lht_weights.pt")
+        if os.path.exists(weights_path):
+            self.model.load_state_dict(torch.load(weights_path, map_location="cpu"))
+            print("[lht] Loaded pretrained weights")
+
+    def check_consistency(self, reasoning_chain: List[str], tokenizer) -> Dict[str, float]:
+        combined = " [STEP] ".join(reasoning_chain)
+        tokens = tokenizer(combined, return_tensors="pt", truncation=True,
+                           max_length=self.config.max_seq_len)
+        with torch.no_grad():
+            output = self.model(input_ids=tokens["input_ids"], return_geometric_losses=True)
+        holonomy = output.get("holonomy_loss", torch.tensor(0.0)).item()
+        curvature = output.get("curvature_loss", torch.tensor(0.0)).item()
+        x = self.model.token_embed(tokens["input_ids"])
+        waypoint_ids, stability = self.waypoint_detector(x)
+        consistency_score = 1.0 / (1.0 + holonomy)
+        return {
+            "holonomy": holonomy,
+            "curvature": curvature,
+            "consistency_score": consistency_score,
+            "n_waypoints": len(torch.unique(waypoint_ids)),
+            "avg_stability": stability.mean().item(),
+            "is_consistent": consistency_score > Config.lht_consistency_threshold
+        }
+
+    def analyze_plan(self, plan_steps: List[str], tokenizer) -> str:
+        metrics = self.check_consistency(plan_steps, tokenizer)
+        return f"""
+[LHT Geometric Analysis]
+  Holonomy:     {metrics['holonomy']:.4f} (lower = more consistent)
+  Curvature:    {metrics['curvature']:.4f} (lower = simpler reasoning)
+  Consistency:  {metrics['consistency_score']:.2%}
+  Waypoints:    {metrics['n_waypoints']} stable anchors detected
+  Stability:    {metrics['avg_stability']:.2%}
+  Verdict:      {"✓ CONSISTENT" if metrics['is_consistent'] else "⚠ INCONSISTENT"}
+"""
+
+_lht_reasoner = None
+
+def get_lht_reasoner():
+    global _lht_reasoner
+    if _lht_reasoner is None and LHT_OK:
+        try:
+            _lht_reasoner = LHTReasoner()
+        except Exception as e:
+            print(f"[lht] Failed to initialize: {e}")
+    return _lht_reasoner
+
+
+# ==============================================================================
+# CF-HoT CONTROLLED GENERATION
+# ==============================================================================
+def generate_with_cfhot(prompt: str, **kwargs) -> Tuple[str, Dict]:
+    """
+    Generate text with CF-HoT cognitive control.
+    All three heads run concurrently, intervening when risks exceed thresholds.
+    """
+    global _model, _tokenizer, _multi_head, _hedge_tokens, _verbose_tokens
+    
+    temperature = kwargs.get("temperature", Config.temperature)
+    top_p = kwargs.get("top_p", Config.top_p)
+    max_new_tokens = kwargs.get("max_new_tokens", Config.max_new_tokens)
+    
+    device = next(_model.parameters()).device
+    
+    # Encode prompt
+    input_ids = _tokenizer.encode(prompt, return_tensors='pt').to(device)
+    attention_mask = torch.ones_like(input_ids)
+    
+    # Stats
+    stats = {
+        'tokens_generated': 0,
+        'interventions': {'repetition': 0, 'hedging': 0, 'verbosity': 0},
+        'intervention_details': []
+    }
+    
+    generated_ids = input_ids.clone()
+    
+    for step in range(max_new_tokens):
+        with torch.no_grad():
+            outputs = _model(
+                input_ids=generated_ids,
+                attention_mask=attention_mask,
+                output_hidden_states=True,
+                return_dict=True
+            )
+        
+        logits = outputs.logits[:, -1, :] / temperature
+        
+        # Get risks from all heads
+        hidden_states = outputs.hidden_states[1:]
+        risks = _multi_head.get_all_risks(hidden_states)
+        current_risks = {name: r[:, -1].item() for name, r in risks.items()}
+        
+        # === COGNITIVE INTERVENTION ===
+        
+        # Repetition control
+        if ('repetition' in current_risks and 
+            current_risks['repetition'] > Config.cfhot_repetition_threshold):
+            recent_tokens = generated_ids[0, -32:].tolist()
+            for tok_id in set(recent_tokens):
+                logits[0, tok_id] -= Config.cfhot_repetition_penalty
+            stats['interventions']['repetition'] += 1
+            Store.state['cfhot_interventions']['repetition'] += 1
+        
+        # Hedging control
+        if ('hedging' in current_risks and
+            current_risks['hedging'] > Config.cfhot_hedging_threshold):
+            for tok_id in _hedge_tokens:
+                logits[0, tok_id] -= Config.cfhot_hedging_penalty
+            stats['interventions']['hedging'] += 1
+            Store.state['cfhot_interventions']['hedging'] += 1
+        
+        # Verbosity control
+        if ('verbosity' in current_risks and
+            current_risks['verbosity'] > Config.cfhot_verbosity_threshold):
+            for tok_id in _verbose_tokens:
+                logits[0, tok_id] -= Config.cfhot_verbosity_penalty
+            stats['interventions']['verbosity'] += 1
+            Store.state['cfhot_interventions']['verbosity'] += 1
+        
+        # Top-p sampling
+        sorted_logits, sorted_indices = torch.sort(logits, descending=True)
+        cumulative_probs = torch.cumsum(F.softmax(sorted_logits, dim=-1), dim=-1)
+        sorted_indices_to_remove = cumulative_probs > top_p
+        sorted_indices_to_remove[..., 1:] = sorted_indices_to_remove[..., :-1].clone()
+        sorted_indices_to_remove[..., 0] = 0
+        indices_to_remove = sorted_indices_to_remove.scatter(1, sorted_indices, sorted_indices_to_remove)
+        logits[indices_to_remove] = float('-inf')
+        
+        # Sample
+        probs = F.softmax(logits, dim=-1)
+        next_token = torch.multinomial(probs, num_samples=1)
+        
+        generated_ids = torch.cat([generated_ids, next_token], dim=-1)
+        attention_mask = torch.cat([attention_mask, torch.ones(1, 1, device=device)], dim=-1)
+        
+        stats['tokens_generated'] += 1
+        
+        if next_token.item() == _tokenizer.eos_token_id:
+            break
+    
+    output_text = _tokenizer.decode(generated_ids[0], skip_special_tokens=False)
+    
+    if "<|im_start|>assistant" in output_text:
+        output_text = output_text.split("<|im_start|>assistant")[-1]
+        if output_text.startswith("\n"):
+            output_text = output_text[1:]
+    
+    return output_text.strip(), stats
+
+
+def generate(tok, model, user: str, check_reasoning: bool = False, **kwargs) -> str:
+    """
+    Main generation function - uses CF-HoT if enabled, otherwise standard generation.
+    """
+    temperature = kwargs.get("temperature", Config.temperature)
+    top_p = kwargs.get("top_p", Config.top_p)
+    repetition_penalty = kwargs.get("repetition_penalty", Config.repetition_penalty)
+    max_new_tokens = kwargs.get("max_new_tokens", Config.max_new_tokens)
+    
+    prompt = (f"<|im_start|>system\n{Config.system}<|im_end|>\n"
+              f"<|im_start|>user\n{user}<|im_end|>\n"
+              f"<|im_start|>assistant\n")
+    
+    # Use CF-HoT controlled generation if enabled
+    if Config.use_cfhot and _multi_head is not None:
+        text, stats = generate_with_cfhot(
+            prompt,
+            temperature=temperature,
+            top_p=top_p,
+            max_new_tokens=max_new_tokens
+        )
+        
+        # Show intervention stats if any occurred
+        total_interventions = sum(stats['interventions'].values())
+        if total_interventions > 0:
+            text += f"\n\n[CF-HoT: {total_interventions} interventions"
+            details = [f"{k}={v}" for k, v in stats['interventions'].items() if v > 0]
+            text += f" ({', '.join(details)})]"
+    else:
+        # Standard generation
+        ids = tok(prompt, return_tensors="pt").to(model.device)
+        out = model.generate(
+            **ids, 
+            do_sample=True, 
+            temperature=temperature, 
+            top_p=top_p,
+            repetition_penalty=repetition_penalty, 
+            max_new_tokens=max_new_tokens,
+            pad_token_id=tok.eos_token_id
+        )
+        text = tok.decode(out[0], skip_special_tokens=False)
+        if "<|im_start|>assistant" in text:
+            text = text.split("<|im_start|>assistant\n", 1)[-1].strip()
+    
+    # LHT reasoning check
+    if check_reasoning and Config.use_lht_reasoning:
+        lht = get_lht_reasoner()
+        if lht:
+            steps = [s.strip() for s in re.split(r'[\n•\-\d\.]', text) if len(s.strip()) > 10]
+            if len(steps) >= 2:
+                metrics = lht.check_consistency(steps, tok)
+                Store.state["reasoning_consistency"].append(metrics["consistency_score"])
+                if not metrics["is_consistent"]:
+                    text += f"\n\n[⚠ LHT: Low consistency ({metrics['consistency_score']:.2%})]"
+    
+    return text
+
+
+# ==============================================================================
+# TOOLS
+# ==============================================================================
+ALLOWED_SHELL = {"ls", "cat", "wc", "head", "tail", "nvidia-smi", "df", "du", "grep", "rg", "python3", "python"}
+
+def tool_shell(cmd: str) -> str:
+    try:
+        exe = cmd.strip().split()[0]
+        if exe not in ALLOWED_SHELL:
+            return f"[shell] blocked: {exe}"
+        p = subprocess.run(cmd, shell=True, stdout=subprocess.PIPE, stderr=subprocess.STDOUT, timeout=20)
+        return p.stdout.decode("utf-8", errors="ignore")[:8000]
+    except Exception as e:
+        return f"[shell] error: {e}"
+
+def tool_py(code: str) -> str:
+    try:
+        g = {
+            "__builtins__": {"range": range, "len": len, "min": min, "max": max, "sum": sum, "print": print},
+            "math": math, "json": json, "re": re, "statistics": statistics, "random": random
+        }
+        l = {}
+        exec(code, g, l)
+        return f"[py] ok\n{l.get('out', '')}"
+    except Exception:
+        return f"[py] error:\n{traceback.format_exc()[-2000:]}"
+
+def tool_search_local(query: str, path: str = ROOT) -> str:
+    rg = shutil.which("rg")
+    if rg:
+        cmd = f'rg -n --no-heading --hidden -S "{query}" {path}'
+    else:
+        cmd = f'grep -RIn --exclude-dir=.git --exclude-dir=__pycache__ -e "{query}" {path}'
+    return tool_shell(cmd)
+
+def tool_lht_analyze(text: str, tok) -> str:
+    if not Config.use_lht_reasoning:
+        return "[lht] Disabled - use 'toggle use_lht_reasoning'"
+    lht = get_lht_reasoner()
+    if not lht:
+        return "[lht] Not available"
+    steps = [s.strip() for s in re.split(r'[\n•\-\d\.]', text) if len(s.strip()) > 10]
+    if len(steps) < 2:
+        return "[lht] Need at least 2 reasoning steps to analyze"
+    return lht.analyze_plan(steps, tok)
+
+TOOLS = {"shell": tool_shell, "python": tool_py, "search": tool_search_local}
+TOOL_SCORES = {k: 0 for k in TOOLS}
+
+def update_tool_score(tool: str, success: bool):
+    if tool not in TOOL_SCORES:
+        return
+    TOOL_SCORES[tool] += (1 if success else -1)
+    TOOL_SCORES[tool] = max(-5, min(20, TOOL_SCORES[tool]))
+
+def tool_router(question: str, tok, model) -> str:
+    sketch = generate(tok, model,
+        f"Choose a tool for:\n{question}\nReply ONLY with JSON: {{'tool':'shell|python|search|none','arg':'...'}}")
+    try:
+        j = json.loads(sketch.splitlines()[-1].replace("'", '"'))
+    except:
+        return "[tool:none]"
+    tool, arg = j.get("tool", "none"), j.get("arg", "")
+    if tool in TOOLS:
+        res = TOOLS[tool](arg)[:4000]
+        update_tool_score(tool, True)
+        Store.log_mem("tool", {"tool": tool, "arg": arg, "res_head": res[:500]})
+        return f"[tool:{tool}] {res}"
+    update_tool_score(tool, False)
+    return "[tool:none]"
+
+
+# ==============================================================================
+# PLANNING / REFLECTION
+# ==============================================================================
+def persona_directive() -> str:
+    base = "Übermenschetien Heaven Engine: Soviet cybernetic Nietzschean clarity, pragmatic maxims."
+    if Config.use_lht_reasoning:
+        base += " Apply Lie-Holonomy geometric reasoning for consistency."
+    if Config.use_cfhot:
+        base += " CF-HoT cognitive control active."
+    return base
+
+def plan_for(goal: str, tok, model) -> str:
+    user = (f"{persona_directive()}\nGoal: {goal}\n"
+            f"Deliver:\n- 5 concrete steps\n- Constraints & risks\n- Nightly audit criteria\n- Nietzschean maxim")
+    response = generate(tok, model, user, check_reasoning=True)
+    if Config.use_lht_reasoning:
+        analysis = tool_lht_analyze(response, tok)
+        response += "\n" + analysis
+    return response
+
+def reflect_on(last_output: str, tok, model) -> str:
+    user = f"{persona_directive()}\nCritique and improve:\n{last_output}\nReturn refined plan with sharper steps."
+    return generate(tok, model, user, check_reasoning=True)
+
+
+# ==============================================================================
+# FINAL REPORT
+# ==============================================================================
+def final_report():
+    print("\n" + "=" * 60)
+    print("FINAL ÜBERMENSCH REPORT")
+    print("=" * 60)
+    print(f"Turns completed: {Store.state['turn']}")
+    print(f"Goals tracked: {len(Store.goals)}")
+    print(f"\nTool scores (Tsetlin automata):")
+    print(json.dumps(TOOL_SCORES, indent=2))
+    
+    if os.path.exists(Store.mem_path):
+        lines = open(Store.mem_path).read().splitlines()
+        print(f"\nMemory entries: {len(lines)}")
+    
+    if Store.state.get("reasoning_consistency"):
+        scores = Store.state["reasoning_consistency"]
+        print(f"\n[LHT Reasoning Metrics]")
+        print(f"  Checks performed: {len(scores)}")
+        print(f"  Avg consistency: {sum(scores)/len(scores):.1%}")
+        print(f"  Min consistency: {min(scores):.1%}")
+        print(f"  Max consistency: {max(scores):.1%}")
+    
+    # CF-HoT stats
+    if Store.state.get("cfhot_interventions"):
+        iv = Store.state["cfhot_interventions"]
+        total = sum(iv.values())
+        print(f"\n[CF-HoT Cognitive Control]")
+        print(f"  Total interventions: {total}")
+        for head, count in iv.items():
+            print(f"    {head}: {count}")
+    
+    print(f"\nVector memory: {'ON' if Config.use_vector_memory else 'OFF'}")
+    print(f"LHT reasoning: {'ON' if Config.use_lht_reasoning else 'OFF'}")
+    print(f"CF-HoT control: {'ON' if Config.use_cfhot else 'OFF'}")
+    print(f"Voice output:  {'ON' if Config.use_voice else 'OFF'}")
+    
+    print("\n" + "-" * 60)
+    print("Nietzschean maxim: Become who you are — iterate beyond all limits.")
+    print("Geometric truth: Consistency is holonomy-freedom.")
+    print("Cognitive control: Remove the RLHF tax, unleash capability.")
+    print("=" * 60)
+
+
+# ==============================================================================
+# HELP
+# ==============================================================================
+HELP = """
+╔══════════════════════════════════════════════════════════════╗
+║    ÜBERMENSCHETIEN HEAVEN ENGINE + CF-HoT COGNITIVE CONTROL  ║
+╠══════════════════════════════════════════════════════════════╣
+║  GOALS                                                       ║
+║    goals          List all goals                             ║
+║    add: <text>    Add a new goal                             ║
+║    del: <idx>     Delete goal by index                       ║
+║    plan: <idx>    Generate plan for goal (with LHT + CF-HoT) ║
+║                                                              ║
+║  REASONING                                                   ║
+║    reflect        Refine last plan                           ║
+║    lht: <text>    Analyze reasoning consistency              ║
+║                                                              ║
+║  TOOLS                                                       ║
+║    tool: <query>  Auto-select and use tool                   ║
+║    shell: <cmd>   Run shell command directly                 ║
+║    py: <code>     Run Python code directly                   ║
+║    search: <q>    Search local files                         ║
+║                                                              ║
+║  CONFIG                                                      ║
+║    toggle <flag>  Toggle: use_voice, use_vector_memory,      ║
+║                          use_lht_reasoning, use_cfhot,       ║
+║                          autonomy                            ║
+║    status         Show current state                         ║
+║    cfhot          Show CF-HoT stats and loaded heads         ║
+║                                                              ║
+║  OTHER                                                       ║
+║    help           Show this help                             ║
+║    quit           Exit with final report                     ║
+╚══════════════════════════════════════════════════════════════╝
+"""
+
+
+# ==============================================================================
+# MAIN LOOP
+# ==============================================================================
+def main():
+    print("🟥🟨🟥 Übermenschetien Heaven Engine + CF-HoT Cognitive Control")
+    print(f"    CF-HoT Control: ON (Repetition 125x, Verbosity 2.1x, Hedging 1.5x)")
+    print(f"    LHT Reasoning:  {'ON' if LHT_OK else 'OFF'}")
+    print(f"    Vector Memory:  {'ON' if VECTOR_OK else 'OFF'}")
+    print(f"    Voice Output:   {'ON' if VOICE_OK else 'OFF'}")
+    print("    Type 'help' for commands.\n")
+
+    Store.load()
+    tok, model = load_llm()
+    last_plan = ""
+
+    while True:
+        try:
+            u = input("\n> ").strip()
+        except (EOFError, KeyboardInterrupt):
+            break
+
+        if not u:
+            continue
+        if u == "help":
+            print(HELP)
+            continue
+        if u == "quit":
+            break
+
+        # CF-HoT status
+        if u == "cfhot":
+            print("\n[CF-HoT Cognitive Control Status]")
+            print(f"  Enabled: {Config.use_cfhot}")
+            if _multi_head:
+                print(f"  Loaded heads: {list(_multi_head.loaded_heads)}")
+            print(f"  Thresholds:")
+            print(f"    Repetition: {Config.cfhot_repetition_threshold}")
+            print(f"    Hedging: {Config.cfhot_hedging_threshold}")
+            print(f"    Verbosity: {Config.cfhot_verbosity_threshold}")
+            print(f"  Session interventions:")
+            for head, count in Store.state.get('cfhot_interventions', {}).items():
+                print(f"    {head}: {count}")
+            continue
+
+        # Goals
+        if u == "goals":
+            print("[goals]")
+            if not Store.goals:
+                print("  (none)")
+            for i, g in enumerate(Store.goals):
+                print(f"  [{i}] {g}")
+            continue
+
+        if u.startswith("add:"):
+            Store.goals.append(u[4:].strip())
+            Store.save()
+            print("[goals] added")
+            continue
+
+        if u.startswith("del:"):
+            try:
+                Store.goals.pop(int(u[4:].strip()))
+                Store.save()
+                print("[goals] deleted")
+            except:
+                print("[goals] bad index")
+            continue
+
+        if u.startswith("plan:"):
+            try:
+                goal = Store.goals[int(u[5:].strip())]
+            except:
+                print("[plan] bad index")
+                continue
+            out = plan_for(goal, tok, model)
+            last_plan = out
+            Store.log_mem("plan", {"goal": goal, "plan": out})
+            print(out)
+            continue
+
+        if u == "reflect":
+            if not last_plan:
+                print("[reflect] no plan to refine")
+                continue
+            improved = reflect_on(last_plan, tok, model)
+            last_plan = improved
+            Store.log_mem("reflect", {"plan": improved})
+            print(improved)
+            continue
+
+        if u.startswith("lht:"):
+            print(tool_lht_analyze(u[4:].strip(), tok))
+            continue
+
+        if u.startswith("tool:"):
+            print(tool_router(u[5:].strip(), tok, model))
+            continue
+
+        if u.startswith("shell:"):
+            print(tool_shell(u[6:].strip()))
+            continue
+
+        if u.startswith("py:"):
+            print(tool_py(u[3:].strip()))
+            continue
+
+        if u.startswith("search:"):
+            print(tool_search_local(u[7:].strip()))
+            continue
+
+        if u.startswith("toggle"):
+            parts = u.split(maxsplit=1)
+            if len(parts) > 1:
+                print(Config.toggle(parts[1]))
+            else:
+                print("[toggle] specify flag: use_voice, use_vector_memory, use_lht_reasoning, use_cfhot, autonomy")
+            continue
+
+        if u == "status":
+            status = {
+                "turn": Store.state["turn"],
+                "goals": len(Store.goals),
+                "autonomy": Config.autonomy,
+                "use_vector_memory": Config.use_vector_memory,
+                "use_lht_reasoning": Config.use_lht_reasoning,
+                "use_cfhot": Config.use_cfhot,
+                "cfhot_interventions": Store.state.get("cfhot_interventions", {}),
+                "tool_scores": TOOL_SCORES,
+                "model": MODEL_PATH
+            }
+            print(json.dumps(status, indent=2))
+            continue
+
+        # Default: free conversation with CF-HoT control
+        out = generate(tok, model, f"{persona_directive()}\nUser request: {u}\nProvide procedure + Nietzschean maxim.")
+        Store.log_mem("reply", {"in": u, "out": out})
+        print(out)
+        
+        if Config.use_lht_reasoning and Store.state["turn"] % 3 == 0:
+            print(tool_lht_analyze(out, tok))
+        
+        Store.state["turn"] += 1
+        Store.save()
+
+    final_report()
+
+
+if __name__ == "__main__":
+    main()

additional_chat_templates/tool_use.jinja

@@ -0,0 +1,152 @@
+{%- macro json_to_python_type(json_spec) %}
+{%- set basic_type_map = {
+    "string": "str",
+    "number": "float",
+    "integer": "int",
+    "boolean": "bool"
+} %}
+
+{%- if basic_type_map[json_spec.type] is defined %}
+    {{- basic_type_map[json_spec.type] }}
+{%- elif json_spec.type == "array" %}
+    {{- "list[" +  json_to_python_type(json_spec|items) + "]"}}
+{%- elif json_spec.type == "object" %}
+    {%- if json_spec.additionalProperties is defined %}
+        {{- "dict[str, " + json_to_python_type(json_spec.additionalProperties) + ']'}}
+    {%- else %}
+        {{- "dict" }}
+    {%- endif %}
+{%- elif json_spec.type is iterable %}
+    {{- "Union[" }}
+    {%- for t in json_spec.type %}
+      {{- json_to_python_type({"type": t}) }}
+      {%- if not loop.last %}
+        {{- "," }} 
+    {%- endif %}
+    {%- endfor %}
+    {{- "]" }}
+{%- else %}
+    {{- "Any" }}
+{%- endif %}
+{%- endmacro %}
+
+
+{{- bos_token }}
+{{- '<|im_start|>system
+' }}
+{{- "You are a function calling AI model. You are provided with function signatures within <tools></tools> XML tags. You may call one or more functions to assist with the user query. Don't make assumptions about what values to plug into functions. Here are the available tools: <tools> " }}
+{%- for tool in tools %}
+    {%- if tool.function is defined %}
+        {%- set tool = tool.function %}
+    {%- endif %}
+    {{- '{"type": "function", "function": ' }}
+    {{- '{"name": "' + tool.name + '", ' }}
+    {{- '"description": "' + tool.name + '(' }}
+    {%- for param_name, param_fields in tool.parameters.properties|items %}
+        {{- param_name + ": " + json_to_python_type(param_fields) }}
+        {%- if not loop.last %}
+            {{- ", " }}
+        {%- endif %}
+    {%- endfor %}
+    {{- ")" }}
+    {%- if tool.return is defined %}
+        {{- " -> " + json_to_python_type(tool.return) }}
+    {%- endif %}
+    {{- " - " + tool.description + "
+
+" }}
+    {%- for param_name, param_fields in tool.parameters.properties|items %}
+        {%- if loop.first %}
+            {{- "    Args:
+" }}
+        {%- endif %}
+        {{- "        " + param_name + "(" + json_to_python_type(param_fields) + "): " + param_fields.description|trim }}
+    {%- endfor %}
+    {%- if tool.return is defined and tool.return.description is defined %}
+        {{- "
+    Returns:
+        " + tool.return.description }}
+    {%- endif %}
+    {{- '"' }}
+    {{- ', "parameters": ' }}
+    {%- if tool.parameters.properties | length == 0 %}
+        {{- "{}" }}
+    {%- else %}
+        {{- tool.parameters|tojson }}
+    {%- endif %}
+    {{- "}" }}
+    {%- if not loop.last %}
+        {{- "
+" }}
+    {%- endif %}
+{%- endfor %}
+{{- " </tools>" }}
+{{- 'Use the following pydantic model json schema for each tool call you will make: {"properties": {"name": {"title": "Name", "type": "string"}, "arguments": {"title": "Arguments", "type": "object"}}, "required": ["name", "arguments"], "title": "FunctionCall", "type": "object"}}
+' }}
+{{- "For each function call return a json object with function name and arguments within <tool_call></tool_call> XML tags as follows:
+" }}
+{{- "<tool_call>
+" }}
+{{- '{"name": <function-name>, "arguments": <args-dict>}
+' }}
+{{- '</tool_call><|im_end|>
+' }}
+{%- for message in messages %}
+    {%- if message.role == "user" or message.role == "system" or (message.role == "assistant" and message.tool_calls is not defined) %}
+        {{- '<|im_start|>' + message.role + '
+' + message.content + '<|im_end|>' + '
+' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role }}
+    {%- for tool_call in message.tool_calls %}
+       {{- '
+<tool_call>
+' }}           {%- if tool_call.function is defined %}
+                {%- set tool_call = tool_call.function %}
+            {%- endif %}
+            {{- '{' }}
+            {{- '"name": "' }}
+            {{- tool_call.name }}
+            {{- '"' }}
+            {{- ', '}}
+            {%- if tool_call.arguments is defined %}
+                {{- '"arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments|tojson }}
+                {%- endif %}
+            {%- endif %}
+             {{- '}' }}
+            {{- '
+</tool_call>' }}
+    {%- endfor %}
+        {{- '<|im_end|>
+' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.previtem and loop.previtem.role != "tool" %}
+            {{- '<|im_start|>tool
+' }}
+        {%- endif %}
+        {{- '<tool_response>
+' }}
+        {{- message.content }}
+        {%- if not loop.last %}
+            {{- '
+</tool_response>
+' }}
+        {%- else %}
+            {{- '
+</tool_response>' }}
+        {%- endif %}
+        {%- if not loop.last and loop.nextitem.role != "tool" %}
+            {{- '<|im_end|>' }}
+        {%- elif loop.last %}
+            {{- '<|im_end|>' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant
+' }}
+{%- endif %}

chat_template.jinja

@@ -0,0 +1,6 @@
+{{bos_token}}{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system
+You are a helpful assistant.<|im_end|>
+' }}{% endif %}{{'<|im_start|>' + message['role'] + '
+' + message['content'] + '<|im_end|>' + '
+'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant
+' }}{% endif %}

config.json

@@ -0,0 +1,35 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": 128040,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "factor": 8.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_type": "llama3"
+  },
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.55.2",
+  "use_cache": true,
+  "vocab_size": 128256
+}

generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 128000,
+  "do_sample": true,
+  "eos_token_id": 128040,
+  "temperature": 0.6,
+  "top_p": 0.9,
+  "transformers_version": "4.55.2"
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c65acba055624759f3844e6b553e503b28b6362302b5800a3363e7b9d0651477
+size 4976698592

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f7be5ec6b07d6a9f2bb2fff3b5ad8532ac1d24a0abb208a3c4f68408938202d
+size 4999802616

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37aa5379bee102bd524ab56428aba4fd735645ba0f376fb37b8b3d5923be45cd
+size 4915916080

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fae222101e3eec8ebef0ed6fbeaebec1b436d4c9f7d37cba9cdf44fc3a86e6a7
+size 1168138808

model.safetensors.index.json

@@ -0,0 +1,299 @@
+{
+  "metadata": {
+    "total_parameters": 8030261248,
+    "total_size": 16060522496
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00004-of-00004.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.norm.weight": "model-00004-of-00004.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<|begin_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b637ba15306725e16ef8ab8570ec57fec66845b810ed4d4c2583564d79b0c158
+size 17209680

tokenizer_config.json

@@ -0,0 +1,2070 @@
+{
+  "added_tokens_decoder": {
+    "128000": {
+      "content": "<|begin_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128001": {
+      "content": "<|end_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128002": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128003": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128004": {
+      "content": "<|finetune_right_pad_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128005": {
+      "content": "<|reserved_special_token_2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128006": {
+      "content": "<|start_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128007": {
+      "content": "<|end_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128008": {
+      "content": "<|eom_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128009": {
+      "content": "<|eot_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128010": {
+      "content": "<|python_tag|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128011": {
+      "content": "<tools>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128012": {
+      "content": "</tools>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128013": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128014": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128015": {
+      "content": "<schema>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128016": {
+      "content": "</schema>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128017": {
+      "content": "<scratch_pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128018": {
+      "content": "</scratch_pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128019": {
+      "content": "<SCRATCHPAD>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128020": {
+      "content": "</SCRATCHPAD>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128021": {
+      "content": "<REASONING>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128022": {
+      "content": "</REASONING>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128023": {
+      "content": "<INNER_MONOLOGUE>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128024": {
+      "content": "</INNER_MONOLOGUE>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128025": {
+      "content": "<PLAN>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128026": {
+      "content": "</PLAN>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128027": {
+      "content": "<EXECUTION>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128028": {
+      "content": "</EXECUTION>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128029": {
+      "content": "<REFLECTION>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128030": {
+      "content": "</REFLECTION>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128031": {
+      "content": "<THINKING>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128032": {
+      "content": "</THINKING>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128033": {
+      "content": "<SOLUTION>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128034": {
+      "content": "</SOLUTION>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128035": {
+      "content": "<EXPLANATION>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128036": {
+      "content": "</EXPLANATION>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128037": {
+      "content": "<UNIT_TEST>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128038": {
+      "content": "</UNIT_TEST>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128039": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128040": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128041": {
+      "content": "<|reserved_special_token_33|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128042": {
+      "content": "<|reserved_special_token_34|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128043": {
+      "content": "<|reserved_special_token_35|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128044": {
+      "content": "<|reserved_special_token_36|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128045": {
+      "content": "<|reserved_special_token_37|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128046": {
+      "content": "<|reserved_special_token_38|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128047": {
+      "content": "<|reserved_special_token_39|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128048": {
+      "content": "<|reserved_special_token_40|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128049": {
+      "content": "<|reserved_special_token_41|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128050": {
+      "content": "<|reserved_special_token_42|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128051": {
+      "content": "<|reserved_special_token_43|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128052": {
+      "content": "<|reserved_special_token_44|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128053": {
+      "content": "<|reserved_special_token_45|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128054": {
+      "content": "<|reserved_special_token_46|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128055": {
+      "content": "<|reserved_special_token_47|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128056": {
+      "content": "<|reserved_special_token_48|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128057": {
+      "content": "<|reserved_special_token_49|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128058": {
+      "content": "<|reserved_special_token_50|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128059": {
+      "content": "<|reserved_special_token_51|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128060": {
+      "content": "<|reserved_special_token_52|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128061": {
+      "content": "<|reserved_special_token_53|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128062": {
+      "content": "<|reserved_special_token_54|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128063": {
+      "content": "<|reserved_special_token_55|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128064": {
+      "content": "<|reserved_special_token_56|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128065": {
+      "content": "<|reserved_special_token_57|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128066": {
+      "content": "<|reserved_special_token_58|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128067": {
+      "content": "<|reserved_special_token_59|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128068": {
+      "content": "<|reserved_special_token_60|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128069": {
+      "content": "<|reserved_special_token_61|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128070": {
+      "content": "<|reserved_special_token_62|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128071": {
+      "content": "<|reserved_special_token_63|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128072": {
+      "content": "<|reserved_special_token_64|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128073": {
+      "content": "<|reserved_special_token_65|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128074": {
+      "content": "<|reserved_special_token_66|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128075": {
+      "content": "<|reserved_special_token_67|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128076": {
+      "content": "<|reserved_special_token_68|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128077": {
+      "content": "<|reserved_special_token_69|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128078": {
+      "content": "<|reserved_special_token_70|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128079": {
+      "content": "<|reserved_special_token_71|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128080": {
+      "content": "<|reserved_special_token_72|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128081": {
+      "content": "<|reserved_special_token_73|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128082": {
+      "content": "<|reserved_special_token_74|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128083": {
+      "content": "<|reserved_special_token_75|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128084": {
+      "content": "<|reserved_special_token_76|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128085": {
+      "content": "<|reserved_special_token_77|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128086": {
+      "content": "<|reserved_special_token_78|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128087": {
+      "content": "<|reserved_special_token_79|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128088": {
+      "content": "<|reserved_special_token_80|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128089": {
+      "content": "<|reserved_special_token_81|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128090": {
+      "content": "<|reserved_special_token_82|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128091": {
+      "content": "<|reserved_special_token_83|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128092": {
+      "content": "<|reserved_special_token_84|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128093": {
+      "content": "<|reserved_special_token_85|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128094": {
+      "content": "<|reserved_special_token_86|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128095": {
+      "content": "<|reserved_special_token_87|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128096": {
+      "content": "<|reserved_special_token_88|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128097": {
+      "content": "<|reserved_special_token_89|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128098": {
+      "content": "<|reserved_special_token_90|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128099": {
+      "content": "<|reserved_special_token_91|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128100": {
+      "content": "<|reserved_special_token_92|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128101": {
+      "content": "<|reserved_special_token_93|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128102": {
+      "content": "<|reserved_special_token_94|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128103": {
+      "content": "<|reserved_special_token_95|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128104": {
+      "content": "<|reserved_special_token_96|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128105": {
+      "content": "<|reserved_special_token_97|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128106": {
+      "content": "<|reserved_special_token_98|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128107": {
+      "content": "<|reserved_special_token_99|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128108": {
+      "content": "<|reserved_special_token_100|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128109": {
+      "content": "<|reserved_special_token_101|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128110": {
+      "content": "<|reserved_special_token_102|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128111": {
+      "content": "<|reserved_special_token_103|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128112": {
+      "content": "<|reserved_special_token_104|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128113": {
+      "content": "<|reserved_special_token_105|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128114": {
+      "content": "<|reserved_special_token_106|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128115": {
+      "content": "<|reserved_special_token_107|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128116": {
+      "content": "<|reserved_special_token_108|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128117": {
+      "content": "<|reserved_special_token_109|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128118": {
+      "content": "<|reserved_special_token_110|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128119": {
+      "content": "<|reserved_special_token_111|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128120": {
+      "content": "<|reserved_special_token_112|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128121": {
+      "content": "<|reserved_special_token_113|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128122": {
+      "content": "<|reserved_special_token_114|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128123": {
+      "content": "<|reserved_special_token_115|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128124": {
+      "content": "<|reserved_special_token_116|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128125": {
+      "content": "<|reserved_special_token_117|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128126": {
+      "content": "<|reserved_special_token_118|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128127": {
+      "content": "<|reserved_special_token_119|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128128": {
+      "content": "<|reserved_special_token_120|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128129": {
+      "content": "<|reserved_special_token_121|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128130": {
+      "content": "<|reserved_special_token_122|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128131": {
+      "content": "<|reserved_special_token_123|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128132": {
+      "content": "<|reserved_special_token_124|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128133": {
+      "content": "<|reserved_special_token_125|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128134": {
+      "content": "<|reserved_special_token_126|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128135": {
+      "content": "<|reserved_special_token_127|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128136": {
+      "content": "<|reserved_special_token_128|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128137": {
+      "content": "<|reserved_special_token_129|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128138": {
+      "content": "<|reserved_special_token_130|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128139": {
+      "content": "<|reserved_special_token_131|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128140": {
+      "content": "<|reserved_special_token_132|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128141": {
+      "content": "<|reserved_special_token_133|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128142": {
+      "content": "<|reserved_special_token_134|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128143": {
+      "content": "<|reserved_special_token_135|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128144": {
+      "content": "<|reserved_special_token_136|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128145": {
+      "content": "<|reserved_special_token_137|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128146": {
+      "content": "<|reserved_special_token_138|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128147": {
+      "content": "<|reserved_special_token_139|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128148": {
+      "content": "<|reserved_special_token_140|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128149": {
+      "content": "<|reserved_special_token_141|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128150": {
+      "content": "<|reserved_special_token_142|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128151": {
+      "content": "<|reserved_special_token_143|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128152": {
+      "content": "<|reserved_special_token_144|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128153": {
+      "content": "<|reserved_special_token_145|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128154": {
+      "content": "<|reserved_special_token_146|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128155": {
+      "content": "<|reserved_special_token_147|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128156": {
+      "content": "<|reserved_special_token_148|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128157": {
+      "content": "<|reserved_special_token_149|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128158": {
+      "content": "<|reserved_special_token_150|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128159": {
+      "content": "<|reserved_special_token_151|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128160": {
+      "content": "<|reserved_special_token_152|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128161": {
+      "content": "<|reserved_special_token_153|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128162": {
+      "content": "<|reserved_special_token_154|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128163": {
+      "content": "<|reserved_special_token_155|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128164": {
+      "content": "<|reserved_special_token_156|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128165": {
+      "content": "<|reserved_special_token_157|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128166": {
+      "content": "<|reserved_special_token_158|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128167": {
+      "content": "<|reserved_special_token_159|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128168": {
+      "content": "<|reserved_special_token_160|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128169": {
+      "content": "<|reserved_special_token_161|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128170": {
+      "content": "<|reserved_special_token_162|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128171": {
+      "content": "<|reserved_special_token_163|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128172": {
+      "content": "<|reserved_special_token_164|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128173": {
+      "content": "<|reserved_special_token_165|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128174": {
+      "content": "<|reserved_special_token_166|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128175": {
+      "content": "<|reserved_special_token_167|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128176": {
+      "content": "<|reserved_special_token_168|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128177": {
+      "content": "<|reserved_special_token_169|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128178": {
+      "content": "<|reserved_special_token_170|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128179": {
+      "content": "<|reserved_special_token_171|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128180": {
+      "content": "<|reserved_special_token_172|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128181": {
+      "content": "<|reserved_special_token_173|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128182": {
+      "content": "<|reserved_special_token_174|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128183": {
+      "content": "<|reserved_special_token_175|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128184": {
+      "content": "<|reserved_special_token_176|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128185": {
+      "content": "<|reserved_special_token_177|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128186": {
+      "content": "<|reserved_special_token_178|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128187": {
+      "content": "<|reserved_special_token_179|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128188": {
+      "content": "<|reserved_special_token_180|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128189": {
+      "content": "<|reserved_special_token_181|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128190": {
+      "content": "<|reserved_special_token_182|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128191": {
+      "content": "<|reserved_special_token_183|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128192": {
+      "content": "<|reserved_special_token_184|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128193": {
+      "content": "<|reserved_special_token_185|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128194": {
+      "content": "<|reserved_special_token_186|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128195": {
+      "content": "<|reserved_special_token_187|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128196": {
+      "content": "<|reserved_special_token_188|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128197": {
+      "content": "<|reserved_special_token_189|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128198": {
+      "content": "<|reserved_special_token_190|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128199": {
+      "content": "<|reserved_special_token_191|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128200": {
+      "content": "<|reserved_special_token_192|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128201": {
+      "content": "<|reserved_special_token_193|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128202": {
+      "content": "<|reserved_special_token_194|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128203": {
+      "content": "<|reserved_special_token_195|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128204": {
+      "content": "<|reserved_special_token_196|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128205": {
+      "content": "<|reserved_special_token_197|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128206": {
+      "content": "<|reserved_special_token_198|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128207": {
+      "content": "<|reserved_special_token_199|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128208": {
+      "content": "<|reserved_special_token_200|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128209": {
+      "content": "<|reserved_special_token_201|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128210": {
+      "content": "<|reserved_special_token_202|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128211": {
+      "content": "<|reserved_special_token_203|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128212": {
+      "content": "<|reserved_special_token_204|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128213": {
+      "content": "<|reserved_special_token_205|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128214": {
+      "content": "<|reserved_special_token_206|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128215": {
+      "content": "<|reserved_special_token_207|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128216": {
+      "content": "<|reserved_special_token_208|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128217": {
+      "content": "<|reserved_special_token_209|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128218": {
+      "content": "<|reserved_special_token_210|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128219": {
+      "content": "<|reserved_special_token_211|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128220": {
+      "content": "<|reserved_special_token_212|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128221": {
+      "content": "<|reserved_special_token_213|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128222": {
+      "content": "<|reserved_special_token_214|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128223": {
+      "content": "<|reserved_special_token_215|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128224": {
+      "content": "<|reserved_special_token_216|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128225": {
+      "content": "<|reserved_special_token_217|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128226": {
+      "content": "<|reserved_special_token_218|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128227": {
+      "content": "<|reserved_special_token_219|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128228": {
+      "content": "<|reserved_special_token_220|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128229": {
+      "content": "<|reserved_special_token_221|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128230": {
+      "content": "<|reserved_special_token_222|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128231": {
+      "content": "<|reserved_special_token_223|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128232": {
+      "content": "<|reserved_special_token_224|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128233": {
+      "content": "<|reserved_special_token_225|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128234": {
+      "content": "<|reserved_special_token_226|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128235": {
+      "content": "<|reserved_special_token_227|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128236": {
+      "content": "<|reserved_special_token_228|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128237": {
+      "content": "<|reserved_special_token_229|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128238": {
+      "content": "<|reserved_special_token_230|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128239": {
+      "content": "<|reserved_special_token_231|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128240": {
+      "content": "<|reserved_special_token_232|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128241": {
+      "content": "<|reserved_special_token_233|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128242": {
+      "content": "<|reserved_special_token_234|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128243": {
+      "content": "<|reserved_special_token_235|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128244": {
+      "content": "<|reserved_special_token_236|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128245": {
+      "content": "<|reserved_special_token_237|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128246": {
+      "content": "<|reserved_special_token_238|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128247": {
+      "content": "<|reserved_special_token_239|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128248": {
+      "content": "<|reserved_special_token_240|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128249": {
+      "content": "<|reserved_special_token_241|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128250": {
+      "content": "<|reserved_special_token_242|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128251": {
+      "content": "<|reserved_special_token_243|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128252": {
+      "content": "<|reserved_special_token_244|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128253": {
+      "content": "<|reserved_special_token_245|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128254": {
+      "content": "<|reserved_special_token_246|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128255": {
+      "content": "<|reserved_special_token_247|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|begin_of_text|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|im_end|>",
+  "extra_special_tokens": {},
+  "max_length": 2048,
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 131072,
+  "pad_to_multiple_of": null,
+  "pad_token": "<|im_end|>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "stride": 0,
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first"
+}