commit 6fef40b9fb286f42c2dabaa94674876ae8cc66c6
Author: ModelHub XC <noreply@modelhub.org.cn>
Date:   Sat Aug 15 16:41:19 2026 +0800

    初始化项目，由ModelHub XC社区提供模型
    
    Model: CalderaAI/30B-Lazarus
    Source: Original Platform

diff --git a/.gitattributes b/.gitattributes
new file mode 100644
index 0000000..c7d9f33
--- /dev/null
+++ b/.gitattributes
@@ -0,0 +1,34 @@
+*.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
+*.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
diff --git a/README.md b/README.md
new file mode 100644
index 0000000..fae36af
--- /dev/null
+++ b/README.md
@@ -0,0 +1,61 @@
+---
+tags:
+- llama
+- alpaca
+- cot
+- vicuna
+- uncensored
+- merge
+- mix
+---
+
+## 30B-Lazarus
+
+## Composition:
+[] = applied as LoRA to a composite model | () = combined as composite models
+
+[SuperCOT([gtp4xalpaca(manticorechatpygalpha+vicunaunlocked)]+[StoryV2(kaiokendev-SuperHOT-LoRA-prototype30b-8192)])]
+
+This model is the result of an experimental use of LoRAs on language models and model merges that are not the base HuggingFace-format LLaMA model they were intended for.
+The desired outcome is to additively apply desired features without paradoxically watering down a model's effective behavior.
+
+Potential limitations - LoRAs applied on top of each other may intercompete.
+
+Subjective results - very promising. Further experimental tests and objective tests are required.
+
+Instruct and Setup Suggestions:
+
+Alpaca instruct is primary, Vicuna instruct format may work.
+If using KoboldAI or Text-Generation-WebUI, recommend switching between Godlike and Storywriter presets and adjusting output length + instructions in memory.
+Other presets as well as custom settings can yield highly different results, especially Temperature.
+If poking it with a stick doesn't work try poking harder.
+
+## Language Models and LoRAs Used Credits:
+
+manticore-30b-chat-pyg-alpha [Epoch0.4] by openaccess-ai-collective
+
+https://huggingface.co/openaccess-ai-collective/manticore-30b-chat-pyg-alpha
+
+SuperCOT-LoRA [30B] by kaiokendev
+
+https://huggingface.co/kaiokendev/SuperCOT-LoRA
+
+Storytelling-LLaMa-LoRA [30B, Version 2] by GamerUnTouch
+
+https://huggingface.co/GamerUntouch/Storytelling-LLaMa-LoRAs
+
+SuperHOT Prototype [30b 8k ctx] by kaiokendev
+
+https://huggingface.co/kaiokendev/SuperHOT-LoRA-prototype
+
+ChanSung's GPT4-Alpaca-LoRA
+https://huggingface.co/chansung/gpt4-alpaca-lora-30b
+
+Neko-Institute-of-Science's Vicuna Unlocked LoRA (Checkpoint 46080)
+https://huggingface.co/Neko-Institute-of-Science/VicUnLocked-30b-LoRA
+
+Also thanks to Meta for LLaMA.
+
+Each model and LoRA was hand picked and considered for what it could contribute to this ensemble.
+Thanks to each and every one of you for your incredible work developing some of the best things
+to come out of this community.
\ No newline at end of file
diff --git a/config.json b/config.json
new file mode 100644
index 0000000..c0466a9
--- /dev/null
+++ b/config.json
@@ -0,0 +1,24 @@
+{
+  "_name_or_path": "30B-Lazarus",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 6656,
+  "initializer_range": 0.02,
+  "intermediate_size": 17920,
+  "max_position_embeddings": 2048,
+  "max_sequence_length": 2048,
+  "model_type": "llama",
+  "num_attention_heads": 52,
+  "num_hidden_layers": 60,
+  "pad_token_id": 0,
+  "rms_norm_eps": 1e-06,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.28.1",
+  "use_cache": true,
+  "vocab_size": 32000
+}
diff --git a/generation_config.json b/generation_config.json
new file mode 100644
index 0000000..1372199
--- /dev/null
+++ b/generation_config.json
@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": 0,
+  "transformers_version": "4.28.1"
+}
diff --git a/model-00001-of-00007.safetensors b/model-00001-of-00007.safetensors
new file mode 100644
index 0000000..2ec505a
--- /dev/null
+++ b/model-00001-of-00007.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c054a62e8e65bbbc4d58f76c8a58654c96a1b1454f9e44a4b0abc9189fb5078
+size 9818304536
diff --git a/model-00002-of-00007.safetensors b/model-00002-of-00007.safetensors
new file mode 100644
index 0000000..a877272
--- /dev/null
+++ b/model-00002-of-00007.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d1858babdb15b98f4494b6b35d74710ea556b4a3d436860c63d08754da2662b
+size 9958081296
diff --git a/model-00003-of-00007.safetensors b/model-00003-of-00007.safetensors
new file mode 100644
index 0000000..aa07764
--- /dev/null
+++ b/model-00003-of-00007.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b039c1885ab8b9c44c86bdde59988019438cb6bbd543566cdae47a20a5830502
+size 9896713232
diff --git a/model-00004-of-00007.safetensors b/model-00004-of-00007.safetensors
new file mode 100644
index 0000000..23bb856
--- /dev/null
+++ b/model-00004-of-00007.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0700e0e2f6a2e1d29d408c3fa3b79ffe80e9f310bf8e83338c9476390554a71b
+size 9869449664
diff --git a/model-00005-of-00007.safetensors b/model-00005-of-00007.safetensors
new file mode 100644
index 0000000..79d9957
--- /dev/null
+++ b/model-00005-of-00007.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36f60909e879f7bb765f3c40fed4dad4242bf785e1fd25a9538c7f605ccdfe30
+size 9869449664
diff --git a/model-00006-of-00007.safetensors b/model-00006-of-00007.safetensors
new file mode 100644
index 0000000..8a4405b
--- /dev/null
+++ b/model-00006-of-00007.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b05e3252d362e686b1b9593d14cd7dc660d8a8a0a22740a98b7a91f2fa57bfa
+size 9958081304
diff --git a/model-00007-of-00007.safetensors b/model-00007-of-00007.safetensors
new file mode 100644
index 0000000..1b5e4b2
--- /dev/null
+++ b/model-00007-of-00007.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21cc0281b0c952f029fa0a2d214def46c17b85a4aedd58c700b4a6d4d537134f
+size 5687891896
diff --git a/model.safetensors.index.json b/model.safetensors.index.json
new file mode 100644
index 0000000..90259b9
--- /dev/null
+++ b/model.safetensors.index.json
@@ -0,0 +1,610 @@
+{
+    "metadata": {
+        "total_size": 65057902592
+    },
+    "weight_map": {
+        "lm_head.weight": "model-00007-of-00007.safetensors",
+        "model.embed_tokens.weight": "model-00001-of-00007.safetensors",
+        "model.layers.0.input_layernorm.weight": "model-00001-of-00007.safetensors",
+        "model.layers.0.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.0.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+        "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.0.self_attn.rotary_emb.inv_freq": "model-00001-of-00007.safetensors",
+        "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.1.input_layernorm.weight": "model-00001-of-00007.safetensors",
+        "model.layers.1.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.1.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+        "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.1.self_attn.rotary_emb.inv_freq": "model-00001-of-00007.safetensors",
+        "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.10.input_layernorm.weight": "model-00002-of-00007.safetensors",
+        "model.layers.10.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.10.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+        "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.10.self_attn.rotary_emb.inv_freq": "model-00002-of-00007.safetensors",
+        "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.11.input_layernorm.weight": "model-00002-of-00007.safetensors",
+        "model.layers.11.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.11.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+        "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.11.self_attn.rotary_emb.inv_freq": "model-00002-of-00007.safetensors",
+        "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.12.input_layernorm.weight": "model-00002-of-00007.safetensors",
+        "model.layers.12.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.12.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+        "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.12.self_attn.rotary_emb.inv_freq": "model-00002-of-00007.safetensors",
+        "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.13.input_layernorm.weight": "model-00002-of-00007.safetensors",
+        "model.layers.13.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.13.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+        "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.13.self_attn.rotary_emb.inv_freq": "model-00002-of-00007.safetensors",
+        "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.14.input_layernorm.weight": "model-00002-of-00007.safetensors",
+        "model.layers.14.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.14.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+        "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.14.self_attn.rotary_emb.inv_freq": "model-00002-of-00007.safetensors",
+        "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.15.input_layernorm.weight": "model-00002-of-00007.safetensors",
+        "model.layers.15.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.15.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+        "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.15.self_attn.rotary_emb.inv_freq": "model-00002-of-00007.safetensors",
+        "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.16.input_layernorm.weight": "model-00002-of-00007.safetensors",
+        "model.layers.16.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.16.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+        "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.16.self_attn.rotary_emb.inv_freq": "model-00002-of-00007.safetensors",
+        "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.17.input_layernorm.weight": "model-00002-of-00007.safetensors",
+        "model.layers.17.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.17.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+        "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.17.self_attn.rotary_emb.inv_freq": "model-00002-of-00007.safetensors",
+        "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.18.input_layernorm.weight": "model-00003-of-00007.safetensors",
+        "model.layers.18.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.18.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+        "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.18.self_attn.rotary_emb.inv_freq": "model-00003-of-00007.safetensors",
+        "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.19.input_layernorm.weight": "model-00003-of-00007.safetensors",
+        "model.layers.19.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.19.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+        "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.19.self_attn.rotary_emb.inv_freq": "model-00003-of-00007.safetensors",
+        "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.2.input_layernorm.weight": "model-00001-of-00007.safetensors",
+        "model.layers.2.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.2.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+        "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.2.self_attn.rotary_emb.inv_freq": "model-00001-of-00007.safetensors",
+        "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.20.input_layernorm.weight": "model-00003-of-00007.safetensors",
+        "model.layers.20.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.20.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+        "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.20.self_attn.rotary_emb.inv_freq": "model-00003-of-00007.safetensors",
+        "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.21.input_layernorm.weight": "model-00003-of-00007.safetensors",
+        "model.layers.21.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.21.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+        "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.21.self_attn.rotary_emb.inv_freq": "model-00003-of-00007.safetensors",
+        "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.22.input_layernorm.weight": "model-00003-of-00007.safetensors",
+        "model.layers.22.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.22.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+        "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.22.self_attn.rotary_emb.inv_freq": "model-00003-of-00007.safetensors",
+        "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.23.input_layernorm.weight": "model-00003-of-00007.safetensors",
+        "model.layers.23.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.23.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+        "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.23.self_attn.rotary_emb.inv_freq": "model-00003-of-00007.safetensors",
+        "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.24.input_layernorm.weight": "model-00003-of-00007.safetensors",
+        "model.layers.24.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.24.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+        "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.24.self_attn.rotary_emb.inv_freq": "model-00003-of-00007.safetensors",
+        "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.25.input_layernorm.weight": "model-00003-of-00007.safetensors",
+        "model.layers.25.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.25.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+        "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.25.self_attn.rotary_emb.inv_freq": "model-00003-of-00007.safetensors",
+        "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.26.input_layernorm.weight": "model-00003-of-00007.safetensors",
+        "model.layers.26.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.26.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+        "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.26.self_attn.rotary_emb.inv_freq": "model-00003-of-00007.safetensors",
+        "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.27.input_layernorm.weight": "model-00004-of-00007.safetensors",
+        "model.layers.27.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.27.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.27.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.27.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+        "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.27.self_attn.rotary_emb.inv_freq": "model-00003-of-00007.safetensors",
+        "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.28.input_layernorm.weight": "model-00004-of-00007.safetensors",
+        "model.layers.28.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.28.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.28.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.28.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+        "model.layers.28.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.28.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.28.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.28.self_attn.rotary_emb.inv_freq": "model-00004-of-00007.safetensors",
+        "model.layers.28.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.29.input_layernorm.weight": "model-00004-of-00007.safetensors",
+        "model.layers.29.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.29.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.29.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.29.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+        "model.layers.29.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.29.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.29.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.29.self_attn.rotary_emb.inv_freq": "model-00004-of-00007.safetensors",
+        "model.layers.29.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.3.input_layernorm.weight": "model-00001-of-00007.safetensors",
+        "model.layers.3.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.3.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+        "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.3.self_attn.rotary_emb.inv_freq": "model-00001-of-00007.safetensors",
+        "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.30.input_layernorm.weight": "model-00004-of-00007.safetensors",
+        "model.layers.30.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.30.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.30.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.30.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+        "model.layers.30.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.30.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.30.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.30.self_attn.rotary_emb.inv_freq": "model-00004-of-00007.safetensors",
+        "model.layers.30.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.31.input_layernorm.weight": "model-00004-of-00007.safetensors",
+        "model.layers.31.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.31.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.31.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+        "model.layers.31.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.31.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.31.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.31.self_attn.rotary_emb.inv_freq": "model-00004-of-00007.safetensors",
+        "model.layers.31.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.32.input_layernorm.weight": "model-00004-of-00007.safetensors",
+        "model.layers.32.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.32.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.32.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.32.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+        "model.layers.32.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.32.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.32.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.32.self_attn.rotary_emb.inv_freq": "model-00004-of-00007.safetensors",
+        "model.layers.32.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.33.input_layernorm.weight": "model-00004-of-00007.safetensors",
+        "model.layers.33.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.33.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.33.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.33.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+        "model.layers.33.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.33.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.33.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.33.self_attn.rotary_emb.inv_freq": "model-00004-of-00007.safetensors",
+        "model.layers.33.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.34.input_layernorm.weight": "model-00004-of-00007.safetensors",
+        "model.layers.34.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.34.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.34.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.34.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+        "model.layers.34.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.34.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.34.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.34.self_attn.rotary_emb.inv_freq": "model-00004-of-00007.safetensors",
+        "model.layers.34.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.35.input_layernorm.weight": "model-00004-of-00007.safetensors",
+        "model.layers.35.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.35.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.35.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.35.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+        "model.layers.35.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.35.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.35.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.35.self_attn.rotary_emb.inv_freq": "model-00004-of-00007.safetensors",
+        "model.layers.35.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.36.input_layernorm.weight": "model-00005-of-00007.safetensors",
+        "model.layers.36.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.36.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.36.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.36.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+        "model.layers.36.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.36.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.36.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.36.self_attn.rotary_emb.inv_freq": "model-00004-of-00007.safetensors",
+        "model.layers.36.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.37.input_layernorm.weight": "model-00005-of-00007.safetensors",
+        "model.layers.37.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.37.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.37.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.37.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+        "model.layers.37.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.37.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.37.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.37.self_attn.rotary_emb.inv_freq": "model-00005-of-00007.safetensors",
+        "model.layers.37.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.38.input_layernorm.weight": "model-00005-of-00007.safetensors",
+        "model.layers.38.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.38.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.38.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.38.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+        "model.layers.38.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.38.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.38.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.38.self_attn.rotary_emb.inv_freq": "model-00005-of-00007.safetensors",
+        "model.layers.38.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.39.input_layernorm.weight": "model-00005-of-00007.safetensors",
+        "model.layers.39.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.39.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.39.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.39.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+        "model.layers.39.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.39.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.39.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.39.self_attn.rotary_emb.inv_freq": "model-00005-of-00007.safetensors",
+        "model.layers.39.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.4.input_layernorm.weight": "model-00001-of-00007.safetensors",
+        "model.layers.4.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.4.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+        "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.4.self_attn.rotary_emb.inv_freq": "model-00001-of-00007.safetensors",
+        "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.40.input_layernorm.weight": "model-00005-of-00007.safetensors",
+        "model.layers.40.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.40.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.40.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.40.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+        "model.layers.40.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.40.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.40.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.40.self_attn.rotary_emb.inv_freq": "model-00005-of-00007.safetensors",
+        "model.layers.40.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.41.input_layernorm.weight": "model-00005-of-00007.safetensors",
+        "model.layers.41.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.41.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.41.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.41.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+        "model.layers.41.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.41.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.41.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.41.self_attn.rotary_emb.inv_freq": "model-00005-of-00007.safetensors",
+        "model.layers.41.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.42.input_layernorm.weight": "model-00005-of-00007.safetensors",
+        "model.layers.42.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.42.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.42.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.42.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+        "model.layers.42.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.42.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.42.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.42.self_attn.rotary_emb.inv_freq": "model-00005-of-00007.safetensors",
+        "model.layers.42.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.43.input_layernorm.weight": "model-00005-of-00007.safetensors",
+        "model.layers.43.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.43.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.43.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.43.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+        "model.layers.43.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.43.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.43.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.43.self_attn.rotary_emb.inv_freq": "model-00005-of-00007.safetensors",
+        "model.layers.43.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.44.input_layernorm.weight": "model-00005-of-00007.safetensors",
+        "model.layers.44.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.44.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.44.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.44.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+        "model.layers.44.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.44.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.44.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.44.self_attn.rotary_emb.inv_freq": "model-00005-of-00007.safetensors",
+        "model.layers.44.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.45.input_layernorm.weight": "model-00006-of-00007.safetensors",
+        "model.layers.45.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.45.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.45.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.45.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+        "model.layers.45.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.45.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.45.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.45.self_attn.rotary_emb.inv_freq": "model-00005-of-00007.safetensors",
+        "model.layers.45.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.46.input_layernorm.weight": "model-00006-of-00007.safetensors",
+        "model.layers.46.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.46.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.46.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.46.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+        "model.layers.46.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.46.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.46.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.46.self_attn.rotary_emb.inv_freq": "model-00006-of-00007.safetensors",
+        "model.layers.46.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.47.input_layernorm.weight": "model-00006-of-00007.safetensors",
+        "model.layers.47.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.47.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.47.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.47.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+        "model.layers.47.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.47.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.47.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.47.self_attn.rotary_emb.inv_freq": "model-00006-of-00007.safetensors",
+        "model.layers.47.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.48.input_layernorm.weight": "model-00006-of-00007.safetensors",
+        "model.layers.48.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.48.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.48.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.48.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+        "model.layers.48.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.48.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.48.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.48.self_attn.rotary_emb.inv_freq": "model-00006-of-00007.safetensors",
+        "model.layers.48.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.49.input_layernorm.weight": "model-00006-of-00007.safetensors",
+        "model.layers.49.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.49.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.49.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.49.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+        "model.layers.49.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.49.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.49.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.49.self_attn.rotary_emb.inv_freq": "model-00006-of-00007.safetensors",
+        "model.layers.49.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.5.input_layernorm.weight": "model-00001-of-00007.safetensors",
+        "model.layers.5.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.5.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+        "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.5.self_attn.rotary_emb.inv_freq": "model-00001-of-00007.safetensors",
+        "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.50.input_layernorm.weight": "model-00006-of-00007.safetensors",
+        "model.layers.50.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.50.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.50.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.50.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+        "model.layers.50.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.50.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.50.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.50.self_attn.rotary_emb.inv_freq": "model-00006-of-00007.safetensors",
+        "model.layers.50.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.51.input_layernorm.weight": "model-00006-of-00007.safetensors",
+        "model.layers.51.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.51.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.51.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.51.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+        "model.layers.51.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.51.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.51.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.51.self_attn.rotary_emb.inv_freq": "model-00006-of-00007.safetensors",
+        "model.layers.51.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.52.input_layernorm.weight": "model-00006-of-00007.safetensors",
+        "model.layers.52.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.52.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.52.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.52.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+        "model.layers.52.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.52.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.52.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.52.self_attn.rotary_emb.inv_freq": "model-00006-of-00007.safetensors",
+        "model.layers.52.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.53.input_layernorm.weight": "model-00006-of-00007.safetensors",
+        "model.layers.53.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.53.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.53.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.53.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+        "model.layers.53.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.53.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.53.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.53.self_attn.rotary_emb.inv_freq": "model-00006-of-00007.safetensors",
+        "model.layers.53.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.54.input_layernorm.weight": "model-00006-of-00007.safetensors",
+        "model.layers.54.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.54.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.54.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.54.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+        "model.layers.54.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.54.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.54.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.54.self_attn.rotary_emb.inv_freq": "model-00006-of-00007.safetensors",
+        "model.layers.54.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.55.input_layernorm.weight": "model-00007-of-00007.safetensors",
+        "model.layers.55.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
+        "model.layers.55.mlp.gate_proj.weight": "model-00007-of-00007.safetensors",
+        "model.layers.55.mlp.up_proj.weight": "model-00007-of-00007.safetensors",
+        "model.layers.55.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
+        "model.layers.55.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
+        "model.layers.55.self_attn.o_proj.weight": "model-00007-of-00007.safetensors",
+        "model.layers.55.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.55.self_attn.rotary_emb.inv_freq": "model-00007-of-00007.safetensors",
+        "model.layers.55.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
+        "model.layers.56.input_layernorm.weight": "model-00007-of-00007.safetensors",
+        "model.layers.56.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
+        "model.layers.56.mlp.gate_proj.weight": "model-00007-of-00007.safetensors",
+        "model.layers.56.mlp.up_proj.weight": "model-00007-of-00007.safetensors",
+        "model.layers.56.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
+        "model.layers.56.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
+        "model.layers.56.self_attn.o_proj.weight": "model-00007-of-00007.safetensors",
+        "model.layers.56.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
+        "model.layers.56.self_attn.rotary_emb.inv_freq": "model-00007-of-00007.safetensors",
+        "model.layers.56.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
+        "model.layers.57.input_layernorm.weight": "model-00007-of-00007.safetensors",
+        "model.layers.57.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
+        "model.layers.57.mlp.gate_proj.weight": "model-00007-of-00007.safetensors",
+        "model.layers.57.mlp.up_proj.weight": "model-00007-of-00007.safetensors",
+        "model.layers.57.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
+        "model.layers.57.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
+        "model.layers.57.self_attn.o_proj.weight": "model-00007-of-00007.safetensors",
+        "model.layers.57.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
+        "model.layers.57.self_attn.rotary_emb.inv_freq": "model-00007-of-00007.safetensors",
+        "model.layers.57.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
+        "model.layers.58.input_layernorm.weight": "model-00007-of-00007.safetensors",
+        "model.layers.58.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
+        "model.layers.58.mlp.gate_proj.weight": "model-00007-of-00007.safetensors",
+        "model.layers.58.mlp.up_proj.weight": "model-00007-of-00007.safetensors",
+        "model.layers.58.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
+        "model.layers.58.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
+        "model.layers.58.self_attn.o_proj.weight": "model-00007-of-00007.safetensors",
+        "model.layers.58.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
+        "model.layers.58.self_attn.rotary_emb.inv_freq": "model-00007-of-00007.safetensors",
+        "model.layers.58.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
+        "model.layers.59.input_layernorm.weight": "model-00007-of-00007.safetensors",
+        "model.layers.59.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
+        "model.layers.59.mlp.gate_proj.weight": "model-00007-of-00007.safetensors",
+        "model.layers.59.mlp.up_proj.weight": "model-00007-of-00007.safetensors",
+        "model.layers.59.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
+        "model.layers.59.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
+        "model.layers.59.self_attn.o_proj.weight": "model-00007-of-00007.safetensors",
+        "model.layers.59.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
+        "model.layers.59.self_attn.rotary_emb.inv_freq": "model-00007-of-00007.safetensors",
+        "model.layers.59.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
+        "model.layers.6.input_layernorm.weight": "model-00001-of-00007.safetensors",
+        "model.layers.6.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.6.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+        "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.6.self_attn.rotary_emb.inv_freq": "model-00001-of-00007.safetensors",
+        "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.7.input_layernorm.weight": "model-00001-of-00007.safetensors",
+        "model.layers.7.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.7.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+        "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.7.self_attn.rotary_emb.inv_freq": "model-00001-of-00007.safetensors",
+        "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.8.input_layernorm.weight": "model-00002-of-00007.safetensors",
+        "model.layers.8.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.8.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+        "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.8.self_attn.rotary_emb.inv_freq": "model-00001-of-00007.safetensors",
+        "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.9.input_layernorm.weight": "model-00002-of-00007.safetensors",
+        "model.layers.9.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.9.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+        "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.9.self_attn.rotary_emb.inv_freq": "model-00002-of-00007.safetensors",
+        "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+        "model.norm.weight": "model-00007-of-00007.safetensors"
+    }
+}
\ No newline at end of file
diff --git a/pytorch_model-00001-of-00007.bin b/pytorch_model-00001-of-00007.bin
new file mode 100644
index 0000000..712c845
--- /dev/null
+++ b/pytorch_model-00001-of-00007.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7251ff7ece48bc6665ee90484a6fead3e1821469d9467b5cabf97869874bf788
+size 9818324627
diff --git a/pytorch_model-00002-of-00007.bin b/pytorch_model-00002-of-00007.bin
new file mode 100644
index 0000000..05dfd84
--- /dev/null
+++ b/pytorch_model-00002-of-00007.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cdcddd8d4786382e51cf098e2fdd8987f5e6805dec90e29cf94ba5554bcc86a8
+size 9958102743
diff --git a/pytorch_model-00003-of-00007.bin b/pytorch_model-00003-of-00007.bin
new file mode 100644
index 0000000..2fa51aa
--- /dev/null
+++ b/pytorch_model-00003-of-00007.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ab371a58a5222f9112a4e847d3a22d8a3d806d2064b98a6c3607ef8347ac050
+size 9896734715
diff --git a/pytorch_model-00004-of-00007.bin b/pytorch_model-00004-of-00007.bin
new file mode 100644
index 0000000..a1c1083
--- /dev/null
+++ b/pytorch_model-00004-of-00007.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a19880993d2fbe719813a276e42fa19d27be980ecba160c41009fd227f62cc07
+size 9869470481
diff --git a/pytorch_model-00005-of-00007.bin b/pytorch_model-00005-of-00007.bin
new file mode 100644
index 0000000..06767aa
--- /dev/null
+++ b/pytorch_model-00005-of-00007.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4028099572ab6a1fc6094b396ef8224e83f6ff2fbd5608fc2a5a06ef2ecb45c3
+size 9869470445
diff --git a/pytorch_model-00006-of-00007.bin b/pytorch_model-00006-of-00007.bin
new file mode 100644
index 0000000..b22bc22
--- /dev/null
+++ b/pytorch_model-00006-of-00007.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21dd5c30fdc687952e8864aa2fa59de1a3e6f2bee55c0c4fb47de84709d18f97
+size 9958102743
diff --git a/pytorch_model-00007-of-00007.bin b/pytorch_model-00007-of-00007.bin
new file mode 100644
index 0000000..9448b71
--- /dev/null
+++ b/pytorch_model-00007-of-00007.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4dc60fe4293de5da177f5fdd2fbf194237f69b55214976971a17013bc1f781a
+size 5687903281
diff --git a/pytorch_model.bin.index.json b/pytorch_model.bin.index.json
new file mode 100644
index 0000000..c76e80d
--- /dev/null
+++ b/pytorch_model.bin.index.json
@@ -0,0 +1,610 @@
+{
+  "metadata": {
+    "total_size": 65057902592
+  },
+  "weight_map": {
+    "lm_head.weight": "pytorch_model-00007-of-00007.bin",
+    "model.embed_tokens.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.0.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00007.bin",
+    "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.1.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00007.bin",
+    "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.10.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.10.mlp.down_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.10.mlp.up_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.10.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00007.bin",
+    "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.11.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.11.mlp.down_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.11.mlp.up_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.11.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00007.bin",
+    "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.12.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.12.mlp.down_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.12.mlp.up_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.12.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00007.bin",
+    "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.13.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.13.mlp.down_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.13.mlp.up_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.13.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00007.bin",
+    "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.14.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.14.mlp.down_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.14.mlp.up_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.14.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00007.bin",
+    "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.15.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.15.mlp.down_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.15.mlp.up_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.15.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00007.bin",
+    "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.16.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.16.mlp.down_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.16.mlp.up_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.16.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00007.bin",
+    "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.17.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.17.mlp.down_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.17.mlp.up_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.17.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00007.bin",
+    "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.18.input_layernorm.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.18.mlp.down_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.18.mlp.up_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.18.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00007.bin",
+    "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.19.input_layernorm.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.19.mlp.down_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.19.mlp.up_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.19.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00007.bin",
+    "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.2.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00007.bin",
+    "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.20.input_layernorm.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.20.mlp.down_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.20.mlp.up_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.20.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00007.bin",
+    "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.21.input_layernorm.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.21.mlp.down_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.21.mlp.up_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.21.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00007.bin",
+    "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.22.input_layernorm.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.22.mlp.down_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.22.mlp.up_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.22.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00007.bin",
+    "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.23.input_layernorm.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.23.mlp.down_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.23.mlp.up_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.23.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00007.bin",
+    "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.24.input_layernorm.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.24.mlp.down_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.24.mlp.up_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.24.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00007.bin",
+    "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.25.input_layernorm.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.25.mlp.down_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.25.mlp.up_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.25.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00007.bin",
+    "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.26.input_layernorm.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.26.mlp.down_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.26.mlp.up_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.26.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00007.bin",
+    "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.27.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.27.mlp.down_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.27.mlp.up_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.27.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00007.bin",
+    "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.28.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.28.mlp.down_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.28.mlp.up_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.28.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00007.bin",
+    "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.29.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.29.mlp.down_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.29.mlp.up_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.29.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00007.bin",
+    "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.3.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00007.bin",
+    "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.30.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.30.mlp.down_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.30.mlp.up_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.30.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00007.bin",
+    "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.31.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.31.mlp.down_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.31.mlp.up_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.31.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00007.bin",
+    "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.32.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.32.mlp.down_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.32.mlp.gate_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.32.mlp.up_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.32.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.32.self_attn.k_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.32.self_attn.o_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.32.self_attn.q_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.32.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00007.bin",
+    "model.layers.32.self_attn.v_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.33.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.33.mlp.down_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.33.mlp.gate_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.33.mlp.up_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.33.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.33.self_attn.k_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.33.self_attn.o_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.33.self_attn.q_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.33.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00007.bin",
+    "model.layers.33.self_attn.v_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.34.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.34.mlp.down_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.34.mlp.gate_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.34.mlp.up_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.34.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.34.self_attn.k_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.34.self_attn.o_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.34.self_attn.q_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.34.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00007.bin",
+    "model.layers.34.self_attn.v_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.35.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.35.mlp.down_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.35.mlp.gate_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.35.mlp.up_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.35.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.35.self_attn.k_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.35.self_attn.o_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.35.self_attn.q_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.35.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00007.bin",
+    "model.layers.35.self_attn.v_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.36.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.36.mlp.down_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.36.mlp.gate_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.36.mlp.up_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.36.post_attention_layernorm.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.36.self_attn.k_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.36.self_attn.o_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.36.self_attn.q_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.36.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00007.bin",
+    "model.layers.36.self_attn.v_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.37.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.37.mlp.down_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.37.mlp.gate_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.37.mlp.up_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.37.post_attention_layernorm.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.37.self_attn.k_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.37.self_attn.o_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.37.self_attn.q_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.37.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00007.bin",
+    "model.layers.37.self_attn.v_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.38.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.38.mlp.down_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.38.mlp.gate_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.38.mlp.up_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.38.post_attention_layernorm.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.38.self_attn.k_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.38.self_attn.o_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.38.self_attn.q_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.38.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00007.bin",
+    "model.layers.38.self_attn.v_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.39.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.39.mlp.down_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.39.mlp.gate_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.39.mlp.up_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.39.post_attention_layernorm.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.39.self_attn.k_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.39.self_attn.o_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.39.self_attn.q_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.39.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00007.bin",
+    "model.layers.39.self_attn.v_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.4.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00007.bin",
+    "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.40.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.40.mlp.down_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.40.mlp.gate_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.40.mlp.up_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.40.post_attention_layernorm.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.40.self_attn.k_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.40.self_attn.o_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.40.self_attn.q_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.40.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00007.bin",
+    "model.layers.40.self_attn.v_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.41.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.41.mlp.down_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.41.mlp.gate_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.41.mlp.up_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.41.post_attention_layernorm.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.41.self_attn.k_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.41.self_attn.o_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.41.self_attn.q_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.41.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00007.bin",
+    "model.layers.41.self_attn.v_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.42.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.42.mlp.down_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.42.mlp.gate_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.42.mlp.up_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.42.post_attention_layernorm.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.42.self_attn.k_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.42.self_attn.o_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.42.self_attn.q_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.42.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00007.bin",
+    "model.layers.42.self_attn.v_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.43.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.43.mlp.down_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.43.mlp.gate_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.43.mlp.up_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.43.post_attention_layernorm.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.43.self_attn.k_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.43.self_attn.o_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.43.self_attn.q_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.43.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00007.bin",
+    "model.layers.43.self_attn.v_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.44.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.44.mlp.down_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.44.mlp.gate_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.44.mlp.up_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.44.post_attention_layernorm.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.44.self_attn.k_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.44.self_attn.o_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.44.self_attn.q_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.44.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00007.bin",
+    "model.layers.44.self_attn.v_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.45.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.45.mlp.down_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.45.mlp.gate_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.45.mlp.up_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.45.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.45.self_attn.k_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.45.self_attn.o_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.45.self_attn.q_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.45.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00007.bin",
+    "model.layers.45.self_attn.v_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.46.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.46.mlp.down_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.46.mlp.gate_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.46.mlp.up_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.46.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.46.self_attn.k_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.46.self_attn.o_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.46.self_attn.q_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.46.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00007.bin",
+    "model.layers.46.self_attn.v_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.47.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.47.mlp.down_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.47.mlp.gate_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.47.mlp.up_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.47.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.47.self_attn.k_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.47.self_attn.o_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.47.self_attn.q_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.47.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00007.bin",
+    "model.layers.47.self_attn.v_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.48.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.48.mlp.down_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.48.mlp.gate_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.48.mlp.up_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.48.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.48.self_attn.k_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.48.self_attn.o_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.48.self_attn.q_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.48.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00007.bin",
+    "model.layers.48.self_attn.v_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.49.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.49.mlp.down_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.49.mlp.gate_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.49.mlp.up_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.49.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.49.self_attn.k_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.49.self_attn.o_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.49.self_attn.q_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.49.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00007.bin",
+    "model.layers.49.self_attn.v_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.5.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00007.bin",
+    "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.50.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.50.mlp.down_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.50.mlp.gate_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.50.mlp.up_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.50.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.50.self_attn.k_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.50.self_attn.o_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.50.self_attn.q_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.50.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00007.bin",
+    "model.layers.50.self_attn.v_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.51.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.51.mlp.down_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.51.mlp.gate_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.51.mlp.up_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.51.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.51.self_attn.k_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.51.self_attn.o_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.51.self_attn.q_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.51.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00007.bin",
+    "model.layers.51.self_attn.v_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.52.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.52.mlp.down_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.52.mlp.gate_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.52.mlp.up_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.52.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.52.self_attn.k_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.52.self_attn.o_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.52.self_attn.q_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.52.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00007.bin",
+    "model.layers.52.self_attn.v_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.53.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.53.mlp.down_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.53.mlp.gate_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.53.mlp.up_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.53.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.53.self_attn.k_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.53.self_attn.o_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.53.self_attn.q_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.53.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00007.bin",
+    "model.layers.53.self_attn.v_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.54.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.54.mlp.down_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.54.mlp.gate_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.54.mlp.up_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.54.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.54.self_attn.k_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.54.self_attn.o_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.54.self_attn.q_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.54.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00007.bin",
+    "model.layers.54.self_attn.v_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.55.input_layernorm.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.55.mlp.down_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.55.mlp.gate_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.55.mlp.up_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.55.post_attention_layernorm.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.55.self_attn.k_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.55.self_attn.o_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.55.self_attn.q_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.55.self_attn.rotary_emb.inv_freq": "pytorch_model-00007-of-00007.bin",
+    "model.layers.55.self_attn.v_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.56.input_layernorm.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.56.mlp.down_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.56.mlp.gate_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.56.mlp.up_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.56.post_attention_layernorm.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.56.self_attn.k_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.56.self_attn.o_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.56.self_attn.q_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.56.self_attn.rotary_emb.inv_freq": "pytorch_model-00007-of-00007.bin",
+    "model.layers.56.self_attn.v_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.57.input_layernorm.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.57.mlp.down_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.57.mlp.gate_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.57.mlp.up_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.57.post_attention_layernorm.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.57.self_attn.k_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.57.self_attn.o_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.57.self_attn.q_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.57.self_attn.rotary_emb.inv_freq": "pytorch_model-00007-of-00007.bin",
+    "model.layers.57.self_attn.v_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.58.input_layernorm.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.58.mlp.down_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.58.mlp.gate_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.58.mlp.up_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.58.post_attention_layernorm.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.58.self_attn.k_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.58.self_attn.o_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.58.self_attn.q_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.58.self_attn.rotary_emb.inv_freq": "pytorch_model-00007-of-00007.bin",
+    "model.layers.58.self_attn.v_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.59.input_layernorm.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.59.mlp.down_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.59.mlp.gate_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.59.mlp.up_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.59.post_attention_layernorm.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.59.self_attn.k_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.59.self_attn.o_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.59.self_attn.q_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.59.self_attn.rotary_emb.inv_freq": "pytorch_model-00007-of-00007.bin",
+    "model.layers.59.self_attn.v_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.6.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00007.bin",
+    "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.7.mlp.up_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.7.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00007.bin",
+    "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.8.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.8.mlp.down_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.8.mlp.up_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.8.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00007.bin",
+    "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.9.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.9.mlp.down_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.9.mlp.up_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.9.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00007.bin",
+    "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.norm.weight": "pytorch_model-00007-of-00007.bin"
+  }
+}
diff --git a/special_tokens_map.json b/special_tokens_map.json
new file mode 100644
index 0000000..d85ba6c
--- /dev/null
+++ b/special_tokens_map.json
@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}
diff --git a/tokenizer.model b/tokenizer.model
new file mode 100644
index 0000000..6c00c74
--- /dev/null
+++ b/tokenizer.model
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723
diff --git a/tokenizer_config.json b/tokenizer_config.json
new file mode 100644
index 0000000..48d369b
--- /dev/null
+++ b/tokenizer_config.json
@@ -0,0 +1,33 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "clean_up_tokenization_spaces": false,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "model_max_length": 2048,
+  "pad_token": null,
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}