commit 195fe3574d1d229414ef13d8d8fb68f967fdf611
Author: ModelHub XC <noreply@modelhub.org.cn>
Date:   Sun Jun 21 18:35:18 2026 +0800

    初始化项目，由ModelHub XC社区提供模型
    
    Model: emylton/arogya-ai-full
    Source: Original Platform

diff --git a/.gitattributes b/.gitattributes
new file mode 100644
index 0000000..7196d6f
--- /dev/null
+++ b/.gitattributes
@@ -0,0 +1,39 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz 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
+arogya-ai-q4.gguf filter=lfs diff=lfs merge=lfs -text
+arogya-ai-q8.gguf filter=lfs diff=lfs merge=lfs -text
+arogya-ai-fp16.gguf filter=lfs diff=lfs merge=lfs -text
diff --git a/Modelfile b/Modelfile
new file mode 100644
index 0000000..5124cb0
--- /dev/null
+++ b/Modelfile
@@ -0,0 +1,14 @@
+FROM ./arogya-ai-q4.gguf
+
+PARAMETER temperature 0.7
+PARAMETER top_p 0.9
+PARAMETER top_k 40
+PARAMETER num_ctx 8192
+
+SYSTEM """Saya adalah Arogya AI, asisten kesehatan untuk Maluku Tenggara."""
+
+TEMPLATE """### Instruction:
+{{ .Prompt }}
+
+### Response:
+"""
diff --git a/README.md b/README.md
new file mode 100644
index 0000000..07f19ef
--- /dev/null
+++ b/README.md
@@ -0,0 +1,364 @@
+---
+language:
+- id
+- en
+license: llama3
+library_name: transformers
+pipeline_tag: text-generation
+tags:
+- healthcare
+- indonesia
+- maluku-tenggara
+- disease-prediction
+- llama-3
+- medical-ai
+base_model: meta-llama/Meta-Llama-3-8B
+datasets:
+- custom
+---
+
+# Arogya AI - Full Model
+
+**Arogya** (Sanskrit: "perfect health") adalah model AI kesehatan yang dilatih khusus untuk analisis dan prediksi data kesehatan di Kabupaten Maluku Tenggara, Indonesia.
+
+🔗 **GitHub Repository**: https://github.com/Rafael2022-prog/arogya-ai
+
+📄 **Research Paper**: 
+- [English](https://github.com/Rafael2022-prog/arogya-ai/blob/main/PAPER_AROGYA_EN.md)
+- [Indonesian](https://github.com/Rafael2022-prog/arogya-ai/blob/main/PAPER_AROGYA_ID.md)
+
+🎯 **LoRA Adapter Version**: [emylton/arogya-health-model](https://huggingface.co/emylton/arogya-health-model) (27 MB)
+
+---
+
+## Model Description
+
+Ini adalah **full merged model** (Llama 3 8B + LoRA adapter) yang siap pakai tanpa perlu download base model terpisah.
+
+### Key Features
+
+- **Ready to use**: Tidak perlu base model Llama 3
+- **Ollama compatible**: Bisa langsung import ke Ollama
+- **Specialized**: Dilatih dengan 10,000+ data kesehatan real dari Maluku Tenggara
+- **Multi-disease**: Mendukung 7 penyakit utama (DBD, ISPA, Malaria, Diare, TB, Stunting, Pneumonia)
+- **Geographic coverage**: 9 kecamatan di Kabupaten Maluku Tenggara
+
+### Training Data
+
+Model dilatih menggunakan 10,000+ records dari 4 sumber data:
+1. **LAMPIRAN PROFIL MALUKU TENGGARA 2023** (Excel)
+2. **LAMPIRAN PROFIL KESEHATAN MALRA 2024** (Excel)
+3. **RENJA 2026 DINKES MALRA** (PDF - 24 pages, 14 tables)
+4. **RENSTRA DINAS KESEHATAN 2025-2029** (PDF - 97 pages, 74 tables)
+
+Data mencakup 169 indikator kesehatan dari tahun 2020-2029.
+
+### Model Details
+
+- **Base Model**: Meta-Llama-3-8B
+- **Fine-tuning Method**: LoRA (r=16, alpha=32)
+- **Training**: 3 epochs, batch_size=4, learning_rate=2e-4
+- **Model Size**: ~16 GB (FP16)
+- **Parameters**: 8 billion
+- **Context Length**: 8192 tokens
+- **Language**: Indonesian & English
+
+---
+
+## Quick Start
+
+### Python (Transformers)
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+import torch
+
+# Load model
+model = AutoModelForCausalLM.from_pretrained(
+    "emylton/arogya-ai-full",
+    torch_dtype=torch.float16,
+    device_map="auto"
+)
+
+tokenizer = AutoTokenizer.from_pretrained("emylton/arogya-ai-full")
+
+# Generate prediction
+prompt = """Prediksi kasus DBD di Kei Kecil untuk bulan depan berdasarkan data:
+- Bulan ini: 45 kasus
+- Bulan lalu: 38 kasus
+- Curah hujan: tinggi
+- Musim: penghujan"""
+
+inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
+outputs = model.generate(
+    **inputs,
+    max_new_tokens=200,
+    temperature=0.7,
+    top_p=0.9,
+    do_sample=True
+)
+
+print(tokenizer.decode(outputs[0], skip_special_tokens=True))
+```
+
+### Ollama
+
+```bash
+# 1. Download model
+huggingface-cli download emylton/arogya-ai-full --local-dir ./arogya-full
+
+# 2. Create Modelfile
+cat > Modelfile << EOF
+FROM ./arogya-full
+PARAMETER temperature 0.7
+PARAMETER top_p 0.9
+PARAMETER num_ctx 8192
+SYSTEM "Saya Arogya AI, asisten kesehatan untuk Kabupaten Maluku Tenggara. Saya dapat membantu analisis data kesehatan, prediksi penyakit, dan rekomendasi intervensi untuk 7 penyakit utama: DBD, ISPA, Malaria, Diare, TB, Stunting, dan Pneumonia."
+EOF
+
+# 3. Import to Ollama
+ollama create arogya-ai -f Modelfile
+
+# 4. Run
+ollama run arogya-ai "Prediksi kasus DBD di Kei Kecil"
+```
+
+---
+
+## Use Cases
+
+### 1. Disease Prediction
+```python
+prompt = "Prediksi kasus Malaria di Kei Besar bulan Maret 2026"
+```
+
+### 2. Trend Analysis
+```python
+prompt = "Analisis trend kasus ISPA di Maluku Tenggara 2023-2024"
+```
+
+### 3. Intervention Recommendations
+```python
+prompt = "Rekomendasi intervensi untuk menurunkan kasus Stunting di Kei Kecil"
+```
+
+### 4. Resource Allocation
+```python
+prompt = "Alokasi sumber daya kesehatan untuk program TB di 9 kecamatan"
+```
+
+### 5. Risk Assessment
+```python
+prompt = "Penilaian risiko outbreak DBD di musim hujan"
+```
+
+---
+
+## Supported Diseases
+
+1. **DBD** (Demam Berdarah Dengue)
+2. **ISPA** (Infeksi Saluran Pernapasan Akut)
+3. **Malaria**
+4. **Diare**
+5. **TB** (Tuberkulosis)
+6. **Stunting**
+7. **Pneumonia**
+
+## Geographic Coverage
+
+9 Kecamatan di Kabupaten Maluku Tenggara:
+- Kei Kecil
+- Kei Besar
+- Kei Besar Selatan
+- Kei Besar Utara Timur
+- Kei Besar Utara Barat
+- Hoat Sorbay
+- Manyeuw
+- Kei Kecil Timur
+- Kei Kecil Barat
+
+---
+
+## Training Details
+
+### Hyperparameters
+
+```python
+{
+    "lora_r": 16,
+    "lora_alpha": 32,
+    "lora_dropout": 0.05,
+    "learning_rate": 2e-4,
+    "num_train_epochs": 3,
+    "per_device_train_batch_size": 4,
+    "gradient_accumulation_steps": 4,
+    "warmup_steps": 100,
+    "max_seq_length": 2048,
+    "optimizer": "paged_adamw_8bit"
+}
+```
+
+### Training Infrastructure
+
+- **Platform**: Google Colab Pro
+- **GPU**: NVIDIA A100 (40GB)
+- **Training Time**: ~6 hours
+- **Framework**: Transformers + PEFT + bitsandbytes
+
+### Data Processing
+
+Data diproses melalui pipeline:
+1. **Excel Extraction**: Pandas untuk structured data
+2. **PDF Extraction**: PyMuPDF + tabula untuk tables
+3. **Data Cleaning**: Normalisasi, deduplication
+4. **Prompt Engineering**: Template khusus untuk health data
+5. **Train/Val Split**: 90/10
+
+---
+
+## Limitations
+
+⚠️ **Important Limitations:**
+
+1. **Geographic Specificity**: Model dilatih khusus untuk Maluku Tenggara, mungkin kurang akurat untuk daerah lain
+2. **Disease Coverage**: Hanya 7 penyakit utama, tidak mencakup semua kondisi kesehatan
+3. **Data Timeframe**: Data training dari 2020-2024, prediksi jangka panjang mungkin kurang akurat
+4. **Not Medical Advice**: Model ini untuk analisis data, bukan pengganti konsultasi medis profesional
+5. **Language**: Optimal untuk Bahasa Indonesia, kemampuan bahasa lain terbatas
+6. **Hallucination**: Seperti LLM lainnya, model dapat menghasilkan informasi yang tidak akurat
+
+---
+
+## Ethical Considerations
+
+### Intended Use
+
+✅ **Recommended:**
+- Analisis data kesehatan populasi
+- Perencanaan program kesehatan
+- Alokasi sumber daya
+- Penelitian epidemiologi
+- Edukasi kesehatan masyarakat
+
+❌ **Not Recommended:**
+- Diagnosis medis individual
+- Keputusan klinis tanpa verifikasi profesional
+- Pengganti tenaga kesehatan
+- Situasi darurat medis
+
+### Privacy & Security
+
+- Model tidak menyimpan data personal
+- Tidak ada identitas pasien dalam training data
+- Semua data diagregasi di level populasi
+- Ikuti regulasi kesehatan lokal saat menggunakan
+
+---
+
+## Performance
+
+### Evaluation Metrics
+
+Model dievaluasi pada validation set (10% dari data):
+
+- **Perplexity**: 2.34
+- **Loss**: 0.85
+- **Accuracy** (classification tasks): 87.3%
+- **F1 Score**: 0.86
+
+### Comparison
+
+| Model | Size | Accuracy | Use Case |
+|-------|------|----------|----------|
+| Base Llama 3 8B | 16 GB | 45.2% | General |
+| Arogya (LoRA) | 27 MB | 87.3% | Health (need base) |
+| Arogya (Full) | 16 GB | 87.3% | Health (standalone) |
+
+---
+
+## Model Versions
+
+### Full Model vs LoRA Adapter
+
+| Aspect | LoRA Adapter | Full Model |
+|--------|--------------|------------|
+| **Repository** | [emylton/arogya-health-model](https://huggingface.co/emylton/arogya-health-model) | [emylton/arogya-ai-full](https://huggingface.co/emylton/arogya-ai-full) |
+| **Size** | 27 MB | ~16 GB |
+| **Download Time** | 1 min | 10-30 min |
+| **Requires Base Model** | ✅ Yes (Llama 3 8B) | ❌ No |
+| **Ollama Compatible** | ❌ No | ✅ Yes |
+| **Best For** | Developers/Researchers | End Users |
+
+**Recommendation**: 
+- Use **LoRA adapter** if you already have Llama 3 8B or want to experiment
+- Use **Full model** for production deployment or Ollama usage
+
+---
+
+## Citation
+
+If you use this model in your research, please cite:
+
+```bibtex
+@software{arogya_ai_2024,
+  title = {Arogya AI: Fine-tuned Language Model for Health Data Analysis in Maluku Tenggara},
+  author = {Rafael and Contributors},
+  year = {2024},
+  url = {https://huggingface.co/emylton/arogya-ai-full},
+  note = {Based on Meta-Llama-3-8B}
+}
+```
+
+**Research Paper**:
+```bibtex
+@article{arogya_paper_2024,
+  title = {Arogya AI: Implementasi Large Language Model untuk Analisis dan Prediksi Data Kesehatan di Kabupaten Maluku Tenggara},
+  author = {Rafael and Contributors},
+  year = {2024},
+  url = {https://github.com/Rafael2022-prog/arogya-ai}
+}
+```
+
+---
+
+## License
+
+This model is based on Meta-Llama-3-8B and follows the [Llama 3 Community License](https://llama.meta.com/llama3/license/).
+
+**Additional Terms:**
+- Model dapat digunakan untuk tujuan penelitian dan komersial
+- Wajib mencantumkan attribution
+- Tidak untuk tujuan yang merugikan atau melanggar hukum
+- Ikuti regulasi kesehatan setempat
+
+---
+
+## Acknowledgments
+
+- **Meta AI** untuk Llama 3 base model
+- **Dinas Kesehatan Kabupaten Maluku Tenggara** untuk data kesehatan
+- **Hugging Face** untuk platform dan tools
+- **Google Colab** untuk training infrastructure
+
+---
+
+## Contact & Support
+
+- **GitHub Issues**: https://github.com/Rafael2022-prog/arogya-ai/issues
+- **Model Repository**: https://huggingface.co/emylton/arogya-ai-full
+- **Documentation**: https://github.com/Rafael2022-prog/arogya-ai
+
+---
+
+## Updates
+
+### Version 1.0 (2024)
+- Initial release
+- 10,000+ training samples
+- 7 diseases coverage
+- 9 sub-districts coverage
+- Full model deployment
+
+---
+
+**Built with ❤️ for better healthcare in Maluku Tenggara**
diff --git a/arogya-ai-fp16.gguf b/arogya-ai-fp16.gguf
new file mode 100644
index 0000000..250f51b
--- /dev/null
+++ b/arogya-ai-fp16.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2df1775adcfe7a8b04cd24f64834b7c346854a1a6339647bf2f2aa820d97d7d8
+size 16068890848
diff --git a/arogya-ai-q4.gguf b/arogya-ai-q4.gguf
new file mode 100644
index 0000000..08e273d
--- /dev/null
+++ b/arogya-ai-q4.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0880c752337e78f6beb053fc3768ba6316c6ff723d5492ffad5b80f295041637
+size 4920733920
diff --git a/arogya-ai-q8.gguf b/arogya-ai-q8.gguf
new file mode 100644
index 0000000..810aa90
--- /dev/null
+++ b/arogya-ai-q8.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7fdc3b2e0ddc0cbf0baea62aca8f5e9d398d44942d9a0ec83d5343b0b94eb389
+size 8540770528
diff --git a/config.json b/config.json
new file mode 100644
index 0000000..a9c6f17
--- /dev/null
+++ b/config.json
@@ -0,0 +1,32 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "dtype": "float16",
+  "eos_token_id": 128001,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 8192,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "pad_token_id": null,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_parameters": {
+    "rope_theta": 500000.0,
+    "rope_type": "default"
+  },
+  "tie_word_embeddings": false,
+  "transformers_version": "5.0.0",
+  "use_cache": true,
+  "vocab_size": 128256
+}
diff --git a/generation_config.json b/generation_config.json
new file mode 100644
index 0000000..844a65b
--- /dev/null
+++ b/generation_config.json
@@ -0,0 +1,9 @@
+{
+  "bos_token_id": 128000,
+  "do_sample": true,
+  "eos_token_id": 128001,
+  "max_length": 4096,
+  "temperature": 0.6,
+  "top_p": 0.9,
+  "transformers_version": "5.0.0"
+}
diff --git a/model-00001-of-00009.safetensors b/model-00001-of-00009.safetensors
new file mode 100644
index 0000000..7a5cb92
--- /dev/null
+++ b/model-00001-of-00009.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4f15e64381b74dcb7857c03cbfb62806534f7582ab885c738980a12e5b78989
+size 1050673280
diff --git a/model-00002-of-00009.safetensors b/model-00002-of-00009.safetensors
new file mode 100644
index 0000000..7fbb48f
--- /dev/null
+++ b/model-00002-of-00009.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f282377d705f6a8214f52e9ecaafd22eadaae153b9a72f1d3f22ae591764a775
+size 1923131656
diff --git a/model-00003-of-00009.safetensors b/model-00003-of-00009.safetensors
new file mode 100644
index 0000000..32df56d
--- /dev/null
+++ b/model-00003-of-00009.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d5fe9f22b671b2ec0162ba14643a0d634a0fd8685cb1b4f96ae56ec10f81366
+size 1979781384
diff --git a/model-00004-of-00009.safetensors b/model-00004-of-00009.safetensors
new file mode 100644
index 0000000..2dea0bd
--- /dev/null
+++ b/model-00004-of-00009.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f81c2cda28007d411a620a0a7382f035601a53d9b482c44b98a7bc0344efdbde
+size 1946243904
diff --git a/model-00005-of-00009.safetensors b/model-00005-of-00009.safetensors
new file mode 100644
index 0000000..a2d7ce5
--- /dev/null
+++ b/model-00005-of-00009.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ea9515fd5acad8457ae718de90279a549824c20defd2d4636501e96ba2695b3
+size 1979781416
diff --git a/model-00006-of-00009.safetensors b/model-00006-of-00009.safetensors
new file mode 100644
index 0000000..3c949e9
--- /dev/null
+++ b/model-00006-of-00009.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ddc9f6971621c8be74fd8016639b93ff953ffa9e6621ea661cfd719a3c104d4
+size 1946243952
diff --git a/model-00007-of-00009.safetensors b/model-00007-of-00009.safetensors
new file mode 100644
index 0000000..d99a0fa
--- /dev/null
+++ b/model-00007-of-00009.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a58540b81ad3dd82d5bf076ae59a1ee983d9b3127180380428ef979ca6a5165
+size 1979781416
diff --git a/model-00008-of-00009.safetensors b/model-00008-of-00009.safetensors
new file mode 100644
index 0000000..45447dd
--- /dev/null
+++ b/model-00008-of-00009.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e3a08640994d46d81c166468b740e2ce129f42077c74d41d16c594d8ec87345
+size 1946243952
diff --git a/model-00009-of-00009.safetensors b/model-00009-of-00009.safetensors
new file mode 100644
index 0000000..2eca6f2
--- /dev/null
+++ b/model-00009-of-00009.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9fff628027311e7c6362fc7784275f5f4caa1bf5874a09b64ec6f14837acb12a
+size 1308675104
diff --git a/model.safetensors.index.json b/model.safetensors.index.json
new file mode 100644
index 0000000..d78ea7b
--- /dev/null
+++ b/model.safetensors.index.json
@@ -0,0 +1,299 @@
+{
+  "metadata": {
+    "total_parameters": 8030261248,
+    "total_size": 16060522496
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00001-of-00009.safetensors",
+    "model.embed_tokens.weight": "model-00002-of-00009.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00002-of-00009.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00002-of-00009.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00002-of-00009.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00009-of-00009.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00009-of-00009.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00009-of-00009.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00009-of-00009.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00009-of-00009.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00009-of-00009.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00009-of-00009.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00009-of-00009.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00009-of-00009.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00009-of-00009.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00009-of-00009.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00009-of-00009.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00009-of-00009.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00009-of-00009.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00009-of-00009.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00009-of-00009.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00009-of-00009.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00009-of-00009.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00009-of-00009.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00009-of-00009.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00009-of-00009.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00009-of-00009.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00009-of-00009.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00009-of-00009.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00009-of-00009.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00009-of-00009.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
+    "model.norm.weight": "model-00009-of-00009.safetensors"
+  }
+}
diff --git a/tokenizer.json b/tokenizer.json
new file mode 100644
index 0000000..be3984c
--- /dev/null
+++ b/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ad8c63d7a9f677a4e93e21e95765331a1bf4cd607714c0ea80a31b988657a2b
+size 17210241
diff --git a/tokenizer_config.json b/tokenizer_config.json
new file mode 100644
index 0000000..9c1e980
--- /dev/null
+++ b/tokenizer_config.json
@@ -0,0 +1,21 @@
+{
+  "backend": "tokenizers",
+  "bos_token": "<|begin_of_text|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|end_of_text|>",
+  "is_local": false,
+  "max_length": 512,
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_to_multiple_of": null,
+  "pad_token": "<|end_of_text|>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "stride": 0,
+  "tokenizer_class": "TokenizersBackend",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first"
+}