commit 248caef6a313458e3797172d44d5d2644488b8e7
Author: ModelHub XC <noreply@modelhub.org.cn>
Date:   Wed Aug 19 10:36:13 2026 +0800

    初始化项目，由ModelHub XC社区提供模型
    
    Model: NucleusAI/nucleus-22B-token-500B
    Source: Original Platform

diff --git a/.gitattributes b/.gitattributes
new file mode 100644
index 0000000..3440220
--- /dev/null
+++ b/.gitattributes
@@ -0,0 +1,59 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bin.* filter=lfs diff=lfs merge=lfs -text
+*.bz2 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
+ 
+*.msgpack 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
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar 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
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zstandard filter=lfs diff=lfs merge=lfs -text
+*.tfevents* filter=lfs diff=lfs merge=lfs -text
+*.db* filter=lfs diff=lfs merge=lfs -text
+*.ark* filter=lfs diff=lfs merge=lfs -text
+**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text
+**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text
+**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text
+ 
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.gguf* filter=lfs diff=lfs merge=lfs -text
+*.ggml filter=lfs diff=lfs merge=lfs -text
+*.llamafile* filter=lfs diff=lfs merge=lfs -text
+*.pt2 filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+
+tokenizer.json filter=lfs diff=lfs merge=lfs -text
+model-00009-of-00009.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00002-of-00009.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00001-of-00009.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00004-of-00009.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00006-of-00009.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00003-of-00009.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00007-of-00009.safetensors filter=lfs diff=lfs merge=lfs -text
+tokenizer.model filter=lfs diff=lfs merge=lfs -text
+model-00008-of-00009.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00005-of-00009.safetensors filter=lfs diff=lfs merge=lfs -text
\ No newline at end of file
diff --git a/README.md b/README.md
new file mode 100644
index 0000000..e6d6a0d
--- /dev/null
+++ b/README.md
@@ -0,0 +1,93 @@
+---
+license: mit
+language:
+- en
+---
+
+# 🚀 Nucleus-22B-token-500B
+
+**Nucleus-22B-token-500B is a 22B parameters causal decoder-only model built by Nucleus.AI and trained on 500B tokens of [RefinedWeb](https://huggingface.co/datasets/tiiuae/falcon-refinedweb) along with curated corpora. It is made available under the MIT license.**
+
+*1T-token model coming soon* 😊.
+
+
+## What about Nucleus-22B-token-500B?
+
+* **It performs well compared to similar-size open-source models** (e.g., [MPT-7B](https://huggingface.co/mosaicml/mpt-7b), [StableLM](https://github.com/Stability-AI/StableLM), [RedPajama](https://huggingface.co/togethercomputer/RedPajama-INCITE-Base-7B-v0.1) etc.), thanks to being trained on 500B tokens of [RefinedWeb](https://huggingface.co/datasets/tiiuae/falcon-refinedweb) enhanced with curated corpora. See the [OpenLLM Leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard).
+* **It is made available under an MIT license**.
+* **It is trained by a small team of four passionate for Open Source**
+
+⚠️ **This is a raw, pretrained model, which should be further finetuned for most usecases.** 
+
+# Model Card for Nucleus-22B-token-500B
+
+## Model Details
+
+### Model Description
+
+- **Developed by:** NucleusAI;
+- **Model type:** Causal decoder-only;
+- **Language(s) (NLP):** English;
+- **License:** MIT.
+
+### Model Source
+
+- **Paper:** *coming soon*.
+
+## Uses
+
+### Direct Use
+
+Research on large language models; as a foundation for further specialization and finetuning for specific usecases (e.g., summarization, text generation, chatbot, etc.)
+
+### Out-of-Scope Use
+
+Production use without adequate assessment of risks and mitigation; any use cases which may be considered irresponsible or harmful.
+
+## Bias, Risks, and Limitations
+
+Nucleus-22B-token-500B is trained on English data only, and will not generalize appropriately to other languages. Furthermore, as it is trained on a large-scale corpora representative of the web, it will carry the stereotypes and biases commonly encountered online.
+
+### Recommendations
+
+We recommend users of Nucleus-22B-token-500B to consider finetuning it for the specific set of tasks of interest, and for guardrails and appropriate precautions to be taken for any production use.
+
+## How to Get Started with the Mode
+
+
+## Training Details
+
+### Training Data
+
+Nucleus-22B-token-500B was trained on 500B tokens of [RefinedWeb](https://huggingface.co/datasets/tiiuae/falcon-refinedweb), along with other corpora.
+
+| **Data source**    | **Fraction** | **Tokens** | **Sources**                       |
+|--------------------|--------------|------------|-----------------------------------|
+| [RefinedWeb-English](https://huggingface.co/datasets/tiiuae/falcon-refinedweb) | 75%          | 200B     | massive web crawl                 |
+| Books              | 7%           | 21B       |                                   |
+| Code               | 7%           | 21B        | Big Code, CodeNet                                  |
+| Technical          | 6%           | 19B        | arXiv        |
+| Math          | 5%           | 17B        | Mathematica, Khan Academy        |
+
+
+The data was tokenized with the tokenizer similar to Llama-[7B](https://huggingface.co/meta-llama/Llama-2-7b).
+
+### Training Procedure
+
+Nucleus-22B-token-500B was trained on 256 A100 80GB GPUs, using a FSDP
+
+#### Training Hyperparameters
+
+| **Hyperparameter** | **Value**  | **Comment**                               |
+|--------------------|------------|-------------------------------------------|
+| Precision          | `bfloat16` |                                           |
+| Optimizer          | AdamW      |                                           |
+| Learning rate      | 2e-4       | 8B tokens warm-up, cosine decay to 1.e-5 |
+| Weight decay       | 1e-1       |                                           |
+| Batch size         | 2048        | constant                         |
+| Context length         | 2048        | constant                         |
+
+
+#### Speeds, Sizes, Times
+
+Training happened in early August 2023 and took about two weeks.
\ No newline at end of file
diff --git a/config.json b/config.json
new file mode 100644
index 0000000..d9eefce
--- /dev/null
+++ b/config.json
@@ -0,0 +1,26 @@
+{
+  "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": 40,
+  "num_key_value_heads": 52,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.30.2",
+  "use_cache": true,
+  "vocab_size": 32000
+}
\ No newline at end of file
diff --git a/configuration.json b/configuration.json
new file mode 100644
index 0000000..bbeeda1
--- /dev/null
+++ b/configuration.json
@@ -0,0 +1 @@
+{"framework": "pytorch", "task": "text-generation", "allow_remote": true}
\ No newline at end of file
diff --git a/generation_config.json b/generation_config.json
new file mode 100644
index 0000000..89c31b8
--- /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": "4.30.2"
+}
diff --git a/model-00001-of-00009.safetensors b/model-00001-of-00009.safetensors
new file mode 100644
index 0000000..72f861f
--- /dev/null
+++ b/model-00001-of-00009.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00e7a41342638aa1bca3fa879ef1cee17ff74ab7ff6f41a31bfcd900ee0f400d
+size 9944389584
diff --git a/model-00002-of-00009.safetensors b/model-00002-of-00009.safetensors
new file mode 100644
index 0000000..3736e7d
--- /dev/null
+++ b/model-00002-of-00009.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:58ad98b7b2f8a9446338199c68782766f884ead49238e34824e7ae36ff5e2ee1
+size 9692207312
diff --git a/model-00003-of-00009.safetensors b/model-00003-of-00009.safetensors
new file mode 100644
index 0000000..10e0e7b
--- /dev/null
+++ b/model-00003-of-00009.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3fe2a1144b2fcf7c0288829cd65e14d038d7a5d6d19adac0077fb5232b09fad
+size 9746787008
diff --git a/model-00004-of-00009.safetensors b/model-00004-of-00009.safetensors
new file mode 100644
index 0000000..f4d0e9e
--- /dev/null
+++ b/model-00004-of-00009.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eecd1103c8de5728d54c7d5711a3cefd3c1ab9388f830160d9506041f08d927e
+size 9992153192
diff --git a/model-00005-of-00009.safetensors b/model-00005-of-00009.safetensors
new file mode 100644
index 0000000..b08e7a0
--- /dev/null
+++ b/model-00005-of-00009.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:513b3505ef2015ba5964d7481a5ac3f48491bae6c281b78083745a9f4757d34d
+size 9746733544
diff --git a/model-00006-of-00009.safetensors b/model-00006-of-00009.safetensors
new file mode 100644
index 0000000..38c119d
--- /dev/null
+++ b/model-00006-of-00009.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d51bea26310158cdf92cfcdcd22b012d8286178f168c93d718a9768fb53b182
+size 9869469920
diff --git a/model-00007-of-00009.safetensors b/model-00007-of-00009.safetensors
new file mode 100644
index 0000000..cec8900
--- /dev/null
+++ b/model-00007-of-00009.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4fa74c99e8c5825be472e9c0eedb49d9ec5ace76bb976222e03eef3b5570f9e6
+size 9869416816
diff --git a/model-00008-of-00009.safetensors b/model-00008-of-00009.safetensors
new file mode 100644
index 0000000..f8dc85e
--- /dev/null
+++ b/model-00008-of-00009.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0511a669a8efbdca08c351b40ebbd0d822ee17d067b5bae10941d29e02aee753
+size 9746787016
diff --git a/model-00009-of-00009.safetensors b/model-00009-of-00009.safetensors
new file mode 100644
index 0000000..a6f42e0
--- /dev/null
+++ b/model-00009-of-00009.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:18e2cb5ab08ae126edeb389c635fa61d35065c0d60a0ed0e8955022f8f917a0a
+size 8703949736
diff --git a/model.safetensors.index.json b/model.safetensors.index.json
new file mode 100644
index 0000000..3e50215
--- /dev/null
+++ b/model.safetensors.index.json
@@ -0,0 +1,410 @@
+{
+  "metadata": {
+    "total_size": 87311847424
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00009-of-00009.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00009.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00009.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00009.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.0.self_attn.rotary_emb.inv_freq": "model-00001-of-00009.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00009.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00009.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.1.self_attn.rotary_emb.inv_freq": "model-00001-of-00009.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.10.self_attn.rotary_emb.inv_freq": "model-00003-of-00009.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.11.self_attn.rotary_emb.inv_freq": "model-00003-of-00009.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.12.self_attn.rotary_emb.inv_freq": "model-00003-of-00009.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.13.self_attn.rotary_emb.inv_freq": "model-00003-of-00009.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.14.self_attn.rotary_emb.inv_freq": "model-00004-of-00009.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.15.self_attn.rotary_emb.inv_freq": "model-00004-of-00009.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.16.self_attn.rotary_emb.inv_freq": "model-00004-of-00009.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.17.self_attn.rotary_emb.inv_freq": "model-00004-of-00009.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.18.self_attn.rotary_emb.inv_freq": "model-00005-of-00009.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.19.self_attn.rotary_emb.inv_freq": "model-00005-of-00009.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00009.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00009.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.2.self_attn.rotary_emb.inv_freq": "model-00001-of-00009.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.20.self_attn.rotary_emb.inv_freq": "model-00005-of-00009.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.21.self_attn.rotary_emb.inv_freq": "model-00005-of-00009.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.22.self_attn.rotary_emb.inv_freq": "model-00005-of-00009.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.23.self_attn.rotary_emb.inv_freq": "model-00006-of-00009.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.24.self_attn.rotary_emb.inv_freq": "model-00006-of-00009.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.25.self_attn.rotary_emb.inv_freq": "model-00006-of-00009.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.26.self_attn.rotary_emb.inv_freq": "model-00006-of-00009.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.27.self_attn.rotary_emb.inv_freq": "model-00007-of-00009.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.28.self_attn.rotary_emb.inv_freq": "model-00007-of-00009.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.29.self_attn.rotary_emb.inv_freq": "model-00007-of-00009.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00009.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00009.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.3.self_attn.rotary_emb.inv_freq": "model-00001-of-00009.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.30.self_attn.rotary_emb.inv_freq": "model-00007-of-00009.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.31.self_attn.rotary_emb.inv_freq": "model-00007-of-00009.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.32.self_attn.rotary_emb.inv_freq": "model-00008-of-00009.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.33.self_attn.rotary_emb.inv_freq": "model-00008-of-00009.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.34.self_attn.rotary_emb.inv_freq": "model-00008-of-00009.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.35.self_attn.rotary_emb.inv_freq": "model-00008-of-00009.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-00009-of-00009.safetensors",
+    "model.layers.36.mlp.down_proj.weight": "model-00009-of-00009.safetensors",
+    "model.layers.36.mlp.gate_proj.weight": "model-00009-of-00009.safetensors",
+    "model.layers.36.mlp.up_proj.weight": "model-00009-of-00009.safetensors",
+    "model.layers.36.post_attention_layernorm.weight": "model-00009-of-00009.safetensors",
+    "model.layers.36.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.36.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.36.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.36.self_attn.rotary_emb.inv_freq": "model-00008-of-00009.safetensors",
+    "model.layers.36.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.37.input_layernorm.weight": "model-00009-of-00009.safetensors",
+    "model.layers.37.mlp.down_proj.weight": "model-00009-of-00009.safetensors",
+    "model.layers.37.mlp.gate_proj.weight": "model-00009-of-00009.safetensors",
+    "model.layers.37.mlp.up_proj.weight": "model-00009-of-00009.safetensors",
+    "model.layers.37.post_attention_layernorm.weight": "model-00009-of-00009.safetensors",
+    "model.layers.37.self_attn.k_proj.weight": "model-00009-of-00009.safetensors",
+    "model.layers.37.self_attn.o_proj.weight": "model-00009-of-00009.safetensors",
+    "model.layers.37.self_attn.q_proj.weight": "model-00009-of-00009.safetensors",
+    "model.layers.37.self_attn.rotary_emb.inv_freq": "model-00009-of-00009.safetensors",
+    "model.layers.37.self_attn.v_proj.weight": "model-00009-of-00009.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-00009-of-00009.safetensors",
+    "model.layers.38.mlp.down_proj.weight": "model-00009-of-00009.safetensors",
+    "model.layers.38.mlp.gate_proj.weight": "model-00009-of-00009.safetensors",
+    "model.layers.38.mlp.up_proj.weight": "model-00009-of-00009.safetensors",
+    "model.layers.38.post_attention_layernorm.weight": "model-00009-of-00009.safetensors",
+    "model.layers.38.self_attn.k_proj.weight": "model-00009-of-00009.safetensors",
+    "model.layers.38.self_attn.o_proj.weight": "model-00009-of-00009.safetensors",
+    "model.layers.38.self_attn.q_proj.weight": "model-00009-of-00009.safetensors",
+    "model.layers.38.self_attn.rotary_emb.inv_freq": "model-00009-of-00009.safetensors",
+    "model.layers.38.self_attn.v_proj.weight": "model-00009-of-00009.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-00009-of-00009.safetensors",
+    "model.layers.39.mlp.down_proj.weight": "model-00009-of-00009.safetensors",
+    "model.layers.39.mlp.gate_proj.weight": "model-00009-of-00009.safetensors",
+    "model.layers.39.mlp.up_proj.weight": "model-00009-of-00009.safetensors",
+    "model.layers.39.post_attention_layernorm.weight": "model-00009-of-00009.safetensors",
+    "model.layers.39.self_attn.k_proj.weight": "model-00009-of-00009.safetensors",
+    "model.layers.39.self_attn.o_proj.weight": "model-00009-of-00009.safetensors",
+    "model.layers.39.self_attn.q_proj.weight": "model-00009-of-00009.safetensors",
+    "model.layers.39.self_attn.rotary_emb.inv_freq": "model-00009-of-00009.safetensors",
+    "model.layers.39.self_attn.v_proj.weight": "model-00009-of-00009.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00002-of-00009.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.4.self_attn.rotary_emb.inv_freq": "model-00002-of-00009.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00002-of-00009.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.5.self_attn.rotary_emb.inv_freq": "model-00002-of-00009.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00002-of-00009.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.6.self_attn.rotary_emb.inv_freq": "model-00002-of-00009.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00002-of-00009.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.7.self_attn.rotary_emb.inv_freq": "model-00002-of-00009.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.8.self_attn.rotary_emb.inv_freq": "model-00002-of-00009.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.9.self_attn.rotary_emb.inv_freq": "model-00003-of-00009.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
+    "model.norm.weight": "model-00009-of-00009.safetensors"
+  }
+}
diff --git a/special_tokens_map.json b/special_tokens_map.json
new file mode 100644
index 0000000..451134b
--- /dev/null
+++ b/special_tokens_map.json
@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}
diff --git a/tokenizer.json b/tokenizer.json
new file mode 100644
index 0000000..21779d6
--- /dev/null
+++ b/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bcd04f0eadf90287bd26e1a183ac487d8a141b09b06aecb7725bbdd343640f2e
+size 1842767
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..5bb6e3b
--- /dev/null
+++ b/tokenizer_config.json
@@ -0,0 +1,33 @@
+{
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "clean_up_tokenization_spaces": false,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": null,
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}