commit 6f79d3c5dbd7ed03f5b8b2c599af10bb6be56c58
Author: ModelHub XC <noreply@modelhub.org.cn>
Date:   Fri Jun 26 19:10:15 2026 +0800

    初始化项目，由ModelHub XC社区提供模型
    
    Model: FP-KCV/jawani-sealion-gatra-2-9b
    Source: Original Platform

diff --git a/.gitattributes b/.gitattributes
new file mode 100644
index 0000000..52373fe
--- /dev/null
+++ b/.gitattributes
@@ -0,0 +1,36 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text
diff --git a/README.md b/README.md
new file mode 100644
index 0000000..83b21a6
--- /dev/null
+++ b/README.md
@@ -0,0 +1,190 @@
+---
+library_name: transformers
+tags: []
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
+
+- **Developed by:** @Turusore @paibar @Raditya-0
+- **Model type:** LLM
+- **Language(s) (NLP):** Javanese
+- **Finetuned from model [optional]:** aisingapore/Gemma-SEA-LION-v3-9B-IT
+
+
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
\ No newline at end of file
diff --git a/chat_template.jinja b/chat_template.jinja
new file mode 100644
index 0000000..6f24167
--- /dev/null
+++ b/chat_template.jinja
@@ -0,0 +1,4 @@
+{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'assistant') %}{% set role = 'model' %}{% else %}{% set role = message['role'] %}{% endif %}{{ '<start_of_turn>' + role + '
+' + message['content'] | trim + '<end_of_turn>
+' }}{% endfor %}{% if add_generation_prompt %}{{'<start_of_turn>model
+'}}{% endif %}
\ No newline at end of file
diff --git a/config.json b/config.json
new file mode 100644
index 0000000..106208a
--- /dev/null
+++ b/config.json
@@ -0,0 +1,85 @@
+{
+  "architectures": [
+    "Gemma2ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "attn_logit_softcapping": 50.0,
+  "bos_token_id": 2,
+  "cache_implementation": "hybrid",
+  "dtype": "float16",
+  "eos_token_id": [
+    1,
+    107
+  ],
+  "final_logit_softcapping": 30.0,
+  "head_dim": 256,
+  "hidden_act": "gelu_pytorch_tanh",
+  "hidden_activation": "gelu_pytorch_tanh",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "layer_types": [
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 8192,
+  "model_type": "gemma2",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 42,
+  "num_key_value_heads": 8,
+  "pad_token_id": 0,
+  "query_pre_attn_scalar": 256,
+  "rms_norm_eps": 1e-06,
+  "rope_parameters": {
+    "rope_theta": 10000.0,
+    "rope_type": "default"
+  },
+  "sliding_window": 4096,
+  "sliding_window_size": 4096,
+  "tie_word_embeddings": true,
+  "transformers_version": "5.0.0",
+  "use_bidirectional_attention": null,
+  "use_cache": true,
+  "vocab_size": 256000
+}
diff --git a/generation_config.json b/generation_config.json
new file mode 100644
index 0000000..d7a19c2
--- /dev/null
+++ b/generation_config.json
@@ -0,0 +1,11 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 2,
+  "cache_implementation": "hybrid",
+  "eos_token_id": [
+    1,
+    107
+  ],
+  "pad_token_id": 0,
+  "transformers_version": "5.0.0"
+}
diff --git a/model-00001-of-00010.safetensors b/model-00001-of-00010.safetensors
new file mode 100644
index 0000000..3131ca7
--- /dev/null
+++ b/model-00001-of-00010.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dbef9d4013b42b149936f3e6b1f3c64173ee09b526aff05febb1a0a6b8333982
+size 1937775976
diff --git a/model-00002-of-00010.safetensors b/model-00002-of-00010.safetensors
new file mode 100644
index 0000000..62e6033
--- /dev/null
+++ b/model-00002-of-00010.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:319b13861ca35493291ab7517aff8b186e897e50b8db352ee7d10109130eb3dd
+size 1981958352
diff --git a/model-00003-of-00010.safetensors b/model-00003-of-00010.safetensors
new file mode 100644
index 0000000..58e55f4
--- /dev/null
+++ b/model-00003-of-00010.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41bfc4939d5e18673570f34c206753951c0bfef9a8e129f4f6ab15894ec28a57
+size 1981958344
diff --git a/model-00004-of-00010.safetensors b/model-00004-of-00010.safetensors
new file mode 100644
index 0000000..d5cef5f
--- /dev/null
+++ b/model-00004-of-00010.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6de49ec1b94e9b5cc96b26572ca8d81ee61567d8a704c690999d33521b2a4a69
+size 1981958408
diff --git a/model-00005-of-00010.safetensors b/model-00005-of-00010.safetensors
new file mode 100644
index 0000000..c100ab3
--- /dev/null
+++ b/model-00005-of-00010.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fecfccf16a76bcc8528d0a433ed1ce915e5ce9e7bc493296f52492480c6f870b
+size 1981958408
diff --git a/model-00006-of-00010.safetensors b/model-00006-of-00010.safetensors
new file mode 100644
index 0000000..6e1da0d
--- /dev/null
+++ b/model-00006-of-00010.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec4beba8b9fcb6edc91dfae8abaff3e98c3a8a84cb1081af101017ac735b8c93
+size 1981958408
diff --git a/model-00007-of-00010.safetensors b/model-00007-of-00010.safetensors
new file mode 100644
index 0000000..b26dcbb
--- /dev/null
+++ b/model-00007-of-00010.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0b5af8ecafb4d6a9f4835a501d3f3a2bbab82f66333d4ab28d262f09f7ec896
+size 1981958408
diff --git a/model-00008-of-00010.safetensors b/model-00008-of-00010.safetensors
new file mode 100644
index 0000000..66efc05
--- /dev/null
+++ b/model-00008-of-00010.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f95d3fd45a78d4e4212a2371570f8e85d58112f33db87fea4c1101794da7b1b
+size 1981958408
diff --git a/model-00009-of-00010.safetensors b/model-00009-of-00010.safetensors
new file mode 100644
index 0000000..c7b46ef
--- /dev/null
+++ b/model-00009-of-00010.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b2fac50f9a087b8ccc4f3e629546cc611bcbb53c55a4b8bbcf223b790a7d58a
+size 1981958408
diff --git a/model-00010-of-00010.safetensors b/model-00010-of-00010.safetensors
new file mode 100644
index 0000000..e6ae0b6
--- /dev/null
+++ b/model-00010-of-00010.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:19ca934ab15cc34100d44055659e26738b1af5f372f05061dc016c98da69d5ea
+size 690022776
diff --git a/model.safetensors.index.json b/model.safetensors.index.json
new file mode 100644
index 0000000..5b2a83e
--- /dev/null
+++ b/model.safetensors.index.json
@@ -0,0 +1,472 @@
+{
+  "metadata": {
+    "total_parameters": 9241705984,
+    "total_size": 18483411968
+  },
+  "weight_map": {
+    "model.embed_tokens.weight": "model-00001-of-00010.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00010.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00010.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00002-of-00010.safetensors",
+    "model.layers.0.post_feedforward_layernorm.weight": "model-00002-of-00010.safetensors",
+    "model.layers.0.pre_feedforward_layernorm.weight": "model-00002-of-00010.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00002-of-00010.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00010.safetensors",
+    "model.layers.1.post_feedforward_layernorm.weight": "model-00002-of-00010.safetensors",
+    "model.layers.1.pre_feedforward_layernorm.weight": "model-00002-of-00010.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00003-of-00010.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00004-of-00010.safetensors",
+    "model.layers.10.post_feedforward_layernorm.weight": "model-00004-of-00010.safetensors",
+    "model.layers.10.pre_feedforward_layernorm.weight": "model-00004-of-00010.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00004-of-00010.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00004-of-00010.safetensors",
+    "model.layers.11.post_feedforward_layernorm.weight": "model-00004-of-00010.safetensors",
+    "model.layers.11.pre_feedforward_layernorm.weight": "model-00004-of-00010.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00004-of-00010.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00004-of-00010.safetensors",
+    "model.layers.12.post_feedforward_layernorm.weight": "model-00004-of-00010.safetensors",
+    "model.layers.12.pre_feedforward_layernorm.weight": "model-00004-of-00010.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00004-of-00010.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00004-of-00010.safetensors",
+    "model.layers.13.post_feedforward_layernorm.weight": "model-00004-of-00010.safetensors",
+    "model.layers.13.pre_feedforward_layernorm.weight": "model-00004-of-00010.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00004-of-00010.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00010.safetensors",
+    "model.layers.14.post_feedforward_layernorm.weight": "model-00004-of-00010.safetensors",
+    "model.layers.14.pre_feedforward_layernorm.weight": "model-00004-of-00010.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00004-of-00010.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00005-of-00010.safetensors",
+    "model.layers.15.post_feedforward_layernorm.weight": "model-00005-of-00010.safetensors",
+    "model.layers.15.pre_feedforward_layernorm.weight": "model-00005-of-00010.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00005-of-00010.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00005-of-00010.safetensors",
+    "model.layers.16.post_feedforward_layernorm.weight": "model-00005-of-00010.safetensors",
+    "model.layers.16.pre_feedforward_layernorm.weight": "model-00005-of-00010.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00005-of-00010.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00005-of-00010.safetensors",
+    "model.layers.17.post_feedforward_layernorm.weight": "model-00005-of-00010.safetensors",
+    "model.layers.17.pre_feedforward_layernorm.weight": "model-00005-of-00010.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00005-of-00010.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00005-of-00010.safetensors",
+    "model.layers.18.post_feedforward_layernorm.weight": "model-00005-of-00010.safetensors",
+    "model.layers.18.pre_feedforward_layernorm.weight": "model-00005-of-00010.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00005-of-00010.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00005-of-00010.safetensors",
+    "model.layers.19.post_feedforward_layernorm.weight": "model-00005-of-00010.safetensors",
+    "model.layers.19.pre_feedforward_layernorm.weight": "model-00005-of-00010.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00002-of-00010.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00010.safetensors",
+    "model.layers.2.post_feedforward_layernorm.weight": "model-00002-of-00010.safetensors",
+    "model.layers.2.pre_feedforward_layernorm.weight": "model-00002-of-00010.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00005-of-00010.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00006-of-00010.safetensors",
+    "model.layers.20.post_feedforward_layernorm.weight": "model-00006-of-00010.safetensors",
+    "model.layers.20.pre_feedforward_layernorm.weight": "model-00006-of-00010.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00006-of-00010.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00006-of-00010.safetensors",
+    "model.layers.21.post_feedforward_layernorm.weight": "model-00006-of-00010.safetensors",
+    "model.layers.21.pre_feedforward_layernorm.weight": "model-00006-of-00010.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00006-of-00010.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00006-of-00010.safetensors",
+    "model.layers.22.post_feedforward_layernorm.weight": "model-00006-of-00010.safetensors",
+    "model.layers.22.pre_feedforward_layernorm.weight": "model-00006-of-00010.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00006-of-00010.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00006-of-00010.safetensors",
+    "model.layers.23.post_feedforward_layernorm.weight": "model-00006-of-00010.safetensors",
+    "model.layers.23.pre_feedforward_layernorm.weight": "model-00006-of-00010.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00006-of-00010.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00006-of-00010.safetensors",
+    "model.layers.24.post_feedforward_layernorm.weight": "model-00006-of-00010.safetensors",
+    "model.layers.24.pre_feedforward_layernorm.weight": "model-00006-of-00010.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00006-of-00010.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00007-of-00010.safetensors",
+    "model.layers.25.post_feedforward_layernorm.weight": "model-00007-of-00010.safetensors",
+    "model.layers.25.pre_feedforward_layernorm.weight": "model-00007-of-00010.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00007-of-00010.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00007-of-00010.safetensors",
+    "model.layers.26.post_feedforward_layernorm.weight": "model-00007-of-00010.safetensors",
+    "model.layers.26.pre_feedforward_layernorm.weight": "model-00007-of-00010.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00007-of-00010.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00007-of-00010.safetensors",
+    "model.layers.27.post_feedforward_layernorm.weight": "model-00007-of-00010.safetensors",
+    "model.layers.27.pre_feedforward_layernorm.weight": "model-00007-of-00010.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00007-of-00010.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00007-of-00010.safetensors",
+    "model.layers.28.post_feedforward_layernorm.weight": "model-00007-of-00010.safetensors",
+    "model.layers.28.pre_feedforward_layernorm.weight": "model-00007-of-00010.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00007-of-00010.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00007-of-00010.safetensors",
+    "model.layers.29.post_feedforward_layernorm.weight": "model-00007-of-00010.safetensors",
+    "model.layers.29.pre_feedforward_layernorm.weight": "model-00007-of-00010.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00002-of-00010.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00010.safetensors",
+    "model.layers.3.post_feedforward_layernorm.weight": "model-00002-of-00010.safetensors",
+    "model.layers.3.pre_feedforward_layernorm.weight": "model-00002-of-00010.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00007-of-00010.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00008-of-00010.safetensors",
+    "model.layers.30.post_feedforward_layernorm.weight": "model-00008-of-00010.safetensors",
+    "model.layers.30.pre_feedforward_layernorm.weight": "model-00008-of-00010.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00008-of-00010.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00008-of-00010.safetensors",
+    "model.layers.31.post_feedforward_layernorm.weight": "model-00008-of-00010.safetensors",
+    "model.layers.31.pre_feedforward_layernorm.weight": "model-00008-of-00010.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00008-of-00010.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00008-of-00010.safetensors",
+    "model.layers.32.post_feedforward_layernorm.weight": "model-00008-of-00010.safetensors",
+    "model.layers.32.pre_feedforward_layernorm.weight": "model-00008-of-00010.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00008-of-00010.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00008-of-00010.safetensors",
+    "model.layers.33.post_feedforward_layernorm.weight": "model-00008-of-00010.safetensors",
+    "model.layers.33.pre_feedforward_layernorm.weight": "model-00008-of-00010.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00008-of-00010.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00008-of-00010.safetensors",
+    "model.layers.34.post_feedforward_layernorm.weight": "model-00008-of-00010.safetensors",
+    "model.layers.34.pre_feedforward_layernorm.weight": "model-00008-of-00010.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00008-of-00010.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00009-of-00010.safetensors",
+    "model.layers.35.post_feedforward_layernorm.weight": "model-00009-of-00010.safetensors",
+    "model.layers.35.pre_feedforward_layernorm.weight": "model-00009-of-00010.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-00009-of-00010.safetensors",
+    "model.layers.36.mlp.down_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.36.mlp.gate_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.36.mlp.up_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.36.post_attention_layernorm.weight": "model-00009-of-00010.safetensors",
+    "model.layers.36.post_feedforward_layernorm.weight": "model-00009-of-00010.safetensors",
+    "model.layers.36.pre_feedforward_layernorm.weight": "model-00009-of-00010.safetensors",
+    "model.layers.36.self_attn.k_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.36.self_attn.o_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.36.self_attn.q_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.36.self_attn.v_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.37.input_layernorm.weight": "model-00009-of-00010.safetensors",
+    "model.layers.37.mlp.down_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.37.mlp.gate_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.37.mlp.up_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.37.post_attention_layernorm.weight": "model-00009-of-00010.safetensors",
+    "model.layers.37.post_feedforward_layernorm.weight": "model-00009-of-00010.safetensors",
+    "model.layers.37.pre_feedforward_layernorm.weight": "model-00009-of-00010.safetensors",
+    "model.layers.37.self_attn.k_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.37.self_attn.o_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.37.self_attn.q_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.37.self_attn.v_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-00009-of-00010.safetensors",
+    "model.layers.38.mlp.down_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.38.mlp.gate_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.38.mlp.up_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.38.post_attention_layernorm.weight": "model-00009-of-00010.safetensors",
+    "model.layers.38.post_feedforward_layernorm.weight": "model-00009-of-00010.safetensors",
+    "model.layers.38.pre_feedforward_layernorm.weight": "model-00009-of-00010.safetensors",
+    "model.layers.38.self_attn.k_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.38.self_attn.o_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.38.self_attn.q_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.38.self_attn.v_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-00009-of-00010.safetensors",
+    "model.layers.39.mlp.down_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.39.mlp.gate_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.39.mlp.up_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.39.post_attention_layernorm.weight": "model-00009-of-00010.safetensors",
+    "model.layers.39.post_feedforward_layernorm.weight": "model-00009-of-00010.safetensors",
+    "model.layers.39.pre_feedforward_layernorm.weight": "model-00009-of-00010.safetensors",
+    "model.layers.39.self_attn.k_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.39.self_attn.o_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.39.self_attn.q_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.39.self_attn.v_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00002-of-00010.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00010.safetensors",
+    "model.layers.4.post_feedforward_layernorm.weight": "model-00002-of-00010.safetensors",
+    "model.layers.4.pre_feedforward_layernorm.weight": "model-00002-of-00010.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.40.input_layernorm.weight": "model-00009-of-00010.safetensors",
+    "model.layers.40.mlp.down_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.40.mlp.gate_proj.weight": "model-00010-of-00010.safetensors",
+    "model.layers.40.mlp.up_proj.weight": "model-00010-of-00010.safetensors",
+    "model.layers.40.post_attention_layernorm.weight": "model-00010-of-00010.safetensors",
+    "model.layers.40.post_feedforward_layernorm.weight": "model-00010-of-00010.safetensors",
+    "model.layers.40.pre_feedforward_layernorm.weight": "model-00010-of-00010.safetensors",
+    "model.layers.40.self_attn.k_proj.weight": "model-00010-of-00010.safetensors",
+    "model.layers.40.self_attn.o_proj.weight": "model-00010-of-00010.safetensors",
+    "model.layers.40.self_attn.q_proj.weight": "model-00010-of-00010.safetensors",
+    "model.layers.40.self_attn.v_proj.weight": "model-00010-of-00010.safetensors",
+    "model.layers.41.input_layernorm.weight": "model-00010-of-00010.safetensors",
+    "model.layers.41.mlp.down_proj.weight": "model-00010-of-00010.safetensors",
+    "model.layers.41.mlp.gate_proj.weight": "model-00010-of-00010.safetensors",
+    "model.layers.41.mlp.up_proj.weight": "model-00010-of-00010.safetensors",
+    "model.layers.41.post_attention_layernorm.weight": "model-00010-of-00010.safetensors",
+    "model.layers.41.post_feedforward_layernorm.weight": "model-00010-of-00010.safetensors",
+    "model.layers.41.pre_feedforward_layernorm.weight": "model-00010-of-00010.safetensors",
+    "model.layers.41.self_attn.k_proj.weight": "model-00010-of-00010.safetensors",
+    "model.layers.41.self_attn.o_proj.weight": "model-00010-of-00010.safetensors",
+    "model.layers.41.self_attn.q_proj.weight": "model-00010-of-00010.safetensors",
+    "model.layers.41.self_attn.v_proj.weight": "model-00010-of-00010.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00002-of-00010.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00003-of-00010.safetensors",
+    "model.layers.5.post_feedforward_layernorm.weight": "model-00003-of-00010.safetensors",
+    "model.layers.5.pre_feedforward_layernorm.weight": "model-00003-of-00010.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00003-of-00010.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00003-of-00010.safetensors",
+    "model.layers.6.post_feedforward_layernorm.weight": "model-00003-of-00010.safetensors",
+    "model.layers.6.pre_feedforward_layernorm.weight": "model-00003-of-00010.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00003-of-00010.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00010.safetensors",
+    "model.layers.7.post_feedforward_layernorm.weight": "model-00003-of-00010.safetensors",
+    "model.layers.7.pre_feedforward_layernorm.weight": "model-00003-of-00010.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00003-of-00010.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00010.safetensors",
+    "model.layers.8.post_feedforward_layernorm.weight": "model-00003-of-00010.safetensors",
+    "model.layers.8.pre_feedforward_layernorm.weight": "model-00003-of-00010.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00003-of-00010.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00010.safetensors",
+    "model.layers.9.post_feedforward_layernorm.weight": "model-00003-of-00010.safetensors",
+    "model.layers.9.pre_feedforward_layernorm.weight": "model-00003-of-00010.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00010.safetensors",
+    "model.norm.weight": "model-00010-of-00010.safetensors"
+  }
+}
diff --git a/tokenizer.json b/tokenizer.json
new file mode 100644
index 0000000..6523cc0
--- /dev/null
+++ b/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:394ace002a144ac6ad5486387502f2d36f70c087310c3d907857240c76fcb36e
+size 34362748
diff --git a/tokenizer_config.json b/tokenizer_config.json
new file mode 100644
index 0000000..095b107
--- /dev/null
+++ b/tokenizer_config.json
@@ -0,0 +1,19 @@
+{
+  "backend": "tokenizers",
+  "bos_token": "<bos>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<eos>",
+  "extra_special_tokens": [
+    "<start_of_turn>",
+    "<end_of_turn>"
+  ],
+  "is_local": true,
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<eos>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "GemmaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}