diff --git a/README.md b/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..bc5f30d6632ac0efdc7be2e9095e9e9579af2e33
--- /dev/null
+++ b/README.md
@@ -0,0 +1,199 @@
+---
+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:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## 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/config.json b/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..23c001baacf57bec3522e231eb41e683bbd9eeb4
--- /dev/null
+++ b/config.json
@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "./merged_model",
+  "architectures": [
+    "Qwen2Model"
+  ],
+  "attention_dropout": 0.0,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 8192,
+  "initializer_range": 0.02,
+  "intermediate_size": 29568,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 80,
+  "model_type": "qwen2",
+  "num_attention_heads": 64,
+  "num_hidden_layers": 86,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.48.1",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 151646
+}
diff --git a/model-00001-of-00066.safetensors b/model-00001-of-00066.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..60918ce57268a37093e5710c7c306a7cfb4b7ad4
--- /dev/null
+++ b/model-00001-of-00066.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:614e38efffed8804cc054f194743b4401787c12f89671cf411f57370cd672e3d
+size 4969136264
diff --git a/model-00002-of-00066.safetensors b/model-00002-of-00066.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..2bd520e07d62d973b8ed3620232b8a96edb14a9e
--- /dev/null
+++ b/model-00002-of-00066.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b7394da4e068ac385f8abfe401f1efa26a86b18c43261090b424fd46bf914f17
+size 4114761736
diff --git a/model-00003-of-00066.safetensors b/model-00003-of-00066.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..2cd6b1798a7bc73dad8cecad096c8bb4d46a6061
--- /dev/null
+++ b/model-00003-of-00066.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c5c179594b0ba0fff1861ceda0b00407967fe74b459092c280df0e18edb5419d
+size 4479624584
diff --git a/model-00004-of-00066.safetensors b/model-00004-of-00066.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..1ad110e1c2555aeb47e4de5e181ac9318923553e
--- /dev/null
+++ b/model-00004-of-00066.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:60a4d0040574d57ba35ab62b2072f88301254dd8c272cbd34258caa0d7328747
+size 4479624584
diff --git a/model-00005-of-00066.safetensors b/model-00005-of-00066.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..0d942757b35391eb0cee741bef720c7088a2efe3
--- /dev/null
+++ b/model-00005-of-00066.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:275a5ecb9ae1e3b387b972e5bb06ef2c309d7f13efba2d30ce3beb3cdb5ec500
+size 4815276256
diff --git a/model-00006-of-00066.safetensors b/model-00006-of-00066.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..bd8744772a6141ba86439936b361fad6fdecd802
--- /dev/null
+++ b/model-00006-of-00066.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f4a8ec64bd0db9546b5158119097b3fed93caefcc7138aca451c568e9e875d3
+size 4748060152
diff --git a/model-00007-of-00066.safetensors b/model-00007-of-00066.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..5446cffc33e8c448a9f0794457d9a1794949796f
--- /dev/null
+++ b/model-00007-of-00066.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c11bb28848b3a147c82ba17e597e9412ab0e1d2e3358113c5a096495db611202
+size 4479624584
diff --git a/model-00008-of-00066.safetensors b/model-00008-of-00066.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..843b96533065a32bacab8149bb57d45c7e493a36
--- /dev/null
+++ b/model-00008-of-00066.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:20605a577c442a845fdf99915c04d8a021123bebd465e0f409b6b939035da954
+size 4815276256
diff --git a/model-00009-of-00066.safetensors b/model-00009-of-00066.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..7cb877975f88f678ab3aed5ec7017b8ed33317d0
--- /dev/null
+++ b/model-00009-of-00066.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c65c9f50f2458a160b691bd9fb3a7e7d6fe0f6dbe840072c7216dc7f603d040
+size 4748060168
diff --git a/model-00010-of-00066.safetensors b/model-00010-of-00066.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..3d7400673f8d11d86d3624ee5fd49a9c435c0037
--- /dev/null
+++ b/model-00010-of-00066.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b09a9a0063673c7fe6d2f530ed87705ff270585107db91131071ccb3d7905ade
+size 4479624600
diff --git a/model-00011-of-00066.safetensors b/model-00011-of-00066.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..3d6ccdb5e747abb2c20e0d861eba7ebdebd71046
--- /dev/null
+++ b/model-00011-of-00066.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a615dd63dbe2ee9dc122d73ac476d8682cd9987f8bbdb307186286c29bb87f2a
+size 4815276272
diff --git a/model-00012-of-00066.safetensors b/model-00012-of-00066.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..50e0dd4a54bb1127d6a4ee3928a0fd65ed007f4a
--- /dev/null
+++ b/model-00012-of-00066.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:010678924de63c200ca95e5f33e3a032990ac48d22caa933086ee5a642bf8f72
+size 4748060168
diff --git a/model-00013-of-00066.safetensors b/model-00013-of-00066.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..d47daafe340d032998693abaf124b33d0afe0876
--- /dev/null
+++ b/model-00013-of-00066.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af8b7c464579d6996082ccb7d725fcfd316120e5c451c5a57fb690182470e665
+size 4479624600
diff --git a/model-00014-of-00066.safetensors b/model-00014-of-00066.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..e1a184c18923a29d7f8fd24c9a8c7e73591a50d1
--- /dev/null
+++ b/model-00014-of-00066.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32d94f3addd951374bdc78d8a9029d95ab328b20ea26988260a3d6bf072c175c
+size 4815276272
diff --git a/model-00015-of-00066.safetensors b/model-00015-of-00066.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..e056d4c3eec2a2d565a8b71242f0efd58f8c8a06
--- /dev/null
+++ b/model-00015-of-00066.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3fa5351d847583f44bb1e544ea41d54e262a54ff6b59e21afdbbc1fcaf382cbb
+size 4748060168
diff --git a/model-00016-of-00066.safetensors b/model-00016-of-00066.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..aceb64df71c30c2b24ecf20da8ecd2903fd32e95
--- /dev/null
+++ b/model-00016-of-00066.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21018f469e27312d125e9297f88fa81ece30bb84b2834a0aa492d994b66f3719
+size 4479624600
diff --git a/model-00017-of-00066.safetensors b/model-00017-of-00066.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..21bc33e968693860dc18396e450c61175bd6793e
--- /dev/null
+++ b/model-00017-of-00066.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a97c155078d3c242d4b72c0d817305c117bf6860abc6b70ce74f11b764ee00a
+size 4815276272
diff --git a/model-00018-of-00066.safetensors b/model-00018-of-00066.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..751b92fdbdd08683614cb8addcb29962e52682d0
--- /dev/null
+++ b/model-00018-of-00066.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b173d7068a85a97e0d63f2e7501ce177bb6fd996e13a5b18839c082ed213b879
+size 4748060168
diff --git a/model-00019-of-00066.safetensors b/model-00019-of-00066.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..9eccbd9abf15dfebf67670857f5ee07eedcb2435
--- /dev/null
+++ b/model-00019-of-00066.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c74543be13a764b10f1aedc7cdb1c468bae9030f612d9fc06f10f5799e1f54c9
+size 4479624600
diff --git a/model-00020-of-00066.safetensors b/model-00020-of-00066.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..949dc55cabb4c365fca7c7ff0cf96eea276bc9c4
--- /dev/null
+++ b/model-00020-of-00066.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e6a646a84773557bf28ce0a3c5e4aaa97293f6757ec011688e15be220d02635
+size 4815276272
diff --git a/model-00021-of-00066.safetensors b/model-00021-of-00066.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..7709f92479495c6edcea35028dcfdb391f7c76a4
--- /dev/null
+++ b/model-00021-of-00066.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a1e4324984d470883a35b9883d11ece35f7f52e42fd3a26f987e1fdf8d49a54
+size 4748060168
diff --git a/model-00022-of-00066.safetensors b/model-00022-of-00066.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..78d29ca05e58e8056d192eade871376be1fc7d0c
--- /dev/null
+++ b/model-00022-of-00066.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:99045083943c5bb5d9552eaed51ef74e223f4b128bc2943280287bfd4017ab1e
+size 4479624600
diff --git a/model-00023-of-00066.safetensors b/model-00023-of-00066.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..2a6fd5151d84b9b118b252ef3c814359e1aa97bc
--- /dev/null
+++ b/model-00023-of-00066.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d387c6f1d9772dcdb91ebba614d06db04b6870d3b0be46f79e6e0723ce98bd92
+size 4815276272
diff --git a/model-00024-of-00066.safetensors b/model-00024-of-00066.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..17ec53f6c0527c7836d4477434545809ec560cf8
--- /dev/null
+++ b/model-00024-of-00066.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:893707cb31f2981e714b8936d696a3315d022b1658072287d0fa04c0c7f71dd9
+size 4748060168
diff --git a/model-00025-of-00066.safetensors b/model-00025-of-00066.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..4776e8bb0b5c25d8ad79494d6dd4863a1d50cd90
--- /dev/null
+++ b/model-00025-of-00066.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:216945a3c5c392bb4e13b29aa4513c3e6b14db7959fd32cbd0350a230d0bd61e
+size 4479624600
diff --git a/model-00026-of-00066.safetensors b/model-00026-of-00066.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..30e74888c5eb739d5b684bb8bf89dcff56a4fd08
--- /dev/null
+++ b/model-00026-of-00066.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:95454ef182095c302ba8354be5c7fda5f0d464c0838e7c2969bdb215d5e6d2a4
+size 4815276272
diff --git a/model-00027-of-00066.safetensors b/model-00027-of-00066.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..1c5c6a86704130b959dc4e605972e3bfd0529c76
--- /dev/null
+++ b/model-00027-of-00066.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee0a700131743cbb0d9e53c3499da1d0d55c2297a81c977865ea4cd8a37c97d9
+size 4748060168
diff --git a/model-00028-of-00066.safetensors b/model-00028-of-00066.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..57671ca400e5d5a4c3fa29d81b8a200c7dcd1d18
--- /dev/null
+++ b/model-00028-of-00066.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29f70aeb5de6069e47bd150ad7dbbc38f0fd0847eed7a9329c2f676fec5e4fbb
+size 4479624600
diff --git a/model-00029-of-00066.safetensors b/model-00029-of-00066.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..1de5f4570b5dfd46c72c5938742b62f3ad3914c8
--- /dev/null
+++ b/model-00029-of-00066.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49e8fa5d023d9d158139bf9690139099de73efb65ddf44e3599bf5e32278a99c
+size 4815276272
diff --git a/model-00030-of-00066.safetensors b/model-00030-of-00066.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..523c0bf5b74e967fca5f2ccc6bf6e477097d95c0
--- /dev/null
+++ b/model-00030-of-00066.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4110f5627f78e55dbb5cb58f070b0c4d8fda2ab4bad60202aac609e883efbf66
+size 4748060168
diff --git a/model-00031-of-00066.safetensors b/model-00031-of-00066.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..17878735155e5934cdabf6207af528a4f81a10b4
--- /dev/null
+++ b/model-00031-of-00066.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32d13f15640e76c08ec540e9be331cf434556e4971d580811657666f39bdffe8
+size 4479624600
diff --git a/model-00032-of-00066.safetensors b/model-00032-of-00066.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..db4ce8f390a40e6cccef50b38ed1d5dcd5904108
--- /dev/null
+++ b/model-00032-of-00066.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92c7f6fe7190679838c55dce65a83d0bce187e21c671c2188c9f177763e83486
+size 4815276272
diff --git a/model-00033-of-00066.safetensors b/model-00033-of-00066.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..53c4bbc4dc0fbc5acbcf636f5fc5a6b21f7a8395
--- /dev/null
+++ b/model-00033-of-00066.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b28f5af8f6f51a34e60452afbab6c3e8cf51ee343b37a4b40b56777bf396cc9
+size 4748060168
diff --git a/model-00034-of-00066.safetensors b/model-00034-of-00066.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..f99ab1845cd63035292102f53860c0b06c594460
--- /dev/null
+++ b/model-00034-of-00066.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e963f5287657b8e7407a99efb1847fcad36fd3aa19331b335a596a42e28a729c
+size 4479624600
diff --git a/model-00035-of-00066.safetensors b/model-00035-of-00066.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..18e755c983dd544ea35eddd5ba9d8cc68746cb50
--- /dev/null
+++ b/model-00035-of-00066.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8495bac7ccb8345dc14e6854c554c4f84d4baab335cb2d06abb811f05dea8b8a
+size 4815276272
diff --git a/model-00036-of-00066.safetensors b/model-00036-of-00066.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..99f2037a852cb452e0b0d5fa97496faaaf51a36f
--- /dev/null
+++ b/model-00036-of-00066.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9dd7148ac63b9d91e88b65d01ca935065240003112f161de77d8634e4eeef605
+size 4748060168
diff --git a/model-00037-of-00066.safetensors b/model-00037-of-00066.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..27eb2b687dcf5e2347ae8507916aed107bc7ccf1
--- /dev/null
+++ b/model-00037-of-00066.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a73c2155b044bf8e194f434705f150f2d569203b73160970b710f4211bf5f8d
+size 4479624600
diff --git a/model-00038-of-00066.safetensors b/model-00038-of-00066.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..a91945818553de22feb050b7c8d3892408527f8e
--- /dev/null
+++ b/model-00038-of-00066.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:544db0d80b9760501814002c934a3dc9fe9e98a78c191a980f7ce67ffd52a018
+size 4815276272
diff --git a/model-00039-of-00066.safetensors b/model-00039-of-00066.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..bab1f0aca479f0eab5c54952ce0a408b356300f3
--- /dev/null
+++ b/model-00039-of-00066.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec5a7f0342c41a0bcfaabf8526702066ed9c128452956ef12eb3a9aee0a0d9ca
+size 4748060168
diff --git a/model-00040-of-00066.safetensors b/model-00040-of-00066.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..f407de2294dc00c357fb4c3b6257a00d8fdba62e
--- /dev/null
+++ b/model-00040-of-00066.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ee4837975609051ea4affca03940cad90d00125b70703014e314e3c607f18bb
+size 4479624600
diff --git a/model-00041-of-00066.safetensors b/model-00041-of-00066.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..b84dc029533e98face2d773bacc4643b2b270c7c
--- /dev/null
+++ b/model-00041-of-00066.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2036c0328b65d92c501a0f0d97b1d9753b6207543ed6b5a97cf4d0f607946088
+size 4815276272
diff --git a/model-00042-of-00066.safetensors b/model-00042-of-00066.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..eaa1575bcd35e81be430972a477e06dbcc7730f9
--- /dev/null
+++ b/model-00042-of-00066.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9536dd7bd478550ca671e8d2e32bb00322f34a24a39dcea9f83fc1019f415c48
+size 4748060168
diff --git a/model-00043-of-00066.safetensors b/model-00043-of-00066.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..8c787799961b247bb27356117c11e09b1834f896
--- /dev/null
+++ b/model-00043-of-00066.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:901c258c2eb17bad2c4b33dbc39090b10d88e48823f1e162cc1f42d66441a290
+size 4479624600
diff --git a/model-00044-of-00066.safetensors b/model-00044-of-00066.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..3b5b59fadd3ee0142533b726b7488342af7248e3
--- /dev/null
+++ b/model-00044-of-00066.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e9e5b66d7d79badcb034a20e54244d2368f534902e15ccad4b81392b6c418a5
+size 4815276272
diff --git a/model-00045-of-00066.safetensors b/model-00045-of-00066.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..7a67d95e8f7d2710ebe97e9c65e9165b7b280642
--- /dev/null
+++ b/model-00045-of-00066.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0335bd762e8d0c258a840eba8b1db99b6c1a1f78297453712507041eed862559
+size 4748060168
diff --git a/model-00046-of-00066.safetensors b/model-00046-of-00066.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..948e21476f474514023c40fae3fba48208f2eca4
--- /dev/null
+++ b/model-00046-of-00066.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24b8f494b219f288697afd3f4def4196c4b2fd601f46c792f8591c770dc31642
+size 4479624600
diff --git a/model-00047-of-00066.safetensors b/model-00047-of-00066.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..f85511e07992fa145ed87e90d98dbc410762b35d
--- /dev/null
+++ b/model-00047-of-00066.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36e9d3b6a1869fe1c9bd360d93f5a0f02ea1aa6ec6668550251821a0242f32ba
+size 4815276272
diff --git a/model-00048-of-00066.safetensors b/model-00048-of-00066.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..cf19a9fadc168208ffee3a8a605af78e350663f1
--- /dev/null
+++ b/model-00048-of-00066.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc5ca75b58301dc0bf704864b72976043e4c8b36274104dd099b06adef9a95ac
+size 4748060168
diff --git a/model-00049-of-00066.safetensors b/model-00049-of-00066.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..fdfa11187702120c23217d81b584ab470748c9e3
--- /dev/null
+++ b/model-00049-of-00066.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb4622b009c9a55394036f51a36fbe86038feb4e0f8309dbde311bd9486add23
+size 4479624600
diff --git a/model-00050-of-00066.safetensors b/model-00050-of-00066.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..40d89deb6cc20d5663595b5a6c3b660c12f507a5
--- /dev/null
+++ b/model-00050-of-00066.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5dc39d6e3e4a0eece4313cadf952e9faeb8b9ef08e12be277b5197f8df7ec7b0
+size 4815276272
diff --git a/model-00051-of-00066.safetensors b/model-00051-of-00066.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..f000dc5fb72fa96c7fa49da19fe4fc0ec8623259
--- /dev/null
+++ b/model-00051-of-00066.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4eaa23f8899212958486c936cce552bb302ba72dc88d1951e8a49d71d3118540
+size 4748060168
diff --git a/model-00052-of-00066.safetensors b/model-00052-of-00066.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..248be8caf9124774bf69e8b783fd338a4f045b05
--- /dev/null
+++ b/model-00052-of-00066.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a459d59a999ae656b06a8a9caf440f94fc25c12abb5dda1a5f0cf822e930a62d
+size 4479624600
diff --git a/model-00053-of-00066.safetensors b/model-00053-of-00066.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..b4aac4b1076bd1a705a5887e6d30f2127042f799
--- /dev/null
+++ b/model-00053-of-00066.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ce290b4d19b9739c6af0d722738b6104a79a0727268891efcc144ea2b50c939
+size 4815276272
diff --git a/model-00054-of-00066.safetensors b/model-00054-of-00066.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..0873639305a52c8e23aaf3c2f01eb7da329b3a30
--- /dev/null
+++ b/model-00054-of-00066.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d1359a3e1d51c6b381d5cd6605aafbc894d734f670739ba3baa005d6bd17728
+size 4748060168
diff --git a/model-00055-of-00066.safetensors b/model-00055-of-00066.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..67dbd8ec00e49b87d279dfa9e8c25cda36495782
--- /dev/null
+++ b/model-00055-of-00066.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e10a6de4092b9e6599c2215f0379c019048b726973b3a465ea41177cc6e80db9
+size 4479624600
diff --git a/model-00056-of-00066.safetensors b/model-00056-of-00066.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..bf20e68874cb4feadc070bf88380f1e406004611
--- /dev/null
+++ b/model-00056-of-00066.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc92b3ecaba25c012174ebf0bb7301b53d876708df0f4b83e07f7a16b9c249a1
+size 4815276272
diff --git a/model-00057-of-00066.safetensors b/model-00057-of-00066.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..1411bb264f9acf458034d7f4b8354bc939cafda6
--- /dev/null
+++ b/model-00057-of-00066.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ab83d29d52df0cc861c526f47c437c25176e974995afa11d6399fd25784569c
+size 4748060168
diff --git a/model-00058-of-00066.safetensors b/model-00058-of-00066.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..820571a91f694e503286eb185192c45f47d065ee
--- /dev/null
+++ b/model-00058-of-00066.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e3dc9dcdc639694cff5f2776399c6006b337197e74abf52ae84ce9745897229
+size 4479624600
diff --git a/model-00059-of-00066.safetensors b/model-00059-of-00066.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..d292f45d1f5bdfa3f8e7cc7eb8fdc3d1b1c9910e
--- /dev/null
+++ b/model-00059-of-00066.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8585971fff67785369e27a267dbd5f9894ea9d3cd81c944590ce9e9d346690f
+size 4815276272
diff --git a/model-00060-of-00066.safetensors b/model-00060-of-00066.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..80383e6b966d60f518572344e00b2bdc2700d8e3
--- /dev/null
+++ b/model-00060-of-00066.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a88d05ffdcc83aa4631a07dc77b5e00abd69b5f96cfd3b8ccf3993627b316c8
+size 4748060168
diff --git a/model-00061-of-00066.safetensors b/model-00061-of-00066.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..8d5c73ee2e60cae14a6a065e28cd498f4661427e
--- /dev/null
+++ b/model-00061-of-00066.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d9af72fb0210e6cf268712623d5150c720c82c211bed3ffdf38c37dc550a3a7
+size 4479624600
diff --git a/model-00062-of-00066.safetensors b/model-00062-of-00066.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..71367e28a414895f046a94e7f63d02f869e2615d
--- /dev/null
+++ b/model-00062-of-00066.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:65599f2f4ce12b39b265fafea7f95269956b0fbe3f1f8d2a317d945cf858b3df
+size 4815276272
diff --git a/model-00063-of-00066.safetensors b/model-00063-of-00066.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..523c32d6e822a771067b12d9aeaa2f4430604d7e
--- /dev/null
+++ b/model-00063-of-00066.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8afa08bec36b67b1db2ed2a7e899f6f0b12836815ea9e13028b3262e6aac14f3
+size 4748060168
diff --git a/model-00064-of-00066.safetensors b/model-00064-of-00066.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..53a8a79537ac7a8482ede0c8503597e056a6d7e6
--- /dev/null
+++ b/model-00064-of-00066.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8922bdd78094aa9df91d7e8365af3b8e177962ff00c9495732dabd392acd10b2
+size 4479624600
diff --git a/model-00065-of-00066.safetensors b/model-00065-of-00066.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..cff688924926df8acd1a4394f0f17aa635c7c444
--- /dev/null
+++ b/model-00065-of-00066.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb07a1c00a645d0b0e2c85b12db3af80c25318d5b062a702206b48a9c7244dab
+size 4815276272
diff --git a/model-00066-of-00066.safetensors b/model-00066-of-00066.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..8af731b5fc04e18961d790f24febe0709ccaf33a
--- /dev/null
+++ b/model-00066-of-00066.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c0f20247efa641139525312ab43280ebb1130c9b123d7b0a8277a07c1df44ce
+size 3175187192
diff --git a/model.safetensors.index.json b/model.safetensors.index.json
new file mode 100644
index 0000000000000000000000000000000000000000..e46f3079bae762bd6bc639d8fa2058b024d4295d
--- /dev/null
+++ b/model.safetensors.index.json
@@ -0,0 +1,1041 @@
+{
+  "metadata": {
+    "total_size": 306892718080
+  },
+  "weight_map": {
+    "embed_tokens.weight": "model-00001-of-00066.safetensors",
+    "layers.0.input_layernorm.weight": "model-00002-of-00066.safetensors",
+    "layers.0.mlp.down_proj.weight": "model-00002-of-00066.safetensors",
+    "layers.0.mlp.gate_proj.weight": "model-00002-of-00066.safetensors",
+    "layers.0.mlp.up_proj.weight": "model-00002-of-00066.safetensors",
+    "layers.0.post_attention_layernorm.weight": "model-00002-of-00066.safetensors",
+    "layers.0.self_attn.k_proj.bias": "model-00002-of-00066.safetensors",
+    "layers.0.self_attn.k_proj.weight": "model-00002-of-00066.safetensors",
+    "layers.0.self_attn.o_proj.weight": "model-00002-of-00066.safetensors",
+    "layers.0.self_attn.q_proj.bias": "model-00002-of-00066.safetensors",
+    "layers.0.self_attn.q_proj.weight": "model-00002-of-00066.safetensors",
+    "layers.0.self_attn.v_proj.bias": "model-00002-of-00066.safetensors",
+    "layers.0.self_attn.v_proj.weight": "model-00002-of-00066.safetensors",
+    "layers.1.input_layernorm.weight": "model-00003-of-00066.safetensors",
+    "layers.1.mlp.down_proj.weight": "model-00003-of-00066.safetensors",
+    "layers.1.mlp.gate_proj.weight": "model-00003-of-00066.safetensors",
+    "layers.1.mlp.up_proj.weight": "model-00003-of-00066.safetensors",
+    "layers.1.post_attention_layernorm.weight": "model-00003-of-00066.safetensors",
+    "layers.1.self_attn.k_proj.bias": "model-00002-of-00066.safetensors",
+    "layers.1.self_attn.k_proj.weight": "model-00002-of-00066.safetensors",
+    "layers.1.self_attn.o_proj.weight": "model-00002-of-00066.safetensors",
+    "layers.1.self_attn.q_proj.bias": "model-00002-of-00066.safetensors",
+    "layers.1.self_attn.q_proj.weight": "model-00002-of-00066.safetensors",
+    "layers.1.self_attn.v_proj.bias": "model-00002-of-00066.safetensors",
+    "layers.1.self_attn.v_proj.weight": "model-00002-of-00066.safetensors",
+    "layers.10.input_layernorm.weight": "model-00010-of-00066.safetensors",
+    "layers.10.mlp.down_proj.weight": "model-00010-of-00066.safetensors",
+    "layers.10.mlp.gate_proj.weight": "model-00009-of-00066.safetensors",
+    "layers.10.mlp.up_proj.weight": "model-00010-of-00066.safetensors",
+    "layers.10.post_attention_layernorm.weight": "model-00010-of-00066.safetensors",
+    "layers.10.self_attn.k_proj.bias": "model-00009-of-00066.safetensors",
+    "layers.10.self_attn.k_proj.weight": "model-00009-of-00066.safetensors",
+    "layers.10.self_attn.o_proj.weight": "model-00009-of-00066.safetensors",
+    "layers.10.self_attn.q_proj.bias": "model-00009-of-00066.safetensors",
+    "layers.10.self_attn.q_proj.weight": "model-00009-of-00066.safetensors",
+    "layers.10.self_attn.v_proj.bias": "model-00009-of-00066.safetensors",
+    "layers.10.self_attn.v_proj.weight": "model-00009-of-00066.safetensors",
+    "layers.11.input_layernorm.weight": "model-00011-of-00066.safetensors",
+    "layers.11.mlp.down_proj.weight": "model-00011-of-00066.safetensors",
+    "layers.11.mlp.gate_proj.weight": "model-00010-of-00066.safetensors",
+    "layers.11.mlp.up_proj.weight": "model-00010-of-00066.safetensors",
+    "layers.11.post_attention_layernorm.weight": "model-00011-of-00066.safetensors",
+    "layers.11.self_attn.k_proj.bias": "model-00010-of-00066.safetensors",
+    "layers.11.self_attn.k_proj.weight": "model-00010-of-00066.safetensors",
+    "layers.11.self_attn.o_proj.weight": "model-00010-of-00066.safetensors",
+    "layers.11.self_attn.q_proj.bias": "model-00010-of-00066.safetensors",
+    "layers.11.self_attn.q_proj.weight": "model-00010-of-00066.safetensors",
+    "layers.11.self_attn.v_proj.bias": "model-00010-of-00066.safetensors",
+    "layers.11.self_attn.v_proj.weight": "model-00010-of-00066.safetensors",
+    "layers.12.input_layernorm.weight": "model-00011-of-00066.safetensors",
+    "layers.12.mlp.down_proj.weight": "model-00011-of-00066.safetensors",
+    "layers.12.mlp.gate_proj.weight": "model-00011-of-00066.safetensors",
+    "layers.12.mlp.up_proj.weight": "model-00011-of-00066.safetensors",
+    "layers.12.post_attention_layernorm.weight": "model-00011-of-00066.safetensors",
+    "layers.12.self_attn.k_proj.bias": "model-00011-of-00066.safetensors",
+    "layers.12.self_attn.k_proj.weight": "model-00011-of-00066.safetensors",
+    "layers.12.self_attn.o_proj.weight": "model-00011-of-00066.safetensors",
+    "layers.12.self_attn.q_proj.bias": "model-00011-of-00066.safetensors",
+    "layers.12.self_attn.q_proj.weight": "model-00011-of-00066.safetensors",
+    "layers.12.self_attn.v_proj.bias": "model-00011-of-00066.safetensors",
+    "layers.12.self_attn.v_proj.weight": "model-00011-of-00066.safetensors",
+    "layers.13.input_layernorm.weight": "model-00012-of-00066.safetensors",
+    "layers.13.mlp.down_proj.weight": "model-00012-of-00066.safetensors",
+    "layers.13.mlp.gate_proj.weight": "model-00012-of-00066.safetensors",
+    "layers.13.mlp.up_proj.weight": "model-00012-of-00066.safetensors",
+    "layers.13.post_attention_layernorm.weight": "model-00012-of-00066.safetensors",
+    "layers.13.self_attn.k_proj.bias": "model-00011-of-00066.safetensors",
+    "layers.13.self_attn.k_proj.weight": "model-00011-of-00066.safetensors",
+    "layers.13.self_attn.o_proj.weight": "model-00012-of-00066.safetensors",
+    "layers.13.self_attn.q_proj.bias": "model-00011-of-00066.safetensors",
+    "layers.13.self_attn.q_proj.weight": "model-00011-of-00066.safetensors",
+    "layers.13.self_attn.v_proj.bias": "model-00011-of-00066.safetensors",
+    "layers.13.self_attn.v_proj.weight": "model-00011-of-00066.safetensors",
+    "layers.14.input_layernorm.weight": "model-00013-of-00066.safetensors",
+    "layers.14.mlp.down_proj.weight": "model-00013-of-00066.safetensors",
+    "layers.14.mlp.gate_proj.weight": "model-00012-of-00066.safetensors",
+    "layers.14.mlp.up_proj.weight": "model-00013-of-00066.safetensors",
+    "layers.14.post_attention_layernorm.weight": "model-00013-of-00066.safetensors",
+    "layers.14.self_attn.k_proj.bias": "model-00012-of-00066.safetensors",
+    "layers.14.self_attn.k_proj.weight": "model-00012-of-00066.safetensors",
+    "layers.14.self_attn.o_proj.weight": "model-00012-of-00066.safetensors",
+    "layers.14.self_attn.q_proj.bias": "model-00012-of-00066.safetensors",
+    "layers.14.self_attn.q_proj.weight": "model-00012-of-00066.safetensors",
+    "layers.14.self_attn.v_proj.bias": "model-00012-of-00066.safetensors",
+    "layers.14.self_attn.v_proj.weight": "model-00012-of-00066.safetensors",
+    "layers.15.input_layernorm.weight": "model-00014-of-00066.safetensors",
+    "layers.15.mlp.down_proj.weight": "model-00014-of-00066.safetensors",
+    "layers.15.mlp.gate_proj.weight": "model-00013-of-00066.safetensors",
+    "layers.15.mlp.up_proj.weight": "model-00013-of-00066.safetensors",
+    "layers.15.post_attention_layernorm.weight": "model-00014-of-00066.safetensors",
+    "layers.15.self_attn.k_proj.bias": "model-00013-of-00066.safetensors",
+    "layers.15.self_attn.k_proj.weight": "model-00013-of-00066.safetensors",
+    "layers.15.self_attn.o_proj.weight": "model-00013-of-00066.safetensors",
+    "layers.15.self_attn.q_proj.bias": "model-00013-of-00066.safetensors",
+    "layers.15.self_attn.q_proj.weight": "model-00013-of-00066.safetensors",
+    "layers.15.self_attn.v_proj.bias": "model-00013-of-00066.safetensors",
+    "layers.15.self_attn.v_proj.weight": "model-00013-of-00066.safetensors",
+    "layers.16.input_layernorm.weight": "model-00014-of-00066.safetensors",
+    "layers.16.mlp.down_proj.weight": "model-00014-of-00066.safetensors",
+    "layers.16.mlp.gate_proj.weight": "model-00014-of-00066.safetensors",
+    "layers.16.mlp.up_proj.weight": "model-00014-of-00066.safetensors",
+    "layers.16.post_attention_layernorm.weight": "model-00014-of-00066.safetensors",
+    "layers.16.self_attn.k_proj.bias": "model-00014-of-00066.safetensors",
+    "layers.16.self_attn.k_proj.weight": "model-00014-of-00066.safetensors",
+    "layers.16.self_attn.o_proj.weight": "model-00014-of-00066.safetensors",
+    "layers.16.self_attn.q_proj.bias": "model-00014-of-00066.safetensors",
+    "layers.16.self_attn.q_proj.weight": "model-00014-of-00066.safetensors",
+    "layers.16.self_attn.v_proj.bias": "model-00014-of-00066.safetensors",
+    "layers.16.self_attn.v_proj.weight": "model-00014-of-00066.safetensors",
+    "layers.17.input_layernorm.weight": "model-00015-of-00066.safetensors",
+    "layers.17.mlp.down_proj.weight": "model-00015-of-00066.safetensors",
+    "layers.17.mlp.gate_proj.weight": "model-00015-of-00066.safetensors",
+    "layers.17.mlp.up_proj.weight": "model-00015-of-00066.safetensors",
+    "layers.17.post_attention_layernorm.weight": "model-00015-of-00066.safetensors",
+    "layers.17.self_attn.k_proj.bias": "model-00014-of-00066.safetensors",
+    "layers.17.self_attn.k_proj.weight": "model-00014-of-00066.safetensors",
+    "layers.17.self_attn.o_proj.weight": "model-00015-of-00066.safetensors",
+    "layers.17.self_attn.q_proj.bias": "model-00014-of-00066.safetensors",
+    "layers.17.self_attn.q_proj.weight": "model-00014-of-00066.safetensors",
+    "layers.17.self_attn.v_proj.bias": "model-00014-of-00066.safetensors",
+    "layers.17.self_attn.v_proj.weight": "model-00014-of-00066.safetensors",
+    "layers.18.input_layernorm.weight": "model-00016-of-00066.safetensors",
+    "layers.18.mlp.down_proj.weight": "model-00016-of-00066.safetensors",
+    "layers.18.mlp.gate_proj.weight": "model-00015-of-00066.safetensors",
+    "layers.18.mlp.up_proj.weight": "model-00016-of-00066.safetensors",
+    "layers.18.post_attention_layernorm.weight": "model-00016-of-00066.safetensors",
+    "layers.18.self_attn.k_proj.bias": "model-00015-of-00066.safetensors",
+    "layers.18.self_attn.k_proj.weight": "model-00015-of-00066.safetensors",
+    "layers.18.self_attn.o_proj.weight": "model-00015-of-00066.safetensors",
+    "layers.18.self_attn.q_proj.bias": "model-00015-of-00066.safetensors",
+    "layers.18.self_attn.q_proj.weight": "model-00015-of-00066.safetensors",
+    "layers.18.self_attn.v_proj.bias": "model-00015-of-00066.safetensors",
+    "layers.18.self_attn.v_proj.weight": "model-00015-of-00066.safetensors",
+    "layers.19.input_layernorm.weight": "model-00017-of-00066.safetensors",
+    "layers.19.mlp.down_proj.weight": "model-00017-of-00066.safetensors",
+    "layers.19.mlp.gate_proj.weight": "model-00016-of-00066.safetensors",
+    "layers.19.mlp.up_proj.weight": "model-00016-of-00066.safetensors",
+    "layers.19.post_attention_layernorm.weight": "model-00017-of-00066.safetensors",
+    "layers.19.self_attn.k_proj.bias": "model-00016-of-00066.safetensors",
+    "layers.19.self_attn.k_proj.weight": "model-00016-of-00066.safetensors",
+    "layers.19.self_attn.o_proj.weight": "model-00016-of-00066.safetensors",
+    "layers.19.self_attn.q_proj.bias": "model-00016-of-00066.safetensors",
+    "layers.19.self_attn.q_proj.weight": "model-00016-of-00066.safetensors",
+    "layers.19.self_attn.v_proj.bias": "model-00016-of-00066.safetensors",
+    "layers.19.self_attn.v_proj.weight": "model-00016-of-00066.safetensors",
+    "layers.2.input_layernorm.weight": "model-00004-of-00066.safetensors",
+    "layers.2.mlp.down_proj.weight": "model-00004-of-00066.safetensors",
+    "layers.2.mlp.gate_proj.weight": "model-00003-of-00066.safetensors",
+    "layers.2.mlp.up_proj.weight": "model-00004-of-00066.safetensors",
+    "layers.2.post_attention_layernorm.weight": "model-00004-of-00066.safetensors",
+    "layers.2.self_attn.k_proj.bias": "model-00003-of-00066.safetensors",
+    "layers.2.self_attn.k_proj.weight": "model-00003-of-00066.safetensors",
+    "layers.2.self_attn.o_proj.weight": "model-00003-of-00066.safetensors",
+    "layers.2.self_attn.q_proj.bias": "model-00003-of-00066.safetensors",
+    "layers.2.self_attn.q_proj.weight": "model-00003-of-00066.safetensors",
+    "layers.2.self_attn.v_proj.bias": "model-00003-of-00066.safetensors",
+    "layers.2.self_attn.v_proj.weight": "model-00003-of-00066.safetensors",
+    "layers.20.input_layernorm.weight": "model-00017-of-00066.safetensors",
+    "layers.20.mlp.down_proj.weight": "model-00017-of-00066.safetensors",
+    "layers.20.mlp.gate_proj.weight": "model-00017-of-00066.safetensors",
+    "layers.20.mlp.up_proj.weight": "model-00017-of-00066.safetensors",
+    "layers.20.post_attention_layernorm.weight": "model-00017-of-00066.safetensors",
+    "layers.20.self_attn.k_proj.bias": "model-00017-of-00066.safetensors",
+    "layers.20.self_attn.k_proj.weight": "model-00017-of-00066.safetensors",
+    "layers.20.self_attn.o_proj.weight": "model-00017-of-00066.safetensors",
+    "layers.20.self_attn.q_proj.bias": "model-00017-of-00066.safetensors",
+    "layers.20.self_attn.q_proj.weight": "model-00017-of-00066.safetensors",
+    "layers.20.self_attn.v_proj.bias": "model-00017-of-00066.safetensors",
+    "layers.20.self_attn.v_proj.weight": "model-00017-of-00066.safetensors",
+    "layers.21.input_layernorm.weight": "model-00018-of-00066.safetensors",
+    "layers.21.mlp.down_proj.weight": "model-00018-of-00066.safetensors",
+    "layers.21.mlp.gate_proj.weight": "model-00018-of-00066.safetensors",
+    "layers.21.mlp.up_proj.weight": "model-00018-of-00066.safetensors",
+    "layers.21.post_attention_layernorm.weight": "model-00018-of-00066.safetensors",
+    "layers.21.self_attn.k_proj.bias": "model-00017-of-00066.safetensors",
+    "layers.21.self_attn.k_proj.weight": "model-00017-of-00066.safetensors",
+    "layers.21.self_attn.o_proj.weight": "model-00018-of-00066.safetensors",
+    "layers.21.self_attn.q_proj.bias": "model-00017-of-00066.safetensors",
+    "layers.21.self_attn.q_proj.weight": "model-00017-of-00066.safetensors",
+    "layers.21.self_attn.v_proj.bias": "model-00017-of-00066.safetensors",
+    "layers.21.self_attn.v_proj.weight": "model-00017-of-00066.safetensors",
+    "layers.22.input_layernorm.weight": "model-00019-of-00066.safetensors",
+    "layers.22.mlp.down_proj.weight": "model-00019-of-00066.safetensors",
+    "layers.22.mlp.gate_proj.weight": "model-00018-of-00066.safetensors",
+    "layers.22.mlp.up_proj.weight": "model-00019-of-00066.safetensors",
+    "layers.22.post_attention_layernorm.weight": "model-00019-of-00066.safetensors",
+    "layers.22.self_attn.k_proj.bias": "model-00018-of-00066.safetensors",
+    "layers.22.self_attn.k_proj.weight": "model-00018-of-00066.safetensors",
+    "layers.22.self_attn.o_proj.weight": "model-00018-of-00066.safetensors",
+    "layers.22.self_attn.q_proj.bias": "model-00018-of-00066.safetensors",
+    "layers.22.self_attn.q_proj.weight": "model-00018-of-00066.safetensors",
+    "layers.22.self_attn.v_proj.bias": "model-00018-of-00066.safetensors",
+    "layers.22.self_attn.v_proj.weight": "model-00018-of-00066.safetensors",
+    "layers.23.input_layernorm.weight": "model-00020-of-00066.safetensors",
+    "layers.23.mlp.down_proj.weight": "model-00020-of-00066.safetensors",
+    "layers.23.mlp.gate_proj.weight": "model-00019-of-00066.safetensors",
+    "layers.23.mlp.up_proj.weight": "model-00019-of-00066.safetensors",
+    "layers.23.post_attention_layernorm.weight": "model-00020-of-00066.safetensors",
+    "layers.23.self_attn.k_proj.bias": "model-00019-of-00066.safetensors",
+    "layers.23.self_attn.k_proj.weight": "model-00019-of-00066.safetensors",
+    "layers.23.self_attn.o_proj.weight": "model-00019-of-00066.safetensors",
+    "layers.23.self_attn.q_proj.bias": "model-00019-of-00066.safetensors",
+    "layers.23.self_attn.q_proj.weight": "model-00019-of-00066.safetensors",
+    "layers.23.self_attn.v_proj.bias": "model-00019-of-00066.safetensors",
+    "layers.23.self_attn.v_proj.weight": "model-00019-of-00066.safetensors",
+    "layers.24.input_layernorm.weight": "model-00020-of-00066.safetensors",
+    "layers.24.mlp.down_proj.weight": "model-00020-of-00066.safetensors",
+    "layers.24.mlp.gate_proj.weight": "model-00020-of-00066.safetensors",
+    "layers.24.mlp.up_proj.weight": "model-00020-of-00066.safetensors",
+    "layers.24.post_attention_layernorm.weight": "model-00020-of-00066.safetensors",
+    "layers.24.self_attn.k_proj.bias": "model-00020-of-00066.safetensors",
+    "layers.24.self_attn.k_proj.weight": "model-00020-of-00066.safetensors",
+    "layers.24.self_attn.o_proj.weight": "model-00020-of-00066.safetensors",
+    "layers.24.self_attn.q_proj.bias": "model-00020-of-00066.safetensors",
+    "layers.24.self_attn.q_proj.weight": "model-00020-of-00066.safetensors",
+    "layers.24.self_attn.v_proj.bias": "model-00020-of-00066.safetensors",
+    "layers.24.self_attn.v_proj.weight": "model-00020-of-00066.safetensors",
+    "layers.25.input_layernorm.weight": "model-00021-of-00066.safetensors",
+    "layers.25.mlp.down_proj.weight": "model-00021-of-00066.safetensors",
+    "layers.25.mlp.gate_proj.weight": "model-00021-of-00066.safetensors",
+    "layers.25.mlp.up_proj.weight": "model-00021-of-00066.safetensors",
+    "layers.25.post_attention_layernorm.weight": "model-00021-of-00066.safetensors",
+    "layers.25.self_attn.k_proj.bias": "model-00020-of-00066.safetensors",
+    "layers.25.self_attn.k_proj.weight": "model-00020-of-00066.safetensors",
+    "layers.25.self_attn.o_proj.weight": "model-00021-of-00066.safetensors",
+    "layers.25.self_attn.q_proj.bias": "model-00020-of-00066.safetensors",
+    "layers.25.self_attn.q_proj.weight": "model-00020-of-00066.safetensors",
+    "layers.25.self_attn.v_proj.bias": "model-00020-of-00066.safetensors",
+    "layers.25.self_attn.v_proj.weight": "model-00020-of-00066.safetensors",
+    "layers.26.input_layernorm.weight": "model-00022-of-00066.safetensors",
+    "layers.26.mlp.down_proj.weight": "model-00022-of-00066.safetensors",
+    "layers.26.mlp.gate_proj.weight": "model-00021-of-00066.safetensors",
+    "layers.26.mlp.up_proj.weight": "model-00022-of-00066.safetensors",
+    "layers.26.post_attention_layernorm.weight": "model-00022-of-00066.safetensors",
+    "layers.26.self_attn.k_proj.bias": "model-00021-of-00066.safetensors",
+    "layers.26.self_attn.k_proj.weight": "model-00021-of-00066.safetensors",
+    "layers.26.self_attn.o_proj.weight": "model-00021-of-00066.safetensors",
+    "layers.26.self_attn.q_proj.bias": "model-00021-of-00066.safetensors",
+    "layers.26.self_attn.q_proj.weight": "model-00021-of-00066.safetensors",
+    "layers.26.self_attn.v_proj.bias": "model-00021-of-00066.safetensors",
+    "layers.26.self_attn.v_proj.weight": "model-00021-of-00066.safetensors",
+    "layers.27.input_layernorm.weight": "model-00023-of-00066.safetensors",
+    "layers.27.mlp.down_proj.weight": "model-00023-of-00066.safetensors",
+    "layers.27.mlp.gate_proj.weight": "model-00022-of-00066.safetensors",
+    "layers.27.mlp.up_proj.weight": "model-00022-of-00066.safetensors",
+    "layers.27.post_attention_layernorm.weight": "model-00023-of-00066.safetensors",
+    "layers.27.self_attn.k_proj.bias": "model-00022-of-00066.safetensors",
+    "layers.27.self_attn.k_proj.weight": "model-00022-of-00066.safetensors",
+    "layers.27.self_attn.o_proj.weight": "model-00022-of-00066.safetensors",
+    "layers.27.self_attn.q_proj.bias": "model-00022-of-00066.safetensors",
+    "layers.27.self_attn.q_proj.weight": "model-00022-of-00066.safetensors",
+    "layers.27.self_attn.v_proj.bias": "model-00022-of-00066.safetensors",
+    "layers.27.self_attn.v_proj.weight": "model-00022-of-00066.safetensors",
+    "layers.28.input_layernorm.weight": "model-00023-of-00066.safetensors",
+    "layers.28.mlp.down_proj.weight": "model-00023-of-00066.safetensors",
+    "layers.28.mlp.gate_proj.weight": "model-00023-of-00066.safetensors",
+    "layers.28.mlp.up_proj.weight": "model-00023-of-00066.safetensors",
+    "layers.28.post_attention_layernorm.weight": "model-00023-of-00066.safetensors",
+    "layers.28.self_attn.k_proj.bias": "model-00023-of-00066.safetensors",
+    "layers.28.self_attn.k_proj.weight": "model-00023-of-00066.safetensors",
+    "layers.28.self_attn.o_proj.weight": "model-00023-of-00066.safetensors",
+    "layers.28.self_attn.q_proj.bias": "model-00023-of-00066.safetensors",
+    "layers.28.self_attn.q_proj.weight": "model-00023-of-00066.safetensors",
+    "layers.28.self_attn.v_proj.bias": "model-00023-of-00066.safetensors",
+    "layers.28.self_attn.v_proj.weight": "model-00023-of-00066.safetensors",
+    "layers.29.input_layernorm.weight": "model-00024-of-00066.safetensors",
+    "layers.29.mlp.down_proj.weight": "model-00024-of-00066.safetensors",
+    "layers.29.mlp.gate_proj.weight": "model-00024-of-00066.safetensors",
+    "layers.29.mlp.up_proj.weight": "model-00024-of-00066.safetensors",
+    "layers.29.post_attention_layernorm.weight": "model-00024-of-00066.safetensors",
+    "layers.29.self_attn.k_proj.bias": "model-00023-of-00066.safetensors",
+    "layers.29.self_attn.k_proj.weight": "model-00023-of-00066.safetensors",
+    "layers.29.self_attn.o_proj.weight": "model-00024-of-00066.safetensors",
+    "layers.29.self_attn.q_proj.bias": "model-00023-of-00066.safetensors",
+    "layers.29.self_attn.q_proj.weight": "model-00023-of-00066.safetensors",
+    "layers.29.self_attn.v_proj.bias": "model-00023-of-00066.safetensors",
+    "layers.29.self_attn.v_proj.weight": "model-00023-of-00066.safetensors",
+    "layers.3.input_layernorm.weight": "model-00005-of-00066.safetensors",
+    "layers.3.mlp.down_proj.weight": "model-00005-of-00066.safetensors",
+    "layers.3.mlp.gate_proj.weight": "model-00004-of-00066.safetensors",
+    "layers.3.mlp.up_proj.weight": "model-00004-of-00066.safetensors",
+    "layers.3.post_attention_layernorm.weight": "model-00005-of-00066.safetensors",
+    "layers.3.self_attn.k_proj.bias": "model-00004-of-00066.safetensors",
+    "layers.3.self_attn.k_proj.weight": "model-00004-of-00066.safetensors",
+    "layers.3.self_attn.o_proj.weight": "model-00004-of-00066.safetensors",
+    "layers.3.self_attn.q_proj.bias": "model-00004-of-00066.safetensors",
+    "layers.3.self_attn.q_proj.weight": "model-00004-of-00066.safetensors",
+    "layers.3.self_attn.v_proj.bias": "model-00004-of-00066.safetensors",
+    "layers.3.self_attn.v_proj.weight": "model-00004-of-00066.safetensors",
+    "layers.30.input_layernorm.weight": "model-00025-of-00066.safetensors",
+    "layers.30.mlp.down_proj.weight": "model-00025-of-00066.safetensors",
+    "layers.30.mlp.gate_proj.weight": "model-00024-of-00066.safetensors",
+    "layers.30.mlp.up_proj.weight": "model-00025-of-00066.safetensors",
+    "layers.30.post_attention_layernorm.weight": "model-00025-of-00066.safetensors",
+    "layers.30.self_attn.k_proj.bias": "model-00024-of-00066.safetensors",
+    "layers.30.self_attn.k_proj.weight": "model-00024-of-00066.safetensors",
+    "layers.30.self_attn.o_proj.weight": "model-00024-of-00066.safetensors",
+    "layers.30.self_attn.q_proj.bias": "model-00024-of-00066.safetensors",
+    "layers.30.self_attn.q_proj.weight": "model-00024-of-00066.safetensors",
+    "layers.30.self_attn.v_proj.bias": "model-00024-of-00066.safetensors",
+    "layers.30.self_attn.v_proj.weight": "model-00024-of-00066.safetensors",
+    "layers.31.input_layernorm.weight": "model-00026-of-00066.safetensors",
+    "layers.31.mlp.down_proj.weight": "model-00026-of-00066.safetensors",
+    "layers.31.mlp.gate_proj.weight": "model-00025-of-00066.safetensors",
+    "layers.31.mlp.up_proj.weight": "model-00025-of-00066.safetensors",
+    "layers.31.post_attention_layernorm.weight": "model-00026-of-00066.safetensors",
+    "layers.31.self_attn.k_proj.bias": "model-00025-of-00066.safetensors",
+    "layers.31.self_attn.k_proj.weight": "model-00025-of-00066.safetensors",
+    "layers.31.self_attn.o_proj.weight": "model-00025-of-00066.safetensors",
+    "layers.31.self_attn.q_proj.bias": "model-00025-of-00066.safetensors",
+    "layers.31.self_attn.q_proj.weight": "model-00025-of-00066.safetensors",
+    "layers.31.self_attn.v_proj.bias": "model-00025-of-00066.safetensors",
+    "layers.31.self_attn.v_proj.weight": "model-00025-of-00066.safetensors",
+    "layers.32.input_layernorm.weight": "model-00026-of-00066.safetensors",
+    "layers.32.mlp.down_proj.weight": "model-00026-of-00066.safetensors",
+    "layers.32.mlp.gate_proj.weight": "model-00026-of-00066.safetensors",
+    "layers.32.mlp.up_proj.weight": "model-00026-of-00066.safetensors",
+    "layers.32.post_attention_layernorm.weight": "model-00026-of-00066.safetensors",
+    "layers.32.self_attn.k_proj.bias": "model-00026-of-00066.safetensors",
+    "layers.32.self_attn.k_proj.weight": "model-00026-of-00066.safetensors",
+    "layers.32.self_attn.o_proj.weight": "model-00026-of-00066.safetensors",
+    "layers.32.self_attn.q_proj.bias": "model-00026-of-00066.safetensors",
+    "layers.32.self_attn.q_proj.weight": "model-00026-of-00066.safetensors",
+    "layers.32.self_attn.v_proj.bias": "model-00026-of-00066.safetensors",
+    "layers.32.self_attn.v_proj.weight": "model-00026-of-00066.safetensors",
+    "layers.33.input_layernorm.weight": "model-00027-of-00066.safetensors",
+    "layers.33.mlp.down_proj.weight": "model-00027-of-00066.safetensors",
+    "layers.33.mlp.gate_proj.weight": "model-00027-of-00066.safetensors",
+    "layers.33.mlp.up_proj.weight": "model-00027-of-00066.safetensors",
+    "layers.33.post_attention_layernorm.weight": "model-00027-of-00066.safetensors",
+    "layers.33.self_attn.k_proj.bias": "model-00026-of-00066.safetensors",
+    "layers.33.self_attn.k_proj.weight": "model-00026-of-00066.safetensors",
+    "layers.33.self_attn.o_proj.weight": "model-00027-of-00066.safetensors",
+    "layers.33.self_attn.q_proj.bias": "model-00026-of-00066.safetensors",
+    "layers.33.self_attn.q_proj.weight": "model-00026-of-00066.safetensors",
+    "layers.33.self_attn.v_proj.bias": "model-00026-of-00066.safetensors",
+    "layers.33.self_attn.v_proj.weight": "model-00026-of-00066.safetensors",
+    "layers.34.input_layernorm.weight": "model-00028-of-00066.safetensors",
+    "layers.34.mlp.down_proj.weight": "model-00028-of-00066.safetensors",
+    "layers.34.mlp.gate_proj.weight": "model-00027-of-00066.safetensors",
+    "layers.34.mlp.up_proj.weight": "model-00028-of-00066.safetensors",
+    "layers.34.post_attention_layernorm.weight": "model-00028-of-00066.safetensors",
+    "layers.34.self_attn.k_proj.bias": "model-00027-of-00066.safetensors",
+    "layers.34.self_attn.k_proj.weight": "model-00027-of-00066.safetensors",
+    "layers.34.self_attn.o_proj.weight": "model-00027-of-00066.safetensors",
+    "layers.34.self_attn.q_proj.bias": "model-00027-of-00066.safetensors",
+    "layers.34.self_attn.q_proj.weight": "model-00027-of-00066.safetensors",
+    "layers.34.self_attn.v_proj.bias": "model-00027-of-00066.safetensors",
+    "layers.34.self_attn.v_proj.weight": "model-00027-of-00066.safetensors",
+    "layers.35.input_layernorm.weight": "model-00029-of-00066.safetensors",
+    "layers.35.mlp.down_proj.weight": "model-00029-of-00066.safetensors",
+    "layers.35.mlp.gate_proj.weight": "model-00028-of-00066.safetensors",
+    "layers.35.mlp.up_proj.weight": "model-00028-of-00066.safetensors",
+    "layers.35.post_attention_layernorm.weight": "model-00029-of-00066.safetensors",
+    "layers.35.self_attn.k_proj.bias": "model-00028-of-00066.safetensors",
+    "layers.35.self_attn.k_proj.weight": "model-00028-of-00066.safetensors",
+    "layers.35.self_attn.o_proj.weight": "model-00028-of-00066.safetensors",
+    "layers.35.self_attn.q_proj.bias": "model-00028-of-00066.safetensors",
+    "layers.35.self_attn.q_proj.weight": "model-00028-of-00066.safetensors",
+    "layers.35.self_attn.v_proj.bias": "model-00028-of-00066.safetensors",
+    "layers.35.self_attn.v_proj.weight": "model-00028-of-00066.safetensors",
+    "layers.36.input_layernorm.weight": "model-00029-of-00066.safetensors",
+    "layers.36.mlp.down_proj.weight": "model-00029-of-00066.safetensors",
+    "layers.36.mlp.gate_proj.weight": "model-00029-of-00066.safetensors",
+    "layers.36.mlp.up_proj.weight": "model-00029-of-00066.safetensors",
+    "layers.36.post_attention_layernorm.weight": "model-00029-of-00066.safetensors",
+    "layers.36.self_attn.k_proj.bias": "model-00029-of-00066.safetensors",
+    "layers.36.self_attn.k_proj.weight": "model-00029-of-00066.safetensors",
+    "layers.36.self_attn.o_proj.weight": "model-00029-of-00066.safetensors",
+    "layers.36.self_attn.q_proj.bias": "model-00029-of-00066.safetensors",
+    "layers.36.self_attn.q_proj.weight": "model-00029-of-00066.safetensors",
+    "layers.36.self_attn.v_proj.bias": "model-00029-of-00066.safetensors",
+    "layers.36.self_attn.v_proj.weight": "model-00029-of-00066.safetensors",
+    "layers.37.input_layernorm.weight": "model-00030-of-00066.safetensors",
+    "layers.37.mlp.down_proj.weight": "model-00030-of-00066.safetensors",
+    "layers.37.mlp.gate_proj.weight": "model-00030-of-00066.safetensors",
+    "layers.37.mlp.up_proj.weight": "model-00030-of-00066.safetensors",
+    "layers.37.post_attention_layernorm.weight": "model-00030-of-00066.safetensors",
+    "layers.37.self_attn.k_proj.bias": "model-00029-of-00066.safetensors",
+    "layers.37.self_attn.k_proj.weight": "model-00029-of-00066.safetensors",
+    "layers.37.self_attn.o_proj.weight": "model-00030-of-00066.safetensors",
+    "layers.37.self_attn.q_proj.bias": "model-00029-of-00066.safetensors",
+    "layers.37.self_attn.q_proj.weight": "model-00029-of-00066.safetensors",
+    "layers.37.self_attn.v_proj.bias": "model-00029-of-00066.safetensors",
+    "layers.37.self_attn.v_proj.weight": "model-00029-of-00066.safetensors",
+    "layers.38.input_layernorm.weight": "model-00031-of-00066.safetensors",
+    "layers.38.mlp.down_proj.weight": "model-00031-of-00066.safetensors",
+    "layers.38.mlp.gate_proj.weight": "model-00030-of-00066.safetensors",
+    "layers.38.mlp.up_proj.weight": "model-00031-of-00066.safetensors",
+    "layers.38.post_attention_layernorm.weight": "model-00031-of-00066.safetensors",
+    "layers.38.self_attn.k_proj.bias": "model-00030-of-00066.safetensors",
+    "layers.38.self_attn.k_proj.weight": "model-00030-of-00066.safetensors",
+    "layers.38.self_attn.o_proj.weight": "model-00030-of-00066.safetensors",
+    "layers.38.self_attn.q_proj.bias": "model-00030-of-00066.safetensors",
+    "layers.38.self_attn.q_proj.weight": "model-00030-of-00066.safetensors",
+    "layers.38.self_attn.v_proj.bias": "model-00030-of-00066.safetensors",
+    "layers.38.self_attn.v_proj.weight": "model-00030-of-00066.safetensors",
+    "layers.39.input_layernorm.weight": "model-00032-of-00066.safetensors",
+    "layers.39.mlp.down_proj.weight": "model-00032-of-00066.safetensors",
+    "layers.39.mlp.gate_proj.weight": "model-00031-of-00066.safetensors",
+    "layers.39.mlp.up_proj.weight": "model-00031-of-00066.safetensors",
+    "layers.39.post_attention_layernorm.weight": "model-00032-of-00066.safetensors",
+    "layers.39.self_attn.k_proj.bias": "model-00031-of-00066.safetensors",
+    "layers.39.self_attn.k_proj.weight": "model-00031-of-00066.safetensors",
+    "layers.39.self_attn.o_proj.weight": "model-00031-of-00066.safetensors",
+    "layers.39.self_attn.q_proj.bias": "model-00031-of-00066.safetensors",
+    "layers.39.self_attn.q_proj.weight": "model-00031-of-00066.safetensors",
+    "layers.39.self_attn.v_proj.bias": "model-00031-of-00066.safetensors",
+    "layers.39.self_attn.v_proj.weight": "model-00031-of-00066.safetensors",
+    "layers.4.input_layernorm.weight": "model-00005-of-00066.safetensors",
+    "layers.4.mlp.down_proj.weight": "model-00005-of-00066.safetensors",
+    "layers.4.mlp.gate_proj.weight": "model-00005-of-00066.safetensors",
+    "layers.4.mlp.up_proj.weight": "model-00005-of-00066.safetensors",
+    "layers.4.post_attention_layernorm.weight": "model-00005-of-00066.safetensors",
+    "layers.4.self_attn.k_proj.bias": "model-00005-of-00066.safetensors",
+    "layers.4.self_attn.k_proj.weight": "model-00005-of-00066.safetensors",
+    "layers.4.self_attn.o_proj.weight": "model-00005-of-00066.safetensors",
+    "layers.4.self_attn.q_proj.bias": "model-00005-of-00066.safetensors",
+    "layers.4.self_attn.q_proj.weight": "model-00005-of-00066.safetensors",
+    "layers.4.self_attn.v_proj.bias": "model-00005-of-00066.safetensors",
+    "layers.4.self_attn.v_proj.weight": "model-00005-of-00066.safetensors",
+    "layers.40.input_layernorm.weight": "model-00032-of-00066.safetensors",
+    "layers.40.mlp.down_proj.weight": "model-00032-of-00066.safetensors",
+    "layers.40.mlp.gate_proj.weight": "model-00032-of-00066.safetensors",
+    "layers.40.mlp.up_proj.weight": "model-00032-of-00066.safetensors",
+    "layers.40.post_attention_layernorm.weight": "model-00032-of-00066.safetensors",
+    "layers.40.self_attn.k_proj.bias": "model-00032-of-00066.safetensors",
+    "layers.40.self_attn.k_proj.weight": "model-00032-of-00066.safetensors",
+    "layers.40.self_attn.o_proj.weight": "model-00032-of-00066.safetensors",
+    "layers.40.self_attn.q_proj.bias": "model-00032-of-00066.safetensors",
+    "layers.40.self_attn.q_proj.weight": "model-00032-of-00066.safetensors",
+    "layers.40.self_attn.v_proj.bias": "model-00032-of-00066.safetensors",
+    "layers.40.self_attn.v_proj.weight": "model-00032-of-00066.safetensors",
+    "layers.41.input_layernorm.weight": "model-00033-of-00066.safetensors",
+    "layers.41.mlp.down_proj.weight": "model-00033-of-00066.safetensors",
+    "layers.41.mlp.gate_proj.weight": "model-00033-of-00066.safetensors",
+    "layers.41.mlp.up_proj.weight": "model-00033-of-00066.safetensors",
+    "layers.41.post_attention_layernorm.weight": "model-00033-of-00066.safetensors",
+    "layers.41.self_attn.k_proj.bias": "model-00032-of-00066.safetensors",
+    "layers.41.self_attn.k_proj.weight": "model-00032-of-00066.safetensors",
+    "layers.41.self_attn.o_proj.weight": "model-00033-of-00066.safetensors",
+    "layers.41.self_attn.q_proj.bias": "model-00032-of-00066.safetensors",
+    "layers.41.self_attn.q_proj.weight": "model-00032-of-00066.safetensors",
+    "layers.41.self_attn.v_proj.bias": "model-00032-of-00066.safetensors",
+    "layers.41.self_attn.v_proj.weight": "model-00032-of-00066.safetensors",
+    "layers.42.input_layernorm.weight": "model-00034-of-00066.safetensors",
+    "layers.42.mlp.down_proj.weight": "model-00034-of-00066.safetensors",
+    "layers.42.mlp.gate_proj.weight": "model-00033-of-00066.safetensors",
+    "layers.42.mlp.up_proj.weight": "model-00034-of-00066.safetensors",
+    "layers.42.post_attention_layernorm.weight": "model-00034-of-00066.safetensors",
+    "layers.42.self_attn.k_proj.bias": "model-00033-of-00066.safetensors",
+    "layers.42.self_attn.k_proj.weight": "model-00033-of-00066.safetensors",
+    "layers.42.self_attn.o_proj.weight": "model-00033-of-00066.safetensors",
+    "layers.42.self_attn.q_proj.bias": "model-00033-of-00066.safetensors",
+    "layers.42.self_attn.q_proj.weight": "model-00033-of-00066.safetensors",
+    "layers.42.self_attn.v_proj.bias": "model-00033-of-00066.safetensors",
+    "layers.42.self_attn.v_proj.weight": "model-00033-of-00066.safetensors",
+    "layers.43.input_layernorm.weight": "model-00035-of-00066.safetensors",
+    "layers.43.mlp.down_proj.weight": "model-00035-of-00066.safetensors",
+    "layers.43.mlp.gate_proj.weight": "model-00034-of-00066.safetensors",
+    "layers.43.mlp.up_proj.weight": "model-00034-of-00066.safetensors",
+    "layers.43.post_attention_layernorm.weight": "model-00035-of-00066.safetensors",
+    "layers.43.self_attn.k_proj.bias": "model-00034-of-00066.safetensors",
+    "layers.43.self_attn.k_proj.weight": "model-00034-of-00066.safetensors",
+    "layers.43.self_attn.o_proj.weight": "model-00034-of-00066.safetensors",
+    "layers.43.self_attn.q_proj.bias": "model-00034-of-00066.safetensors",
+    "layers.43.self_attn.q_proj.weight": "model-00034-of-00066.safetensors",
+    "layers.43.self_attn.v_proj.bias": "model-00034-of-00066.safetensors",
+    "layers.43.self_attn.v_proj.weight": "model-00034-of-00066.safetensors",
+    "layers.44.input_layernorm.weight": "model-00035-of-00066.safetensors",
+    "layers.44.mlp.down_proj.weight": "model-00035-of-00066.safetensors",
+    "layers.44.mlp.gate_proj.weight": "model-00035-of-00066.safetensors",
+    "layers.44.mlp.up_proj.weight": "model-00035-of-00066.safetensors",
+    "layers.44.post_attention_layernorm.weight": "model-00035-of-00066.safetensors",
+    "layers.44.self_attn.k_proj.bias": "model-00035-of-00066.safetensors",
+    "layers.44.self_attn.k_proj.weight": "model-00035-of-00066.safetensors",
+    "layers.44.self_attn.o_proj.weight": "model-00035-of-00066.safetensors",
+    "layers.44.self_attn.q_proj.bias": "model-00035-of-00066.safetensors",
+    "layers.44.self_attn.q_proj.weight": "model-00035-of-00066.safetensors",
+    "layers.44.self_attn.v_proj.bias": "model-00035-of-00066.safetensors",
+    "layers.44.self_attn.v_proj.weight": "model-00035-of-00066.safetensors",
+    "layers.45.input_layernorm.weight": "model-00036-of-00066.safetensors",
+    "layers.45.mlp.down_proj.weight": "model-00036-of-00066.safetensors",
+    "layers.45.mlp.gate_proj.weight": "model-00036-of-00066.safetensors",
+    "layers.45.mlp.up_proj.weight": "model-00036-of-00066.safetensors",
+    "layers.45.post_attention_layernorm.weight": "model-00036-of-00066.safetensors",
+    "layers.45.self_attn.k_proj.bias": "model-00035-of-00066.safetensors",
+    "layers.45.self_attn.k_proj.weight": "model-00035-of-00066.safetensors",
+    "layers.45.self_attn.o_proj.weight": "model-00036-of-00066.safetensors",
+    "layers.45.self_attn.q_proj.bias": "model-00035-of-00066.safetensors",
+    "layers.45.self_attn.q_proj.weight": "model-00035-of-00066.safetensors",
+    "layers.45.self_attn.v_proj.bias": "model-00035-of-00066.safetensors",
+    "layers.45.self_attn.v_proj.weight": "model-00035-of-00066.safetensors",
+    "layers.46.input_layernorm.weight": "model-00037-of-00066.safetensors",
+    "layers.46.mlp.down_proj.weight": "model-00037-of-00066.safetensors",
+    "layers.46.mlp.gate_proj.weight": "model-00036-of-00066.safetensors",
+    "layers.46.mlp.up_proj.weight": "model-00037-of-00066.safetensors",
+    "layers.46.post_attention_layernorm.weight": "model-00037-of-00066.safetensors",
+    "layers.46.self_attn.k_proj.bias": "model-00036-of-00066.safetensors",
+    "layers.46.self_attn.k_proj.weight": "model-00036-of-00066.safetensors",
+    "layers.46.self_attn.o_proj.weight": "model-00036-of-00066.safetensors",
+    "layers.46.self_attn.q_proj.bias": "model-00036-of-00066.safetensors",
+    "layers.46.self_attn.q_proj.weight": "model-00036-of-00066.safetensors",
+    "layers.46.self_attn.v_proj.bias": "model-00036-of-00066.safetensors",
+    "layers.46.self_attn.v_proj.weight": "model-00036-of-00066.safetensors",
+    "layers.47.input_layernorm.weight": "model-00038-of-00066.safetensors",
+    "layers.47.mlp.down_proj.weight": "model-00038-of-00066.safetensors",
+    "layers.47.mlp.gate_proj.weight": "model-00037-of-00066.safetensors",
+    "layers.47.mlp.up_proj.weight": "model-00037-of-00066.safetensors",
+    "layers.47.post_attention_layernorm.weight": "model-00038-of-00066.safetensors",
+    "layers.47.self_attn.k_proj.bias": "model-00037-of-00066.safetensors",
+    "layers.47.self_attn.k_proj.weight": "model-00037-of-00066.safetensors",
+    "layers.47.self_attn.o_proj.weight": "model-00037-of-00066.safetensors",
+    "layers.47.self_attn.q_proj.bias": "model-00037-of-00066.safetensors",
+    "layers.47.self_attn.q_proj.weight": "model-00037-of-00066.safetensors",
+    "layers.47.self_attn.v_proj.bias": "model-00037-of-00066.safetensors",
+    "layers.47.self_attn.v_proj.weight": "model-00037-of-00066.safetensors",
+    "layers.48.input_layernorm.weight": "model-00038-of-00066.safetensors",
+    "layers.48.mlp.down_proj.weight": "model-00038-of-00066.safetensors",
+    "layers.48.mlp.gate_proj.weight": "model-00038-of-00066.safetensors",
+    "layers.48.mlp.up_proj.weight": "model-00038-of-00066.safetensors",
+    "layers.48.post_attention_layernorm.weight": "model-00038-of-00066.safetensors",
+    "layers.48.self_attn.k_proj.bias": "model-00038-of-00066.safetensors",
+    "layers.48.self_attn.k_proj.weight": "model-00038-of-00066.safetensors",
+    "layers.48.self_attn.o_proj.weight": "model-00038-of-00066.safetensors",
+    "layers.48.self_attn.q_proj.bias": "model-00038-of-00066.safetensors",
+    "layers.48.self_attn.q_proj.weight": "model-00038-of-00066.safetensors",
+    "layers.48.self_attn.v_proj.bias": "model-00038-of-00066.safetensors",
+    "layers.48.self_attn.v_proj.weight": "model-00038-of-00066.safetensors",
+    "layers.49.input_layernorm.weight": "model-00039-of-00066.safetensors",
+    "layers.49.mlp.down_proj.weight": "model-00039-of-00066.safetensors",
+    "layers.49.mlp.gate_proj.weight": "model-00039-of-00066.safetensors",
+    "layers.49.mlp.up_proj.weight": "model-00039-of-00066.safetensors",
+    "layers.49.post_attention_layernorm.weight": "model-00039-of-00066.safetensors",
+    "layers.49.self_attn.k_proj.bias": "model-00038-of-00066.safetensors",
+    "layers.49.self_attn.k_proj.weight": "model-00038-of-00066.safetensors",
+    "layers.49.self_attn.o_proj.weight": "model-00039-of-00066.safetensors",
+    "layers.49.self_attn.q_proj.bias": "model-00038-of-00066.safetensors",
+    "layers.49.self_attn.q_proj.weight": "model-00038-of-00066.safetensors",
+    "layers.49.self_attn.v_proj.bias": "model-00038-of-00066.safetensors",
+    "layers.49.self_attn.v_proj.weight": "model-00038-of-00066.safetensors",
+    "layers.5.input_layernorm.weight": "model-00006-of-00066.safetensors",
+    "layers.5.mlp.down_proj.weight": "model-00006-of-00066.safetensors",
+    "layers.5.mlp.gate_proj.weight": "model-00006-of-00066.safetensors",
+    "layers.5.mlp.up_proj.weight": "model-00006-of-00066.safetensors",
+    "layers.5.post_attention_layernorm.weight": "model-00006-of-00066.safetensors",
+    "layers.5.self_attn.k_proj.bias": "model-00005-of-00066.safetensors",
+    "layers.5.self_attn.k_proj.weight": "model-00005-of-00066.safetensors",
+    "layers.5.self_attn.o_proj.weight": "model-00006-of-00066.safetensors",
+    "layers.5.self_attn.q_proj.bias": "model-00005-of-00066.safetensors",
+    "layers.5.self_attn.q_proj.weight": "model-00005-of-00066.safetensors",
+    "layers.5.self_attn.v_proj.bias": "model-00005-of-00066.safetensors",
+    "layers.5.self_attn.v_proj.weight": "model-00005-of-00066.safetensors",
+    "layers.50.input_layernorm.weight": "model-00040-of-00066.safetensors",
+    "layers.50.mlp.down_proj.weight": "model-00040-of-00066.safetensors",
+    "layers.50.mlp.gate_proj.weight": "model-00039-of-00066.safetensors",
+    "layers.50.mlp.up_proj.weight": "model-00040-of-00066.safetensors",
+    "layers.50.post_attention_layernorm.weight": "model-00040-of-00066.safetensors",
+    "layers.50.self_attn.k_proj.bias": "model-00039-of-00066.safetensors",
+    "layers.50.self_attn.k_proj.weight": "model-00039-of-00066.safetensors",
+    "layers.50.self_attn.o_proj.weight": "model-00039-of-00066.safetensors",
+    "layers.50.self_attn.q_proj.bias": "model-00039-of-00066.safetensors",
+    "layers.50.self_attn.q_proj.weight": "model-00039-of-00066.safetensors",
+    "layers.50.self_attn.v_proj.bias": "model-00039-of-00066.safetensors",
+    "layers.50.self_attn.v_proj.weight": "model-00039-of-00066.safetensors",
+    "layers.51.input_layernorm.weight": "model-00041-of-00066.safetensors",
+    "layers.51.mlp.down_proj.weight": "model-00041-of-00066.safetensors",
+    "layers.51.mlp.gate_proj.weight": "model-00040-of-00066.safetensors",
+    "layers.51.mlp.up_proj.weight": "model-00040-of-00066.safetensors",
+    "layers.51.post_attention_layernorm.weight": "model-00041-of-00066.safetensors",
+    "layers.51.self_attn.k_proj.bias": "model-00040-of-00066.safetensors",
+    "layers.51.self_attn.k_proj.weight": "model-00040-of-00066.safetensors",
+    "layers.51.self_attn.o_proj.weight": "model-00040-of-00066.safetensors",
+    "layers.51.self_attn.q_proj.bias": "model-00040-of-00066.safetensors",
+    "layers.51.self_attn.q_proj.weight": "model-00040-of-00066.safetensors",
+    "layers.51.self_attn.v_proj.bias": "model-00040-of-00066.safetensors",
+    "layers.51.self_attn.v_proj.weight": "model-00040-of-00066.safetensors",
+    "layers.52.input_layernorm.weight": "model-00041-of-00066.safetensors",
+    "layers.52.mlp.down_proj.weight": "model-00041-of-00066.safetensors",
+    "layers.52.mlp.gate_proj.weight": "model-00041-of-00066.safetensors",
+    "layers.52.mlp.up_proj.weight": "model-00041-of-00066.safetensors",
+    "layers.52.post_attention_layernorm.weight": "model-00041-of-00066.safetensors",
+    "layers.52.self_attn.k_proj.bias": "model-00041-of-00066.safetensors",
+    "layers.52.self_attn.k_proj.weight": "model-00041-of-00066.safetensors",
+    "layers.52.self_attn.o_proj.weight": "model-00041-of-00066.safetensors",
+    "layers.52.self_attn.q_proj.bias": "model-00041-of-00066.safetensors",
+    "layers.52.self_attn.q_proj.weight": "model-00041-of-00066.safetensors",
+    "layers.52.self_attn.v_proj.bias": "model-00041-of-00066.safetensors",
+    "layers.52.self_attn.v_proj.weight": "model-00041-of-00066.safetensors",
+    "layers.53.input_layernorm.weight": "model-00042-of-00066.safetensors",
+    "layers.53.mlp.down_proj.weight": "model-00042-of-00066.safetensors",
+    "layers.53.mlp.gate_proj.weight": "model-00042-of-00066.safetensors",
+    "layers.53.mlp.up_proj.weight": "model-00042-of-00066.safetensors",
+    "layers.53.post_attention_layernorm.weight": "model-00042-of-00066.safetensors",
+    "layers.53.self_attn.k_proj.bias": "model-00041-of-00066.safetensors",
+    "layers.53.self_attn.k_proj.weight": "model-00041-of-00066.safetensors",
+    "layers.53.self_attn.o_proj.weight": "model-00042-of-00066.safetensors",
+    "layers.53.self_attn.q_proj.bias": "model-00041-of-00066.safetensors",
+    "layers.53.self_attn.q_proj.weight": "model-00041-of-00066.safetensors",
+    "layers.53.self_attn.v_proj.bias": "model-00041-of-00066.safetensors",
+    "layers.53.self_attn.v_proj.weight": "model-00041-of-00066.safetensors",
+    "layers.54.input_layernorm.weight": "model-00043-of-00066.safetensors",
+    "layers.54.mlp.down_proj.weight": "model-00043-of-00066.safetensors",
+    "layers.54.mlp.gate_proj.weight": "model-00042-of-00066.safetensors",
+    "layers.54.mlp.up_proj.weight": "model-00043-of-00066.safetensors",
+    "layers.54.post_attention_layernorm.weight": "model-00043-of-00066.safetensors",
+    "layers.54.self_attn.k_proj.bias": "model-00042-of-00066.safetensors",
+    "layers.54.self_attn.k_proj.weight": "model-00042-of-00066.safetensors",
+    "layers.54.self_attn.o_proj.weight": "model-00042-of-00066.safetensors",
+    "layers.54.self_attn.q_proj.bias": "model-00042-of-00066.safetensors",
+    "layers.54.self_attn.q_proj.weight": "model-00042-of-00066.safetensors",
+    "layers.54.self_attn.v_proj.bias": "model-00042-of-00066.safetensors",
+    "layers.54.self_attn.v_proj.weight": "model-00042-of-00066.safetensors",
+    "layers.55.input_layernorm.weight": "model-00044-of-00066.safetensors",
+    "layers.55.mlp.down_proj.weight": "model-00044-of-00066.safetensors",
+    "layers.55.mlp.gate_proj.weight": "model-00043-of-00066.safetensors",
+    "layers.55.mlp.up_proj.weight": "model-00043-of-00066.safetensors",
+    "layers.55.post_attention_layernorm.weight": "model-00044-of-00066.safetensors",
+    "layers.55.self_attn.k_proj.bias": "model-00043-of-00066.safetensors",
+    "layers.55.self_attn.k_proj.weight": "model-00043-of-00066.safetensors",
+    "layers.55.self_attn.o_proj.weight": "model-00043-of-00066.safetensors",
+    "layers.55.self_attn.q_proj.bias": "model-00043-of-00066.safetensors",
+    "layers.55.self_attn.q_proj.weight": "model-00043-of-00066.safetensors",
+    "layers.55.self_attn.v_proj.bias": "model-00043-of-00066.safetensors",
+    "layers.55.self_attn.v_proj.weight": "model-00043-of-00066.safetensors",
+    "layers.56.input_layernorm.weight": "model-00044-of-00066.safetensors",
+    "layers.56.mlp.down_proj.weight": "model-00044-of-00066.safetensors",
+    "layers.56.mlp.gate_proj.weight": "model-00044-of-00066.safetensors",
+    "layers.56.mlp.up_proj.weight": "model-00044-of-00066.safetensors",
+    "layers.56.post_attention_layernorm.weight": "model-00044-of-00066.safetensors",
+    "layers.56.self_attn.k_proj.bias": "model-00044-of-00066.safetensors",
+    "layers.56.self_attn.k_proj.weight": "model-00044-of-00066.safetensors",
+    "layers.56.self_attn.o_proj.weight": "model-00044-of-00066.safetensors",
+    "layers.56.self_attn.q_proj.bias": "model-00044-of-00066.safetensors",
+    "layers.56.self_attn.q_proj.weight": "model-00044-of-00066.safetensors",
+    "layers.56.self_attn.v_proj.bias": "model-00044-of-00066.safetensors",
+    "layers.56.self_attn.v_proj.weight": "model-00044-of-00066.safetensors",
+    "layers.57.input_layernorm.weight": "model-00045-of-00066.safetensors",
+    "layers.57.mlp.down_proj.weight": "model-00045-of-00066.safetensors",
+    "layers.57.mlp.gate_proj.weight": "model-00045-of-00066.safetensors",
+    "layers.57.mlp.up_proj.weight": "model-00045-of-00066.safetensors",
+    "layers.57.post_attention_layernorm.weight": "model-00045-of-00066.safetensors",
+    "layers.57.self_attn.k_proj.bias": "model-00044-of-00066.safetensors",
+    "layers.57.self_attn.k_proj.weight": "model-00044-of-00066.safetensors",
+    "layers.57.self_attn.o_proj.weight": "model-00045-of-00066.safetensors",
+    "layers.57.self_attn.q_proj.bias": "model-00044-of-00066.safetensors",
+    "layers.57.self_attn.q_proj.weight": "model-00044-of-00066.safetensors",
+    "layers.57.self_attn.v_proj.bias": "model-00044-of-00066.safetensors",
+    "layers.57.self_attn.v_proj.weight": "model-00044-of-00066.safetensors",
+    "layers.58.input_layernorm.weight": "model-00046-of-00066.safetensors",
+    "layers.58.mlp.down_proj.weight": "model-00046-of-00066.safetensors",
+    "layers.58.mlp.gate_proj.weight": "model-00045-of-00066.safetensors",
+    "layers.58.mlp.up_proj.weight": "model-00046-of-00066.safetensors",
+    "layers.58.post_attention_layernorm.weight": "model-00046-of-00066.safetensors",
+    "layers.58.self_attn.k_proj.bias": "model-00045-of-00066.safetensors",
+    "layers.58.self_attn.k_proj.weight": "model-00045-of-00066.safetensors",
+    "layers.58.self_attn.o_proj.weight": "model-00045-of-00066.safetensors",
+    "layers.58.self_attn.q_proj.bias": "model-00045-of-00066.safetensors",
+    "layers.58.self_attn.q_proj.weight": "model-00045-of-00066.safetensors",
+    "layers.58.self_attn.v_proj.bias": "model-00045-of-00066.safetensors",
+    "layers.58.self_attn.v_proj.weight": "model-00045-of-00066.safetensors",
+    "layers.59.input_layernorm.weight": "model-00047-of-00066.safetensors",
+    "layers.59.mlp.down_proj.weight": "model-00047-of-00066.safetensors",
+    "layers.59.mlp.gate_proj.weight": "model-00046-of-00066.safetensors",
+    "layers.59.mlp.up_proj.weight": "model-00046-of-00066.safetensors",
+    "layers.59.post_attention_layernorm.weight": "model-00047-of-00066.safetensors",
+    "layers.59.self_attn.k_proj.bias": "model-00046-of-00066.safetensors",
+    "layers.59.self_attn.k_proj.weight": "model-00046-of-00066.safetensors",
+    "layers.59.self_attn.o_proj.weight": "model-00046-of-00066.safetensors",
+    "layers.59.self_attn.q_proj.bias": "model-00046-of-00066.safetensors",
+    "layers.59.self_attn.q_proj.weight": "model-00046-of-00066.safetensors",
+    "layers.59.self_attn.v_proj.bias": "model-00046-of-00066.safetensors",
+    "layers.59.self_attn.v_proj.weight": "model-00046-of-00066.safetensors",
+    "layers.6.input_layernorm.weight": "model-00007-of-00066.safetensors",
+    "layers.6.mlp.down_proj.weight": "model-00007-of-00066.safetensors",
+    "layers.6.mlp.gate_proj.weight": "model-00006-of-00066.safetensors",
+    "layers.6.mlp.up_proj.weight": "model-00007-of-00066.safetensors",
+    "layers.6.post_attention_layernorm.weight": "model-00007-of-00066.safetensors",
+    "layers.6.self_attn.k_proj.bias": "model-00006-of-00066.safetensors",
+    "layers.6.self_attn.k_proj.weight": "model-00006-of-00066.safetensors",
+    "layers.6.self_attn.o_proj.weight": "model-00006-of-00066.safetensors",
+    "layers.6.self_attn.q_proj.bias": "model-00006-of-00066.safetensors",
+    "layers.6.self_attn.q_proj.weight": "model-00006-of-00066.safetensors",
+    "layers.6.self_attn.v_proj.bias": "model-00006-of-00066.safetensors",
+    "layers.6.self_attn.v_proj.weight": "model-00006-of-00066.safetensors",
+    "layers.60.input_layernorm.weight": "model-00047-of-00066.safetensors",
+    "layers.60.mlp.down_proj.weight": "model-00047-of-00066.safetensors",
+    "layers.60.mlp.gate_proj.weight": "model-00047-of-00066.safetensors",
+    "layers.60.mlp.up_proj.weight": "model-00047-of-00066.safetensors",
+    "layers.60.post_attention_layernorm.weight": "model-00047-of-00066.safetensors",
+    "layers.60.self_attn.k_proj.bias": "model-00047-of-00066.safetensors",
+    "layers.60.self_attn.k_proj.weight": "model-00047-of-00066.safetensors",
+    "layers.60.self_attn.o_proj.weight": "model-00047-of-00066.safetensors",
+    "layers.60.self_attn.q_proj.bias": "model-00047-of-00066.safetensors",
+    "layers.60.self_attn.q_proj.weight": "model-00047-of-00066.safetensors",
+    "layers.60.self_attn.v_proj.bias": "model-00047-of-00066.safetensors",
+    "layers.60.self_attn.v_proj.weight": "model-00047-of-00066.safetensors",
+    "layers.61.input_layernorm.weight": "model-00048-of-00066.safetensors",
+    "layers.61.mlp.down_proj.weight": "model-00048-of-00066.safetensors",
+    "layers.61.mlp.gate_proj.weight": "model-00048-of-00066.safetensors",
+    "layers.61.mlp.up_proj.weight": "model-00048-of-00066.safetensors",
+    "layers.61.post_attention_layernorm.weight": "model-00048-of-00066.safetensors",
+    "layers.61.self_attn.k_proj.bias": "model-00047-of-00066.safetensors",
+    "layers.61.self_attn.k_proj.weight": "model-00047-of-00066.safetensors",
+    "layers.61.self_attn.o_proj.weight": "model-00048-of-00066.safetensors",
+    "layers.61.self_attn.q_proj.bias": "model-00047-of-00066.safetensors",
+    "layers.61.self_attn.q_proj.weight": "model-00047-of-00066.safetensors",
+    "layers.61.self_attn.v_proj.bias": "model-00047-of-00066.safetensors",
+    "layers.61.self_attn.v_proj.weight": "model-00047-of-00066.safetensors",
+    "layers.62.input_layernorm.weight": "model-00049-of-00066.safetensors",
+    "layers.62.mlp.down_proj.weight": "model-00049-of-00066.safetensors",
+    "layers.62.mlp.gate_proj.weight": "model-00048-of-00066.safetensors",
+    "layers.62.mlp.up_proj.weight": "model-00049-of-00066.safetensors",
+    "layers.62.post_attention_layernorm.weight": "model-00049-of-00066.safetensors",
+    "layers.62.self_attn.k_proj.bias": "model-00048-of-00066.safetensors",
+    "layers.62.self_attn.k_proj.weight": "model-00048-of-00066.safetensors",
+    "layers.62.self_attn.o_proj.weight": "model-00048-of-00066.safetensors",
+    "layers.62.self_attn.q_proj.bias": "model-00048-of-00066.safetensors",
+    "layers.62.self_attn.q_proj.weight": "model-00048-of-00066.safetensors",
+    "layers.62.self_attn.v_proj.bias": "model-00048-of-00066.safetensors",
+    "layers.62.self_attn.v_proj.weight": "model-00048-of-00066.safetensors",
+    "layers.63.input_layernorm.weight": "model-00050-of-00066.safetensors",
+    "layers.63.mlp.down_proj.weight": "model-00050-of-00066.safetensors",
+    "layers.63.mlp.gate_proj.weight": "model-00049-of-00066.safetensors",
+    "layers.63.mlp.up_proj.weight": "model-00049-of-00066.safetensors",
+    "layers.63.post_attention_layernorm.weight": "model-00050-of-00066.safetensors",
+    "layers.63.self_attn.k_proj.bias": "model-00049-of-00066.safetensors",
+    "layers.63.self_attn.k_proj.weight": "model-00049-of-00066.safetensors",
+    "layers.63.self_attn.o_proj.weight": "model-00049-of-00066.safetensors",
+    "layers.63.self_attn.q_proj.bias": "model-00049-of-00066.safetensors",
+    "layers.63.self_attn.q_proj.weight": "model-00049-of-00066.safetensors",
+    "layers.63.self_attn.v_proj.bias": "model-00049-of-00066.safetensors",
+    "layers.63.self_attn.v_proj.weight": "model-00049-of-00066.safetensors",
+    "layers.64.input_layernorm.weight": "model-00050-of-00066.safetensors",
+    "layers.64.mlp.down_proj.weight": "model-00050-of-00066.safetensors",
+    "layers.64.mlp.gate_proj.weight": "model-00050-of-00066.safetensors",
+    "layers.64.mlp.up_proj.weight": "model-00050-of-00066.safetensors",
+    "layers.64.post_attention_layernorm.weight": "model-00050-of-00066.safetensors",
+    "layers.64.self_attn.k_proj.bias": "model-00050-of-00066.safetensors",
+    "layers.64.self_attn.k_proj.weight": "model-00050-of-00066.safetensors",
+    "layers.64.self_attn.o_proj.weight": "model-00050-of-00066.safetensors",
+    "layers.64.self_attn.q_proj.bias": "model-00050-of-00066.safetensors",
+    "layers.64.self_attn.q_proj.weight": "model-00050-of-00066.safetensors",
+    "layers.64.self_attn.v_proj.bias": "model-00050-of-00066.safetensors",
+    "layers.64.self_attn.v_proj.weight": "model-00050-of-00066.safetensors",
+    "layers.65.input_layernorm.weight": "model-00051-of-00066.safetensors",
+    "layers.65.mlp.down_proj.weight": "model-00051-of-00066.safetensors",
+    "layers.65.mlp.gate_proj.weight": "model-00051-of-00066.safetensors",
+    "layers.65.mlp.up_proj.weight": "model-00051-of-00066.safetensors",
+    "layers.65.post_attention_layernorm.weight": "model-00051-of-00066.safetensors",
+    "layers.65.self_attn.k_proj.bias": "model-00050-of-00066.safetensors",
+    "layers.65.self_attn.k_proj.weight": "model-00050-of-00066.safetensors",
+    "layers.65.self_attn.o_proj.weight": "model-00051-of-00066.safetensors",
+    "layers.65.self_attn.q_proj.bias": "model-00050-of-00066.safetensors",
+    "layers.65.self_attn.q_proj.weight": "model-00050-of-00066.safetensors",
+    "layers.65.self_attn.v_proj.bias": "model-00050-of-00066.safetensors",
+    "layers.65.self_attn.v_proj.weight": "model-00050-of-00066.safetensors",
+    "layers.66.input_layernorm.weight": "model-00052-of-00066.safetensors",
+    "layers.66.mlp.down_proj.weight": "model-00052-of-00066.safetensors",
+    "layers.66.mlp.gate_proj.weight": "model-00051-of-00066.safetensors",
+    "layers.66.mlp.up_proj.weight": "model-00052-of-00066.safetensors",
+    "layers.66.post_attention_layernorm.weight": "model-00052-of-00066.safetensors",
+    "layers.66.self_attn.k_proj.bias": "model-00051-of-00066.safetensors",
+    "layers.66.self_attn.k_proj.weight": "model-00051-of-00066.safetensors",
+    "layers.66.self_attn.o_proj.weight": "model-00051-of-00066.safetensors",
+    "layers.66.self_attn.q_proj.bias": "model-00051-of-00066.safetensors",
+    "layers.66.self_attn.q_proj.weight": "model-00051-of-00066.safetensors",
+    "layers.66.self_attn.v_proj.bias": "model-00051-of-00066.safetensors",
+    "layers.66.self_attn.v_proj.weight": "model-00051-of-00066.safetensors",
+    "layers.67.input_layernorm.weight": "model-00053-of-00066.safetensors",
+    "layers.67.mlp.down_proj.weight": "model-00053-of-00066.safetensors",
+    "layers.67.mlp.gate_proj.weight": "model-00052-of-00066.safetensors",
+    "layers.67.mlp.up_proj.weight": "model-00052-of-00066.safetensors",
+    "layers.67.post_attention_layernorm.weight": "model-00053-of-00066.safetensors",
+    "layers.67.self_attn.k_proj.bias": "model-00052-of-00066.safetensors",
+    "layers.67.self_attn.k_proj.weight": "model-00052-of-00066.safetensors",
+    "layers.67.self_attn.o_proj.weight": "model-00052-of-00066.safetensors",
+    "layers.67.self_attn.q_proj.bias": "model-00052-of-00066.safetensors",
+    "layers.67.self_attn.q_proj.weight": "model-00052-of-00066.safetensors",
+    "layers.67.self_attn.v_proj.bias": "model-00052-of-00066.safetensors",
+    "layers.67.self_attn.v_proj.weight": "model-00052-of-00066.safetensors",
+    "layers.68.input_layernorm.weight": "model-00053-of-00066.safetensors",
+    "layers.68.mlp.down_proj.weight": "model-00053-of-00066.safetensors",
+    "layers.68.mlp.gate_proj.weight": "model-00053-of-00066.safetensors",
+    "layers.68.mlp.up_proj.weight": "model-00053-of-00066.safetensors",
+    "layers.68.post_attention_layernorm.weight": "model-00053-of-00066.safetensors",
+    "layers.68.self_attn.k_proj.bias": "model-00053-of-00066.safetensors",
+    "layers.68.self_attn.k_proj.weight": "model-00053-of-00066.safetensors",
+    "layers.68.self_attn.o_proj.weight": "model-00053-of-00066.safetensors",
+    "layers.68.self_attn.q_proj.bias": "model-00053-of-00066.safetensors",
+    "layers.68.self_attn.q_proj.weight": "model-00053-of-00066.safetensors",
+    "layers.68.self_attn.v_proj.bias": "model-00053-of-00066.safetensors",
+    "layers.68.self_attn.v_proj.weight": "model-00053-of-00066.safetensors",
+    "layers.69.input_layernorm.weight": "model-00054-of-00066.safetensors",
+    "layers.69.mlp.down_proj.weight": "model-00054-of-00066.safetensors",
+    "layers.69.mlp.gate_proj.weight": "model-00054-of-00066.safetensors",
+    "layers.69.mlp.up_proj.weight": "model-00054-of-00066.safetensors",
+    "layers.69.post_attention_layernorm.weight": "model-00054-of-00066.safetensors",
+    "layers.69.self_attn.k_proj.bias": "model-00053-of-00066.safetensors",
+    "layers.69.self_attn.k_proj.weight": "model-00053-of-00066.safetensors",
+    "layers.69.self_attn.o_proj.weight": "model-00054-of-00066.safetensors",
+    "layers.69.self_attn.q_proj.bias": "model-00053-of-00066.safetensors",
+    "layers.69.self_attn.q_proj.weight": "model-00053-of-00066.safetensors",
+    "layers.69.self_attn.v_proj.bias": "model-00053-of-00066.safetensors",
+    "layers.69.self_attn.v_proj.weight": "model-00053-of-00066.safetensors",
+    "layers.7.input_layernorm.weight": "model-00008-of-00066.safetensors",
+    "layers.7.mlp.down_proj.weight": "model-00008-of-00066.safetensors",
+    "layers.7.mlp.gate_proj.weight": "model-00007-of-00066.safetensors",
+    "layers.7.mlp.up_proj.weight": "model-00007-of-00066.safetensors",
+    "layers.7.post_attention_layernorm.weight": "model-00008-of-00066.safetensors",
+    "layers.7.self_attn.k_proj.bias": "model-00007-of-00066.safetensors",
+    "layers.7.self_attn.k_proj.weight": "model-00007-of-00066.safetensors",
+    "layers.7.self_attn.o_proj.weight": "model-00007-of-00066.safetensors",
+    "layers.7.self_attn.q_proj.bias": "model-00007-of-00066.safetensors",
+    "layers.7.self_attn.q_proj.weight": "model-00007-of-00066.safetensors",
+    "layers.7.self_attn.v_proj.bias": "model-00007-of-00066.safetensors",
+    "layers.7.self_attn.v_proj.weight": "model-00007-of-00066.safetensors",
+    "layers.70.input_layernorm.weight": "model-00055-of-00066.safetensors",
+    "layers.70.mlp.down_proj.weight": "model-00055-of-00066.safetensors",
+    "layers.70.mlp.gate_proj.weight": "model-00054-of-00066.safetensors",
+    "layers.70.mlp.up_proj.weight": "model-00055-of-00066.safetensors",
+    "layers.70.post_attention_layernorm.weight": "model-00055-of-00066.safetensors",
+    "layers.70.self_attn.k_proj.bias": "model-00054-of-00066.safetensors",
+    "layers.70.self_attn.k_proj.weight": "model-00054-of-00066.safetensors",
+    "layers.70.self_attn.o_proj.weight": "model-00054-of-00066.safetensors",
+    "layers.70.self_attn.q_proj.bias": "model-00054-of-00066.safetensors",
+    "layers.70.self_attn.q_proj.weight": "model-00054-of-00066.safetensors",
+    "layers.70.self_attn.v_proj.bias": "model-00054-of-00066.safetensors",
+    "layers.70.self_attn.v_proj.weight": "model-00054-of-00066.safetensors",
+    "layers.71.input_layernorm.weight": "model-00056-of-00066.safetensors",
+    "layers.71.mlp.down_proj.weight": "model-00056-of-00066.safetensors",
+    "layers.71.mlp.gate_proj.weight": "model-00055-of-00066.safetensors",
+    "layers.71.mlp.up_proj.weight": "model-00055-of-00066.safetensors",
+    "layers.71.post_attention_layernorm.weight": "model-00056-of-00066.safetensors",
+    "layers.71.self_attn.k_proj.bias": "model-00055-of-00066.safetensors",
+    "layers.71.self_attn.k_proj.weight": "model-00055-of-00066.safetensors",
+    "layers.71.self_attn.o_proj.weight": "model-00055-of-00066.safetensors",
+    "layers.71.self_attn.q_proj.bias": "model-00055-of-00066.safetensors",
+    "layers.71.self_attn.q_proj.weight": "model-00055-of-00066.safetensors",
+    "layers.71.self_attn.v_proj.bias": "model-00055-of-00066.safetensors",
+    "layers.71.self_attn.v_proj.weight": "model-00055-of-00066.safetensors",
+    "layers.72.input_layernorm.weight": "model-00056-of-00066.safetensors",
+    "layers.72.mlp.down_proj.weight": "model-00056-of-00066.safetensors",
+    "layers.72.mlp.gate_proj.weight": "model-00056-of-00066.safetensors",
+    "layers.72.mlp.up_proj.weight": "model-00056-of-00066.safetensors",
+    "layers.72.post_attention_layernorm.weight": "model-00056-of-00066.safetensors",
+    "layers.72.self_attn.k_proj.bias": "model-00056-of-00066.safetensors",
+    "layers.72.self_attn.k_proj.weight": "model-00056-of-00066.safetensors",
+    "layers.72.self_attn.o_proj.weight": "model-00056-of-00066.safetensors",
+    "layers.72.self_attn.q_proj.bias": "model-00056-of-00066.safetensors",
+    "layers.72.self_attn.q_proj.weight": "model-00056-of-00066.safetensors",
+    "layers.72.self_attn.v_proj.bias": "model-00056-of-00066.safetensors",
+    "layers.72.self_attn.v_proj.weight": "model-00056-of-00066.safetensors",
+    "layers.73.input_layernorm.weight": "model-00057-of-00066.safetensors",
+    "layers.73.mlp.down_proj.weight": "model-00057-of-00066.safetensors",
+    "layers.73.mlp.gate_proj.weight": "model-00057-of-00066.safetensors",
+    "layers.73.mlp.up_proj.weight": "model-00057-of-00066.safetensors",
+    "layers.73.post_attention_layernorm.weight": "model-00057-of-00066.safetensors",
+    "layers.73.self_attn.k_proj.bias": "model-00056-of-00066.safetensors",
+    "layers.73.self_attn.k_proj.weight": "model-00056-of-00066.safetensors",
+    "layers.73.self_attn.o_proj.weight": "model-00057-of-00066.safetensors",
+    "layers.73.self_attn.q_proj.bias": "model-00056-of-00066.safetensors",
+    "layers.73.self_attn.q_proj.weight": "model-00056-of-00066.safetensors",
+    "layers.73.self_attn.v_proj.bias": "model-00056-of-00066.safetensors",
+    "layers.73.self_attn.v_proj.weight": "model-00056-of-00066.safetensors",
+    "layers.74.input_layernorm.weight": "model-00058-of-00066.safetensors",
+    "layers.74.mlp.down_proj.weight": "model-00058-of-00066.safetensors",
+    "layers.74.mlp.gate_proj.weight": "model-00057-of-00066.safetensors",
+    "layers.74.mlp.up_proj.weight": "model-00058-of-00066.safetensors",
+    "layers.74.post_attention_layernorm.weight": "model-00058-of-00066.safetensors",
+    "layers.74.self_attn.k_proj.bias": "model-00057-of-00066.safetensors",
+    "layers.74.self_attn.k_proj.weight": "model-00057-of-00066.safetensors",
+    "layers.74.self_attn.o_proj.weight": "model-00057-of-00066.safetensors",
+    "layers.74.self_attn.q_proj.bias": "model-00057-of-00066.safetensors",
+    "layers.74.self_attn.q_proj.weight": "model-00057-of-00066.safetensors",
+    "layers.74.self_attn.v_proj.bias": "model-00057-of-00066.safetensors",
+    "layers.74.self_attn.v_proj.weight": "model-00057-of-00066.safetensors",
+    "layers.75.input_layernorm.weight": "model-00059-of-00066.safetensors",
+    "layers.75.mlp.down_proj.weight": "model-00059-of-00066.safetensors",
+    "layers.75.mlp.gate_proj.weight": "model-00058-of-00066.safetensors",
+    "layers.75.mlp.up_proj.weight": "model-00058-of-00066.safetensors",
+    "layers.75.post_attention_layernorm.weight": "model-00059-of-00066.safetensors",
+    "layers.75.self_attn.k_proj.bias": "model-00058-of-00066.safetensors",
+    "layers.75.self_attn.k_proj.weight": "model-00058-of-00066.safetensors",
+    "layers.75.self_attn.o_proj.weight": "model-00058-of-00066.safetensors",
+    "layers.75.self_attn.q_proj.bias": "model-00058-of-00066.safetensors",
+    "layers.75.self_attn.q_proj.weight": "model-00058-of-00066.safetensors",
+    "layers.75.self_attn.v_proj.bias": "model-00058-of-00066.safetensors",
+    "layers.75.self_attn.v_proj.weight": "model-00058-of-00066.safetensors",
+    "layers.76.input_layernorm.weight": "model-00059-of-00066.safetensors",
+    "layers.76.mlp.down_proj.weight": "model-00059-of-00066.safetensors",
+    "layers.76.mlp.gate_proj.weight": "model-00059-of-00066.safetensors",
+    "layers.76.mlp.up_proj.weight": "model-00059-of-00066.safetensors",
+    "layers.76.post_attention_layernorm.weight": "model-00059-of-00066.safetensors",
+    "layers.76.self_attn.k_proj.bias": "model-00059-of-00066.safetensors",
+    "layers.76.self_attn.k_proj.weight": "model-00059-of-00066.safetensors",
+    "layers.76.self_attn.o_proj.weight": "model-00059-of-00066.safetensors",
+    "layers.76.self_attn.q_proj.bias": "model-00059-of-00066.safetensors",
+    "layers.76.self_attn.q_proj.weight": "model-00059-of-00066.safetensors",
+    "layers.76.self_attn.v_proj.bias": "model-00059-of-00066.safetensors",
+    "layers.76.self_attn.v_proj.weight": "model-00059-of-00066.safetensors",
+    "layers.77.input_layernorm.weight": "model-00060-of-00066.safetensors",
+    "layers.77.mlp.down_proj.weight": "model-00060-of-00066.safetensors",
+    "layers.77.mlp.gate_proj.weight": "model-00060-of-00066.safetensors",
+    "layers.77.mlp.up_proj.weight": "model-00060-of-00066.safetensors",
+    "layers.77.post_attention_layernorm.weight": "model-00060-of-00066.safetensors",
+    "layers.77.self_attn.k_proj.bias": "model-00059-of-00066.safetensors",
+    "layers.77.self_attn.k_proj.weight": "model-00059-of-00066.safetensors",
+    "layers.77.self_attn.o_proj.weight": "model-00060-of-00066.safetensors",
+    "layers.77.self_attn.q_proj.bias": "model-00059-of-00066.safetensors",
+    "layers.77.self_attn.q_proj.weight": "model-00059-of-00066.safetensors",
+    "layers.77.self_attn.v_proj.bias": "model-00059-of-00066.safetensors",
+    "layers.77.self_attn.v_proj.weight": "model-00059-of-00066.safetensors",
+    "layers.78.input_layernorm.weight": "model-00061-of-00066.safetensors",
+    "layers.78.mlp.down_proj.weight": "model-00061-of-00066.safetensors",
+    "layers.78.mlp.gate_proj.weight": "model-00060-of-00066.safetensors",
+    "layers.78.mlp.up_proj.weight": "model-00061-of-00066.safetensors",
+    "layers.78.post_attention_layernorm.weight": "model-00061-of-00066.safetensors",
+    "layers.78.self_attn.k_proj.bias": "model-00060-of-00066.safetensors",
+    "layers.78.self_attn.k_proj.weight": "model-00060-of-00066.safetensors",
+    "layers.78.self_attn.o_proj.weight": "model-00060-of-00066.safetensors",
+    "layers.78.self_attn.q_proj.bias": "model-00060-of-00066.safetensors",
+    "layers.78.self_attn.q_proj.weight": "model-00060-of-00066.safetensors",
+    "layers.78.self_attn.v_proj.bias": "model-00060-of-00066.safetensors",
+    "layers.78.self_attn.v_proj.weight": "model-00060-of-00066.safetensors",
+    "layers.79.input_layernorm.weight": "model-00062-of-00066.safetensors",
+    "layers.79.mlp.down_proj.weight": "model-00062-of-00066.safetensors",
+    "layers.79.mlp.gate_proj.weight": "model-00061-of-00066.safetensors",
+    "layers.79.mlp.up_proj.weight": "model-00061-of-00066.safetensors",
+    "layers.79.post_attention_layernorm.weight": "model-00062-of-00066.safetensors",
+    "layers.79.self_attn.k_proj.bias": "model-00061-of-00066.safetensors",
+    "layers.79.self_attn.k_proj.weight": "model-00061-of-00066.safetensors",
+    "layers.79.self_attn.o_proj.weight": "model-00061-of-00066.safetensors",
+    "layers.79.self_attn.q_proj.bias": "model-00061-of-00066.safetensors",
+    "layers.79.self_attn.q_proj.weight": "model-00061-of-00066.safetensors",
+    "layers.79.self_attn.v_proj.bias": "model-00061-of-00066.safetensors",
+    "layers.79.self_attn.v_proj.weight": "model-00061-of-00066.safetensors",
+    "layers.8.input_layernorm.weight": "model-00008-of-00066.safetensors",
+    "layers.8.mlp.down_proj.weight": "model-00008-of-00066.safetensors",
+    "layers.8.mlp.gate_proj.weight": "model-00008-of-00066.safetensors",
+    "layers.8.mlp.up_proj.weight": "model-00008-of-00066.safetensors",
+    "layers.8.post_attention_layernorm.weight": "model-00008-of-00066.safetensors",
+    "layers.8.self_attn.k_proj.bias": "model-00008-of-00066.safetensors",
+    "layers.8.self_attn.k_proj.weight": "model-00008-of-00066.safetensors",
+    "layers.8.self_attn.o_proj.weight": "model-00008-of-00066.safetensors",
+    "layers.8.self_attn.q_proj.bias": "model-00008-of-00066.safetensors",
+    "layers.8.self_attn.q_proj.weight": "model-00008-of-00066.safetensors",
+    "layers.8.self_attn.v_proj.bias": "model-00008-of-00066.safetensors",
+    "layers.8.self_attn.v_proj.weight": "model-00008-of-00066.safetensors",
+    "layers.80.input_layernorm.weight": "model-00062-of-00066.safetensors",
+    "layers.80.mlp.down_proj.weight": "model-00062-of-00066.safetensors",
+    "layers.80.mlp.gate_proj.weight": "model-00062-of-00066.safetensors",
+    "layers.80.mlp.up_proj.weight": "model-00062-of-00066.safetensors",
+    "layers.80.post_attention_layernorm.weight": "model-00062-of-00066.safetensors",
+    "layers.80.self_attn.k_proj.bias": "model-00062-of-00066.safetensors",
+    "layers.80.self_attn.k_proj.weight": "model-00062-of-00066.safetensors",
+    "layers.80.self_attn.o_proj.weight": "model-00062-of-00066.safetensors",
+    "layers.80.self_attn.q_proj.bias": "model-00062-of-00066.safetensors",
+    "layers.80.self_attn.q_proj.weight": "model-00062-of-00066.safetensors",
+    "layers.80.self_attn.v_proj.bias": "model-00062-of-00066.safetensors",
+    "layers.80.self_attn.v_proj.weight": "model-00062-of-00066.safetensors",
+    "layers.81.input_layernorm.weight": "model-00063-of-00066.safetensors",
+    "layers.81.mlp.down_proj.weight": "model-00063-of-00066.safetensors",
+    "layers.81.mlp.gate_proj.weight": "model-00063-of-00066.safetensors",
+    "layers.81.mlp.up_proj.weight": "model-00063-of-00066.safetensors",
+    "layers.81.post_attention_layernorm.weight": "model-00063-of-00066.safetensors",
+    "layers.81.self_attn.k_proj.bias": "model-00062-of-00066.safetensors",
+    "layers.81.self_attn.k_proj.weight": "model-00062-of-00066.safetensors",
+    "layers.81.self_attn.o_proj.weight": "model-00063-of-00066.safetensors",
+    "layers.81.self_attn.q_proj.bias": "model-00062-of-00066.safetensors",
+    "layers.81.self_attn.q_proj.weight": "model-00062-of-00066.safetensors",
+    "layers.81.self_attn.v_proj.bias": "model-00062-of-00066.safetensors",
+    "layers.81.self_attn.v_proj.weight": "model-00062-of-00066.safetensors",
+    "layers.82.input_layernorm.weight": "model-00064-of-00066.safetensors",
+    "layers.82.mlp.down_proj.weight": "model-00064-of-00066.safetensors",
+    "layers.82.mlp.gate_proj.weight": "model-00063-of-00066.safetensors",
+    "layers.82.mlp.up_proj.weight": "model-00064-of-00066.safetensors",
+    "layers.82.post_attention_layernorm.weight": "model-00064-of-00066.safetensors",
+    "layers.82.self_attn.k_proj.bias": "model-00063-of-00066.safetensors",
+    "layers.82.self_attn.k_proj.weight": "model-00063-of-00066.safetensors",
+    "layers.82.self_attn.o_proj.weight": "model-00063-of-00066.safetensors",
+    "layers.82.self_attn.q_proj.bias": "model-00063-of-00066.safetensors",
+    "layers.82.self_attn.q_proj.weight": "model-00063-of-00066.safetensors",
+    "layers.82.self_attn.v_proj.bias": "model-00063-of-00066.safetensors",
+    "layers.82.self_attn.v_proj.weight": "model-00063-of-00066.safetensors",
+    "layers.83.input_layernorm.weight": "model-00065-of-00066.safetensors",
+    "layers.83.mlp.down_proj.weight": "model-00065-of-00066.safetensors",
+    "layers.83.mlp.gate_proj.weight": "model-00064-of-00066.safetensors",
+    "layers.83.mlp.up_proj.weight": "model-00064-of-00066.safetensors",
+    "layers.83.post_attention_layernorm.weight": "model-00065-of-00066.safetensors",
+    "layers.83.self_attn.k_proj.bias": "model-00064-of-00066.safetensors",
+    "layers.83.self_attn.k_proj.weight": "model-00064-of-00066.safetensors",
+    "layers.83.self_attn.o_proj.weight": "model-00064-of-00066.safetensors",
+    "layers.83.self_attn.q_proj.bias": "model-00064-of-00066.safetensors",
+    "layers.83.self_attn.q_proj.weight": "model-00064-of-00066.safetensors",
+    "layers.83.self_attn.v_proj.bias": "model-00064-of-00066.safetensors",
+    "layers.83.self_attn.v_proj.weight": "model-00064-of-00066.safetensors",
+    "layers.84.input_layernorm.weight": "model-00065-of-00066.safetensors",
+    "layers.84.mlp.down_proj.weight": "model-00065-of-00066.safetensors",
+    "layers.84.mlp.gate_proj.weight": "model-00065-of-00066.safetensors",
+    "layers.84.mlp.up_proj.weight": "model-00065-of-00066.safetensors",
+    "layers.84.post_attention_layernorm.weight": "model-00065-of-00066.safetensors",
+    "layers.84.self_attn.k_proj.bias": "model-00065-of-00066.safetensors",
+    "layers.84.self_attn.k_proj.weight": "model-00065-of-00066.safetensors",
+    "layers.84.self_attn.o_proj.weight": "model-00065-of-00066.safetensors",
+    "layers.84.self_attn.q_proj.bias": "model-00065-of-00066.safetensors",
+    "layers.84.self_attn.q_proj.weight": "model-00065-of-00066.safetensors",
+    "layers.84.self_attn.v_proj.bias": "model-00065-of-00066.safetensors",
+    "layers.84.self_attn.v_proj.weight": "model-00065-of-00066.safetensors",
+    "layers.85.input_layernorm.weight": "model-00066-of-00066.safetensors",
+    "layers.85.mlp.down_proj.weight": "model-00066-of-00066.safetensors",
+    "layers.85.mlp.gate_proj.weight": "model-00066-of-00066.safetensors",
+    "layers.85.mlp.up_proj.weight": "model-00066-of-00066.safetensors",
+    "layers.85.post_attention_layernorm.weight": "model-00066-of-00066.safetensors",
+    "layers.85.self_attn.k_proj.bias": "model-00065-of-00066.safetensors",
+    "layers.85.self_attn.k_proj.weight": "model-00065-of-00066.safetensors",
+    "layers.85.self_attn.o_proj.weight": "model-00066-of-00066.safetensors",
+    "layers.85.self_attn.q_proj.bias": "model-00065-of-00066.safetensors",
+    "layers.85.self_attn.q_proj.weight": "model-00065-of-00066.safetensors",
+    "layers.85.self_attn.v_proj.bias": "model-00065-of-00066.safetensors",
+    "layers.85.self_attn.v_proj.weight": "model-00065-of-00066.safetensors",
+    "layers.9.input_layernorm.weight": "model-00009-of-00066.safetensors",
+    "layers.9.mlp.down_proj.weight": "model-00009-of-00066.safetensors",
+    "layers.9.mlp.gate_proj.weight": "model-00009-of-00066.safetensors",
+    "layers.9.mlp.up_proj.weight": "model-00009-of-00066.safetensors",
+    "layers.9.post_attention_layernorm.weight": "model-00009-of-00066.safetensors",
+    "layers.9.self_attn.k_proj.bias": "model-00008-of-00066.safetensors",
+    "layers.9.self_attn.k_proj.weight": "model-00008-of-00066.safetensors",
+    "layers.9.self_attn.o_proj.weight": "model-00009-of-00066.safetensors",
+    "layers.9.self_attn.q_proj.bias": "model-00008-of-00066.safetensors",
+    "layers.9.self_attn.q_proj.weight": "model-00008-of-00066.safetensors",
+    "layers.9.self_attn.v_proj.bias": "model-00008-of-00066.safetensors",
+    "layers.9.self_attn.v_proj.weight": "model-00008-of-00066.safetensors",
+    "norm.weight": "model-00066-of-00066.safetensors"
+  }
+}