Upload folder using huggingface_hub

README.md

@@ -0,0 +1,65 @@
+---
+license: cc-by-nc-4.0
+base_model: athirdpath/Harmonia-20B
+tags:
+- generated_from_trainer
+model-index:
+- name: lora
+  results: []
+---
+This was mostly a test to see what the loss/eval looked like when training on top of Harmonia, and in that sense it was a sterling success, without the "jitter" I experienced training on top of Nethena 20b.
+Quick testing shows a bit of derpiness, but a nice conversational flow. Overall, this will be helpful in developing additional 20b merges.
+
+
+[<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl)
+# NOTES
+
+This model is a fine-tuned version of [athirdpath/Harmonia-20B](https://huggingface.co/athirdpath/Harmonia-20B) on the HF No Robots dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.4881
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 3.5e-05
+- train_batch_size: 3
+- eval_batch_size: 3
+- seed: 42
+- gradient_accumulation_steps: 3
+- total_train_batch_size: 9
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 10
+- num_epochs: 3
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 1.5598        | 0.55  | 50   | 1.5816          |
+| 1.5384        | 1.08  | 100  | 1.5146          |
+| 1.5362        | 1.64  | 150  | 1.4972          |
+| 1.4234        | 2.17  | 200  | 1.4902          |
+| 1.4678        | 2.72  | 250  | 1.4881          |
+
+
+### Framework versions
+
+- Transformers 4.35.2
+- Pytorch 2.0.1+cu118
+- Datasets 2.15.0
+- Tokenizers 0.15.0

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "[PAD]": 32000
+}

config.json

@@ -0,0 +1,40 @@
+{
+    "_name_or_path": "athirdpath/Harmonia-20B",
+    "architectures": [
+        "LlamaForCausalLM"
+    ],
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "bos_token_id": 1,
+    "eos_token_id": 2,
+    "hidden_act": "silu",
+    "hidden_size": 5120,
+    "initializer_range": 0.02,
+    "intermediate_size": 13824,
+    "max_position_embeddings": 4096,
+    "model_type": "llama",
+    "num_attention_heads": 40,
+    "num_hidden_layers": 62,
+    "num_key_value_heads": 40,
+    "pad_token_id": 0,
+    "pretraining_tp": 1,
+    "rms_norm_eps": 1e-05,
+    "rope_scaling": null,
+    "rope_theta": 10000.0,
+    "tie_word_embeddings": false,
+    "torch_dtype": "float16",
+    "transformers_version": "4.35.2",
+    "use_cache": false,
+    "vocab_size": 32001,
+    "quantization_config": {
+        "quant_method": "exl2",
+        "version": "0.0.16",
+        "bits": 6.0,
+        "head_bits": 6,
+        "calibration": {
+            "rows": 100,
+            "length": 2048,
+            "dataset": "(default)"
+        }
+    }
+}

generation_config.json

@@ -0,0 +1,8 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": 0,
+  "transformers_version": "4.35.2",
+  "use_cache": false
+}

output-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb40aae848727f0aa4fc56317aa7ce72192e0b36a1521969e871de6f17fa055f
+size 8584167658

output-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5bde66d264858a6bf55d093a8c1860b2eff7283e4a8a40a7f9bd91210c623a6a
+size 6623603426

pytorch_model.bin.index.json

@@ -0,0 +1,568 @@
+{
+  "metadata": {
+    "total_size": 39988746240
+  },
+  "weight_map": {
+    "lm_head.weight": "pytorch_model-00009-of-00009.bin",
+    "model.embed_tokens.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.10.input_layernorm.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.10.mlp.down_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.10.mlp.up_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.11.input_layernorm.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.11.mlp.down_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.11.mlp.up_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.12.input_layernorm.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.12.mlp.down_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.12.mlp.up_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.13.input_layernorm.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.13.mlp.down_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.13.mlp.up_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.14.input_layernorm.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.14.mlp.down_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.14.mlp.up_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.15.input_layernorm.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.15.mlp.down_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.15.mlp.up_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.16.input_layernorm.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.16.mlp.down_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.16.mlp.up_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.17.input_layernorm.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.17.mlp.down_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.17.mlp.up_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.18.input_layernorm.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.18.mlp.down_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.18.mlp.up_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.19.input_layernorm.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.19.mlp.down_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.19.mlp.up_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.20.input_layernorm.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.20.mlp.down_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.20.mlp.up_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.21.input_layernorm.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.21.mlp.down_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.21.mlp.up_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.22.input_layernorm.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.22.mlp.down_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.22.mlp.up_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.23.input_layernorm.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.23.mlp.down_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.23.mlp.up_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.24.input_layernorm.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.24.mlp.down_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.24.mlp.up_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.25.input_layernorm.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.25.mlp.down_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.25.mlp.up_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.26.input_layernorm.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.26.mlp.down_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.26.mlp.up_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.27.input_layernorm.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.27.mlp.down_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.27.mlp.up_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.28.input_layernorm.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.28.mlp.down_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.28.mlp.up_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.29.input_layernorm.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.29.mlp.down_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.29.mlp.up_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.30.input_layernorm.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.30.mlp.down_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.30.mlp.up_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.31.input_layernorm.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.31.mlp.down_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.31.mlp.up_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.32.input_layernorm.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.32.mlp.down_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.32.mlp.gate_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.32.mlp.up_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.32.post_attention_layernorm.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.32.self_attn.k_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.32.self_attn.o_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.32.self_attn.q_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.32.self_attn.v_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.33.input_layernorm.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.33.mlp.down_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.33.mlp.gate_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.33.mlp.up_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.33.post_attention_layernorm.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.33.self_attn.k_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.33.self_attn.o_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.33.self_attn.q_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.33.self_attn.v_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.34.input_layernorm.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.34.mlp.down_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.34.mlp.gate_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.34.mlp.up_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.34.post_attention_layernorm.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.34.self_attn.k_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.34.self_attn.o_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.34.self_attn.q_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.34.self_attn.v_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.35.input_layernorm.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.35.mlp.down_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.35.mlp.gate_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.35.mlp.up_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.35.post_attention_layernorm.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.35.self_attn.k_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.35.self_attn.o_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.35.self_attn.q_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.35.self_attn.v_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.36.input_layernorm.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.36.mlp.down_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.36.mlp.gate_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.36.mlp.up_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.36.post_attention_layernorm.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.36.self_attn.k_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.36.self_attn.o_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.36.self_attn.q_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.36.self_attn.v_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.37.input_layernorm.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.37.mlp.down_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.37.mlp.gate_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.37.mlp.up_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.37.post_attention_layernorm.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.37.self_attn.k_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.37.self_attn.o_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.37.self_attn.q_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.37.self_attn.v_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.38.input_layernorm.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.38.mlp.down_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.38.mlp.gate_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.38.mlp.up_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.38.post_attention_layernorm.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.38.self_attn.k_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.38.self_attn.o_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.38.self_attn.q_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.38.self_attn.v_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.39.input_layernorm.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.39.mlp.down_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.39.mlp.gate_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.39.mlp.up_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.39.post_attention_layernorm.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.39.self_attn.k_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.39.self_attn.o_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.39.self_attn.q_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.39.self_attn.v_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.40.input_layernorm.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.40.mlp.down_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.40.mlp.gate_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.40.mlp.up_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.40.post_attention_layernorm.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.40.self_attn.k_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.40.self_attn.o_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.40.self_attn.q_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.40.self_attn.v_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.41.input_layernorm.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.41.mlp.down_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.41.mlp.gate_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.41.mlp.up_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.41.post_attention_layernorm.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.41.self_attn.k_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.41.self_attn.o_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.41.self_attn.q_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.41.self_attn.v_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.42.input_layernorm.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.42.mlp.down_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.42.mlp.gate_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.42.mlp.up_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.42.post_attention_layernorm.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.42.self_attn.k_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.42.self_attn.o_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.42.self_attn.q_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.42.self_attn.v_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.43.input_layernorm.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.43.mlp.down_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.43.mlp.gate_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.43.mlp.up_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.43.post_attention_layernorm.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.43.self_attn.k_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.43.self_attn.o_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.43.self_attn.q_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.43.self_attn.v_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.44.input_layernorm.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.44.mlp.down_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.44.mlp.gate_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.44.mlp.up_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.44.post_attention_layernorm.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.44.self_attn.k_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.44.self_attn.o_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.44.self_attn.q_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.44.self_attn.v_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.45.input_layernorm.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.45.mlp.down_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.45.mlp.gate_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.45.mlp.up_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.45.post_attention_layernorm.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.45.self_attn.k_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.45.self_attn.o_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.45.self_attn.q_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.45.self_attn.v_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.46.input_layernorm.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.46.mlp.down_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.46.mlp.gate_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.46.mlp.up_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.46.post_attention_layernorm.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.46.self_attn.k_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.46.self_attn.o_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.46.self_attn.q_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.46.self_attn.v_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.47.input_layernorm.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.47.mlp.down_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.47.mlp.gate_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.47.mlp.up_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.47.post_attention_layernorm.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.47.self_attn.k_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.47.self_attn.o_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.47.self_attn.q_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.47.self_attn.v_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.48.input_layernorm.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.48.mlp.down_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.48.mlp.gate_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.48.mlp.up_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.48.post_attention_layernorm.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.48.self_attn.k_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.48.self_attn.o_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.48.self_attn.q_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.48.self_attn.v_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.49.input_layernorm.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.49.mlp.down_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.49.mlp.gate_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.49.mlp.up_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.49.post_attention_layernorm.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.49.self_attn.k_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.49.self_attn.o_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.49.self_attn.q_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.49.self_attn.v_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.50.input_layernorm.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.50.mlp.down_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.50.mlp.gate_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.50.mlp.up_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.50.post_attention_layernorm.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.50.self_attn.k_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.50.self_attn.o_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.50.self_attn.q_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.50.self_attn.v_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.51.input_layernorm.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.51.mlp.down_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.51.mlp.gate_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.51.mlp.up_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.51.post_attention_layernorm.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.51.self_attn.k_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.51.self_attn.o_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.51.self_attn.q_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.51.self_attn.v_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.52.input_layernorm.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.52.mlp.down_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.52.mlp.gate_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.52.mlp.up_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.52.post_attention_layernorm.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.52.self_attn.k_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.52.self_attn.o_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.52.self_attn.q_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.52.self_attn.v_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.53.input_layernorm.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.53.mlp.down_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.53.mlp.gate_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.53.mlp.up_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.53.post_attention_layernorm.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.53.self_attn.k_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.53.self_attn.o_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.53.self_attn.q_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.53.self_attn.v_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.54.input_layernorm.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.54.mlp.down_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.54.mlp.gate_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.54.mlp.up_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.54.post_attention_layernorm.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.54.self_attn.k_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.54.self_attn.o_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.54.self_attn.q_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.54.self_attn.v_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.55.input_layernorm.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.55.mlp.down_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.55.mlp.gate_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.55.mlp.up_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.55.post_attention_layernorm.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.55.self_attn.k_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.55.self_attn.o_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.55.self_attn.q_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.55.self_attn.v_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.56.input_layernorm.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.56.mlp.down_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.56.mlp.gate_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.56.mlp.up_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.56.post_attention_layernorm.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.56.self_attn.k_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.56.self_attn.o_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.56.self_attn.q_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.56.self_attn.v_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.57.input_layernorm.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.57.mlp.down_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.57.mlp.gate_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.57.mlp.up_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.57.post_attention_layernorm.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.57.self_attn.k_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.57.self_attn.o_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.57.self_attn.q_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.57.self_attn.v_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.58.input_layernorm.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.58.mlp.down_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.58.mlp.gate_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.58.mlp.up_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.58.post_attention_layernorm.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.58.self_attn.k_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.58.self_attn.o_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.58.self_attn.q_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.58.self_attn.v_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.59.input_layernorm.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.59.mlp.down_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.59.mlp.gate_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.59.mlp.up_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.59.post_attention_layernorm.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.59.self_attn.k_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.59.self_attn.o_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.59.self_attn.q_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.59.self_attn.v_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.60.input_layernorm.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.60.mlp.down_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.60.mlp.gate_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.60.mlp.up_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.60.post_attention_layernorm.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.60.self_attn.k_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.60.self_attn.o_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.60.self_attn.q_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.60.self_attn.v_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.61.input_layernorm.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.61.mlp.down_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.61.mlp.gate_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.61.mlp.up_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.61.post_attention_layernorm.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.61.self_attn.k_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.61.self_attn.o_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.61.self_attn.q_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.61.self_attn.v_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.7.input_layernorm.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.7.mlp.down_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.7.mlp.up_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.8.input_layernorm.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.8.mlp.down_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.8.mlp.up_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.9.input_layernorm.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.9.mlp.down_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.9.mlp.up_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "model.norm.weight": "pytorch_model-00008-of-00009.bin"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -0,0 +1,52 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32000": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 2048,
+  "pad_token": "[PAD]",
+  "padding_side": "left",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "trust_remote_code": false,
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false,
+  "use_fast": true
+}