Upload BeigeTTS - Research release for neural speech synthesis (CC BY-NC 4.0)

.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

README.md

@@ -0,0 +1,234 @@
+---
+language: en
+license: cc-by-nc-4.0
+library_name: transformers
+tags:
+  - tts
+  - text-to-speech
+  - neucodec
+  - audio-generation
+  - research
+  - speech-synthesis
+datasets:
+  - custom
+model-index:
+  - name: BeigeTTS
+    results: []
+---
+
+# BeigeTTS: Research Release for Neural Speech Synthesis
+
+## Overview
+
+BeigeTTS is a research release from BlandAI, representing a scaled-down version of our production Khaki TTS system. This model demonstrates state-of-the-art neural speech synthesis capabilities by combining Google's Gemma-3 4B architecture with NeuCodec audio token generation. We're releasing BeigeTTS to the research community to advance the field of neural speech synthesis and enable academic exploration of large-scale TTS architectures.
+
+## Research Context & Motivation
+
+BeigeTTS serves as a public research artifact derived from our larger Khaki TTS system, which powers BlandAI's production speech synthesis infrastructure. While Khaki operates at significantly larger scale with enhanced capabilities including:
+- Multi-speaker voice cloning (10,000+ voices)
+- Real-time multilingual synthesis (57 languages)
+- Emotion and prosody transfer
+- Sub-50ms streaming latency
+- Production-grade robustness
+
+BeigeTTS represents the core architectural innovations in a more accessible 4B parameter model suitable for research purposes.
+
+## Technical Architecture
+
+### Model Foundation
+- **Base Model**: Google Gemma-3 4B Instruct
+- **Parameter Count**: ~4 billion parameters (Khaki uses 70B+)
+- **Audio Codec**: NeuCodec (24kHz, single codebook)
+- **Training Steps**: 1,435,000 steps
+- **Context Length**: 2048 tokens
+- **Vocabulary Size**: Extended to 327,690 tokens (includes NeuCodec token space)
+
+### Research Implications
+
+This release enables researchers to explore:
+
+1. **Unified Text-Audio Modeling**: How large language models can be adapted for audio generation tasks
+2. **Token-Based Audio Synthesis**: Advantages of discrete token representations over continuous methods
+3. **Efficient Streaming**: Real-time generation with minimal latency
+4. **Cross-Modal Learning**: Transfer learning between text and audio modalities
+
+### Token Space Design
+
+The model employs a unified token space combining text and audio:
+
+```
+Standard Gemma Tokens: 0-262,144
+Special Audio Markers:
+  - AUDIO_START: 262,145
+  - AUDIO_END: 262,146
+NeuCodec Audio Tokens: 262,154-327,689 (65,536 tokens)
+```
+
+## Capabilities & Limitations
+
+### Current Capabilities (BeigeTTS)
+- High-quality English speech synthesis
+- Natural prosody and intonation
+- Streaming generation support
+- Adjustable speaking rate and style
+- Context-aware generation
+
+### Production Capabilities (Khaki - Not Released)
+- **Multilingual**: 57 languages with accent control
+- **Voice Cloning**: Zero-shot and few-shot speaker adaptation
+- **Emotion Control**: 12 distinct emotional states
+- **Ultra-Low Latency**: <50ms time-to-first-audio
+- **Long-Form**: Stable generation for 30+ minute audio
+- **Voice Conversion**: Real-time voice transformation
+- **Singing Synthesis**: Musical vocal generation
+
+### Research Limitations
+
+BeigeTTS is released for non-commercial research purposes only. Key limitations include:
+- English-only synthesis (multilingual reserved for Khaki)
+- Single speaker (multi-speaker in Khaki)
+- 10-second maximum generation (unlimited in Khaki)
+- No voice cloning (available in Khaki)
+- Research license only
+
+## Installation
+
+```bash
+pip install torch transformers accelerate
+pip install git+https://github.com/neuphonic/neucodec.git
+pip install soundfile numpy scipy
+```
+
+## Quick Start
+
+```python
+import torch
+from transformers import AutoModelForCausalLM, AutoTokenizer
+from neucodec import NeuCodec
+import soundfile as sf
+
+# Load model
+model = AutoModelForCausalLM.from_pretrained("BlandAI/BeigeTTS")
+tokenizer = AutoTokenizer.from_pretrained("BlandAI/BeigeTTS")
+neucodec = NeuCodec.from_pretrained("neuphonic/neucodec")
+
+# Generate speech
+text = "Hello! This is BeigeTTS, a research release from BlandAI."
+prompt = f"<start_of_turn>user\n{text}<end_of_turn>\n<start_of_turn>model\n<start_of_speech>"
+
+# Tokenize and generate
+inputs = tokenizer(prompt, return_tensors="pt")
+with torch.no_grad():
+    outputs = model.generate(
+        inputs.input_ids,
+        max_new_tokens=500,
+        temperature=0.1,
+        top_p=0.97,
+        eos_token_id=[tokenizer.eos_token_id, 262146]
+    )
+
+# Decode audio (see inference script for full implementation)
+```
+
+## Research Applications
+
+### Suggested Research Directions
+
+1. **Prosody Modeling**: Investigating controllable prosody generation
+2. **Cross-Lingual Transfer**: Adapting to new languages with minimal data
+3. **Emotion Synthesis**: Fine-tuning for emotional speech generation
+4. **Compression Studies**: Analyzing audio token efficiency
+5. **Streaming Optimization**: Reducing latency for real-time applications
+6. **Robustness Analysis**: Handling out-of-distribution text inputs
+
+### Academic Collaborations
+
+We welcome academic collaborations. For research partnerships or access to evaluation datasets, contact research@bland.ai
+
+## Performance Characteristics
+
+- **Inference Speed**: ~150 tokens/second on A100
+- **Audio Quality**: 24kHz (Khaki supports 48kHz)
+- **Latency**: <500ms first audio (Khaki: <50ms)
+- **Memory Usage**: ~16GB VRAM
+
+## Multilingual Research Notes
+
+While BeigeTTS is English-only, the architecture supports multilingual synthesis through:
+- Language-specific token embeddings
+- Cross-lingual phoneme mapping
+- Accent and dialect modeling
+- Code-switching capabilities
+
+The full Khaki system demonstrates these capabilities across 57 languages with accent preservation and cross-lingual voice transfer. Researchers interested in multilingual TTS can use BeigeTTS as a foundation for exploring these directions.
+
+## Ethical Considerations & License
+
+### Non-Commercial Use Only
+
+BeigeTTS is released under Creative Commons Attribution-NonCommercial 4.0 International (CC BY-NC 4.0). This means:
+- ✅ Research and academic use
+- ✅ Personal experimentation
+- ✅ Open-source contributions
+- ❌ Commercial applications
+- ❌ Production deployment
+- ❌ Monetized services
+
+For commercial licensing of our full Khaki system, contact partnerships@bland.ai
+
+### Responsible AI Guidelines
+
+- Always disclose AI-generated content
+- Do not use for impersonation without consent
+- Respect privacy and intellectual property
+- Consider potential biases in synthesis
+- Implement appropriate safety measures
+
+## Citation
+
+If you use BeigeTTS in your research, please cite:
+
+```bibtex
+@misc{blandai2024beigetss,
+  title={BeigeTTS: A Research Release for Large-Scale Neural Speech Synthesis},
+  author={BlandAI Research Team},
+  year={2024},
+  publisher={HuggingFace},
+  note={Scaled research version of the Khaki TTS system}
+}
+```
+
+## Related Work
+
+BeigeTTS builds upon:
+- Gemma (Google, 2024)
+- NeuCodec (Neuphonic, 2024)
+- Our production Khaki TTS system (not publicly available)
+
+## Future Research Releases
+
+We plan to release additional research artifacts:
+- **TaupeVC**: Voice conversion research model
+- **EcruTTS**: Lightweight edge deployment model
+- **SandAlign**: Forced alignment for TTS training
+
+## Support & Community
+
+- Research inquiries: research@bland.ai
+- Technical issues: GitHub Issues
+- Commercial licensing: partnerships@bland.ai
+
+## Acknowledgments
+
+We thank the open-source community and our research partners. Special recognition to:
+- Google for the Gemma foundation model
+- Neuphonic for NeuCodec
+- The broader TTS research community
+
+## Disclaimer
+
+BeigeTTS is a research release with no warranties. The full production capabilities described for Khaki are not available in this release. For production-grade TTS, please contact BlandAI for commercial licensing options.
+
+---
+
+*BeigeTTS is a research artifact from BlandAI's speech synthesis team. For production applications, explore our commercial Khaki TTS API at bland.ai*

added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "<end_of_speech>": 262146,
+  "<image_soft_token>": 262144,
+  "<start_of_speech>": 262145
+}

config.json

@@ -0,0 +1,95 @@
+{
+  "architectures": [
+    "GemmaForCausalLM"
+  ],
+  "boi_token_index": 255999,
+  "eoi_token_index": 256000,
+  "eos_token_id": 107,
+  "image_token_index": 262144,
+  "initializer_range": 0.02,
+  "mm_tokens_per_image": 256,
+  "model_type": "gemma",
+  "text_config": {
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "attn_logit_softcapping": null,
+    "cache_implementation": "hybrid",
+    "final_logit_softcapping": null,
+    "head_dim": 256,
+    "hidden_activation": "gelu_pytorch_tanh",
+    "hidden_size": 2560,
+    "initializer_range": 0.02,
+    "intermediate_size": 10240,
+    "max_position_embeddings": 131072,
+    "model_type": "gemma3_text",
+    "num_attention_heads": 8,
+    "num_hidden_layers": 34,
+    "num_key_value_heads": 4,
+    "query_pre_attn_scalar": 256,
+    "rms_norm_eps": 1e-06,
+    "rope_local_base_freq": 10000.0,
+    "rope_scaling": {
+      "factor": 8.0,
+      "rope_type": "linear"
+    },
+    "rope_theta": 1000000.0,
+    "sliding_window": 1024,
+    "sliding_window_pattern": 6,
+    "torch_dtype": "bfloat16",
+    "use_cache": true,
+    "vocab_size": 327690
+  },
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.51.3",
+  "use_cache": true,
+  "vision_config": {
+    "attention_dropout": 0.0,
+    "hidden_act": "gelu_pytorch_tanh",
+    "hidden_size": 1152,
+    "image_size": 896,
+    "intermediate_size": 4304,
+    "layer_norm_eps": 1e-06,
+    "model_type": "siglip_vision_model",
+    "num_attention_heads": 16,
+    "num_channels": 3,
+    "num_hidden_layers": 27,
+    "patch_size": 14,
+    "torch_dtype": "bfloat16",
+    "vision_use_head": false
+  },
+  "model_name": "BeigeTTS",
+  "model_variant": "research_release",
+  "production_model": "Khaki_TTS",
+  "vocab_size": 327690,
+  "hidden_size": 3584,
+  "intermediate_size": 14336,
+  "num_hidden_layers": 40,
+  "num_attention_heads": 16,
+  "num_key_value_heads": 8,
+  "head_dim": 256,
+  "hidden_act": "gelu_pytorch_tanh",
+  "max_position_embeddings": 8192,
+  "rms_norm_eps": 1e-06,
+  "pad_token_id": 0,
+  "bos_token_id": 106,
+  "tie_word_embeddings": true,
+  "rope_theta": 10000.0,
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "audio_config": {
+    "audio_start_token": 262145,
+    "audio_end_token": 262146,
+    "neucodec_offset": 262154,
+    "neucodec_vocab_size": 65536,
+    "sample_rate": 24000,
+    "codec": "neucodec",
+    "supported_languages": [
+      "en"
+    ],
+    "production_languages": 57,
+    "max_duration_seconds": 10,
+    "production_max_duration": "unlimited"
+  },
+  "license": "cc-by-nc-4.0",
+  "organization": "BlandAI"
+}

generation_config.json

@@ -0,0 +1,10 @@
+{
+  "temperature": 0.1,
+  "top_p": 0.97,
+  "do_sample": true,
+  "max_new_tokens": 500,
+  "eos_token_id": [
+    107,
+    262146
+  ]
+}

inference.py

@@ -0,0 +1,258 @@
+#!/usr/bin/env python3
+"""
+BeigeTTS - Standard Inference Script
+Research release for high-quality neural speech synthesis
+Based on BlandAI's production Khaki TTS system
+"""
+
+import torch
+import soundfile as sf
+import numpy as np
+from neucodec import NeuCodec
+from transformers import AutoModelForCausalLM, AutoTokenizer
+import argparse
+from typing import Optional, List, Tuple
+
+# ═══════════════════════════════════════════════════════════════════
+# Configuration
+# ═══════════════════════════════════════════════════════════════════
+
+class TTSConfig:
+    """Configuration for BeigeTTS inference"""
+    # Audio tokens
+    AUDIO_START_TOKEN = 262145
+    AUDIO_END_TOKEN = 262146
+    NEUCODEC_BASE_OFFSET = 262154
+    NEUCODEC_VOCABULARY_SIZE = 65536
+    AUDIO_TOKEN_MIN = NEUCODEC_BASE_OFFSET
+    AUDIO_TOKEN_MAX = NEUCODEC_BASE_OFFSET + NEUCODEC_VOCABULARY_SIZE
+
+    # Generation parameters
+    DEFAULT_TEMPERATURE = 0.1
+    DEFAULT_TOP_P = 0.97
+    DEFAULT_MAX_TOKENS = 500
+    SAMPLE_RATE = 24000
+
+    # Safety limits (full Khaki system supports unlimited duration)
+    MAX_AUDIO_TOKENS = 1000  # ~10 seconds
+
+# ═══════════════════════════════════════════════════════════════════
+# TTS Engine
+# ═══════════════════════════════════════════════════════════════════
+
+class BeigeTTS:
+    """BeigeTTS synthesis engine - research version of Khaki TTS"""
+
+    def __init__(self, model_path: str = "BlandAI/BeigeTTS", device: str = "auto"):
+        """Initialize BeigeTTS engine
+
+        Args:
+            model_path: HuggingFace model path or local directory
+            device: Device for inference ("auto", "cuda", "cpu")
+        """
+        self.config = TTSConfig()
+        self.device = self._setup_device(device)
+
+        print("Loading BeigeTTS model (research release)...")
+        self.model = AutoModelForCausalLM.from_pretrained(
+            model_path,
+            torch_dtype=torch.float16 if self.device.type == "cuda" else torch.float32,
+            device_map="auto" if device == "auto" else None,
+            trust_remote_code=True,
+        )
+        if device != "auto":
+            self.model = self.model.to(self.device)
+        self.model.eval()
+
+        print("Loading tokenizer...")
+        self.tokenizer = AutoTokenizer.from_pretrained(model_path)
+        if self.tokenizer.pad_token is None:
+            self.tokenizer.pad_token = self.tokenizer.eos_token
+
+        print("Loading NeuCodec...")
+        self.neucodec = NeuCodec.from_pretrained("neuphonic/neucodec")
+        self.neucodec.eval()
+        if self.device.type == "cuda":
+            self.neucodec = self.neucodec.to(self.device)
+
+    def _setup_device(self, device: str) -> torch.device:
+        """Setup compute device"""
+        if device == "auto":
+            return torch.device("cuda" if torch.cuda.is_available() else "cpu")
+        return torch.device(device)
+
+    def synthesize(
+        self,
+        text: str,
+        temperature: float = None,
+        top_p: float = None,
+        max_tokens: int = None,
+        voice_prompt: Optional[str] = None
+    ) -> Tuple[np.ndarray, int]:
+        """Synthesize speech from text
+
+        Note: Full Khaki system supports 57 languages, voice cloning,
+        and unlimited duration. This research release is English-only.
+
+        Args:
+            text: Input text to synthesize
+            temperature: Sampling temperature (lower = more deterministic)
+            top_p: Nucleus sampling parameter
+            max_tokens: Maximum tokens to generate
+            voice_prompt: Optional voice conditioning (limited in BeigeTTS)
+
+        Returns:
+            Tuple of (audio_array, sample_rate)
+        """
+        # Use defaults if not specified
+        temperature = temperature or self.config.DEFAULT_TEMPERATURE
+        top_p = top_p or self.config.DEFAULT_TOP_P
+        max_tokens = max_tokens or self.config.DEFAULT_MAX_TOKENS
+
+        # Format prompt
+        prompt = self._format_prompt(text, voice_prompt)
+
+        # Generate audio tokens
+        audio_tokens = self._generate_tokens(prompt, temperature, top_p, max_tokens)
+
+        if not audio_tokens:
+            raise ValueError("No audio tokens generated")
+
+        # Decode to audio
+        audio = self._decode_audio(audio_tokens)
+
+        return audio, self.config.SAMPLE_RATE
+
+    def _format_prompt(self, text: str, voice_prompt: Optional[str] = None) -> str:
+        """Format text into model prompt"""
+        # Basic conversational format
+        base_prompt = f"<start_of_turn>user\n{text}<end_of_turn>\n<start_of_turn>model\n<start_of_speech>"
+
+        # Add voice conditioning if provided (limited compared to Khaki)
+        if voice_prompt:
+            base_prompt = f"[Voice: {voice_prompt}]\n{base_prompt}"
+
+        return base_prompt
+
+    def _generate_tokens(
+        self,
+        prompt: str,
+        temperature: float,
+        top_p: float,
+        max_tokens: int
+    ) -> List[int]:
+        """Generate audio tokens from prompt"""
+
+        # Tokenize input
+        inputs = self.tokenizer(prompt, return_tensors="pt")
+        input_ids = inputs.input_ids.to(self.model.device)
+
+        print(f"Generating audio tokens (temp={temperature}, top_p={top_p})...")
+
+        # Generate
+        with torch.no_grad():
+            outputs = self.model.generate(
+                input_ids,
+                max_new_tokens=max_tokens,
+                temperature=temperature,
+                top_p=top_p,
+                do_sample=True,
+                pad_token_id=self.tokenizer.pad_token_id,
+                eos_token_id=[self.tokenizer.eos_token_id, self.config.AUDIO_END_TOKEN],
+            )
+
+        # Extract audio tokens
+        generated = outputs[0, input_ids.shape[1]:].cpu().tolist()
+        audio_tokens = []
+
+        for token_id in generated:
+            if self.config.AUDIO_TOKEN_MIN <= token_id < self.config.AUDIO_TOKEN_MAX:
+                audio_tokens.append(token_id - self.config.NEUCODEC_BASE_OFFSET)
+            elif token_id == self.config.AUDIO_END_TOKEN:
+                break
+
+            if len(audio_tokens) >= self.config.MAX_AUDIO_TOKENS:
+                print(f"Reached maximum audio length ({self.config.MAX_AUDIO_TOKENS} tokens)")
+                break
+
+        print(f"Generated {len(audio_tokens)} audio tokens")
+        return audio_tokens
+
+    def _decode_audio(self, audio_tokens: List[int]) -> np.ndarray:
+        """Decode audio tokens to waveform"""
+
+        # Prepare tokens for NeuCodec
+        audio_array = np.array(audio_tokens, dtype=np.int32)
+        audio_array = np.clip(audio_array, 0, self.config.NEUCODEC_VOCABULARY_SIZE - 1)
+
+        # NeuCodec expects [batch, channels, frames]
+        fsq_codes = torch.tensor(audio_array, dtype=torch.long)
+        fsq_codes = fsq_codes.unsqueeze(0).unsqueeze(1)  # [1, 1, frames]
+
+        if self.device.type == "cuda":
+            fsq_codes = fsq_codes.to(self.device)
+
+        print(f"Decoding audio (shape: {fsq_codes.shape})...")
+
+        # Decode
+        with torch.no_grad():
+            wav = self.neucodec.decode_code(fsq_codes).cpu()
+
+        # Extract waveform
+        if wav.dim() == 3:
+            wav = wav[0, 0]
+        elif wav.dim() == 2:
+            wav = wav[0]
+
+        wav = wav.numpy()
+
+        # Normalize
+        if np.abs(wav).max() > 0:
+            wav = wav / np.abs(wav).max() * 0.95
+
+        return wav
+
+# ═══════════════════════════════════════════════════════════════════
+# CLI Interface
+# ═══════════════════════════════════════════════════════════════════
+
+def main():
+    parser = argparse.ArgumentParser(description="BeigeTTS Synthesis (Research Release)")
+    parser.add_argument("text", type=str, help="Text to synthesize")
+    parser.add_argument("-o", "--output", type=str, default="output.wav", help="Output WAV file")
+    parser.add_argument("-m", "--model", type=str, default="BlandAI/BeigeTTS", help="Model path")
+    parser.add_argument("-t", "--temperature", type=float, default=0.1, help="Sampling temperature")
+    parser.add_argument("-p", "--top-p", type=float, default=0.97, help="Top-p sampling")
+    parser.add_argument("--max-tokens", type=int, default=500, help="Maximum tokens to generate")
+    parser.add_argument("--voice", type=str, help="Voice conditioning prompt")
+    parser.add_argument("--device", type=str, default="auto", help="Device (auto/cuda/cpu)")
+
+    args = parser.parse_args()
+
+    # Initialize TTS
+    tts = BeigeTTS(model_path=args.model, device=args.device)
+
+    # Synthesize
+    try:
+        audio, sr = tts.synthesize(
+            text=args.text,
+            temperature=args.temperature,
+            top_p=args.top_p,
+            max_tokens=args.max_tokens,
+            voice_prompt=args.voice
+        )
+
+        # Save audio
+        sf.write(args.output, audio, sr)
+        duration = len(audio) / sr
+        print(f"✅ Saved {duration:.1f}s of audio to {args.output}")
+        print("Note: This is a research release. Production Khaki TTS supports 57 languages and unlimited duration.")
+
+    except Exception as e:
+        print(f"❌ Synthesis failed: {e}")
+        return 1
+
+    return 0
+
+if __name__ == "__main__":
+    exit(main())

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf4e31125d94734cf8805be64bbb4d655dcab6b59072e1f3f39658a69abc88df
+size 4992407664

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:124a6e1d54ca791e234a0a20df24d6288bc1b32b005f5de0467dec43075e4a9f
+size 3943138080

model.safetensors.index.json

@@ -0,0 +1,890 @@
+{
+  "metadata": {
+    "total_size": 8935426784
+  },
+  "weight_map": {
+    "language_model.model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.0.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.0.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.0.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.0.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.1.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.1.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.1.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.1.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.10.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.10.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.10.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.10.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.11.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.11.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.11.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.11.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.12.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.12.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.12.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.12.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.13.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.13.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.13.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.13.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.13.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.13.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.13.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.13.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.13.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.13.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.14.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.14.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.14.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.14.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.14.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.14.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.14.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.14.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.14.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.14.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.14.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.14.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.14.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.15.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.15.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.15.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.15.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.15.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.15.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.15.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.15.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.15.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.15.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.15.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.15.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.15.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.16.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.16.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.16.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.16.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.16.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.16.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.16.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.16.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.16.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.16.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.16.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.16.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.16.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.17.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.17.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.17.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.17.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.17.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.17.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.17.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.17.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.17.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.17.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.17.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.17.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.17.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.18.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.18.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.18.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.18.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.18.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.18.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.18.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.18.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.18.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.18.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.18.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.18.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.18.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.19.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.19.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.19.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.19.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.19.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.19.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.19.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.19.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.19.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.19.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.19.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.19.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.19.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.2.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.2.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.2.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.2.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.20.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.20.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.20.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.20.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.20.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.20.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.20.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.20.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.20.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.20.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.21.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.21.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.21.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.21.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.22.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.22.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.22.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.22.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.23.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.23.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.23.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.23.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.24.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.24.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.24.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.24.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.25.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.25.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.25.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.25.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.26.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.26.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.26.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.26.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.27.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.27.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.27.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.27.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.28.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.28.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.28.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.28.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.28.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.28.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.29.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.29.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.29.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.29.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.3.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.3.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.3.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.3.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.30.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.30.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.30.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.30.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.31.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.31.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.31.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.31.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.32.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.32.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.32.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.32.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.32.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.32.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.32.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.32.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.32.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.32.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.32.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.32.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.32.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.33.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.33.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.33.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.33.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.33.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.33.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.33.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.33.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.33.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.33.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.33.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.33.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.33.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.4.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.4.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.4.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.4.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.5.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.5.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.5.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.5.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.6.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.6.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.6.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.6.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.7.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.7.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.7.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.7.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.8.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.8.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.8.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.8.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.9.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.9.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.9.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.9.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.norm.weight": "model-00002-of-00002.safetensors",
+    "multi_modal_projector.mm_input_projection_weight": "model-00001-of-00002.safetensors",
+    "multi_modal_projector.mm_soft_emb_norm.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.embeddings.patch_embedding.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.embeddings.patch_embedding.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.embeddings.position_embedding.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.layer_norm1.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.layer_norm1.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.layer_norm2.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.layer_norm2.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.layer_norm1.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.layer_norm1.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.layer_norm2.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.layer_norm2.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.layer_norm1.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.layer_norm1.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.layer_norm2.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.layer_norm2.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.layer_norm1.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.layer_norm1.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.layer_norm2.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.layer_norm2.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.layer_norm1.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.layer_norm1.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.layer_norm2.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.layer_norm2.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.layer_norm1.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.layer_norm1.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.layer_norm2.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.layer_norm2.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.layer_norm1.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.layer_norm1.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.layer_norm2.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.layer_norm2.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.layer_norm1.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.layer_norm1.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.layer_norm2.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.layer_norm2.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.layer_norm1.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.layer_norm1.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.layer_norm2.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.layer_norm2.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.layer_norm1.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.layer_norm1.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.layer_norm2.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.layer_norm2.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.layer_norm1.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.layer_norm1.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.layer_norm2.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.layer_norm2.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.layer_norm1.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.layer_norm1.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.layer_norm2.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.layer_norm2.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.layer_norm1.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.layer_norm1.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.layer_norm2.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.layer_norm2.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.layer_norm1.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.layer_norm1.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.layer_norm2.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.layer_norm2.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.layer_norm1.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.layer_norm1.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.layer_norm2.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.layer_norm2.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.layer_norm1.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.layer_norm1.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.layer_norm2.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.layer_norm2.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.layer_norm1.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.layer_norm1.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.layer_norm2.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.layer_norm2.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.24.layer_norm1.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.24.layer_norm1.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.24.layer_norm2.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.24.layer_norm2.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.24.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.24.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.24.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.24.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.24.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.24.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.24.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.24.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.24.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.25.layer_norm1.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.25.layer_norm1.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.25.layer_norm2.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.25.layer_norm2.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.25.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.25.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.25.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.25.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.25.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.25.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.25.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.25.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.25.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.25.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.26.layer_norm1.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.26.layer_norm1.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.26.layer_norm2.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.26.layer_norm2.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.26.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.26.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.26.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.26.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.26.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.26.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.26.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.26.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.26.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.26.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.26.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.26.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.layer_norm1.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.layer_norm1.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.layer_norm2.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.layer_norm2.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.layer_norm1.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.layer_norm1.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.layer_norm2.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.layer_norm2.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.layer_norm1.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.layer_norm1.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.layer_norm2.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.layer_norm2.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.layer_norm1.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.layer_norm1.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.layer_norm2.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.layer_norm2.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.layer_norm1.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.layer_norm1.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.layer_norm2.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.layer_norm2.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.layer_norm1.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.layer_norm1.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.layer_norm2.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.layer_norm2.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.layer_norm1.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.layer_norm1.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.layer_norm2.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.layer_norm2.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.post_layernorm.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.vision_model.post_layernorm.weight": "model-00001-of-00002.safetensors"
+  }
+}

requirements.txt

@@ -0,0 +1,9 @@
+torch>=2.0.0
+transformers>=4.35.0
+accelerate>=0.24.0
+soundfile>=0.12.0
+numpy>=1.24.0
+scipy>=1.10.0
+pyaudio>=0.2.11
+huggingface-hub>=0.19.0
+git+https://github.com/neuphonic/neucodec.git

special_tokens_map.json

@@ -0,0 +1,39 @@
+{
+  "additional_special_tokens": [
+    "<start_of_turn>",
+    "<end_of_turn>",
+    "<start_of_speech>",
+    "<end_of_speech>"
+  ],
+  "boi_token": "<start_of_image>",
+  "bos_token": {
+    "content": "<bos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eoi_token": "<end_of_image>",
+  "eos_token": {
+    "content": "<eos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "image_token": "<image_soft_token>",
+  "pad_token": {
+    "content": "<eos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

streaming_inference.py

@@ -0,0 +1,400 @@
+#!/usr/bin/env python3
+"""
+BeigeTTS - Streaming Inference
+Real-time streaming text-to-speech with chunk-based generation
+Research release derived from BlandAI's Khaki TTS system
+"""
+
+import torch
+import numpy as np
+import soundfile as sf
+from neucodec import NeuCodec
+from transformers import AutoModelForCausalLM, AutoTokenizer
+import threading
+import queue
+import time
+from typing import Optional, Generator, Tuple
+import pyaudio
+import argparse
+
+# ═══════════════════════════════════════════════════════════════════
+# Configuration
+# ═══════════════════════════════════════════════════════════════════
+
+class StreamingConfig:
+    """Configuration for streaming TTS"""
+    # Audio tokens
+    AUDIO_START_TOKEN = 262145
+    AUDIO_END_TOKEN = 262146
+    NEUCODEC_BASE_OFFSET = 262154
+    NEUCODEC_VOCABULARY_SIZE = 65536
+    AUDIO_TOKEN_MIN = NEUCODEC_BASE_OFFSET
+    AUDIO_TOKEN_MAX = NEUCODEC_BASE_OFFSET + NEUCODEC_VOCABULARY_SIZE
+
+    # Streaming parameters
+    CHUNK_SIZE = 50  # Audio tokens per chunk (~500ms)
+    BUFFER_SIZE = 3  # Number of chunks to buffer
+    SAMPLE_RATE = 24000
+
+    # Generation parameters
+    DEFAULT_TEMPERATURE = 0.1
+    DEFAULT_TOP_P = 0.97
+    MAX_TOTAL_TOKENS = 1000  # Limited in research release (Khaki: unlimited)
+
+# ═══════════════════════════════════════════════════════════════════
+# Streaming TTS Engine
+# ═══════════════════════════════════════════════════════════════════
+
+class StreamingBeigeTTS:
+    """Streaming BeigeTTS engine with chunk-based generation
+
+    Note: Production Khaki system achieves <50ms latency with 
+    advanced buffering and predictive generation.
+    """
+
+    def __init__(self, model_path: str = "BlandAI/BeigeTTS"):
+        """Initialize streaming TTS engine"""
+        self.config = StreamingConfig()
+        self.device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+
+        print("Initializing BeigeTTS streaming engine (research release)...")
+        print("Note: Khaki production system supports <50ms latency and 57 languages")
+
+        # Load models
+        self._load_models(model_path)
+
+        # Streaming state
+        self.audio_queue = queue.Queue(maxsize=self.config.BUFFER_SIZE)
+        self.generation_complete = threading.Event()
+        self.stop_generation = threading.Event()
+
+        # PyAudio for playback
+        self.audio_interface = None
+        self.audio_stream = None
+
+    def _load_models(self, model_path: str):
+        """Load BeigeTTS and NeuCodec models"""
+        print("Loading BeigeTTS model...")
+        self.model = AutoModelForCausalLM.from_pretrained(
+            model_path,
+            torch_dtype=torch.float16 if self.device.type == "cuda" else torch.float32,
+            device_map="auto",
+            trust_remote_code=True,
+        )
+        self.model.eval()
+
+        print("Loading tokenizer...")
+        self.tokenizer = AutoTokenizer.from_pretrained(model_path)
+        if self.tokenizer.pad_token is None:
+            self.tokenizer.pad_token = self.tokenizer.eos_token
+
+        print("Loading NeuCodec...")
+        self.neucodec = NeuCodec.from_pretrained("neuphonic/neucodec")
+        self.neucodec.eval()
+        if self.device.type == "cuda":
+            self.neucodec = self.neucodec.to(self.device)
+
+    def stream_synthesize(
+        self,
+        text: str,
+        temperature: float = None,
+        top_p: float = None,
+        play_audio: bool = False
+    ) -> Generator[np.ndarray, None, None]:
+        """Stream synthesize speech from text
+
+        Args:
+            text: Input text to synthesize
+            temperature: Sampling temperature
+            top_p: Nucleus sampling parameter
+            play_audio: Whether to play audio in real-time
+
+        Yields:
+            Audio chunks as numpy arrays
+        """
+        temperature = temperature or self.config.DEFAULT_TEMPERATURE
+        top_p = top_p or self.config.DEFAULT_TOP_P
+
+        # Reset state
+        self.generation_complete.clear()
+        self.stop_generation.clear()
+
+        # Start generation thread
+        generation_thread = threading.Thread(
+            target=self._generation_worker,
+            args=(text, temperature, top_p)
+        )
+        generation_thread.start()
+
+        # Start playback if requested
+        if play_audio:
+            playback_thread = threading.Thread(target=self._playback_worker)
+            playback_thread.start()
+
+        # Yield audio chunks
+        try:
+            while not self.generation_complete.is_set() or not self.audio_queue.empty():
+                try:
+                    audio_chunk = self.audio_queue.get(timeout=0.1)
+                    yield audio_chunk
+                except queue.Empty:
+                    continue
+        finally:
+            # Cleanup
+            self.stop_generation.set()
+            generation_thread.join()
+            if play_audio:
+                playback_thread.join()
+
+    def _generation_worker(self, text: str, temperature: float, top_p: float):
+        """Worker thread for token generation"""
+        try:
+            # Format prompt
+            prompt = f"<start_of_turn>user\n{text}<end_of_turn>\n<start_of_turn>model\n<start_of_speech>"
+
+            # Tokenize
+            inputs = self.tokenizer(prompt, return_tensors="pt")
+            input_ids = inputs.input_ids.to(self.model.device)
+
+            # Initialize generation
+            past_key_values = None
+            current_ids = input_ids
+            audio_token_buffer = []
+            total_generated = 0
+
+            print("Starting streaming generation...")
+            print("(BeigeTTS research mode - Khaki production offers superior latency)")
+
+            with torch.no_grad():
+                while total_generated < self.config.MAX_TOTAL_TOKENS and not self.stop_generation.is_set():
+                    # Generate next token
+                    outputs = self.model(
+                        input_ids=current_ids,
+                        past_key_values=past_key_values,
+                        use_cache=True
+                    )
+
+                    logits = outputs.logits[:, -1, :]
+                    past_key_values = outputs.past_key_values
+
+                    # Sample next token
+                    if temperature > 0:
+                        probs = torch.nn.functional.softmax(logits / temperature, dim=-1)
+
+                        # Apply top-p filtering
+                        if top_p < 1.0:
+                            sorted_probs, sorted_indices = torch.sort(probs, descending=True)
+                            cumulative_probs = torch.cumsum(sorted_probs, dim=-1)
+
+                            # Remove tokens with cumulative probability above threshold
+                            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
+                            )
+                            probs[indices_to_remove] = 0
+                            probs = probs / probs.sum(dim=-1, keepdim=True)
+
+                        next_token = torch.multinomial(probs, num_samples=1)
+                    else:
+                        next_token = torch.argmax(logits, dim=-1, keepdim=True)
+
+                    token_id = next_token.item()
+
+                    # Check for end token
+                    if token_id == self.config.AUDIO_END_TOKEN or token_id == self.tokenizer.eos_token_id:
+                        break
+
+                    # Process audio token
+                    if self.config.AUDIO_TOKEN_MIN <= token_id < self.config.AUDIO_TOKEN_MAX:
+                        audio_token_buffer.append(token_id - self.config.NEUCODEC_BASE_OFFSET)
+
+                        # Decode and send chunk
+                        if len(audio_token_buffer) >= self.config.CHUNK_SIZE:
+                            audio_chunk = self._decode_chunk(audio_token_buffer[:self.config.CHUNK_SIZE])
+                            self.audio_queue.put(audio_chunk)
+                            audio_token_buffer = audio_token_buffer[self.config.CHUNK_SIZE:]
+                            print(f"Streamed chunk {total_generated // self.config.CHUNK_SIZE}")
+
+                    # Prepare for next iteration
+                    current_ids = next_token
+                    total_generated += 1
+
+            # Process remaining tokens
+            if audio_token_buffer:
+                audio_chunk = self._decode_chunk(audio_token_buffer)
+                self.audio_queue.put(audio_chunk)
+
+            print(f"Generation complete. Total tokens: {total_generated}")
+
+        except Exception as e:
+            print(f"Generation error: {e}")
+        finally:
+            self.generation_complete.set()
+
+    def _decode_chunk(self, audio_tokens: list) -> np.ndarray:
+        """Decode a chunk of audio tokens"""
+        # Prepare tokens
+        audio_array = np.array(audio_tokens, dtype=np.int32)
+        audio_array = np.clip(audio_array, 0, self.config.NEUCODEC_VOCABULARY_SIZE - 1)
+
+        # Format for NeuCodec
+        fsq_codes = torch.tensor(audio_array, dtype=torch.long)
+        fsq_codes = fsq_codes.unsqueeze(0).unsqueeze(1)
+
+        if self.device.type == "cuda":
+            fsq_codes = fsq_codes.to(self.device)
+
+        # Decode
+        with torch.no_grad():
+            wav = self.neucodec.decode_code(fsq_codes).cpu()
+
+        # Extract waveform
+        if wav.dim() == 3:
+            wav = wav[0, 0]
+        elif wav.dim() == 2:
+            wav = wav[0]
+
+        wav = wav.numpy()
+
+        # Normalize
+        if np.abs(wav).max() > 0:
+            wav = wav / np.abs(wav).max() * 0.95
+
+        return wav
+
+    def _playback_worker(self):
+        """Worker thread for audio playback"""
+        try:
+            # Initialize PyAudio
+            self.audio_interface = pyaudio.PyAudio()
+            self.audio_stream = self.audio_interface.open(
+                format=pyaudio.paFloat32,
+                channels=1,
+                rate=self.config.SAMPLE_RATE,
+                output=True
+            )
+
+            print("Starting audio playback...")
+
+            while not self.generation_complete.is_set() or not self.audio_queue.empty():
+                try:
+                    audio_chunk = self.audio_queue.get(timeout=0.1)
+                    self.audio_stream.write(audio_chunk.astype(np.float32).tobytes())
+                except queue.Empty:
+                    continue
+
+        except Exception as e:
+            print(f"Playback error: {e}")
+        finally:
+            if self.audio_stream:
+                self.audio_stream.stop_stream()
+                self.audio_stream.close()
+            if self.audio_interface:
+                self.audio_interface.terminate()
+
+# ═══════════════════════════════════════════════════════════════════
+# Advanced Streaming Features
+# ═══════════════════════════════════════════════════════════════════
+
+class AdaptiveBeigeTTS(StreamingBeigeTTS):
+    """Advanced streaming with adaptive chunk sizing
+
+    Note: This demonstrates research concepts. Production Khaki system
+    includes predictive buffering, voice activity detection, and 
+    neural vocoder post-processing for superior quality.
+    """
+
+    def __init__(self, model_path: str = "BlandAI/BeigeTTS"):
+        super().__init__(model_path)
+
+        # Adaptive streaming parameters
+        self.min_chunk_size = 25  # Minimum tokens per chunk
+        self.max_chunk_size = 100  # Maximum tokens per chunk
+        self.target_latency_ms = 200  # Target latency in milliseconds
+        self.generation_speed_ema = 0.0
+        self.ema_alpha = 0.1
+
+    def adaptive_stream(
+        self,
+        text: str,
+        quality_priority: float = 0.5  # 0 = speed, 1 = quality
+    ) -> Generator[np.ndarray, None, None]:
+        """Stream with adaptive chunk sizing based on generation speed
+
+        Args:
+            text: Input text
+            quality_priority: Balance between speed and quality (0-1)
+
+        Yields:
+            Adaptively sized audio chunks
+        """
+        # Adjust parameters based on priority
+        temperature = 0.05 + (0.15 * quality_priority)
+        top_p = 0.9 + (0.08 * quality_priority)
+
+        # Calculate adaptive chunk size
+        chunk_size = int(self.min_chunk_size + 
+                        (self.max_chunk_size - self.min_chunk_size) * quality_priority)
+
+        print(f"Adaptive streaming: chunk_size={chunk_size}, temp={temperature:.2f}, top_p={top_p:.2f}")
+        print("(Khaki production includes neural enhancement for optimal quality)")
+
+        # Override chunk size temporarily
+        original_chunk = self.config.CHUNK_SIZE
+        self.config.CHUNK_SIZE = chunk_size
+
+        try:
+            yield from self.stream_synthesize(text, temperature, top_p)
+        finally:
+            self.config.CHUNK_SIZE = original_chunk
+
+# ═══════════════════════════════════════════════════════════════════
+# CLI Interface
+# ═══════════════════════════════════════════════════════════════════
+
+def main():
+    parser = argparse.ArgumentParser(description="BeigeTTS Streaming (Research Release)")
+    parser.add_argument("text", type=str, help="Text to synthesize")
+    parser.add_argument("-o", "--output", type=str, help="Output WAV file (optional)")
+    parser.add_argument("-m", "--model", type=str, default="BlandAI/BeigeTTS", help="Model path")
+    parser.add_argument("--play", action="store_true", help="Play audio in real-time")
+    parser.add_argument("--adaptive", action="store_true", help="Use adaptive streaming")
+    parser.add_argument("--quality", type=float, default=0.5, help="Quality priority (0-1)")
+
+    args = parser.parse_args()
+
+    print("BeigeTTS Streaming - Research Release")
+    print("Production Khaki TTS: <50ms latency, 57 languages, unlimited duration")
+    print("-" * 60)
+
+    # Initialize TTS
+    if args.adaptive:
+        tts = AdaptiveBeigeTTS(model_path=args.model)
+        stream_gen = tts.adaptive_stream(args.text, quality_priority=args.quality)
+    else:
+        tts = StreamingBeigeTTS(model_path=args.model)
+        stream_gen = tts.stream_synthesize(args.text, play_audio=args.play)
+
+    # Collect audio chunks
+    audio_chunks = []
+    print("Streaming audio generation...")
+
+    for i, chunk in enumerate(stream_gen):
+        audio_chunks.append(chunk)
+        print(f"  Received chunk {i+1} ({len(chunk)/tts.config.SAMPLE_RATE:.2f}s)")
+
+    # Save if output specified
+    if args.output and audio_chunks:
+        full_audio = np.concatenate(audio_chunks)
+        sf.write(args.output, full_audio, tts.config.SAMPLE_RATE)
+        duration = len(full_audio) / tts.config.SAMPLE_RATE
+        print(f"\n✅ Saved {duration:.1f}s of audio to {args.output}")
+
+    print("\n✨ Streaming complete!")
+    print("For commercial use and advanced features, contact partnerships@bland.ai")
+
+if __name__ == "__main__":
+    main()

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1cfdfbadc2cef8f5558377a4bf7ad30da3c6af4618164efdbb4c96ea31e72cd1
+size 33384954

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1299c11d7cf632ef3b4e11937501358ada021bbdf7c47638d13c0ee982f2e79c
+size 4689074