Hugging Face's logo

apple
/
FastVLM-7B-int4

Core ML
Safetensors
ml-fastvlm
llava_qwen2
Model card Files
xet
Community
1
fartashf commited on
Commit
f6ee2c0
·
verified ·
1 Parent(s): c59ee59

Upload folder using huggingface_hub

Browse files
Files changed (18) hide show
  1. .gitattributes +2 -0
  2. LICENSE +88 -0
  3. README.md +53 -0
  4. acc_vs_latency_qwen-2.png +3 -0
  5. added_tokens.json +25 -0
  6. config.json +50 -0
  7. fastvithd.mlpackage/Data/com.apple.CoreML/model.mlmodel +3 -0
  8. fastvithd.mlpackage/Data/com.apple.CoreML/weights/weight.bin +3 -0
  9. fastvithd.mlpackage/Manifest.json +18 -0
  10. merges.txt +0 -0
  11. model.safetensors +3 -0
  12. model.safetensors.index.json +750 -0
  13. preprocessor_config.json +28 -0
  14. processor_config.json +7 -0
  15. special_tokens_map.json +31 -0
  16. tokenizer.json +3 -0
  17. tokenizer_config.json +219 -0
  18. vocab.json +0 -0
.gitattributes CHANGED
@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ acc_vs_latency_qwen-2.png filter=lfs diff=lfs merge=lfs -text
37
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
LICENSE ADDED
@@ -0,0 +1,88 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ Disclaimer: IMPORTANT: This Apple Machine Learning Research Model is
2
+ specifically developed and released by Apple Inc. ("Apple") for the sole purpose
3
+ of scientific research of artificial intelligence and machine-learning
4
+ technology. “Apple Machine Learning Research Model” means the model, including
5
+ but not limited to algorithms, formulas, trained model weights, parameters,
6
+ configurations, checkpoints, and any related materials (including
7
+ documentation).
8
+
9
+ This Apple Machine Learning Research Model is provided to You by
10
+ Apple in consideration of your agreement to the following terms, and your use,
11
+ modification, creation of Model Derivatives, and or redistribution of the Apple
12
+ Machine Learning Research Model constitutes acceptance of this Agreement. If You
13
+ do not agree with these terms, please do not use, modify, create Model
14
+ Derivatives of, or distribute this Apple Machine Learning Research Model or
15
+ Model Derivatives.
16
+
17
+ * License Scope: In consideration of your agreement to abide by the following
18
+ terms, and subject to these terms, Apple hereby grants you a personal,
19
+ non-exclusive, worldwide, non-transferable, royalty-free, revocable, and
20
+ limited license, to use, copy, modify, distribute, and create Model
21
+ Derivatives (defined below) of the Apple Machine Learning Research Model
22
+ exclusively for Research Purposes. You agree that any Model Derivatives You
23
+ may create or that may be created for You will be limited to Research Purposes
24
+ as well. “Research Purposes” means non-commercial scientific research and
25
+ academic development activities, such as experimentation, analysis, testing
26
+ conducted by You with the sole intent to advance scientific knowledge and
27
+ research. “Research Purposes” does not include any commercial exploitation,
28
+ product development or use in any commercial product or service.
29
+
30
+ * Distribution of Apple Machine Learning Research Model and Model Derivatives:
31
+ If you choose to redistribute Apple Machine Learning Research Model or its
32
+ Model Derivatives, you must provide a copy of this Agreement to such third
33
+ party, and ensure that the following attribution notice be provided: “Apple
34
+ Machine Learning Research Model is licensed under the Apple Machine Learning
35
+ Research Model License Agreement.” Additionally, all Model Derivatives must
36
+ clearly be identified as such, including disclosure of modifications and
37
+ changes made to the Apple Machine Learning Research Model. The name,
38
+ trademarks, service marks or logos of Apple may not be used to endorse or
39
+ promote Model Derivatives or the relationship between You and Apple. “Model
40
+ Derivatives” means any models or any other artifacts created by modifications,
41
+ improvements, adaptations, alterations to the architecture, algorithm or
42
+ training processes of the Apple Machine Learning Research Model, or by any
43
+ retraining, fine-tuning of the Apple Machine Learning Research Model.
44
+
45
+ * No Other License: Except as expressly stated in this notice, no other rights
46
+ or licenses, express or implied, are granted by Apple herein, including but
47
+ not limited to any patent, trademark, and similar intellectual property rights
48
+ worldwide that may be infringed by the Apple Machine Learning Research Model,
49
+ the Model Derivatives or by other works in which the Apple Machine Learning
50
+ Research Model may be incorporated.
51
+
52
+ * Compliance with Laws: Your use of Apple Machine Learning Research Model must
53
+ be in compliance with all applicable laws and regulations.
54
+
55
+ * Term and Termination: The term of this Agreement will begin upon your
56
+ acceptance of this Agreement or use of the Apple Machine Learning Research
57
+ Model and will continue until terminated in accordance with the following
58
+ terms. Apple may terminate this Agreement at any time if You are in breach of
59
+ any term or condition of this Agreement. Upon termination of this Agreement,
60
+ You must cease to use all Apple Machine Learning Research Models and Model
61
+ Derivatives and permanently delete any copy thereof. Sections 3, 6 and 7 will
62
+ survive termination.
63
+
64
+ * Disclaimer and Limitation of Liability: This Apple Machine Learning Research
65
+ Model and any outputs generated by the Apple Machine Learning Research Model
66
+ are provided on an “AS IS” basis. APPLE MAKES NO WARRANTIES, EXPRESS OR
67
+ IMPLIED, INCLUDING WITHOUT LIMITATION THE IMPLIED WARRANTIES OF
68
+ NON-INFRINGEMENT, MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE,
69
+ REGARDING THE APPLE MACHINE LEARNING RESEARCH MODEL OR OUTPUTS GENERATED BY
70
+ THE APPLE MACHINE LEARNING RESEARCH MODEL. You are solely responsible for
71
+ determining the appropriateness of using or redistributing the Apple Machine
72
+ Learning Research Model and any outputs of the Apple Machine Learning Research
73
+ Model and assume any risks associated with Your use of the Apple Machine
74
+ Learning Research Model and any output and results. IN NO EVENT SHALL APPLE BE
75
+ LIABLE FOR ANY SPECIAL, INDIRECT, INCIDENTAL OR CONSEQUENTIAL DAMAGES ARISING
76
+ IN ANY WAY OUT OF THE USE, REPRODUCTION, MODIFICATION AND/OR DISTRIBUTION OF
77
+ THE APPLE MACHINE LEARNING RESEARCH MODEL AND ANY OUTPUTS OF THE APPLE MACHINE
78
+ LEARNING RESEARCH MODEL, HOWEVER CAUSED AND WHETHER UNDER THEORY OF CONTRACT,
79
+ TORT (INCLUDING NEGLIGENCE), STRICT LIABILITY OR OTHERWISE, EVEN IF APPLE HAS
80
+ BEEN ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
81
+
82
+ * Governing Law: This Agreement will be governed by and construed under the laws
83
+ of the State of California without regard to its choice of law principles. The
84
+ Convention on Contracts for the International Sale of Goods shall not apply to
85
+ the Agreement except that the arbitration clause and any arbitration hereunder
86
+ shall be governed by the Federal Arbitration Act, Chapters 1 and 2. 
87
+
88
+ Copyright (C) 2025 Apple Inc. All Rights Reserved.
README.md ADDED
@@ -0,0 +1,53 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apple-amlr
3
+ license_name: apple-ascl
4
+ license_link: https://github.com/apple/ml-fastvlm/blob/main/LICENSE_MODEL
5
+ library_name: ml-fastvlm
6
+ ---
7
+ # FastVLM: Efficient Vision Encoding for Vision Language Models
8
+
9
+ FastVLM was introduced in
10
+ **[FastVLM: Efficient Vision Encoding for Vision Language Models](https://www.arxiv.org/abs/2412.13303). (CVPR 2025)**
11
+
12
+ [//]: # (![FastViTHD Performance](acc_vs_latency_qwen-2.png))
13
+ <p align="center">
14
+ <img src="acc_vs_latency_qwen-2.png" alt="Accuracy vs latency figure." width="400"/>
15
+ </p>
16
+
17
+ ### Highlights
18
+ * We introduce FastViTHD, a novel hybrid vision encoder designed to output fewer tokens and significantly reduce encoding time for high-resolution images.
19
+ * Our smallest variant outperforms LLaVA-OneVision-0.5B with 85x faster Time-to-First-Token (TTFT) and 3.4x smaller vision encoder.
20
+ * Our larger variants using Qwen2-7B LLM outperform recent works like Cambrian-1-8B while using a single image encoder with a 7.9x faster TTFT.
21
+
22
+
23
+ ### Evaluations
24
+ | Benchmark | FastVLM-0.5B | FastVLM-1.5B | FastVLM-7B |
25
+ |:--------------|:------------:|:------------:|:----------:|
26
+ | Ai2D | 68.0 | 77.4 | 83.6 |
27
+ | ScienceQA | 85.2 | 94.4 | 96.7 |
28
+ | MMMU | 33.9 | 37.8 | 45.4 |
29
+ | VQAv2 | 76.3 | 79.1 | 80.8 |
30
+ | ChartQA | 76.0 | 80.1 | 85.0 |
31
+ | TextVQA | 64.5 | 70.4 | 74.9 |
32
+ | InfoVQA | 46.4 | 59.7 | 75.8 |
33
+ | DocVQA | 82.5 | 88.3 | 93.2 |
34
+ | OCRBench | 63.9 | 70.2 | 73.1 |
35
+ | RealWorldQA | 56.1 | 61.2 | 67.2 |
36
+ | SeedBench-Img | 71.0 | 74.2 | 75.4 |
37
+
38
+
39
+ ### Usage Example
40
+ The model has been exported to run with MLX. Follow the instructions in the official repository to use it in an iOS or macOS app.
41
+
42
+
43
+ ## Citation
44
+ If you found this model useful, please cite the following paper:
45
+ ```
46
+ @InProceedings{fastvlm2025,
47
+ author = {Pavan Kumar Anasosalu Vasu, Fartash Faghri, Chun-Liang Li, Cem Koc, Nate True, Albert Antony, Gokul Santhanam, James Gabriel, Peter Grasch, Oncel Tuzel, Hadi Pouransari},
48
+ title = {FastVLM: Efficient Vision Encoding for Vision Language Models},
49
+ booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
50
+ month = {June},
51
+ year = {2025},
52
+ }
53
+ ```
acc_vs_latency_qwen-2.png ADDED

Git LFS Details

  • SHA256: ddb1d072926fa84a40a5112fc0c69743dbf74c023e1c2b74e35e95317b9cd0ae
  • Pointer size: 131 Bytes
  • Size of remote file: 229 kB
added_tokens.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</tool_call>": 151658,
3
+ "<image>": 151665,
4
+ "<tool_call>": 151657,
5
+ "<|box_end|>": 151649,
6
+ "<|box_start|>": 151648,
7
+ "<|endoftext|>": 151643,
8
+ "<|file_sep|>": 151664,
9
+ "<|fim_middle|>": 151660,
10
+ "<|fim_pad|>": 151662,
11
+ "<|fim_prefix|>": 151659,
12
+ "<|fim_suffix|>": 151661,
13
+ "<|im_end|>": 151645,
14
+ "<|im_start|>": 151644,
15
+ "<|image_pad|>": 151655,
16
+ "<|object_ref_end|>": 151647,
17
+ "<|object_ref_start|>": 151646,
18
+ "<|quad_end|>": 151651,
19
+ "<|quad_start|>": 151650,
20
+ "<|repo_name|>": 151663,
21
+ "<|video_pad|>": 151656,
22
+ "<|vision_end|>": 151653,
23
+ "<|vision_pad|>": 151654,
24
+ "<|vision_start|>": 151652
25
+ }
config.json ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "LlavaQwen2ForCausalLM"
4
+ ],
5
+ "attention_dropout": 0.0,
6
+ "bos_token_id": 151643,
7
+ "eos_token_id": 151645,
8
+ "freeze_mm_mlp_adapter": false,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 3584,
11
+ "image_aspect_ratio": "pad",
12
+ "image_grid_pinpoints": null,
13
+ "image_token_index": 151665,
14
+ "initializer_range": 0.02,
15
+ "intermediate_size": 18944,
16
+ "max_position_embeddings": 32768,
17
+ "max_window_layers": 28,
18
+ "mm_hidden_size": 3072,
19
+ "mm_patch_merge_type": "flat",
20
+ "mm_projector_lr": null,
21
+ "mm_projector_type": "mlp2x_gelu",
22
+ "mm_use_im_patch_token": false,
23
+ "mm_use_im_start_end": false,
24
+ "mm_vision_select_feature": "patch",
25
+ "mm_vision_select_layer": -2,
26
+ "mm_vision_tower": "mobileclip_l_1024",
27
+ "model_type": "llava_qwen2",
28
+ "num_attention_heads": 28,
29
+ "num_hidden_layers": 28,
30
+ "num_key_value_heads": 4,
31
+ "quantization": {
32
+ "group_size": 64,
33
+ "bits": 4
34
+ },
35
+ "rms_norm_eps": 1e-06,
36
+ "rope_theta": 1000000.0,
37
+ "sliding_window": 131072,
38
+ "tie_word_embeddings": false,
39
+ "tokenizer_model_max_length": 8192,
40
+ "tokenizer_padding_side": "right",
41
+ "torch_dtype": "bfloat16",
42
+ "transformers_version": "4.39.3",
43
+ "tune_mm_mlp_adapter": false,
44
+ "unfreeze_mm_vision_tower": true,
45
+ "use_cache": true,
46
+ "use_mm_proj": true,
47
+ "use_sliding_window": false,
48
+ "vision_config": {},
49
+ "vocab_size": 152064
50
+ }
fastvithd.mlpackage/Data/com.apple.CoreML/model.mlmodel ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef95cee6af9141959f98a97b980e33f447ff4de8c843668b6f59df02234f0f79
3
+ size 323561
fastvithd.mlpackage/Data/com.apple.CoreML/weights/weight.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a2e2e3c3740f411d3090b6bb9e8c71cf17e5a239a7c9ade4ff060dca80b3add7
3
+ size 490786624
fastvithd.mlpackage/Manifest.json ADDED
@@ -0,0 +1,18 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "fileFormatVersion": "1.0.0",
3
+ "itemInfoEntries": {
4
+ "7877E2AC-98B7-4AF4-8DF5-6BDC7DE598C8": {
5
+ "author": "com.apple.CoreML",
6
+ "description": "CoreML Model Weights",
7
+ "name": "weights",
8
+ "path": "com.apple.CoreML/weights"
9
+ },
10
+ "DEBF73A7-707F-4150-A735-9B63586A67E8": {
11
+ "author": "com.apple.CoreML",
12
+ "description": "CoreML Model Specification",
13
+ "name": "model.mlmodel",
14
+ "path": "com.apple.CoreML/model.mlmodel"
15
+ }
16
+ },
17
+ "rootModelIdentifier": "DEBF73A7-707F-4150-A735-9B63586A67E8"
18
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a4d20f84628e28465947de96411bdcc0bbaf0319211e4d061f053513babd7a21
3
+ size 4297790862
model.safetensors.index.json ADDED
@@ -0,0 +1,750 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 4297696256
4
+ },
5
+ "weight_map": {
6
+ "language_model.lm_head.biases": "model.safetensors",
7
+ "language_model.lm_head.scales": "model.safetensors",
8
+ "language_model.lm_head.weight": "model.safetensors",
9
+ "language_model.model.embed_tokens.biases": "model.safetensors",
10
+ "language_model.model.embed_tokens.scales": "model.safetensors",
11
+ "language_model.model.embed_tokens.weight": "model.safetensors",
12
+ "language_model.model.layers.0.input_layernorm.weight": "model.safetensors",
13
+ "language_model.model.layers.0.mlp.down_proj.biases": "model.safetensors",
14
+ "language_model.model.layers.0.mlp.down_proj.scales": "model.safetensors",
15
+ "language_model.model.layers.0.mlp.down_proj.weight": "model.safetensors",
16
+ "language_model.model.layers.0.mlp.gate_proj.biases": "model.safetensors",
17
+ "language_model.model.layers.0.mlp.gate_proj.scales": "model.safetensors",
18
+ "language_model.model.layers.0.mlp.gate_proj.weight": "model.safetensors",
19
+ "language_model.model.layers.0.mlp.up_proj.biases": "model.safetensors",
20
+ "language_model.model.layers.0.mlp.up_proj.scales": "model.safetensors",
21
+ "language_model.model.layers.0.mlp.up_proj.weight": "model.safetensors",
22
+ "language_model.model.layers.0.post_attention_layernorm.weight": "model.safetensors",
23
+ "language_model.model.layers.0.self_attn.k_proj.bias": "model.safetensors",
24
+ "language_model.model.layers.0.self_attn.k_proj.biases": "model.safetensors",
25
+ "language_model.model.layers.0.self_attn.k_proj.scales": "model.safetensors",
26
+ "language_model.model.layers.0.self_attn.k_proj.weight": "model.safetensors",
27
+ "language_model.model.layers.0.self_attn.o_proj.biases": "model.safetensors",
28
+ "language_model.model.layers.0.self_attn.o_proj.scales": "model.safetensors",
29
+ "language_model.model.layers.0.self_attn.o_proj.weight": "model.safetensors",
30
+ "language_model.model.layers.0.self_attn.q_proj.bias": "model.safetensors",
31
+ "language_model.model.layers.0.self_attn.q_proj.biases": "model.safetensors",
32
+ "language_model.model.layers.0.self_attn.q_proj.scales": "model.safetensors",
33
+ "language_model.model.layers.0.self_attn.q_proj.weight": "model.safetensors",
34
+ "language_model.model.layers.0.self_attn.v_proj.bias": "model.safetensors",
35
+ "language_model.model.layers.0.self_attn.v_proj.biases": "model.safetensors",
36
+ "language_model.model.layers.0.self_attn.v_proj.scales": "model.safetensors",
37
+ "language_model.model.layers.0.self_attn.v_proj.weight": "model.safetensors",
38
+ "language_model.model.layers.1.input_layernorm.weight": "model.safetensors",
39
+ "language_model.model.layers.1.mlp.down_proj.biases": "model.safetensors",
40
+ "language_model.model.layers.1.mlp.down_proj.scales": "model.safetensors",
41
+ "language_model.model.layers.1.mlp.down_proj.weight": "model.safetensors",
42
+ "language_model.model.layers.1.mlp.gate_proj.biases": "model.safetensors",
43
+ "language_model.model.layers.1.mlp.gate_proj.scales": "model.safetensors",
44
+ "language_model.model.layers.1.mlp.gate_proj.weight": "model.safetensors",
45
+ "language_model.model.layers.1.mlp.up_proj.biases": "model.safetensors",
46
+ "language_model.model.layers.1.mlp.up_proj.scales": "model.safetensors",
47
+ "language_model.model.layers.1.mlp.up_proj.weight": "model.safetensors",
48
+ "language_model.model.layers.1.post_attention_layernorm.weight": "model.safetensors",
49
+ "language_model.model.layers.1.self_attn.k_proj.bias": "model.safetensors",
50
+ "language_model.model.layers.1.self_attn.k_proj.biases": "model.safetensors",
51
+ "language_model.model.layers.1.self_attn.k_proj.scales": "model.safetensors",
52
+ "language_model.model.layers.1.self_attn.k_proj.weight": "model.safetensors",
53
+ "language_model.model.layers.1.self_attn.o_proj.biases": "model.safetensors",
54
+ "language_model.model.layers.1.self_attn.o_proj.scales": "model.safetensors",
55
+ "language_model.model.layers.1.self_attn.o_proj.weight": "model.safetensors",
56
+ "language_model.model.layers.1.self_attn.q_proj.bias": "model.safetensors",
57
+ "language_model.model.layers.1.self_attn.q_proj.biases": "model.safetensors",
58
+ "language_model.model.layers.1.self_attn.q_proj.scales": "model.safetensors",
59
+ "language_model.model.layers.1.self_attn.q_proj.weight": "model.safetensors",
60
+ "language_model.model.layers.1.self_attn.v_proj.bias": "model.safetensors",
61
+ "language_model.model.layers.1.self_attn.v_proj.biases": "model.safetensors",
62
+ "language_model.model.layers.1.self_attn.v_proj.scales": "model.safetensors",
63
+ "language_model.model.layers.1.self_attn.v_proj.weight": "model.safetensors",
64
+ "language_model.model.layers.10.input_layernorm.weight": "model.safetensors",
65
+ "language_model.model.layers.10.mlp.down_proj.biases": "model.safetensors",
66
+ "language_model.model.layers.10.mlp.down_proj.scales": "model.safetensors",
67
+ "language_model.model.layers.10.mlp.down_proj.weight": "model.safetensors",
68
+ "language_model.model.layers.10.mlp.gate_proj.biases": "model.safetensors",
69
+ "language_model.model.layers.10.mlp.gate_proj.scales": "model.safetensors",
70
+ "language_model.model.layers.10.mlp.gate_proj.weight": "model.safetensors",
71
+ "language_model.model.layers.10.mlp.up_proj.biases": "model.safetensors",
72
+ "language_model.model.layers.10.mlp.up_proj.scales": "model.safetensors",
73
+ "language_model.model.layers.10.mlp.up_proj.weight": "model.safetensors",
74
+ "language_model.model.layers.10.post_attention_layernorm.weight": "model.safetensors",
75
+ "language_model.model.layers.10.self_attn.k_proj.bias": "model.safetensors",
76
+ "language_model.model.layers.10.self_attn.k_proj.biases": "model.safetensors",
77
+ "language_model.model.layers.10.self_attn.k_proj.scales": "model.safetensors",
78
+ "language_model.model.layers.10.self_attn.k_proj.weight": "model.safetensors",
79
+ "language_model.model.layers.10.self_attn.o_proj.biases": "model.safetensors",
80
+ "language_model.model.layers.10.self_attn.o_proj.scales": "model.safetensors",
81
+ "language_model.model.layers.10.self_attn.o_proj.weight": "model.safetensors",
82
+ "language_model.model.layers.10.self_attn.q_proj.bias": "model.safetensors",
83
+ "language_model.model.layers.10.self_attn.q_proj.biases": "model.safetensors",
84
+ "language_model.model.layers.10.self_attn.q_proj.scales": "model.safetensors",
85
+ "language_model.model.layers.10.self_attn.q_proj.weight": "model.safetensors",
86
+ "language_model.model.layers.10.self_attn.v_proj.bias": "model.safetensors",
87
+ "language_model.model.layers.10.self_attn.v_proj.biases": "model.safetensors",
88
+ "language_model.model.layers.10.self_attn.v_proj.scales": "model.safetensors",
89
+ "language_model.model.layers.10.self_attn.v_proj.weight": "model.safetensors",
90
+ "language_model.model.layers.11.input_layernorm.weight": "model.safetensors",
91
+ "language_model.model.layers.11.mlp.down_proj.biases": "model.safetensors",
92
+ "language_model.model.layers.11.mlp.down_proj.scales": "model.safetensors",
93
+ "language_model.model.layers.11.mlp.down_proj.weight": "model.safetensors",
94
+ "language_model.model.layers.11.mlp.gate_proj.biases": "model.safetensors",
95
+ "language_model.model.layers.11.mlp.gate_proj.scales": "model.safetensors",
96
+ "language_model.model.layers.11.mlp.gate_proj.weight": "model.safetensors",
97
+ "language_model.model.layers.11.mlp.up_proj.biases": "model.safetensors",
98
+ "language_model.model.layers.11.mlp.up_proj.scales": "model.safetensors",
99
+ "language_model.model.layers.11.mlp.up_proj.weight": "model.safetensors",
100
+ "language_model.model.layers.11.post_attention_layernorm.weight": "model.safetensors",
101
+ "language_model.model.layers.11.self_attn.k_proj.bias": "model.safetensors",
102
+ "language_model.model.layers.11.self_attn.k_proj.biases": "model.safetensors",
103
+ "language_model.model.layers.11.self_attn.k_proj.scales": "model.safetensors",
104
+ "language_model.model.layers.11.self_attn.k_proj.weight": "model.safetensors",
105
+ "language_model.model.layers.11.self_attn.o_proj.biases": "model.safetensors",
106
+ "language_model.model.layers.11.self_attn.o_proj.scales": "model.safetensors",
107
+ "language_model.model.layers.11.self_attn.o_proj.weight": "model.safetensors",
108
+ "language_model.model.layers.11.self_attn.q_proj.bias": "model.safetensors",
109
+ "language_model.model.layers.11.self_attn.q_proj.biases": "model.safetensors",
110
+ "language_model.model.layers.11.self_attn.q_proj.scales": "model.safetensors",
111
+ "language_model.model.layers.11.self_attn.q_proj.weight": "model.safetensors",
112
+ "language_model.model.layers.11.self_attn.v_proj.bias": "model.safetensors",
113
+ "language_model.model.layers.11.self_attn.v_proj.biases": "model.safetensors",
114
+ "language_model.model.layers.11.self_attn.v_proj.scales": "model.safetensors",
115
+ "language_model.model.layers.11.self_attn.v_proj.weight": "model.safetensors",
116
+ "language_model.model.layers.12.input_layernorm.weight": "model.safetensors",
117
+ "language_model.model.layers.12.mlp.down_proj.biases": "model.safetensors",
118
+ "language_model.model.layers.12.mlp.down_proj.scales": "model.safetensors",
119
+ "language_model.model.layers.12.mlp.down_proj.weight": "model.safetensors",
120
+ "language_model.model.layers.12.mlp.gate_proj.biases": "model.safetensors",
121
+ "language_model.model.layers.12.mlp.gate_proj.scales": "model.safetensors",
122
+ "language_model.model.layers.12.mlp.gate_proj.weight": "model.safetensors",
123
+ "language_model.model.layers.12.mlp.up_proj.biases": "model.safetensors",
124
+ "language_model.model.layers.12.mlp.up_proj.scales": "model.safetensors",
125
+ "language_model.model.layers.12.mlp.up_proj.weight": "model.safetensors",
126
+ "language_model.model.layers.12.post_attention_layernorm.weight": "model.safetensors",
127
+ "language_model.model.layers.12.self_attn.k_proj.bias": "model.safetensors",
128
+ "language_model.model.layers.12.self_attn.k_proj.biases": "model.safetensors",
129
+ "language_model.model.layers.12.self_attn.k_proj.scales": "model.safetensors",
130
+ "language_model.model.layers.12.self_attn.k_proj.weight": "model.safetensors",
131
+ "language_model.model.layers.12.self_attn.o_proj.biases": "model.safetensors",
132
+ "language_model.model.layers.12.self_attn.o_proj.scales": "model.safetensors",
133
+ "language_model.model.layers.12.self_attn.o_proj.weight": "model.safetensors",
134
+ "language_model.model.layers.12.self_attn.q_proj.bias": "model.safetensors",
135
+ "language_model.model.layers.12.self_attn.q_proj.biases": "model.safetensors",
136
+ "language_model.model.layers.12.self_attn.q_proj.scales": "model.safetensors",
137
+ "language_model.model.layers.12.self_attn.q_proj.weight": "model.safetensors",
138
+ "language_model.model.layers.12.self_attn.v_proj.bias": "model.safetensors",
139
+ "language_model.model.layers.12.self_attn.v_proj.biases": "model.safetensors",
140
+ "language_model.model.layers.12.self_attn.v_proj.scales": "model.safetensors",
141
+ "language_model.model.layers.12.self_attn.v_proj.weight": "model.safetensors",
142
+ "language_model.model.layers.13.input_layernorm.weight": "model.safetensors",
143
+ "language_model.model.layers.13.mlp.down_proj.biases": "model.safetensors",
144
+ "language_model.model.layers.13.mlp.down_proj.scales": "model.safetensors",
145
+ "language_model.model.layers.13.mlp.down_proj.weight": "model.safetensors",
146
+ "language_model.model.layers.13.mlp.gate_proj.biases": "model.safetensors",
147
+ "language_model.model.layers.13.mlp.gate_proj.scales": "model.safetensors",
148
+ "language_model.model.layers.13.mlp.gate_proj.weight": "model.safetensors",
149
+ "language_model.model.layers.13.mlp.up_proj.biases": "model.safetensors",
150
+ "language_model.model.layers.13.mlp.up_proj.scales": "model.safetensors",
151
+ "language_model.model.layers.13.mlp.up_proj.weight": "model.safetensors",
152
+ "language_model.model.layers.13.post_attention_layernorm.weight": "model.safetensors",
153
+ "language_model.model.layers.13.self_attn.k_proj.bias": "model.safetensors",
154
+ "language_model.model.layers.13.self_attn.k_proj.biases": "model.safetensors",
155
+ "language_model.model.layers.13.self_attn.k_proj.scales": "model.safetensors",
156
+ "language_model.model.layers.13.self_attn.k_proj.weight": "model.safetensors",
157
+ "language_model.model.layers.13.self_attn.o_proj.biases": "model.safetensors",
158
+ "language_model.model.layers.13.self_attn.o_proj.scales": "model.safetensors",
159
+ "language_model.model.layers.13.self_attn.o_proj.weight": "model.safetensors",
160
+ "language_model.model.layers.13.self_attn.q_proj.bias": "model.safetensors",
161
+ "language_model.model.layers.13.self_attn.q_proj.biases": "model.safetensors",
162
+ "language_model.model.layers.13.self_attn.q_proj.scales": "model.safetensors",
163
+ "language_model.model.layers.13.self_attn.q_proj.weight": "model.safetensors",
164
+ "language_model.model.layers.13.self_attn.v_proj.bias": "model.safetensors",
165
+ "language_model.model.layers.13.self_attn.v_proj.biases": "model.safetensors",
166
+ "language_model.model.layers.13.self_attn.v_proj.scales": "model.safetensors",
167
+ "language_model.model.layers.13.self_attn.v_proj.weight": "model.safetensors",
168
+ "language_model.model.layers.14.input_layernorm.weight": "model.safetensors",
169
+ "language_model.model.layers.14.mlp.down_proj.biases": "model.safetensors",
170
+ "language_model.model.layers.14.mlp.down_proj.scales": "model.safetensors",
171
+ "language_model.model.layers.14.mlp.down_proj.weight": "model.safetensors",
172
+ "language_model.model.layers.14.mlp.gate_proj.biases": "model.safetensors",
173
+ "language_model.model.layers.14.mlp.gate_proj.scales": "model.safetensors",
174
+ "language_model.model.layers.14.mlp.gate_proj.weight": "model.safetensors",
175
+ "language_model.model.layers.14.mlp.up_proj.biases": "model.safetensors",
176
+ "language_model.model.layers.14.mlp.up_proj.scales": "model.safetensors",
177
+ "language_model.model.layers.14.mlp.up_proj.weight": "model.safetensors",
178
+ "language_model.model.layers.14.post_attention_layernorm.weight": "model.safetensors",
179
+ "language_model.model.layers.14.self_attn.k_proj.bias": "model.safetensors",
180
+ "language_model.model.layers.14.self_attn.k_proj.biases": "model.safetensors",
181
+ "language_model.model.layers.14.self_attn.k_proj.scales": "model.safetensors",
182
+ "language_model.model.layers.14.self_attn.k_proj.weight": "model.safetensors",
183
+ "language_model.model.layers.14.self_attn.o_proj.biases": "model.safetensors",
184
+ "language_model.model.layers.14.self_attn.o_proj.scales": "model.safetensors",
185
+ "language_model.model.layers.14.self_attn.o_proj.weight": "model.safetensors",
186
+ "language_model.model.layers.14.self_attn.q_proj.bias": "model.safetensors",
187
+ "language_model.model.layers.14.self_attn.q_proj.biases": "model.safetensors",
188
+ "language_model.model.layers.14.self_attn.q_proj.scales": "model.safetensors",
189
+ "language_model.model.layers.14.self_attn.q_proj.weight": "model.safetensors",
190
+ "language_model.model.layers.14.self_attn.v_proj.bias": "model.safetensors",
191
+ "language_model.model.layers.14.self_attn.v_proj.biases": "model.safetensors",
192
+ "language_model.model.layers.14.self_attn.v_proj.scales": "model.safetensors",
193
+ "language_model.model.layers.14.self_attn.v_proj.weight": "model.safetensors",
194
+ "language_model.model.layers.15.input_layernorm.weight": "model.safetensors",
195
+ "language_model.model.layers.15.mlp.down_proj.biases": "model.safetensors",
196
+ "language_model.model.layers.15.mlp.down_proj.scales": "model.safetensors",
197
+ "language_model.model.layers.15.mlp.down_proj.weight": "model.safetensors",
198
+ "language_model.model.layers.15.mlp.gate_proj.biases": "model.safetensors",
199
+ "language_model.model.layers.15.mlp.gate_proj.scales": "model.safetensors",
200
+ "language_model.model.layers.15.mlp.gate_proj.weight": "model.safetensors",
201
+ "language_model.model.layers.15.mlp.up_proj.biases": "model.safetensors",
202
+ "language_model.model.layers.15.mlp.up_proj.scales": "model.safetensors",
203
+ "language_model.model.layers.15.mlp.up_proj.weight": "model.safetensors",
204
+ "language_model.model.layers.15.post_attention_layernorm.weight": "model.safetensors",
205
+ "language_model.model.layers.15.self_attn.k_proj.bias": "model.safetensors",
206
+ "language_model.model.layers.15.self_attn.k_proj.biases": "model.safetensors",
207
+ "language_model.model.layers.15.self_attn.k_proj.scales": "model.safetensors",
208
+ "language_model.model.layers.15.self_attn.k_proj.weight": "model.safetensors",
209
+ "language_model.model.layers.15.self_attn.o_proj.biases": "model.safetensors",
210
+ "language_model.model.layers.15.self_attn.o_proj.scales": "model.safetensors",
211
+ "language_model.model.layers.15.self_attn.o_proj.weight": "model.safetensors",
212
+ "language_model.model.layers.15.self_attn.q_proj.bias": "model.safetensors",
213
+ "language_model.model.layers.15.self_attn.q_proj.biases": "model.safetensors",
214
+ "language_model.model.layers.15.self_attn.q_proj.scales": "model.safetensors",
215
+ "language_model.model.layers.15.self_attn.q_proj.weight": "model.safetensors",
216
+ "language_model.model.layers.15.self_attn.v_proj.bias": "model.safetensors",
217
+ "language_model.model.layers.15.self_attn.v_proj.biases": "model.safetensors",
218
+ "language_model.model.layers.15.self_attn.v_proj.scales": "model.safetensors",
219
+ "language_model.model.layers.15.self_attn.v_proj.weight": "model.safetensors",
220
+ "language_model.model.layers.16.input_layernorm.weight": "model.safetensors",
221
+ "language_model.model.layers.16.mlp.down_proj.biases": "model.safetensors",
222
+ "language_model.model.layers.16.mlp.down_proj.scales": "model.safetensors",
223
+ "language_model.model.layers.16.mlp.down_proj.weight": "model.safetensors",
224
+ "language_model.model.layers.16.mlp.gate_proj.biases": "model.safetensors",
225
+ "language_model.model.layers.16.mlp.gate_proj.scales": "model.safetensors",
226
+ "language_model.model.layers.16.mlp.gate_proj.weight": "model.safetensors",
227
+ "language_model.model.layers.16.mlp.up_proj.biases": "model.safetensors",
228
+ "language_model.model.layers.16.mlp.up_proj.scales": "model.safetensors",
229
+ "language_model.model.layers.16.mlp.up_proj.weight": "model.safetensors",
230
+ "language_model.model.layers.16.post_attention_layernorm.weight": "model.safetensors",
231
+ "language_model.model.layers.16.self_attn.k_proj.bias": "model.safetensors",
232
+ "language_model.model.layers.16.self_attn.k_proj.biases": "model.safetensors",
233
+ "language_model.model.layers.16.self_attn.k_proj.scales": "model.safetensors",
234
+ "language_model.model.layers.16.self_attn.k_proj.weight": "model.safetensors",
235
+ "language_model.model.layers.16.self_attn.o_proj.biases": "model.safetensors",
236
+ "language_model.model.layers.16.self_attn.o_proj.scales": "model.safetensors",
237
+ "language_model.model.layers.16.self_attn.o_proj.weight": "model.safetensors",
238
+ "language_model.model.layers.16.self_attn.q_proj.bias": "model.safetensors",
239
+ "language_model.model.layers.16.self_attn.q_proj.biases": "model.safetensors",
240
+ "language_model.model.layers.16.self_attn.q_proj.scales": "model.safetensors",
241
+ "language_model.model.layers.16.self_attn.q_proj.weight": "model.safetensors",
242
+ "language_model.model.layers.16.self_attn.v_proj.bias": "model.safetensors",
243
+ "language_model.model.layers.16.self_attn.v_proj.biases": "model.safetensors",
244
+ "language_model.model.layers.16.self_attn.v_proj.scales": "model.safetensors",
245
+ "language_model.model.layers.16.self_attn.v_proj.weight": "model.safetensors",
246
+ "language_model.model.layers.17.input_layernorm.weight": "model.safetensors",
247
+ "language_model.model.layers.17.mlp.down_proj.biases": "model.safetensors",
248
+ "language_model.model.layers.17.mlp.down_proj.scales": "model.safetensors",
249
+ "language_model.model.layers.17.mlp.down_proj.weight": "model.safetensors",
250
+ "language_model.model.layers.17.mlp.gate_proj.biases": "model.safetensors",
251
+ "language_model.model.layers.17.mlp.gate_proj.scales": "model.safetensors",
252
+ "language_model.model.layers.17.mlp.gate_proj.weight": "model.safetensors",
253
+ "language_model.model.layers.17.mlp.up_proj.biases": "model.safetensors",
254
+ "language_model.model.layers.17.mlp.up_proj.scales": "model.safetensors",
255
+ "language_model.model.layers.17.mlp.up_proj.weight": "model.safetensors",
256
+ "language_model.model.layers.17.post_attention_layernorm.weight": "model.safetensors",
257
+ "language_model.model.layers.17.self_attn.k_proj.bias": "model.safetensors",
258
+ "language_model.model.layers.17.self_attn.k_proj.biases": "model.safetensors",
259
+ "language_model.model.layers.17.self_attn.k_proj.scales": "model.safetensors",
260
+ "language_model.model.layers.17.self_attn.k_proj.weight": "model.safetensors",
261
+ "language_model.model.layers.17.self_attn.o_proj.biases": "model.safetensors",
262
+ "language_model.model.layers.17.self_attn.o_proj.scales": "model.safetensors",
263
+ "language_model.model.layers.17.self_attn.o_proj.weight": "model.safetensors",
264
+ "language_model.model.layers.17.self_attn.q_proj.bias": "model.safetensors",
265
+ "language_model.model.layers.17.self_attn.q_proj.biases": "model.safetensors",
266
+ "language_model.model.layers.17.self_attn.q_proj.scales": "model.safetensors",
267
+ "language_model.model.layers.17.self_attn.q_proj.weight": "model.safetensors",
268
+ "language_model.model.layers.17.self_attn.v_proj.bias": "model.safetensors",
269
+ "language_model.model.layers.17.self_attn.v_proj.biases": "model.safetensors",
270
+ "language_model.model.layers.17.self_attn.v_proj.scales": "model.safetensors",
271
+ "language_model.model.layers.17.self_attn.v_proj.weight": "model.safetensors",
272
+ "language_model.model.layers.18.input_layernorm.weight": "model.safetensors",
273
+ "language_model.model.layers.18.mlp.down_proj.biases": "model.safetensors",
274
+ "language_model.model.layers.18.mlp.down_proj.scales": "model.safetensors",
275
+ "language_model.model.layers.18.mlp.down_proj.weight": "model.safetensors",
276
+ "language_model.model.layers.18.mlp.gate_proj.biases": "model.safetensors",
277
+ "language_model.model.layers.18.mlp.gate_proj.scales": "model.safetensors",
278
+ "language_model.model.layers.18.mlp.gate_proj.weight": "model.safetensors",
279
+ "language_model.model.layers.18.mlp.up_proj.biases": "model.safetensors",
280
+ "language_model.model.layers.18.mlp.up_proj.scales": "model.safetensors",
281
+ "language_model.model.layers.18.mlp.up_proj.weight": "model.safetensors",
282
+ "language_model.model.layers.18.post_attention_layernorm.weight": "model.safetensors",
283
+ "language_model.model.layers.18.self_attn.k_proj.bias": "model.safetensors",
284
+ "language_model.model.layers.18.self_attn.k_proj.biases": "model.safetensors",
285
+ "language_model.model.layers.18.self_attn.k_proj.scales": "model.safetensors",
286
+ "language_model.model.layers.18.self_attn.k_proj.weight": "model.safetensors",
287
+ "language_model.model.layers.18.self_attn.o_proj.biases": "model.safetensors",
288
+ "language_model.model.layers.18.self_attn.o_proj.scales": "model.safetensors",
289
+ "language_model.model.layers.18.self_attn.o_proj.weight": "model.safetensors",
290
+ "language_model.model.layers.18.self_attn.q_proj.bias": "model.safetensors",
291
+ "language_model.model.layers.18.self_attn.q_proj.biases": "model.safetensors",
292
+ "language_model.model.layers.18.self_attn.q_proj.scales": "model.safetensors",
293
+ "language_model.model.layers.18.self_attn.q_proj.weight": "model.safetensors",
294
+ "language_model.model.layers.18.self_attn.v_proj.bias": "model.safetensors",
295
+ "language_model.model.layers.18.self_attn.v_proj.biases": "model.safetensors",
296
+ "language_model.model.layers.18.self_attn.v_proj.scales": "model.safetensors",
297
+ "language_model.model.layers.18.self_attn.v_proj.weight": "model.safetensors",
298
+ "language_model.model.layers.19.input_layernorm.weight": "model.safetensors",
299
+ "language_model.model.layers.19.mlp.down_proj.biases": "model.safetensors",
300
+ "language_model.model.layers.19.mlp.down_proj.scales": "model.safetensors",
301
+ "language_model.model.layers.19.mlp.down_proj.weight": "model.safetensors",
302
+ "language_model.model.layers.19.mlp.gate_proj.biases": "model.safetensors",
303
+ "language_model.model.layers.19.mlp.gate_proj.scales": "model.safetensors",
304
+ "language_model.model.layers.19.mlp.gate_proj.weight": "model.safetensors",
305
+ "language_model.model.layers.19.mlp.up_proj.biases": "model.safetensors",
306
+ "language_model.model.layers.19.mlp.up_proj.scales": "model.safetensors",
307
+ "language_model.model.layers.19.mlp.up_proj.weight": "model.safetensors",
308
+ "language_model.model.layers.19.post_attention_layernorm.weight": "model.safetensors",
309
+ "language_model.model.layers.19.self_attn.k_proj.bias": "model.safetensors",
310
+ "language_model.model.layers.19.self_attn.k_proj.biases": "model.safetensors",
311
+ "language_model.model.layers.19.self_attn.k_proj.scales": "model.safetensors",
312
+ "language_model.model.layers.19.self_attn.k_proj.weight": "model.safetensors",
313
+ "language_model.model.layers.19.self_attn.o_proj.biases": "model.safetensors",
314
+ "language_model.model.layers.19.self_attn.o_proj.scales": "model.safetensors",
315
+ "language_model.model.layers.19.self_attn.o_proj.weight": "model.safetensors",
316
+ "language_model.model.layers.19.self_attn.q_proj.bias": "model.safetensors",
317
+ "language_model.model.layers.19.self_attn.q_proj.biases": "model.safetensors",
318
+ "language_model.model.layers.19.self_attn.q_proj.scales": "model.safetensors",
319
+ "language_model.model.layers.19.self_attn.q_proj.weight": "model.safetensors",
320
+ "language_model.model.layers.19.self_attn.v_proj.bias": "model.safetensors",
321
+ "language_model.model.layers.19.self_attn.v_proj.biases": "model.safetensors",
322
+ "language_model.model.layers.19.self_attn.v_proj.scales": "model.safetensors",
323
+ "language_model.model.layers.19.self_attn.v_proj.weight": "model.safetensors",
324
+ "language_model.model.layers.2.input_layernorm.weight": "model.safetensors",
325
+ "language_model.model.layers.2.mlp.down_proj.biases": "model.safetensors",
326
+ "language_model.model.layers.2.mlp.down_proj.scales": "model.safetensors",
327
+ "language_model.model.layers.2.mlp.down_proj.weight": "model.safetensors",
328
+ "language_model.model.layers.2.mlp.gate_proj.biases": "model.safetensors",
329
+ "language_model.model.layers.2.mlp.gate_proj.scales": "model.safetensors",
330
+ "language_model.model.layers.2.mlp.gate_proj.weight": "model.safetensors",
331
+ "language_model.model.layers.2.mlp.up_proj.biases": "model.safetensors",
332
+ "language_model.model.layers.2.mlp.up_proj.scales": "model.safetensors",
333
+ "language_model.model.layers.2.mlp.up_proj.weight": "model.safetensors",
334
+ "language_model.model.layers.2.post_attention_layernorm.weight": "model.safetensors",
335
+ "language_model.model.layers.2.self_attn.k_proj.bias": "model.safetensors",
336
+ "language_model.model.layers.2.self_attn.k_proj.biases": "model.safetensors",
337
+ "language_model.model.layers.2.self_attn.k_proj.scales": "model.safetensors",
338
+ "language_model.model.layers.2.self_attn.k_proj.weight": "model.safetensors",
339
+ "language_model.model.layers.2.self_attn.o_proj.biases": "model.safetensors",
340
+ "language_model.model.layers.2.self_attn.o_proj.scales": "model.safetensors",
341
+ "language_model.model.layers.2.self_attn.o_proj.weight": "model.safetensors",
342
+ "language_model.model.layers.2.self_attn.q_proj.bias": "model.safetensors",
343
+ "language_model.model.layers.2.self_attn.q_proj.biases": "model.safetensors",
344
+ "language_model.model.layers.2.self_attn.q_proj.scales": "model.safetensors",
345
+ "language_model.model.layers.2.self_attn.q_proj.weight": "model.safetensors",
346
+ "language_model.model.layers.2.self_attn.v_proj.bias": "model.safetensors",
347
+ "language_model.model.layers.2.self_attn.v_proj.biases": "model.safetensors",
348
+ "language_model.model.layers.2.self_attn.v_proj.scales": "model.safetensors",
349
+ "language_model.model.layers.2.self_attn.v_proj.weight": "model.safetensors",
350
+ "language_model.model.layers.20.input_layernorm.weight": "model.safetensors",
351
+ "language_model.model.layers.20.mlp.down_proj.biases": "model.safetensors",
352
+ "language_model.model.layers.20.mlp.down_proj.scales": "model.safetensors",
353
+ "language_model.model.layers.20.mlp.down_proj.weight": "model.safetensors",
354
+ "language_model.model.layers.20.mlp.gate_proj.biases": "model.safetensors",
355
+ "language_model.model.layers.20.mlp.gate_proj.scales": "model.safetensors",
356
+ "language_model.model.layers.20.mlp.gate_proj.weight": "model.safetensors",
357
+ "language_model.model.layers.20.mlp.up_proj.biases": "model.safetensors",
358
+ "language_model.model.layers.20.mlp.up_proj.scales": "model.safetensors",
359
+ "language_model.model.layers.20.mlp.up_proj.weight": "model.safetensors",
360
+ "language_model.model.layers.20.post_attention_layernorm.weight": "model.safetensors",
361
+ "language_model.model.layers.20.self_attn.k_proj.bias": "model.safetensors",
362
+ "language_model.model.layers.20.self_attn.k_proj.biases": "model.safetensors",
363
+ "language_model.model.layers.20.self_attn.k_proj.scales": "model.safetensors",
364
+ "language_model.model.layers.20.self_attn.k_proj.weight": "model.safetensors",
365
+ "language_model.model.layers.20.self_attn.o_proj.biases": "model.safetensors",
366
+ "language_model.model.layers.20.self_attn.o_proj.scales": "model.safetensors",
367
+ "language_model.model.layers.20.self_attn.o_proj.weight": "model.safetensors",
368
+ "language_model.model.layers.20.self_attn.q_proj.bias": "model.safetensors",
369
+ "language_model.model.layers.20.self_attn.q_proj.biases": "model.safetensors",
370
+ "language_model.model.layers.20.self_attn.q_proj.scales": "model.safetensors",
371
+ "language_model.model.layers.20.self_attn.q_proj.weight": "model.safetensors",
372
+ "language_model.model.layers.20.self_attn.v_proj.bias": "model.safetensors",
373
+ "language_model.model.layers.20.self_attn.v_proj.biases": "model.safetensors",
374
+ "language_model.model.layers.20.self_attn.v_proj.scales": "model.safetensors",
375
+ "language_model.model.layers.20.self_attn.v_proj.weight": "model.safetensors",
376
+ "language_model.model.layers.21.input_layernorm.weight": "model.safetensors",
377
+ "language_model.model.layers.21.mlp.down_proj.biases": "model.safetensors",
378
+ "language_model.model.layers.21.mlp.down_proj.scales": "model.safetensors",
379
+ "language_model.model.layers.21.mlp.down_proj.weight": "model.safetensors",
380
+ "language_model.model.layers.21.mlp.gate_proj.biases": "model.safetensors",
381
+ "language_model.model.layers.21.mlp.gate_proj.scales": "model.safetensors",
382
+ "language_model.model.layers.21.mlp.gate_proj.weight": "model.safetensors",
383
+ "language_model.model.layers.21.mlp.up_proj.biases": "model.safetensors",
384
+ "language_model.model.layers.21.mlp.up_proj.scales": "model.safetensors",
385
+ "language_model.model.layers.21.mlp.up_proj.weight": "model.safetensors",
386
+ "language_model.model.layers.21.post_attention_layernorm.weight": "model.safetensors",
387
+ "language_model.model.layers.21.self_attn.k_proj.bias": "model.safetensors",
388
+ "language_model.model.layers.21.self_attn.k_proj.biases": "model.safetensors",
389
+ "language_model.model.layers.21.self_attn.k_proj.scales": "model.safetensors",
390
+ "language_model.model.layers.21.self_attn.k_proj.weight": "model.safetensors",
391
+ "language_model.model.layers.21.self_attn.o_proj.biases": "model.safetensors",
392
+ "language_model.model.layers.21.self_attn.o_proj.scales": "model.safetensors",
393
+ "language_model.model.layers.21.self_attn.o_proj.weight": "model.safetensors",
394
+ "language_model.model.layers.21.self_attn.q_proj.bias": "model.safetensors",
395
+ "language_model.model.layers.21.self_attn.q_proj.biases": "model.safetensors",
396
+ "language_model.model.layers.21.self_attn.q_proj.scales": "model.safetensors",
397
+ "language_model.model.layers.21.self_attn.q_proj.weight": "model.safetensors",
398
+ "language_model.model.layers.21.self_attn.v_proj.bias": "model.safetensors",
399
+ "language_model.model.layers.21.self_attn.v_proj.biases": "model.safetensors",
400
+ "language_model.model.layers.21.self_attn.v_proj.scales": "model.safetensors",
401
+ "language_model.model.layers.21.self_attn.v_proj.weight": "model.safetensors",
402
+ "language_model.model.layers.22.input_layernorm.weight": "model.safetensors",
403
+ "language_model.model.layers.22.mlp.down_proj.biases": "model.safetensors",
404
+ "language_model.model.layers.22.mlp.down_proj.scales": "model.safetensors",
405
+ "language_model.model.layers.22.mlp.down_proj.weight": "model.safetensors",
406
+ "language_model.model.layers.22.mlp.gate_proj.biases": "model.safetensors",
407
+ "language_model.model.layers.22.mlp.gate_proj.scales": "model.safetensors",
408
+ "language_model.model.layers.22.mlp.gate_proj.weight": "model.safetensors",
409
+ "language_model.model.layers.22.mlp.up_proj.biases": "model.safetensors",
410
+ "language_model.model.layers.22.mlp.up_proj.scales": "model.safetensors",
411
+ "language_model.model.layers.22.mlp.up_proj.weight": "model.safetensors",
412
+ "language_model.model.layers.22.post_attention_layernorm.weight": "model.safetensors",
413
+ "language_model.model.layers.22.self_attn.k_proj.bias": "model.safetensors",
414
+ "language_model.model.layers.22.self_attn.k_proj.biases": "model.safetensors",
415
+ "language_model.model.layers.22.self_attn.k_proj.scales": "model.safetensors",
416
+ "language_model.model.layers.22.self_attn.k_proj.weight": "model.safetensors",
417
+ "language_model.model.layers.22.self_attn.o_proj.biases": "model.safetensors",
418
+ "language_model.model.layers.22.self_attn.o_proj.scales": "model.safetensors",
419
+ "language_model.model.layers.22.self_attn.o_proj.weight": "model.safetensors",
420
+ "language_model.model.layers.22.self_attn.q_proj.bias": "model.safetensors",
421
+ "language_model.model.layers.22.self_attn.q_proj.biases": "model.safetensors",
422
+ "language_model.model.layers.22.self_attn.q_proj.scales": "model.safetensors",
423
+ "language_model.model.layers.22.self_attn.q_proj.weight": "model.safetensors",
424
+ "language_model.model.layers.22.self_attn.v_proj.bias": "model.safetensors",
425
+ "language_model.model.layers.22.self_attn.v_proj.biases": "model.safetensors",
426
+ "language_model.model.layers.22.self_attn.v_proj.scales": "model.safetensors",
427
+ "language_model.model.layers.22.self_attn.v_proj.weight": "model.safetensors",
428
+ "language_model.model.layers.23.input_layernorm.weight": "model.safetensors",
429
+ "language_model.model.layers.23.mlp.down_proj.biases": "model.safetensors",
430
+ "language_model.model.layers.23.mlp.down_proj.scales": "model.safetensors",
431
+ "language_model.model.layers.23.mlp.down_proj.weight": "model.safetensors",
432
+ "language_model.model.layers.23.mlp.gate_proj.biases": "model.safetensors",
433
+ "language_model.model.layers.23.mlp.gate_proj.scales": "model.safetensors",
434
+ "language_model.model.layers.23.mlp.gate_proj.weight": "model.safetensors",
435
+ "language_model.model.layers.23.mlp.up_proj.biases": "model.safetensors",
436
+ "language_model.model.layers.23.mlp.up_proj.scales": "model.safetensors",
437
+ "language_model.model.layers.23.mlp.up_proj.weight": "model.safetensors",
438
+ "language_model.model.layers.23.post_attention_layernorm.weight": "model.safetensors",
439
+ "language_model.model.layers.23.self_attn.k_proj.bias": "model.safetensors",
440
+ "language_model.model.layers.23.self_attn.k_proj.biases": "model.safetensors",
441
+ "language_model.model.layers.23.self_attn.k_proj.scales": "model.safetensors",
442
+ "language_model.model.layers.23.self_attn.k_proj.weight": "model.safetensors",
443
+ "language_model.model.layers.23.self_attn.o_proj.biases": "model.safetensors",
444
+ "language_model.model.layers.23.self_attn.o_proj.scales": "model.safetensors",
445
+ "language_model.model.layers.23.self_attn.o_proj.weight": "model.safetensors",
446
+ "language_model.model.layers.23.self_attn.q_proj.bias": "model.safetensors",
447
+ "language_model.model.layers.23.self_attn.q_proj.biases": "model.safetensors",
448
+ "language_model.model.layers.23.self_attn.q_proj.scales": "model.safetensors",
449
+ "language_model.model.layers.23.self_attn.q_proj.weight": "model.safetensors",
450
+ "language_model.model.layers.23.self_attn.v_proj.bias": "model.safetensors",
451
+ "language_model.model.layers.23.self_attn.v_proj.biases": "model.safetensors",
452
+ "language_model.model.layers.23.self_attn.v_proj.scales": "model.safetensors",
453
+ "language_model.model.layers.23.self_attn.v_proj.weight": "model.safetensors",
454
+ "language_model.model.layers.24.input_layernorm.weight": "model.safetensors",
455
+ "language_model.model.layers.24.mlp.down_proj.biases": "model.safetensors",
456
+ "language_model.model.layers.24.mlp.down_proj.scales": "model.safetensors",
457
+ "language_model.model.layers.24.mlp.down_proj.weight": "model.safetensors",
458
+ "language_model.model.layers.24.mlp.gate_proj.biases": "model.safetensors",
459
+ "language_model.model.layers.24.mlp.gate_proj.scales": "model.safetensors",
460
+ "language_model.model.layers.24.mlp.gate_proj.weight": "model.safetensors",
461
+ "language_model.model.layers.24.mlp.up_proj.biases": "model.safetensors",
462
+ "language_model.model.layers.24.mlp.up_proj.scales": "model.safetensors",
463
+ "language_model.model.layers.24.mlp.up_proj.weight": "model.safetensors",
464
+ "language_model.model.layers.24.post_attention_layernorm.weight": "model.safetensors",
465
+ "language_model.model.layers.24.self_attn.k_proj.bias": "model.safetensors",
466
+ "language_model.model.layers.24.self_attn.k_proj.biases": "model.safetensors",
467
+ "language_model.model.layers.24.self_attn.k_proj.scales": "model.safetensors",
468
+ "language_model.model.layers.24.self_attn.k_proj.weight": "model.safetensors",
469
+ "language_model.model.layers.24.self_attn.o_proj.biases": "model.safetensors",
470
+ "language_model.model.layers.24.self_attn.o_proj.scales": "model.safetensors",
471
+ "language_model.model.layers.24.self_attn.o_proj.weight": "model.safetensors",
472
+ "language_model.model.layers.24.self_attn.q_proj.bias": "model.safetensors",
473
+ "language_model.model.layers.24.self_attn.q_proj.biases": "model.safetensors",
474
+ "language_model.model.layers.24.self_attn.q_proj.scales": "model.safetensors",
475
+ "language_model.model.layers.24.self_attn.q_proj.weight": "model.safetensors",
476
+ "language_model.model.layers.24.self_attn.v_proj.bias": "model.safetensors",
477
+ "language_model.model.layers.24.self_attn.v_proj.biases": "model.safetensors",
478
+ "language_model.model.layers.24.self_attn.v_proj.scales": "model.safetensors",
479
+ "language_model.model.layers.24.self_attn.v_proj.weight": "model.safetensors",
480
+ "language_model.model.layers.25.input_layernorm.weight": "model.safetensors",
481
+ "language_model.model.layers.25.mlp.down_proj.biases": "model.safetensors",
482
+ "language_model.model.layers.25.mlp.down_proj.scales": "model.safetensors",
483
+ "language_model.model.layers.25.mlp.down_proj.weight": "model.safetensors",
484
+ "language_model.model.layers.25.mlp.gate_proj.biases": "model.safetensors",
485
+ "language_model.model.layers.25.mlp.gate_proj.scales": "model.safetensors",
486
+ "language_model.model.layers.25.mlp.gate_proj.weight": "model.safetensors",
487
+ "language_model.model.layers.25.mlp.up_proj.biases": "model.safetensors",
488
+ "language_model.model.layers.25.mlp.up_proj.scales": "model.safetensors",
489
+ "language_model.model.layers.25.mlp.up_proj.weight": "model.safetensors",
490
+ "language_model.model.layers.25.post_attention_layernorm.weight": "model.safetensors",
491
+ "language_model.model.layers.25.self_attn.k_proj.bias": "model.safetensors",
492
+ "language_model.model.layers.25.self_attn.k_proj.biases": "model.safetensors",
493
+ "language_model.model.layers.25.self_attn.k_proj.scales": "model.safetensors",
494
+ "language_model.model.layers.25.self_attn.k_proj.weight": "model.safetensors",
495
+ "language_model.model.layers.25.self_attn.o_proj.biases": "model.safetensors",
496
+ "language_model.model.layers.25.self_attn.o_proj.scales": "model.safetensors",
497
+ "language_model.model.layers.25.self_attn.o_proj.weight": "model.safetensors",
498
+ "language_model.model.layers.25.self_attn.q_proj.bias": "model.safetensors",
499
+ "language_model.model.layers.25.self_attn.q_proj.biases": "model.safetensors",
500
+ "language_model.model.layers.25.self_attn.q_proj.scales": "model.safetensors",
501
+ "language_model.model.layers.25.self_attn.q_proj.weight": "model.safetensors",
502
+ "language_model.model.layers.25.self_attn.v_proj.bias": "model.safetensors",
503
+ "language_model.model.layers.25.self_attn.v_proj.biases": "model.safetensors",
504
+ "language_model.model.layers.25.self_attn.v_proj.scales": "model.safetensors",
505
+ "language_model.model.layers.25.self_attn.v_proj.weight": "model.safetensors",
506
+ "language_model.model.layers.26.input_layernorm.weight": "model.safetensors",
507
+ "language_model.model.layers.26.mlp.down_proj.biases": "model.safetensors",
508
+ "language_model.model.layers.26.mlp.down_proj.scales": "model.safetensors",
509
+ "language_model.model.layers.26.mlp.down_proj.weight": "model.safetensors",
510
+ "language_model.model.layers.26.mlp.gate_proj.biases": "model.safetensors",
511
+ "language_model.model.layers.26.mlp.gate_proj.scales": "model.safetensors",
512
+ "language_model.model.layers.26.mlp.gate_proj.weight": "model.safetensors",
513
+ "language_model.model.layers.26.mlp.up_proj.biases": "model.safetensors",
514
+ "language_model.model.layers.26.mlp.up_proj.scales": "model.safetensors",
515
+ "language_model.model.layers.26.mlp.up_proj.weight": "model.safetensors",
516
+ "language_model.model.layers.26.post_attention_layernorm.weight": "model.safetensors",
517
+ "language_model.model.layers.26.self_attn.k_proj.bias": "model.safetensors",
518
+ "language_model.model.layers.26.self_attn.k_proj.biases": "model.safetensors",
519
+ "language_model.model.layers.26.self_attn.k_proj.scales": "model.safetensors",
520
+ "language_model.model.layers.26.self_attn.k_proj.weight": "model.safetensors",
521
+ "language_model.model.layers.26.self_attn.o_proj.biases": "model.safetensors",
522
+ "language_model.model.layers.26.self_attn.o_proj.scales": "model.safetensors",
523
+ "language_model.model.layers.26.self_attn.o_proj.weight": "model.safetensors",
524
+ "language_model.model.layers.26.self_attn.q_proj.bias": "model.safetensors",
525
+ "language_model.model.layers.26.self_attn.q_proj.biases": "model.safetensors",
526
+ "language_model.model.layers.26.self_attn.q_proj.scales": "model.safetensors",
527
+ "language_model.model.layers.26.self_attn.q_proj.weight": "model.safetensors",
528
+ "language_model.model.layers.26.self_attn.v_proj.bias": "model.safetensors",
529
+ "language_model.model.layers.26.self_attn.v_proj.biases": "model.safetensors",
530
+ "language_model.model.layers.26.self_attn.v_proj.scales": "model.safetensors",
531
+ "language_model.model.layers.26.self_attn.v_proj.weight": "model.safetensors",
532
+ "language_model.model.layers.27.input_layernorm.weight": "model.safetensors",
533
+ "language_model.model.layers.27.mlp.down_proj.biases": "model.safetensors",
534
+ "language_model.model.layers.27.mlp.down_proj.scales": "model.safetensors",
535
+ "language_model.model.layers.27.mlp.down_proj.weight": "model.safetensors",
536
+ "language_model.model.layers.27.mlp.gate_proj.biases": "model.safetensors",
537
+ "language_model.model.layers.27.mlp.gate_proj.scales": "model.safetensors",
538
+ "language_model.model.layers.27.mlp.gate_proj.weight": "model.safetensors",
539
+ "language_model.model.layers.27.mlp.up_proj.biases": "model.safetensors",
540
+ "language_model.model.layers.27.mlp.up_proj.scales": "model.safetensors",
541
+ "language_model.model.layers.27.mlp.up_proj.weight": "model.safetensors",
542
+ "language_model.model.layers.27.post_attention_layernorm.weight": "model.safetensors",
543
+ "language_model.model.layers.27.self_attn.k_proj.bias": "model.safetensors",
544
+ "language_model.model.layers.27.self_attn.k_proj.biases": "model.safetensors",
545
+ "language_model.model.layers.27.self_attn.k_proj.scales": "model.safetensors",
546
+ "language_model.model.layers.27.self_attn.k_proj.weight": "model.safetensors",
547
+ "language_model.model.layers.27.self_attn.o_proj.biases": "model.safetensors",
548
+ "language_model.model.layers.27.self_attn.o_proj.scales": "model.safetensors",
549
+ "language_model.model.layers.27.self_attn.o_proj.weight": "model.safetensors",
550
+ "language_model.model.layers.27.self_attn.q_proj.bias": "model.safetensors",
551
+ "language_model.model.layers.27.self_attn.q_proj.biases": "model.safetensors",
552
+ "language_model.model.layers.27.self_attn.q_proj.scales": "model.safetensors",
553
+ "language_model.model.layers.27.self_attn.q_proj.weight": "model.safetensors",
554
+ "language_model.model.layers.27.self_attn.v_proj.bias": "model.safetensors",
555
+ "language_model.model.layers.27.self_attn.v_proj.biases": "model.safetensors",
556
+ "language_model.model.layers.27.self_attn.v_proj.scales": "model.safetensors",
557
+ "language_model.model.layers.27.self_attn.v_proj.weight": "model.safetensors",
558
+ "language_model.model.layers.3.input_layernorm.weight": "model.safetensors",
559
+ "language_model.model.layers.3.mlp.down_proj.biases": "model.safetensors",
560
+ "language_model.model.layers.3.mlp.down_proj.scales": "model.safetensors",
561
+ "language_model.model.layers.3.mlp.down_proj.weight": "model.safetensors",
562
+ "language_model.model.layers.3.mlp.gate_proj.biases": "model.safetensors",
563
+ "language_model.model.layers.3.mlp.gate_proj.scales": "model.safetensors",
564
+ "language_model.model.layers.3.mlp.gate_proj.weight": "model.safetensors",
565
+ "language_model.model.layers.3.mlp.up_proj.biases": "model.safetensors",
566
+ "language_model.model.layers.3.mlp.up_proj.scales": "model.safetensors",
567
+ "language_model.model.layers.3.mlp.up_proj.weight": "model.safetensors",
568
+ "language_model.model.layers.3.post_attention_layernorm.weight": "model.safetensors",
569
+ "language_model.model.layers.3.self_attn.k_proj.bias": "model.safetensors",
570
+ "language_model.model.layers.3.self_attn.k_proj.biases": "model.safetensors",
571
+ "language_model.model.layers.3.self_attn.k_proj.scales": "model.safetensors",
572
+ "language_model.model.layers.3.self_attn.k_proj.weight": "model.safetensors",
573
+ "language_model.model.layers.3.self_attn.o_proj.biases": "model.safetensors",
574
+ "language_model.model.layers.3.self_attn.o_proj.scales": "model.safetensors",
575
+ "language_model.model.layers.3.self_attn.o_proj.weight": "model.safetensors",
576
+ "language_model.model.layers.3.self_attn.q_proj.bias": "model.safetensors",
577
+ "language_model.model.layers.3.self_attn.q_proj.biases": "model.safetensors",
578
+ "language_model.model.layers.3.self_attn.q_proj.scales": "model.safetensors",
579
+ "language_model.model.layers.3.self_attn.q_proj.weight": "model.safetensors",
580
+ "language_model.model.layers.3.self_attn.v_proj.bias": "model.safetensors",
581
+ "language_model.model.layers.3.self_attn.v_proj.biases": "model.safetensors",
582
+ "language_model.model.layers.3.self_attn.v_proj.scales": "model.safetensors",
583
+ "language_model.model.layers.3.self_attn.v_proj.weight": "model.safetensors",
584
+ "language_model.model.layers.4.input_layernorm.weight": "model.safetensors",
585
+ "language_model.model.layers.4.mlp.down_proj.biases": "model.safetensors",
586
+ "language_model.model.layers.4.mlp.down_proj.scales": "model.safetensors",
587
+ "language_model.model.layers.4.mlp.down_proj.weight": "model.safetensors",
588
+ "language_model.model.layers.4.mlp.gate_proj.biases": "model.safetensors",
589
+ "language_model.model.layers.4.mlp.gate_proj.scales": "model.safetensors",
590
+ "language_model.model.layers.4.mlp.gate_proj.weight": "model.safetensors",
591
+ "language_model.model.layers.4.mlp.up_proj.biases": "model.safetensors",
592
+ "language_model.model.layers.4.mlp.up_proj.scales": "model.safetensors",
593
+ "language_model.model.layers.4.mlp.up_proj.weight": "model.safetensors",
594
+ "language_model.model.layers.4.post_attention_layernorm.weight": "model.safetensors",
595
+ "language_model.model.layers.4.self_attn.k_proj.bias": "model.safetensors",
596
+ "language_model.model.layers.4.self_attn.k_proj.biases": "model.safetensors",
597
+ "language_model.model.layers.4.self_attn.k_proj.scales": "model.safetensors",
598
+ "language_model.model.layers.4.self_attn.k_proj.weight": "model.safetensors",
599
+ "language_model.model.layers.4.self_attn.o_proj.biases": "model.safetensors",
600
+ "language_model.model.layers.4.self_attn.o_proj.scales": "model.safetensors",
601
+ "language_model.model.layers.4.self_attn.o_proj.weight": "model.safetensors",
602
+ "language_model.model.layers.4.self_attn.q_proj.bias": "model.safetensors",
603
+ "language_model.model.layers.4.self_attn.q_proj.biases": "model.safetensors",
604
+ "language_model.model.layers.4.self_attn.q_proj.scales": "model.safetensors",
605
+ "language_model.model.layers.4.self_attn.q_proj.weight": "model.safetensors",
606
+ "language_model.model.layers.4.self_attn.v_proj.bias": "model.safetensors",
607
+ "language_model.model.layers.4.self_attn.v_proj.biases": "model.safetensors",
608
+ "language_model.model.layers.4.self_attn.v_proj.scales": "model.safetensors",
609
+ "language_model.model.layers.4.self_attn.v_proj.weight": "model.safetensors",
610
+ "language_model.model.layers.5.input_layernorm.weight": "model.safetensors",
611
+ "language_model.model.layers.5.mlp.down_proj.biases": "model.safetensors",
612
+ "language_model.model.layers.5.mlp.down_proj.scales": "model.safetensors",
613
+ "language_model.model.layers.5.mlp.down_proj.weight": "model.safetensors",
614
+ "language_model.model.layers.5.mlp.gate_proj.biases": "model.safetensors",
615
+ "language_model.model.layers.5.mlp.gate_proj.scales": "model.safetensors",
616
+ "language_model.model.layers.5.mlp.gate_proj.weight": "model.safetensors",
617
+ "language_model.model.layers.5.mlp.up_proj.biases": "model.safetensors",
618
+ "language_model.model.layers.5.mlp.up_proj.scales": "model.safetensors",
619
+ "language_model.model.layers.5.mlp.up_proj.weight": "model.safetensors",
620
+ "language_model.model.layers.5.post_attention_layernorm.weight": "model.safetensors",
621
+ "language_model.model.layers.5.self_attn.k_proj.bias": "model.safetensors",
622
+ "language_model.model.layers.5.self_attn.k_proj.biases": "model.safetensors",
623
+ "language_model.model.layers.5.self_attn.k_proj.scales": "model.safetensors",
624
+ "language_model.model.layers.5.self_attn.k_proj.weight": "model.safetensors",
625
+ "language_model.model.layers.5.self_attn.o_proj.biases": "model.safetensors",
626
+ "language_model.model.layers.5.self_attn.o_proj.scales": "model.safetensors",
627
+ "language_model.model.layers.5.self_attn.o_proj.weight": "model.safetensors",
628
+ "language_model.model.layers.5.self_attn.q_proj.bias": "model.safetensors",
629
+ "language_model.model.layers.5.self_attn.q_proj.biases": "model.safetensors",
630
+ "language_model.model.layers.5.self_attn.q_proj.scales": "model.safetensors",
631
+ "language_model.model.layers.5.self_attn.q_proj.weight": "model.safetensors",
632
+ "language_model.model.layers.5.self_attn.v_proj.bias": "model.safetensors",
633
+ "language_model.model.layers.5.self_attn.v_proj.biases": "model.safetensors",
634
+ "language_model.model.layers.5.self_attn.v_proj.scales": "model.safetensors",
635
+ "language_model.model.layers.5.self_attn.v_proj.weight": "model.safetensors",
636
+ "language_model.model.layers.6.input_layernorm.weight": "model.safetensors",
637
+ "language_model.model.layers.6.mlp.down_proj.biases": "model.safetensors",
638
+ "language_model.model.layers.6.mlp.down_proj.scales": "model.safetensors",
639
+ "language_model.model.layers.6.mlp.down_proj.weight": "model.safetensors",
640
+ "language_model.model.layers.6.mlp.gate_proj.biases": "model.safetensors",
641
+ "language_model.model.layers.6.mlp.gate_proj.scales": "model.safetensors",
642
+ "language_model.model.layers.6.mlp.gate_proj.weight": "model.safetensors",
643
+ "language_model.model.layers.6.mlp.up_proj.biases": "model.safetensors",
644
+ "language_model.model.layers.6.mlp.up_proj.scales": "model.safetensors",
645
+ "language_model.model.layers.6.mlp.up_proj.weight": "model.safetensors",
646
+ "language_model.model.layers.6.post_attention_layernorm.weight": "model.safetensors",
647
+ "language_model.model.layers.6.self_attn.k_proj.bias": "model.safetensors",
648
+ "language_model.model.layers.6.self_attn.k_proj.biases": "model.safetensors",
649
+ "language_model.model.layers.6.self_attn.k_proj.scales": "model.safetensors",
650
+ "language_model.model.layers.6.self_attn.k_proj.weight": "model.safetensors",
651
+ "language_model.model.layers.6.self_attn.o_proj.biases": "model.safetensors",
652
+ "language_model.model.layers.6.self_attn.o_proj.scales": "model.safetensors",
653
+ "language_model.model.layers.6.self_attn.o_proj.weight": "model.safetensors",
654
+ "language_model.model.layers.6.self_attn.q_proj.bias": "model.safetensors",
655
+ "language_model.model.layers.6.self_attn.q_proj.biases": "model.safetensors",
656
+ "language_model.model.layers.6.self_attn.q_proj.scales": "model.safetensors",
657
+ "language_model.model.layers.6.self_attn.q_proj.weight": "model.safetensors",
658
+ "language_model.model.layers.6.self_attn.v_proj.bias": "model.safetensors",
659
+ "language_model.model.layers.6.self_attn.v_proj.biases": "model.safetensors",
660
+ "language_model.model.layers.6.self_attn.v_proj.scales": "model.safetensors",
661
+ "language_model.model.layers.6.self_attn.v_proj.weight": "model.safetensors",
662
+ "language_model.model.layers.7.input_layernorm.weight": "model.safetensors",
663
+ "language_model.model.layers.7.mlp.down_proj.biases": "model.safetensors",
664
+ "language_model.model.layers.7.mlp.down_proj.scales": "model.safetensors",
665
+ "language_model.model.layers.7.mlp.down_proj.weight": "model.safetensors",
666
+ "language_model.model.layers.7.mlp.gate_proj.biases": "model.safetensors",
667
+ "language_model.model.layers.7.mlp.gate_proj.scales": "model.safetensors",
668
+ "language_model.model.layers.7.mlp.gate_proj.weight": "model.safetensors",
669
+ "language_model.model.layers.7.mlp.up_proj.biases": "model.safetensors",
670
+ "language_model.model.layers.7.mlp.up_proj.scales": "model.safetensors",
671
+ "language_model.model.layers.7.mlp.up_proj.weight": "model.safetensors",
672
+ "language_model.model.layers.7.post_attention_layernorm.weight": "model.safetensors",
673
+ "language_model.model.layers.7.self_attn.k_proj.bias": "model.safetensors",
674
+ "language_model.model.layers.7.self_attn.k_proj.biases": "model.safetensors",
675
+ "language_model.model.layers.7.self_attn.k_proj.scales": "model.safetensors",
676
+ "language_model.model.layers.7.self_attn.k_proj.weight": "model.safetensors",
677
+ "language_model.model.layers.7.self_attn.o_proj.biases": "model.safetensors",
678
+ "language_model.model.layers.7.self_attn.o_proj.scales": "model.safetensors",
679
+ "language_model.model.layers.7.self_attn.o_proj.weight": "model.safetensors",
680
+ "language_model.model.layers.7.self_attn.q_proj.bias": "model.safetensors",
681
+ "language_model.model.layers.7.self_attn.q_proj.biases": "model.safetensors",
682
+ "language_model.model.layers.7.self_attn.q_proj.scales": "model.safetensors",
683
+ "language_model.model.layers.7.self_attn.q_proj.weight": "model.safetensors",
684
+ "language_model.model.layers.7.self_attn.v_proj.bias": "model.safetensors",
685
+ "language_model.model.layers.7.self_attn.v_proj.biases": "model.safetensors",
686
+ "language_model.model.layers.7.self_attn.v_proj.scales": "model.safetensors",
687
+ "language_model.model.layers.7.self_attn.v_proj.weight": "model.safetensors",
688
+ "language_model.model.layers.8.input_layernorm.weight": "model.safetensors",
689
+ "language_model.model.layers.8.mlp.down_proj.biases": "model.safetensors",
690
+ "language_model.model.layers.8.mlp.down_proj.scales": "model.safetensors",
691
+ "language_model.model.layers.8.mlp.down_proj.weight": "model.safetensors",
692
+ "language_model.model.layers.8.mlp.gate_proj.biases": "model.safetensors",
693
+ "language_model.model.layers.8.mlp.gate_proj.scales": "model.safetensors",
694
+ "language_model.model.layers.8.mlp.gate_proj.weight": "model.safetensors",
695
+ "language_model.model.layers.8.mlp.up_proj.biases": "model.safetensors",
696
+ "language_model.model.layers.8.mlp.up_proj.scales": "model.safetensors",
697
+ "language_model.model.layers.8.mlp.up_proj.weight": "model.safetensors",
698
+ "language_model.model.layers.8.post_attention_layernorm.weight": "model.safetensors",
699
+ "language_model.model.layers.8.self_attn.k_proj.bias": "model.safetensors",
700
+ "language_model.model.layers.8.self_attn.k_proj.biases": "model.safetensors",
701
+ "language_model.model.layers.8.self_attn.k_proj.scales": "model.safetensors",
702
+ "language_model.model.layers.8.self_attn.k_proj.weight": "model.safetensors",
703
+ "language_model.model.layers.8.self_attn.o_proj.biases": "model.safetensors",
704
+ "language_model.model.layers.8.self_attn.o_proj.scales": "model.safetensors",
705
+ "language_model.model.layers.8.self_attn.o_proj.weight": "model.safetensors",
706
+ "language_model.model.layers.8.self_attn.q_proj.bias": "model.safetensors",
707
+ "language_model.model.layers.8.self_attn.q_proj.biases": "model.safetensors",
708
+ "language_model.model.layers.8.self_attn.q_proj.scales": "model.safetensors",
709
+ "language_model.model.layers.8.self_attn.q_proj.weight": "model.safetensors",
710
+ "language_model.model.layers.8.self_attn.v_proj.bias": "model.safetensors",
711
+ "language_model.model.layers.8.self_attn.v_proj.biases": "model.safetensors",
712
+ "language_model.model.layers.8.self_attn.v_proj.scales": "model.safetensors",
713
+ "language_model.model.layers.8.self_attn.v_proj.weight": "model.safetensors",
714
+ "language_model.model.layers.9.input_layernorm.weight": "model.safetensors",
715
+ "language_model.model.layers.9.mlp.down_proj.biases": "model.safetensors",
716
+ "language_model.model.layers.9.mlp.down_proj.scales": "model.safetensors",
717
+ "language_model.model.layers.9.mlp.down_proj.weight": "model.safetensors",
718
+ "language_model.model.layers.9.mlp.gate_proj.biases": "model.safetensors",
719
+ "language_model.model.layers.9.mlp.gate_proj.scales": "model.safetensors",
720
+ "language_model.model.layers.9.mlp.gate_proj.weight": "model.safetensors",
721
+ "language_model.model.layers.9.mlp.up_proj.biases": "model.safetensors",
722
+ "language_model.model.layers.9.mlp.up_proj.scales": "model.safetensors",
723
+ "language_model.model.layers.9.mlp.up_proj.weight": "model.safetensors",
724
+ "language_model.model.layers.9.post_attention_layernorm.weight": "model.safetensors",
725
+ "language_model.model.layers.9.self_attn.k_proj.bias": "model.safetensors",
726
+ "language_model.model.layers.9.self_attn.k_proj.biases": "model.safetensors",
727
+ "language_model.model.layers.9.self_attn.k_proj.scales": "model.safetensors",
728
+ "language_model.model.layers.9.self_attn.k_proj.weight": "model.safetensors",
729
+ "language_model.model.layers.9.self_attn.o_proj.biases": "model.safetensors",
730
+ "language_model.model.layers.9.self_attn.o_proj.scales": "model.safetensors",
731
+ "language_model.model.layers.9.self_attn.o_proj.weight": "model.safetensors",
732
+ "language_model.model.layers.9.self_attn.q_proj.bias": "model.safetensors",
733
+ "language_model.model.layers.9.self_attn.q_proj.biases": "model.safetensors",
734
+ "language_model.model.layers.9.self_attn.q_proj.scales": "model.safetensors",
735
+ "language_model.model.layers.9.self_attn.q_proj.weight": "model.safetensors",
736
+ "language_model.model.layers.9.self_attn.v_proj.bias": "model.safetensors",
737
+ "language_model.model.layers.9.self_attn.v_proj.biases": "model.safetensors",
738
+ "language_model.model.layers.9.self_attn.v_proj.scales": "model.safetensors",
739
+ "language_model.model.layers.9.self_attn.v_proj.weight": "model.safetensors",
740
+ "language_model.model.norm.weight": "model.safetensors",
741
+ "multi_modal_projector.linear_0.bias": "model.safetensors",
742
+ "multi_modal_projector.linear_0.biases": "model.safetensors",
743
+ "multi_modal_projector.linear_0.scales": "model.safetensors",
744
+ "multi_modal_projector.linear_0.weight": "model.safetensors",
745
+ "multi_modal_projector.linear_2.bias": "model.safetensors",
746
+ "multi_modal_projector.linear_2.biases": "model.safetensors",
747
+ "multi_modal_projector.linear_2.scales": "model.safetensors",
748
+ "multi_modal_projector.linear_2.weight": "model.safetensors"
749
+ }
750
+ }
preprocessor_config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "crop_size": {
3
+ "height": 1024,
4
+ "width": 1024
5
+ },
6
+ "do_center_crop": true,
7
+ "do_convert_rgb": true,
8
+ "do_normalize": true,
9
+ "do_rescale": true,
10
+ "do_resize": true,
11
+ "image_mean": [
12
+ 0.0,
13
+ 0.0,
14
+ 0.0
15
+ ],
16
+ "image_processor_type": "CLIPImageProcessor",
17
+ "image_std": [
18
+ 1.0,
19
+ 1.0,
20
+ 1.0
21
+ ],
22
+ "processor_class": "LlavaProcessor",
23
+ "resample": 3,
24
+ "rescale_factor": 0.00392156862745098,
25
+ "size": {
26
+ "shortest_edge": 1024
27
+ }
28
+ }
processor_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "image_token": "<image>",
3
+ "num_additional_image_tokens": 0,
4
+ "patch_size": 64,
5
+ "processor_class": "LlavaProcessor",
6
+ "vision_feature_select_strategy": null
7
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|object_ref_start|>",
6
+ "<|object_ref_end|>",
7
+ "<|box_start|>",
8
+ "<|box_end|>",
9
+ "<|quad_start|>",
10
+ "<|quad_end|>",
11
+ "<|vision_start|>",
12
+ "<|vision_end|>",
13
+ "<|vision_pad|>",
14
+ "<|image_pad|>",
15
+ "<|video_pad|>"
16
+ ],
17
+ "eos_token": {
18
+ "content": "<|im_end|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ "pad_token": {
25
+ "content": "<|endoftext|>",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ }
31
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:80bf0b2985eb0adea043055e425b9230bd3e3b246069ee66db3f98847aba1c00
3
+ size 11416914
tokenizer_config.json ADDED
@@ -0,0 +1,219 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "151643": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "151644": {
14
+ "content": "<|im_start|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "151645": {
22
+ "content": "<|im_end|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "151646": {
30
+ "content": "<|object_ref_start|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "151647": {
38
+ "content": "<|object_ref_end|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "151648": {
46
+ "content": "<|box_start|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "151649": {
54
+ "content": "<|box_end|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "151650": {
62
+ "content": "<|quad_start|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "151651": {
70
+ "content": "<|quad_end|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "151652": {
78
+ "content": "<|vision_start|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "151653": {
86
+ "content": "<|vision_end|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "151654": {
94
+ "content": "<|vision_pad|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "151655": {
102
+ "content": "<|image_pad|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "151656": {
110
+ "content": "<|video_pad|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "151657": {
118
+ "content": "<tool_call>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": false
124
+ },
125
+ "151658": {
126
+ "content": "</tool_call>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "151659": {
134
+ "content": "<|fim_prefix|>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "151660": {
142
+ "content": "<|fim_middle|>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "151661": {
150
+ "content": "<|fim_suffix|>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "151662": {
158
+ "content": "<|fim_pad|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "151663": {
166
+ "content": "<|repo_name|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": false
172
+ },
173
+ "151664": {
174
+ "content": "<|file_sep|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": false
180
+ },
181
+ "151665": {
182
+ "content": "<image>",
183
+ "lstrip": false,
184
+ "normalized": false,
185
+ "rstrip": false,
186
+ "single_word": false,
187
+ "special": true
188
+ }
189
+ },
190
+ "additional_special_tokens": [
191
+ "<|im_start|>",
192
+ "<|im_end|>",
193
+ "<|object_ref_start|>",
194
+ "<|object_ref_end|>",
195
+ "<|box_start|>",
196
+ "<|box_end|>",
197
+ "<|quad_start|>",
198
+ "<|quad_end|>",
199
+ "<|vision_start|>",
200
+ "<|vision_end|>",
201
+ "<|vision_pad|>",
202
+ "<|image_pad|>",
203
+ "<|video_pad|>"
204
+ ],
205
+ "bos_token": null,
206
+ "chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0]['role'] == 'system' %}\n {{- messages[0]['content'] }}\n {%- else %}\n {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n {%- endif %}\n {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0]['role'] == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n {%- else %}\n {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role }}\n {%- if message.content %}\n {{- '\\n' + message.content }}\n {%- endif %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '\\n<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- message.content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
207
+ "clean_up_tokenization_spaces": false,
208
+ "eos_token": "<|im_end|>",
209
+ "errors": "replace",
210
+ "extra_special_tokens": {},
211
+ "model_max_length": 8192,
212
+ "only_llm": true,
213
+ "pad_token": "<|endoftext|>",
214
+ "padding_side": "right",
215
+ "processor_class": "LlavaProcessor",
216
+ "split_special_tokens": false,
217
+ "tokenizer_class": "Qwen2Tokenizer",
218
+ "unk_token": null
219
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff