junukwon-fai ZAHNGYUXUAN commited on
Commit
30910b5
·
verified ·
0 Parent(s):

Duplicate from THUDM/GLM-4.1V-9B-Thinking

Browse files

Co-authored-by: zR <[email protected]>

.gitattributes ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ *.7z filter=lfs diff=lfs merge=lfs -text
2
+ *.arrow filter=lfs diff=lfs merge=lfs -text
3
+ *.bin filter=lfs diff=lfs merge=lfs -text
4
+ *.bz2 filter=lfs diff=lfs merge=lfs -text
5
+ *.ckpt filter=lfs diff=lfs merge=lfs -text
6
+ *.ftz filter=lfs diff=lfs merge=lfs -text
7
+ *.gz filter=lfs diff=lfs merge=lfs -text
8
+ *.h5 filter=lfs diff=lfs merge=lfs -text
9
+ *.joblib filter=lfs diff=lfs merge=lfs -text
10
+ *.lfs.* filter=lfs diff=lfs merge=lfs -text
11
+ *.mlmodel filter=lfs diff=lfs merge=lfs -text
12
+ *.model filter=lfs diff=lfs merge=lfs -text
13
+ *.msgpack filter=lfs diff=lfs merge=lfs -text
14
+ *.npy filter=lfs diff=lfs merge=lfs -text
15
+ *.npz filter=lfs diff=lfs merge=lfs -text
16
+ *.onnx filter=lfs diff=lfs merge=lfs -text
17
+ *.ot filter=lfs diff=lfs merge=lfs -text
18
+ *.parquet filter=lfs diff=lfs merge=lfs -text
19
+ *.pb filter=lfs diff=lfs merge=lfs -text
20
+ *.pickle filter=lfs diff=lfs merge=lfs -text
21
+ *.pkl filter=lfs diff=lfs merge=lfs -text
22
+ *.pt filter=lfs diff=lfs merge=lfs -text
23
+ *.pth filter=lfs diff=lfs merge=lfs -text
24
+ *.rar filter=lfs diff=lfs merge=lfs -text
25
+ *.safetensors filter=lfs diff=lfs merge=lfs -text
26
+ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
27
+ *.tar.* filter=lfs diff=lfs merge=lfs -text
28
+ *.tar filter=lfs diff=lfs merge=lfs -text
29
+ *.tflite filter=lfs diff=lfs merge=lfs -text
30
+ *.tgz filter=lfs diff=lfs merge=lfs -text
31
+ *.wasm filter=lfs diff=lfs merge=lfs -text
32
+ *.xz 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
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,112 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ language:
4
+ - en
5
+ - zh
6
+ base_model:
7
+ - THUDM/GLM-4-9B-0414
8
+ pipeline_tag: image-text-to-text
9
+ library_name: transformers
10
+ tags:
11
+ - reasoning
12
+ ---
13
+
14
+ # GLM-4.1V-9B-Thinking
15
+
16
+ <div align="center">
17
+ <img src=https://raw.githubusercontent.com/THUDM/GLM-4.1V-Thinking/99c5eb6563236f0ff43605d91d107544da9863b2/resources/logo.svg width="40%"/>
18
+ </div>
19
+ <p align="center">
20
+ 📖 View the GLM-4.1V-9B-Thinking <a href="https://arxiv.org/abs/2507.01006" target="_blank">paper</a>.
21
+ <br>
22
+ 💡 Try the <a href="https://huggingface.co/spaces/THUDM/GLM-4.1V-9B-Thinking-Demo" target="_blank">Hugging Face</a> or <a href="https://modelscope.cn/studios/ZhipuAI/GLM-4.1V-9B-Thinking-Demo" target="_blank">ModelScope</a> online demo for GLM-4.1V-9B-Thinking.
23
+ <br>
24
+ 📍 Using GLM-4.1V-9B-Thinking API at <a href="https://www.bigmodel.cn/dev/api/visual-reasoning-model/GLM-4.1V-Thinking">Zhipu Foundation Model Open Platform</a>
25
+ </p>
26
+
27
+
28
+ ## Model Introduction
29
+
30
+ Vision-Language Models (VLMs) have become foundational components of intelligent systems. As real-world AI tasks grow
31
+ increasingly complex, VLMs must evolve beyond basic multimodal perception to enhance their reasoning capabilities in
32
+ complex tasks. This involves improving accuracy, comprehensiveness, and intelligence, enabling applications such as
33
+ complex problem solving, long-context understanding, and multimodal agents.
34
+
35
+ Based on the [GLM-4-9B-0414](https://github.com/THUDM/GLM-4) foundation model, we present the new open-source VLM model
36
+ **GLM-4.1V-9B-Thinking**, designed to explore the upper limits of reasoning in vision-language models. By introducing
37
+ a "thinking paradigm" and leveraging reinforcement learning, the model significantly enhances its capabilities. It
38
+ achieves state-of-the-art performance among 10B-parameter VLMs, matching or even surpassing the 72B-parameter
39
+ Qwen-2.5-VL-72B on 18 benchmark tasks. We are also open-sourcing the base model GLM-4.1V-9B-Base to
40
+ support further research into the boundaries of VLM capabilities.
41
+
42
+ ![rl](https://raw.githubusercontent.com/THUDM/GLM-4.1V-Thinking/refs/heads/main/resources/rl.jpeg)
43
+
44
+ Compared to the previous generation models CogVLM2 and the GLM-4V series, **GLM-4.1V-Thinking** offers the
45
+ following improvements:
46
+
47
+ 1. The first reasoning-focused model in the series, achieving world-leading performance not only in mathematics but also
48
+ across various sub-domains.
49
+ 2. Supports **64k** context length.
50
+ 3. Handles **arbitrary aspect ratios** and up to **4K** image resolution.
51
+ 4. Provides an open-source version supporting both **Chinese and English bilingual** usage.
52
+
53
+ ## Benchmark Performance
54
+
55
+ By incorporating the Chain-of-Thought reasoning paradigm, GLM-4.1V-9B-Thinking significantly improves answer accuracy,
56
+ richness, and interpretability. It comprehensively surpasses traditional non-reasoning visual models.
57
+ Out of 28 benchmark tasks, it achieved the best performance among 10B-level models on 23 tasks,
58
+ and even outperformed the 72B-parameter Qwen-2.5-VL-72B on 18 tasks.
59
+
60
+ ![bench](https://raw.githubusercontent.com/THUDM/GLM-4.1V-Thinking/refs/heads/main/resources/bench.jpeg)
61
+
62
+ ## Quick Inference
63
+
64
+ This is a simple example of running single-image inference using the `transformers` library.
65
+ First, install the `transformers` library from source:
66
+
67
+ ```
68
+ pip install git+https://github.com/huggingface/transformers.git
69
+ ```
70
+
71
+ Then, run the following code:
72
+
73
+ ```python
74
+ from transformers import AutoProcessor, Glm4vForConditionalGeneration
75
+ import torch
76
+
77
+ MODEL_PATH = "THUDM/GLM-4.1V-9B-Thinking"
78
+ messages = [
79
+ {
80
+ "role": "user",
81
+ "content": [
82
+ {
83
+ "type": "image",
84
+ "url": "https://upload.wikimedia.org/wikipedia/commons/f/fa/Grayscale_8bits_palette_sample_image.png"
85
+ },
86
+ {
87
+ "type": "text",
88
+ "text": "describe this image"
89
+ }
90
+ ],
91
+ }
92
+ ]
93
+ processor = AutoProcessor.from_pretrained(MODEL_PATH, use_fast=True)
94
+ model = Glm4vForConditionalGeneration.from_pretrained(
95
+ pretrained_model_name_or_path=MODEL_PATH,
96
+ torch_dtype=torch.bfloat16,
97
+ device_map="auto",
98
+ )
99
+ inputs = processor.apply_chat_template(
100
+ messages,
101
+ tokenize=True,
102
+ add_generation_prompt=True,
103
+ return_dict=True,
104
+ return_tensors="pt"
105
+ ).to(model.device)
106
+ generated_ids = model.generate(**inputs, max_new_tokens=8192)
107
+ output_text = processor.decode(generated_ids[0][inputs["input_ids"].shape[1]:], skip_special_tokens=False)
108
+ print(output_text)
109
+ ```
110
+
111
+ For video reasoning, web demo deployment, and more code, please check
112
+ our [GitHub](https://github.com/THUDM/GLM-4.1V-Thinking).
chat_template.jinja ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [gMASK]<sop>
2
+ {%- for msg in messages %}
3
+ {%- if msg.role == 'system' %}
4
+ <|system|>
5
+ {{ msg.content }}
6
+ {%- elif msg.role == 'user' %}
7
+ <|user|>{{ '\n' }}
8
+
9
+ {%- if msg.content is string %}
10
+ {{ msg.content }}
11
+ {%- else %}
12
+ {%- for item in msg.content %}
13
+ {%- if item.type == 'video' or 'video' in item %}
14
+ <|begin_of_video|><|video|><|end_of_video|>
15
+ {%- elif item.type == 'image' or 'image' in item %}
16
+ <|begin_of_image|><|image|><|end_of_image|>
17
+ {%- elif item.type == 'text' %}
18
+ {{ item.text }}
19
+ {%- endif %}
20
+ {%- endfor %}
21
+ {%- endif %}
22
+ {%- elif msg.role == 'assistant' %}
23
+ {%- if msg.metadata %}
24
+ <|assistant|>{{ msg.metadata }}
25
+ {{ msg.content }}
26
+ {%- else %}
27
+ <|assistant|>
28
+ {{ msg.content }}
29
+ {%- endif %}
30
+ {%- endif %}
31
+ {%- endfor %}
32
+ {% if add_generation_prompt %}<|assistant|>
33
+ {% endif %}
config.json ADDED
@@ -0,0 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Glm4vForConditionalGeneration"
4
+ ],
5
+ "model_type": "glm4v",
6
+ "attention_bias": true,
7
+ "attention_dropout": 0.0,
8
+ "pad_token_id": 151329,
9
+ "eos_token_id": [
10
+ 151329,
11
+ 151336,
12
+ 151338,
13
+ 151348
14
+ ],
15
+ "image_start_token_id": 151339,
16
+ "image_end_token_id": 151340,
17
+ "video_start_token_id": 151341,
18
+ "video_end_token_id": 151342,
19
+ "image_token_id": 151343,
20
+ "video_token_id": 151344,
21
+ "hidden_act": "silu",
22
+ "hidden_size": 4096,
23
+ "initializer_range": 0.02,
24
+ "intermediate_size": 13696,
25
+ "max_position_embeddings": 65536,
26
+ "num_attention_heads": 32,
27
+ "num_hidden_layers": 40,
28
+ "num_key_value_heads": 2,
29
+ "rms_norm_eps": 1e-05,
30
+ "rope_theta": 10000.0,
31
+ "tie_word_embeddings": false,
32
+ "torch_dtype": "bfloat16",
33
+ "transformers_version": "4.53.0dev",
34
+ "use_cache": true,
35
+ "vocab_size": 151552,
36
+ "partial_rotary_factor": 0.5,
37
+ "vision_config": {
38
+ "hidden_size": 1536,
39
+ "depth": 24,
40
+ "num_heads": 12,
41
+ "attention_bias": false,
42
+ "intermediate_size": 13696,
43
+ "hidden_act": "silu",
44
+ "hidden_dropout_prob": 0.0,
45
+ "initializer_range": 0.02,
46
+ "image_size": 336,
47
+ "patch_size": 14,
48
+ "out_hidden_size": 4096,
49
+ "rms_norm_eps": 1e-05,
50
+ "spatial_merge_size": 2,
51
+ "temporal_patch_size": 2
52
+ },
53
+ "rope_scaling": {
54
+ "type": "default",
55
+ "mrope_section": [
56
+ 8,
57
+ 12,
58
+ 12
59
+ ]
60
+ }
61
+ }
model-00001-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:56708b3541e1f69c9843ae19eaa23720c5cee9f3d0c9ed101c3b9b43b40974a1
3
+ size 5303216560
model-00002-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7c353db4141fdd9a0c6b990d50040a28812bb56dc91c42154abc5a4ee81fe698
3
+ size 5303216696
model-00003-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f3fab833fe4cad6cbce924908e1a58320217295417bbf87aa810fff6e4b634a4
3
+ size 5303216696
model-00004-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b3c7723fac7de60f2b67e4f84f2d8648d7431ff32c95c630dcc17790091005eb
3
+ size 4675994152
model.safetensors.index.json ADDED
@@ -0,0 +1,711 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 20585554944
4
+ },
5
+ "weight_map": {
6
+ "model.language_model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
7
+ "model.language_model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
8
+ "model.language_model.layers.0.post_self_attn_layernorm.weight": "model-00001-of-00004.safetensors",
9
+ "model.language_model.layers.0.post_mlp_layernorm.weight": "model-00001-of-00004.safetensors",
10
+ "model.language_model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
11
+ "model.language_model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
12
+ "model.language_model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
13
+ "model.language_model.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
14
+ "model.language_model.layers.0.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
15
+ "model.language_model.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
16
+ "model.language_model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
17
+ "model.language_model.layers.0.mlp.gate_up_proj.weight": "model-00001-of-00004.safetensors",
18
+ "model.language_model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
19
+ "model.language_model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
20
+ "model.language_model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
21
+ "model.language_model.layers.1.post_self_attn_layernorm.weight": "model-00001-of-00004.safetensors",
22
+ "model.language_model.layers.1.post_mlp_layernorm.weight": "model-00001-of-00004.safetensors",
23
+ "model.language_model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
24
+ "model.language_model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
25
+ "model.language_model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
26
+ "model.language_model.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
27
+ "model.language_model.layers.1.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
28
+ "model.language_model.layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
29
+ "model.language_model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
30
+ "model.language_model.layers.1.mlp.gate_up_proj.weight": "model-00001-of-00004.safetensors",
31
+ "model.language_model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
32
+ "model.language_model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
33
+ "model.language_model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
34
+ "model.language_model.layers.2.post_self_attn_layernorm.weight": "model-00001-of-00004.safetensors",
35
+ "model.language_model.layers.2.post_mlp_layernorm.weight": "model-00001-of-00004.safetensors",
36
+ "model.language_model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
37
+ "model.language_model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
38
+ "model.language_model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
39
+ "model.language_model.layers.2.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
40
+ "model.language_model.layers.2.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
41
+ "model.language_model.layers.2.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
42
+ "model.language_model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
43
+ "model.language_model.layers.2.mlp.gate_up_proj.weight": "model-00001-of-00004.safetensors",
44
+ "model.language_model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
45
+ "model.language_model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
46
+ "model.language_model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
47
+ "model.language_model.layers.3.post_self_attn_layernorm.weight": "model-00001-of-00004.safetensors",
48
+ "model.language_model.layers.3.post_mlp_layernorm.weight": "model-00001-of-00004.safetensors",
49
+ "model.language_model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
50
+ "model.language_model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
51
+ "model.language_model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
52
+ "model.language_model.layers.3.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
53
+ "model.language_model.layers.3.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
54
+ "model.language_model.layers.3.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
55
+ "model.language_model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
56
+ "model.language_model.layers.3.mlp.gate_up_proj.weight": "model-00001-of-00004.safetensors",
57
+ "model.language_model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
58
+ "model.language_model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
59
+ "model.language_model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
60
+ "model.language_model.layers.4.post_self_attn_layernorm.weight": "model-00001-of-00004.safetensors",
61
+ "model.language_model.layers.4.post_mlp_layernorm.weight": "model-00001-of-00004.safetensors",
62
+ "model.language_model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
63
+ "model.language_model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
64
+ "model.language_model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
65
+ "model.language_model.layers.4.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
66
+ "model.language_model.layers.4.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
67
+ "model.language_model.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
68
+ "model.language_model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
69
+ "model.language_model.layers.4.mlp.gate_up_proj.weight": "model-00001-of-00004.safetensors",
70
+ "model.language_model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
71
+ "model.language_model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
72
+ "model.language_model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
73
+ "model.language_model.layers.5.post_self_attn_layernorm.weight": "model-00001-of-00004.safetensors",
74
+ "model.language_model.layers.5.post_mlp_layernorm.weight": "model-00001-of-00004.safetensors",
75
+ "model.language_model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
76
+ "model.language_model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
77
+ "model.language_model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
78
+ "model.language_model.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
79
+ "model.language_model.layers.5.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
80
+ "model.language_model.layers.5.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
81
+ "model.language_model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
82
+ "model.language_model.layers.5.mlp.gate_up_proj.weight": "model-00001-of-00004.safetensors",
83
+ "model.language_model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
84
+ "model.language_model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
85
+ "model.language_model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
86
+ "model.language_model.layers.6.post_self_attn_layernorm.weight": "model-00001-of-00004.safetensors",
87
+ "model.language_model.layers.6.post_mlp_layernorm.weight": "model-00001-of-00004.safetensors",
88
+ "model.language_model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
89
+ "model.language_model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
90
+ "model.language_model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
91
+ "model.language_model.layers.6.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
92
+ "model.language_model.layers.6.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
93
+ "model.language_model.layers.6.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
94
+ "model.language_model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
95
+ "model.language_model.layers.6.mlp.gate_up_proj.weight": "model-00001-of-00004.safetensors",
96
+ "model.language_model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
97
+ "model.language_model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
98
+ "model.language_model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
99
+ "model.language_model.layers.7.post_self_attn_layernorm.weight": "model-00001-of-00004.safetensors",
100
+ "model.language_model.layers.7.post_mlp_layernorm.weight": "model-00001-of-00004.safetensors",
101
+ "model.language_model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
102
+ "model.language_model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
103
+ "model.language_model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
104
+ "model.language_model.layers.7.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
105
+ "model.language_model.layers.7.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
106
+ "model.language_model.layers.7.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
107
+ "model.language_model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
108
+ "model.language_model.layers.7.mlp.gate_up_proj.weight": "model-00001-of-00004.safetensors",
109
+ "model.language_model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
110
+ "model.language_model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
111
+ "model.language_model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
112
+ "model.language_model.layers.8.post_self_attn_layernorm.weight": "model-00001-of-00004.safetensors",
113
+ "model.language_model.layers.8.post_mlp_layernorm.weight": "model-00001-of-00004.safetensors",
114
+ "model.language_model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
115
+ "model.language_model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
116
+ "model.language_model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
117
+ "model.language_model.layers.8.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
118
+ "model.language_model.layers.8.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
119
+ "model.language_model.layers.8.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
120
+ "model.language_model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
121
+ "model.language_model.layers.8.mlp.gate_up_proj.weight": "model-00001-of-00004.safetensors",
122
+ "model.language_model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
123
+ "model.language_model.layers.9.input_layernorm.weight": "model-00001-of-00004.safetensors",
124
+ "model.language_model.layers.9.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
125
+ "model.language_model.layers.9.post_self_attn_layernorm.weight": "model-00001-of-00004.safetensors",
126
+ "model.language_model.layers.9.post_mlp_layernorm.weight": "model-00001-of-00004.safetensors",
127
+ "model.language_model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
128
+ "model.language_model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
129
+ "model.language_model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
130
+ "model.language_model.layers.9.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
131
+ "model.language_model.layers.9.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
132
+ "model.language_model.layers.9.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
133
+ "model.language_model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
134
+ "model.language_model.layers.9.mlp.gate_up_proj.weight": "model-00001-of-00004.safetensors",
135
+ "model.language_model.layers.9.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
136
+ "model.language_model.layers.10.input_layernorm.weight": "model-00001-of-00004.safetensors",
137
+ "model.language_model.layers.10.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
138
+ "model.language_model.layers.10.post_self_attn_layernorm.weight": "model-00001-of-00004.safetensors",
139
+ "model.language_model.layers.10.post_mlp_layernorm.weight": "model-00001-of-00004.safetensors",
140
+ "model.language_model.layers.10.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
141
+ "model.language_model.layers.10.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
142
+ "model.language_model.layers.10.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
143
+ "model.language_model.layers.10.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
144
+ "model.language_model.layers.10.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
145
+ "model.language_model.layers.10.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
146
+ "model.language_model.layers.10.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
147
+ "model.language_model.layers.10.mlp.gate_up_proj.weight": "model-00001-of-00004.safetensors",
148
+ "model.language_model.layers.10.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
149
+ "model.language_model.layers.11.input_layernorm.weight": "model-00001-of-00004.safetensors",
150
+ "model.language_model.layers.11.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
151
+ "model.language_model.layers.11.post_self_attn_layernorm.weight": "model-00001-of-00004.safetensors",
152
+ "model.language_model.layers.11.post_mlp_layernorm.weight": "model-00001-of-00004.safetensors",
153
+ "model.language_model.layers.11.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
154
+ "model.language_model.layers.11.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
155
+ "model.language_model.layers.11.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
156
+ "model.language_model.layers.11.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
157
+ "model.language_model.layers.11.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
158
+ "model.language_model.layers.11.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
159
+ "model.language_model.layers.11.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
160
+ "model.language_model.layers.11.mlp.gate_up_proj.weight": "model-00001-of-00004.safetensors",
161
+ "model.language_model.layers.11.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
162
+ "model.language_model.layers.12.input_layernorm.weight": "model-00001-of-00004.safetensors",
163
+ "model.language_model.layers.12.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
164
+ "model.language_model.layers.12.post_self_attn_layernorm.weight": "model-00001-of-00004.safetensors",
165
+ "model.language_model.layers.12.post_mlp_layernorm.weight": "model-00001-of-00004.safetensors",
166
+ "model.language_model.layers.12.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
167
+ "model.language_model.layers.12.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
168
+ "model.language_model.layers.12.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
169
+ "model.language_model.layers.12.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
170
+ "model.language_model.layers.12.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
171
+ "model.language_model.layers.12.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
172
+ "model.language_model.layers.12.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
173
+ "model.language_model.layers.12.mlp.gate_up_proj.weight": "model-00001-of-00004.safetensors",
174
+ "model.language_model.layers.12.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
175
+ "model.language_model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
176
+ "model.language_model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
177
+ "model.language_model.layers.13.post_self_attn_layernorm.weight": "model-00002-of-00004.safetensors",
178
+ "model.language_model.layers.13.post_mlp_layernorm.weight": "model-00002-of-00004.safetensors",
179
+ "model.language_model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
180
+ "model.language_model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
181
+ "model.language_model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
182
+ "model.language_model.layers.13.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
183
+ "model.language_model.layers.13.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
184
+ "model.language_model.layers.13.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
185
+ "model.language_model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
186
+ "model.language_model.layers.13.mlp.gate_up_proj.weight": "model-00002-of-00004.safetensors",
187
+ "model.language_model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
188
+ "model.language_model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
189
+ "model.language_model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
190
+ "model.language_model.layers.14.post_self_attn_layernorm.weight": "model-00002-of-00004.safetensors",
191
+ "model.language_model.layers.14.post_mlp_layernorm.weight": "model-00002-of-00004.safetensors",
192
+ "model.language_model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
193
+ "model.language_model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
194
+ "model.language_model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
195
+ "model.language_model.layers.14.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
196
+ "model.language_model.layers.14.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
197
+ "model.language_model.layers.14.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
198
+ "model.language_model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
199
+ "model.language_model.layers.14.mlp.gate_up_proj.weight": "model-00002-of-00004.safetensors",
200
+ "model.language_model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
201
+ "model.language_model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
202
+ "model.language_model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
203
+ "model.language_model.layers.15.post_self_attn_layernorm.weight": "model-00002-of-00004.safetensors",
204
+ "model.language_model.layers.15.post_mlp_layernorm.weight": "model-00002-of-00004.safetensors",
205
+ "model.language_model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
206
+ "model.language_model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
207
+ "model.language_model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
208
+ "model.language_model.layers.15.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
209
+ "model.language_model.layers.15.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
210
+ "model.language_model.layers.15.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
211
+ "model.language_model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
212
+ "model.language_model.layers.15.mlp.gate_up_proj.weight": "model-00002-of-00004.safetensors",
213
+ "model.language_model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
214
+ "model.language_model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
215
+ "model.language_model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
216
+ "model.language_model.layers.16.post_self_attn_layernorm.weight": "model-00002-of-00004.safetensors",
217
+ "model.language_model.layers.16.post_mlp_layernorm.weight": "model-00002-of-00004.safetensors",
218
+ "model.language_model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
219
+ "model.language_model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
220
+ "model.language_model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
221
+ "model.language_model.layers.16.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
222
+ "model.language_model.layers.16.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
223
+ "model.language_model.layers.16.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
224
+ "model.language_model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
225
+ "model.language_model.layers.16.mlp.gate_up_proj.weight": "model-00002-of-00004.safetensors",
226
+ "model.language_model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
227
+ "model.language_model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
228
+ "model.language_model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
229
+ "model.language_model.layers.17.post_self_attn_layernorm.weight": "model-00002-of-00004.safetensors",
230
+ "model.language_model.layers.17.post_mlp_layernorm.weight": "model-00002-of-00004.safetensors",
231
+ "model.language_model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
232
+ "model.language_model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
233
+ "model.language_model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
234
+ "model.language_model.layers.17.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
235
+ "model.language_model.layers.17.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
236
+ "model.language_model.layers.17.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
237
+ "model.language_model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
238
+ "model.language_model.layers.17.mlp.gate_up_proj.weight": "model-00002-of-00004.safetensors",
239
+ "model.language_model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
240
+ "model.language_model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
241
+ "model.language_model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
242
+ "model.language_model.layers.18.post_self_attn_layernorm.weight": "model-00002-of-00004.safetensors",
243
+ "model.language_model.layers.18.post_mlp_layernorm.weight": "model-00002-of-00004.safetensors",
244
+ "model.language_model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
245
+ "model.language_model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
246
+ "model.language_model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
247
+ "model.language_model.layers.18.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
248
+ "model.language_model.layers.18.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
249
+ "model.language_model.layers.18.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
250
+ "model.language_model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
251
+ "model.language_model.layers.18.mlp.gate_up_proj.weight": "model-00002-of-00004.safetensors",
252
+ "model.language_model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
253
+ "model.language_model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
254
+ "model.language_model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
255
+ "model.language_model.layers.19.post_self_attn_layernorm.weight": "model-00002-of-00004.safetensors",
256
+ "model.language_model.layers.19.post_mlp_layernorm.weight": "model-00002-of-00004.safetensors",
257
+ "model.language_model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
258
+ "model.language_model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
259
+ "model.language_model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
260
+ "model.language_model.layers.19.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
261
+ "model.language_model.layers.19.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
262
+ "model.language_model.layers.19.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
263
+ "model.language_model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
264
+ "model.language_model.layers.19.mlp.gate_up_proj.weight": "model-00002-of-00004.safetensors",
265
+ "model.language_model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
266
+ "model.language_model.layers.20.input_layernorm.weight": "model-00002-of-00004.safetensors",
267
+ "model.language_model.layers.20.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
268
+ "model.language_model.layers.20.post_self_attn_layernorm.weight": "model-00002-of-00004.safetensors",
269
+ "model.language_model.layers.20.post_mlp_layernorm.weight": "model-00002-of-00004.safetensors",
270
+ "model.language_model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
271
+ "model.language_model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
272
+ "model.language_model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
273
+ "model.language_model.layers.20.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
274
+ "model.language_model.layers.20.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
275
+ "model.language_model.layers.20.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
276
+ "model.language_model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
277
+ "model.language_model.layers.20.mlp.gate_up_proj.weight": "model-00002-of-00004.safetensors",
278
+ "model.language_model.layers.20.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
279
+ "model.language_model.layers.21.input_layernorm.weight": "model-00002-of-00004.safetensors",
280
+ "model.language_model.layers.21.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
281
+ "model.language_model.layers.21.post_self_attn_layernorm.weight": "model-00002-of-00004.safetensors",
282
+ "model.language_model.layers.21.post_mlp_layernorm.weight": "model-00002-of-00004.safetensors",
283
+ "model.language_model.layers.21.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
284
+ "model.language_model.layers.21.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
285
+ "model.language_model.layers.21.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
286
+ "model.language_model.layers.21.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
287
+ "model.language_model.layers.21.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
288
+ "model.language_model.layers.21.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
289
+ "model.language_model.layers.21.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
290
+ "model.language_model.layers.21.mlp.gate_up_proj.weight": "model-00002-of-00004.safetensors",
291
+ "model.language_model.layers.21.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
292
+ "model.language_model.layers.22.input_layernorm.weight": "model-00002-of-00004.safetensors",
293
+ "model.language_model.layers.22.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
294
+ "model.language_model.layers.22.post_self_attn_layernorm.weight": "model-00002-of-00004.safetensors",
295
+ "model.language_model.layers.22.post_mlp_layernorm.weight": "model-00002-of-00004.safetensors",
296
+ "model.language_model.layers.22.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
297
+ "model.language_model.layers.22.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
298
+ "model.language_model.layers.22.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
299
+ "model.language_model.layers.22.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
300
+ "model.language_model.layers.22.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
301
+ "model.language_model.layers.22.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
302
+ "model.language_model.layers.22.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
303
+ "model.language_model.layers.22.mlp.gate_up_proj.weight": "model-00002-of-00004.safetensors",
304
+ "model.language_model.layers.22.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
305
+ "model.language_model.layers.23.input_layernorm.weight": "model-00002-of-00004.safetensors",
306
+ "model.language_model.layers.23.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
307
+ "model.language_model.layers.23.post_self_attn_layernorm.weight": "model-00002-of-00004.safetensors",
308
+ "model.language_model.layers.23.post_mlp_layernorm.weight": "model-00002-of-00004.safetensors",
309
+ "model.language_model.layers.23.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
310
+ "model.language_model.layers.23.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
311
+ "model.language_model.layers.23.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
312
+ "model.language_model.layers.23.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
313
+ "model.language_model.layers.23.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
314
+ "model.language_model.layers.23.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
315
+ "model.language_model.layers.23.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
316
+ "model.language_model.layers.23.mlp.gate_up_proj.weight": "model-00002-of-00004.safetensors",
317
+ "model.language_model.layers.23.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
318
+ "model.language_model.layers.24.input_layernorm.weight": "model-00002-of-00004.safetensors",
319
+ "model.language_model.layers.24.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
320
+ "model.language_model.layers.24.post_self_attn_layernorm.weight": "model-00002-of-00004.safetensors",
321
+ "model.language_model.layers.24.post_mlp_layernorm.weight": "model-00002-of-00004.safetensors",
322
+ "model.language_model.layers.24.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
323
+ "model.language_model.layers.24.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
324
+ "model.language_model.layers.24.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
325
+ "model.language_model.layers.24.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
326
+ "model.language_model.layers.24.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
327
+ "model.language_model.layers.24.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
328
+ "model.language_model.layers.24.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
329
+ "model.language_model.layers.24.mlp.gate_up_proj.weight": "model-00002-of-00004.safetensors",
330
+ "model.language_model.layers.24.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
331
+ "model.language_model.layers.25.input_layernorm.weight": "model-00002-of-00004.safetensors",
332
+ "model.language_model.layers.25.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
333
+ "model.language_model.layers.25.post_self_attn_layernorm.weight": "model-00002-of-00004.safetensors",
334
+ "model.language_model.layers.25.post_mlp_layernorm.weight": "model-00002-of-00004.safetensors",
335
+ "model.language_model.layers.25.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
336
+ "model.language_model.layers.25.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
337
+ "model.language_model.layers.25.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
338
+ "model.language_model.layers.25.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
339
+ "model.language_model.layers.25.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
340
+ "model.language_model.layers.25.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
341
+ "model.language_model.layers.25.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
342
+ "model.language_model.layers.25.mlp.gate_up_proj.weight": "model-00002-of-00004.safetensors",
343
+ "model.language_model.layers.25.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
344
+ "model.language_model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
345
+ "model.language_model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
346
+ "model.language_model.layers.26.post_self_attn_layernorm.weight": "model-00003-of-00004.safetensors",
347
+ "model.language_model.layers.26.post_mlp_layernorm.weight": "model-00003-of-00004.safetensors",
348
+ "model.language_model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
349
+ "model.language_model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
350
+ "model.language_model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
351
+ "model.language_model.layers.26.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
352
+ "model.language_model.layers.26.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
353
+ "model.language_model.layers.26.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
354
+ "model.language_model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
355
+ "model.language_model.layers.26.mlp.gate_up_proj.weight": "model-00003-of-00004.safetensors",
356
+ "model.language_model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
357
+ "model.language_model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
358
+ "model.language_model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
359
+ "model.language_model.layers.27.post_self_attn_layernorm.weight": "model-00003-of-00004.safetensors",
360
+ "model.language_model.layers.27.post_mlp_layernorm.weight": "model-00003-of-00004.safetensors",
361
+ "model.language_model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
362
+ "model.language_model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
363
+ "model.language_model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
364
+ "model.language_model.layers.27.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
365
+ "model.language_model.layers.27.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
366
+ "model.language_model.layers.27.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
367
+ "model.language_model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
368
+ "model.language_model.layers.27.mlp.gate_up_proj.weight": "model-00003-of-00004.safetensors",
369
+ "model.language_model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
370
+ "model.language_model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
371
+ "model.language_model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
372
+ "model.language_model.layers.28.post_self_attn_layernorm.weight": "model-00003-of-00004.safetensors",
373
+ "model.language_model.layers.28.post_mlp_layernorm.weight": "model-00003-of-00004.safetensors",
374
+ "model.language_model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
375
+ "model.language_model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
376
+ "model.language_model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
377
+ "model.language_model.layers.28.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
378
+ "model.language_model.layers.28.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
379
+ "model.language_model.layers.28.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
380
+ "model.language_model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
381
+ "model.language_model.layers.28.mlp.gate_up_proj.weight": "model-00003-of-00004.safetensors",
382
+ "model.language_model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
383
+ "model.language_model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
384
+ "model.language_model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
385
+ "model.language_model.layers.29.post_self_attn_layernorm.weight": "model-00003-of-00004.safetensors",
386
+ "model.language_model.layers.29.post_mlp_layernorm.weight": "model-00003-of-00004.safetensors",
387
+ "model.language_model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
388
+ "model.language_model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
389
+ "model.language_model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
390
+ "model.language_model.layers.29.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
391
+ "model.language_model.layers.29.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
392
+ "model.language_model.layers.29.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
393
+ "model.language_model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
394
+ "model.language_model.layers.29.mlp.gate_up_proj.weight": "model-00003-of-00004.safetensors",
395
+ "model.language_model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
396
+ "model.language_model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
397
+ "model.language_model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
398
+ "model.language_model.layers.30.post_self_attn_layernorm.weight": "model-00003-of-00004.safetensors",
399
+ "model.language_model.layers.30.post_mlp_layernorm.weight": "model-00003-of-00004.safetensors",
400
+ "model.language_model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
401
+ "model.language_model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
402
+ "model.language_model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
403
+ "model.language_model.layers.30.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
404
+ "model.language_model.layers.30.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
405
+ "model.language_model.layers.30.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
406
+ "model.language_model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
407
+ "model.language_model.layers.30.mlp.gate_up_proj.weight": "model-00003-of-00004.safetensors",
408
+ "model.language_model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
409
+ "model.language_model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors",
410
+ "model.language_model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
411
+ "model.language_model.layers.31.post_self_attn_layernorm.weight": "model-00003-of-00004.safetensors",
412
+ "model.language_model.layers.31.post_mlp_layernorm.weight": "model-00003-of-00004.safetensors",
413
+ "model.language_model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
414
+ "model.language_model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
415
+ "model.language_model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
416
+ "model.language_model.layers.31.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
417
+ "model.language_model.layers.31.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
418
+ "model.language_model.layers.31.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
419
+ "model.language_model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
420
+ "model.language_model.layers.31.mlp.gate_up_proj.weight": "model-00003-of-00004.safetensors",
421
+ "model.language_model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
422
+ "model.language_model.layers.32.input_layernorm.weight": "model-00003-of-00004.safetensors",
423
+ "model.language_model.layers.32.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
424
+ "model.language_model.layers.32.post_self_attn_layernorm.weight": "model-00003-of-00004.safetensors",
425
+ "model.language_model.layers.32.post_mlp_layernorm.weight": "model-00003-of-00004.safetensors",
426
+ "model.language_model.layers.32.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
427
+ "model.language_model.layers.32.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
428
+ "model.language_model.layers.32.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
429
+ "model.language_model.layers.32.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
430
+ "model.language_model.layers.32.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
431
+ "model.language_model.layers.32.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
432
+ "model.language_model.layers.32.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
433
+ "model.language_model.layers.32.mlp.gate_up_proj.weight": "model-00003-of-00004.safetensors",
434
+ "model.language_model.layers.32.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
435
+ "model.language_model.layers.33.input_layernorm.weight": "model-00003-of-00004.safetensors",
436
+ "model.language_model.layers.33.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
437
+ "model.language_model.layers.33.post_self_attn_layernorm.weight": "model-00003-of-00004.safetensors",
438
+ "model.language_model.layers.33.post_mlp_layernorm.weight": "model-00003-of-00004.safetensors",
439
+ "model.language_model.layers.33.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
440
+ "model.language_model.layers.33.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
441
+ "model.language_model.layers.33.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
442
+ "model.language_model.layers.33.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
443
+ "model.language_model.layers.33.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
444
+ "model.language_model.layers.33.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
445
+ "model.language_model.layers.33.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
446
+ "model.language_model.layers.33.mlp.gate_up_proj.weight": "model-00003-of-00004.safetensors",
447
+ "model.language_model.layers.33.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
448
+ "model.language_model.layers.34.input_layernorm.weight": "model-00003-of-00004.safetensors",
449
+ "model.language_model.layers.34.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
450
+ "model.language_model.layers.34.post_self_attn_layernorm.weight": "model-00003-of-00004.safetensors",
451
+ "model.language_model.layers.34.post_mlp_layernorm.weight": "model-00003-of-00004.safetensors",
452
+ "model.language_model.layers.34.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
453
+ "model.language_model.layers.34.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
454
+ "model.language_model.layers.34.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
455
+ "model.language_model.layers.34.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
456
+ "model.language_model.layers.34.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
457
+ "model.language_model.layers.34.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
458
+ "model.language_model.layers.34.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
459
+ "model.language_model.layers.34.mlp.gate_up_proj.weight": "model-00003-of-00004.safetensors",
460
+ "model.language_model.layers.34.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
461
+ "model.language_model.layers.35.input_layernorm.weight": "model-00003-of-00004.safetensors",
462
+ "model.language_model.layers.35.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
463
+ "model.language_model.layers.35.post_self_attn_layernorm.weight": "model-00003-of-00004.safetensors",
464
+ "model.language_model.layers.35.post_mlp_layernorm.weight": "model-00003-of-00004.safetensors",
465
+ "model.language_model.layers.35.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
466
+ "model.language_model.layers.35.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
467
+ "model.language_model.layers.35.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
468
+ "model.language_model.layers.35.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
469
+ "model.language_model.layers.35.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
470
+ "model.language_model.layers.35.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
471
+ "model.language_model.layers.35.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
472
+ "model.language_model.layers.35.mlp.gate_up_proj.weight": "model-00003-of-00004.safetensors",
473
+ "model.language_model.layers.35.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
474
+ "model.language_model.layers.36.input_layernorm.weight": "model-00003-of-00004.safetensors",
475
+ "model.language_model.layers.36.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
476
+ "model.language_model.layers.36.post_self_attn_layernorm.weight": "model-00003-of-00004.safetensors",
477
+ "model.language_model.layers.36.post_mlp_layernorm.weight": "model-00003-of-00004.safetensors",
478
+ "model.language_model.layers.36.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
479
+ "model.language_model.layers.36.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
480
+ "model.language_model.layers.36.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
481
+ "model.language_model.layers.36.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
482
+ "model.language_model.layers.36.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
483
+ "model.language_model.layers.36.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
484
+ "model.language_model.layers.36.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
485
+ "model.language_model.layers.36.mlp.gate_up_proj.weight": "model-00003-of-00004.safetensors",
486
+ "model.language_model.layers.36.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
487
+ "model.language_model.layers.37.input_layernorm.weight": "model-00003-of-00004.safetensors",
488
+ "model.language_model.layers.37.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
489
+ "model.language_model.layers.37.post_self_attn_layernorm.weight": "model-00003-of-00004.safetensors",
490
+ "model.language_model.layers.37.post_mlp_layernorm.weight": "model-00003-of-00004.safetensors",
491
+ "model.language_model.layers.37.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
492
+ "model.language_model.layers.37.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
493
+ "model.language_model.layers.37.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
494
+ "model.language_model.layers.37.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
495
+ "model.language_model.layers.37.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
496
+ "model.language_model.layers.37.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
497
+ "model.language_model.layers.37.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
498
+ "model.language_model.layers.37.mlp.gate_up_proj.weight": "model-00003-of-00004.safetensors",
499
+ "model.language_model.layers.37.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
500
+ "model.language_model.layers.38.input_layernorm.weight": "model-00003-of-00004.safetensors",
501
+ "model.language_model.layers.38.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
502
+ "model.language_model.layers.38.post_self_attn_layernorm.weight": "model-00003-of-00004.safetensors",
503
+ "model.language_model.layers.38.post_mlp_layernorm.weight": "model-00003-of-00004.safetensors",
504
+ "model.language_model.layers.38.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
505
+ "model.language_model.layers.38.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
506
+ "model.language_model.layers.38.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
507
+ "model.language_model.layers.38.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
508
+ "model.language_model.layers.38.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
509
+ "model.language_model.layers.38.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
510
+ "model.language_model.layers.38.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
511
+ "model.language_model.layers.38.mlp.gate_up_proj.weight": "model-00003-of-00004.safetensors",
512
+ "model.language_model.layers.38.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
513
+ "model.language_model.layers.39.input_layernorm.weight": "model-00004-of-00004.safetensors",
514
+ "model.language_model.layers.39.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
515
+ "model.language_model.layers.39.post_self_attn_layernorm.weight": "model-00004-of-00004.safetensors",
516
+ "model.language_model.layers.39.post_mlp_layernorm.weight": "model-00004-of-00004.safetensors",
517
+ "model.language_model.layers.39.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
518
+ "model.language_model.layers.39.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
519
+ "model.language_model.layers.39.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
520
+ "model.language_model.layers.39.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
521
+ "model.language_model.layers.39.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
522
+ "model.language_model.layers.39.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
523
+ "model.language_model.layers.39.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
524
+ "model.language_model.layers.39.mlp.gate_up_proj.weight": "model-00004-of-00004.safetensors",
525
+ "model.language_model.layers.39.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
526
+ "model.visual.blocks.0.norm1.weight": "model-00004-of-00004.safetensors",
527
+ "model.visual.blocks.0.norm2.weight": "model-00004-of-00004.safetensors",
528
+ "model.visual.blocks.0.attn.qkv.weight": "model-00004-of-00004.safetensors",
529
+ "model.visual.blocks.0.attn.proj.weight": "model-00004-of-00004.safetensors",
530
+ "model.visual.blocks.0.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
531
+ "model.visual.blocks.0.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
532
+ "model.visual.blocks.0.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
533
+ "model.visual.blocks.1.norm1.weight": "model-00004-of-00004.safetensors",
534
+ "model.visual.blocks.1.norm2.weight": "model-00004-of-00004.safetensors",
535
+ "model.visual.blocks.1.attn.qkv.weight": "model-00004-of-00004.safetensors",
536
+ "model.visual.blocks.1.attn.proj.weight": "model-00004-of-00004.safetensors",
537
+ "model.visual.blocks.1.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
538
+ "model.visual.blocks.1.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
539
+ "model.visual.blocks.1.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
540
+ "model.visual.blocks.2.norm1.weight": "model-00004-of-00004.safetensors",
541
+ "model.visual.blocks.2.norm2.weight": "model-00004-of-00004.safetensors",
542
+ "model.visual.blocks.2.attn.qkv.weight": "model-00004-of-00004.safetensors",
543
+ "model.visual.blocks.2.attn.proj.weight": "model-00004-of-00004.safetensors",
544
+ "model.visual.blocks.2.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
545
+ "model.visual.blocks.2.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
546
+ "model.visual.blocks.2.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
547
+ "model.visual.blocks.3.norm1.weight": "model-00004-of-00004.safetensors",
548
+ "model.visual.blocks.3.norm2.weight": "model-00004-of-00004.safetensors",
549
+ "model.visual.blocks.3.attn.qkv.weight": "model-00004-of-00004.safetensors",
550
+ "model.visual.blocks.3.attn.proj.weight": "model-00004-of-00004.safetensors",
551
+ "model.visual.blocks.3.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
552
+ "model.visual.blocks.3.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
553
+ "model.visual.blocks.3.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
554
+ "model.visual.blocks.4.norm1.weight": "model-00004-of-00004.safetensors",
555
+ "model.visual.blocks.4.norm2.weight": "model-00004-of-00004.safetensors",
556
+ "model.visual.blocks.4.attn.qkv.weight": "model-00004-of-00004.safetensors",
557
+ "model.visual.blocks.4.attn.proj.weight": "model-00004-of-00004.safetensors",
558
+ "model.visual.blocks.4.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
559
+ "model.visual.blocks.4.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
560
+ "model.visual.blocks.4.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
561
+ "model.visual.blocks.5.norm1.weight": "model-00004-of-00004.safetensors",
562
+ "model.visual.blocks.5.norm2.weight": "model-00004-of-00004.safetensors",
563
+ "model.visual.blocks.5.attn.qkv.weight": "model-00004-of-00004.safetensors",
564
+ "model.visual.blocks.5.attn.proj.weight": "model-00004-of-00004.safetensors",
565
+ "model.visual.blocks.5.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
566
+ "model.visual.blocks.5.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
567
+ "model.visual.blocks.5.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
568
+ "model.visual.blocks.6.norm1.weight": "model-00004-of-00004.safetensors",
569
+ "model.visual.blocks.6.norm2.weight": "model-00004-of-00004.safetensors",
570
+ "model.visual.blocks.6.attn.qkv.weight": "model-00004-of-00004.safetensors",
571
+ "model.visual.blocks.6.attn.proj.weight": "model-00004-of-00004.safetensors",
572
+ "model.visual.blocks.6.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
573
+ "model.visual.blocks.6.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
574
+ "model.visual.blocks.6.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
575
+ "model.visual.blocks.7.norm1.weight": "model-00004-of-00004.safetensors",
576
+ "model.visual.blocks.7.norm2.weight": "model-00004-of-00004.safetensors",
577
+ "model.visual.blocks.7.attn.qkv.weight": "model-00004-of-00004.safetensors",
578
+ "model.visual.blocks.7.attn.proj.weight": "model-00004-of-00004.safetensors",
579
+ "model.visual.blocks.7.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
580
+ "model.visual.blocks.7.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
581
+ "model.visual.blocks.7.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
582
+ "model.visual.blocks.8.norm1.weight": "model-00004-of-00004.safetensors",
583
+ "model.visual.blocks.8.norm2.weight": "model-00004-of-00004.safetensors",
584
+ "model.visual.blocks.8.attn.qkv.weight": "model-00004-of-00004.safetensors",
585
+ "model.visual.blocks.8.attn.proj.weight": "model-00004-of-00004.safetensors",
586
+ "model.visual.blocks.8.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
587
+ "model.visual.blocks.8.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
588
+ "model.visual.blocks.8.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
589
+ "model.visual.blocks.9.norm1.weight": "model-00004-of-00004.safetensors",
590
+ "model.visual.blocks.9.norm2.weight": "model-00004-of-00004.safetensors",
591
+ "model.visual.blocks.9.attn.qkv.weight": "model-00004-of-00004.safetensors",
592
+ "model.visual.blocks.9.attn.proj.weight": "model-00004-of-00004.safetensors",
593
+ "model.visual.blocks.9.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
594
+ "model.visual.blocks.9.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
595
+ "model.visual.blocks.9.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
596
+ "model.visual.blocks.10.norm1.weight": "model-00004-of-00004.safetensors",
597
+ "model.visual.blocks.10.norm2.weight": "model-00004-of-00004.safetensors",
598
+ "model.visual.blocks.10.attn.qkv.weight": "model-00004-of-00004.safetensors",
599
+ "model.visual.blocks.10.attn.proj.weight": "model-00004-of-00004.safetensors",
600
+ "model.visual.blocks.10.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
601
+ "model.visual.blocks.10.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
602
+ "model.visual.blocks.10.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
603
+ "model.visual.blocks.11.norm1.weight": "model-00004-of-00004.safetensors",
604
+ "model.visual.blocks.11.norm2.weight": "model-00004-of-00004.safetensors",
605
+ "model.visual.blocks.11.attn.qkv.weight": "model-00004-of-00004.safetensors",
606
+ "model.visual.blocks.11.attn.proj.weight": "model-00004-of-00004.safetensors",
607
+ "model.visual.blocks.11.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
608
+ "model.visual.blocks.11.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
609
+ "model.visual.blocks.11.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
610
+ "model.visual.blocks.12.norm1.weight": "model-00004-of-00004.safetensors",
611
+ "model.visual.blocks.12.norm2.weight": "model-00004-of-00004.safetensors",
612
+ "model.visual.blocks.12.attn.qkv.weight": "model-00004-of-00004.safetensors",
613
+ "model.visual.blocks.12.attn.proj.weight": "model-00004-of-00004.safetensors",
614
+ "model.visual.blocks.12.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
615
+ "model.visual.blocks.12.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
616
+ "model.visual.blocks.12.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
617
+ "model.visual.blocks.13.norm1.weight": "model-00004-of-00004.safetensors",
618
+ "model.visual.blocks.13.norm2.weight": "model-00004-of-00004.safetensors",
619
+ "model.visual.blocks.13.attn.qkv.weight": "model-00004-of-00004.safetensors",
620
+ "model.visual.blocks.13.attn.proj.weight": "model-00004-of-00004.safetensors",
621
+ "model.visual.blocks.13.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
622
+ "model.visual.blocks.13.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
623
+ "model.visual.blocks.13.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
624
+ "model.visual.blocks.14.norm1.weight": "model-00004-of-00004.safetensors",
625
+ "model.visual.blocks.14.norm2.weight": "model-00004-of-00004.safetensors",
626
+ "model.visual.blocks.14.attn.qkv.weight": "model-00004-of-00004.safetensors",
627
+ "model.visual.blocks.14.attn.proj.weight": "model-00004-of-00004.safetensors",
628
+ "model.visual.blocks.14.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
629
+ "model.visual.blocks.14.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
630
+ "model.visual.blocks.14.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
631
+ "model.visual.blocks.15.norm1.weight": "model-00004-of-00004.safetensors",
632
+ "model.visual.blocks.15.norm2.weight": "model-00004-of-00004.safetensors",
633
+ "model.visual.blocks.15.attn.qkv.weight": "model-00004-of-00004.safetensors",
634
+ "model.visual.blocks.15.attn.proj.weight": "model-00004-of-00004.safetensors",
635
+ "model.visual.blocks.15.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
636
+ "model.visual.blocks.15.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
637
+ "model.visual.blocks.15.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
638
+ "model.visual.blocks.16.norm1.weight": "model-00004-of-00004.safetensors",
639
+ "model.visual.blocks.16.norm2.weight": "model-00004-of-00004.safetensors",
640
+ "model.visual.blocks.16.attn.qkv.weight": "model-00004-of-00004.safetensors",
641
+ "model.visual.blocks.16.attn.proj.weight": "model-00004-of-00004.safetensors",
642
+ "model.visual.blocks.16.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
643
+ "model.visual.blocks.16.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
644
+ "model.visual.blocks.16.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
645
+ "model.visual.blocks.17.norm1.weight": "model-00004-of-00004.safetensors",
646
+ "model.visual.blocks.17.norm2.weight": "model-00004-of-00004.safetensors",
647
+ "model.visual.blocks.17.attn.qkv.weight": "model-00004-of-00004.safetensors",
648
+ "model.visual.blocks.17.attn.proj.weight": "model-00004-of-00004.safetensors",
649
+ "model.visual.blocks.17.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
650
+ "model.visual.blocks.17.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
651
+ "model.visual.blocks.17.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
652
+ "model.visual.blocks.18.norm1.weight": "model-00004-of-00004.safetensors",
653
+ "model.visual.blocks.18.norm2.weight": "model-00004-of-00004.safetensors",
654
+ "model.visual.blocks.18.attn.qkv.weight": "model-00004-of-00004.safetensors",
655
+ "model.visual.blocks.18.attn.proj.weight": "model-00004-of-00004.safetensors",
656
+ "model.visual.blocks.18.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
657
+ "model.visual.blocks.18.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
658
+ "model.visual.blocks.18.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
659
+ "model.visual.blocks.19.norm1.weight": "model-00004-of-00004.safetensors",
660
+ "model.visual.blocks.19.norm2.weight": "model-00004-of-00004.safetensors",
661
+ "model.visual.blocks.19.attn.qkv.weight": "model-00004-of-00004.safetensors",
662
+ "model.visual.blocks.19.attn.proj.weight": "model-00004-of-00004.safetensors",
663
+ "model.visual.blocks.19.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
664
+ "model.visual.blocks.19.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
665
+ "model.visual.blocks.19.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
666
+ "model.visual.blocks.20.norm1.weight": "model-00004-of-00004.safetensors",
667
+ "model.visual.blocks.20.norm2.weight": "model-00004-of-00004.safetensors",
668
+ "model.visual.blocks.20.attn.qkv.weight": "model-00004-of-00004.safetensors",
669
+ "model.visual.blocks.20.attn.proj.weight": "model-00004-of-00004.safetensors",
670
+ "model.visual.blocks.20.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
671
+ "model.visual.blocks.20.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
672
+ "model.visual.blocks.20.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
673
+ "model.visual.blocks.21.norm1.weight": "model-00004-of-00004.safetensors",
674
+ "model.visual.blocks.21.norm2.weight": "model-00004-of-00004.safetensors",
675
+ "model.visual.blocks.21.attn.qkv.weight": "model-00004-of-00004.safetensors",
676
+ "model.visual.blocks.21.attn.proj.weight": "model-00004-of-00004.safetensors",
677
+ "model.visual.blocks.21.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
678
+ "model.visual.blocks.21.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
679
+ "model.visual.blocks.21.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
680
+ "model.visual.blocks.22.norm1.weight": "model-00004-of-00004.safetensors",
681
+ "model.visual.blocks.22.norm2.weight": "model-00004-of-00004.safetensors",
682
+ "model.visual.blocks.22.attn.qkv.weight": "model-00004-of-00004.safetensors",
683
+ "model.visual.blocks.22.attn.proj.weight": "model-00004-of-00004.safetensors",
684
+ "model.visual.blocks.22.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
685
+ "model.visual.blocks.22.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
686
+ "model.visual.blocks.22.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
687
+ "model.visual.blocks.23.norm1.weight": "model-00004-of-00004.safetensors",
688
+ "model.visual.blocks.23.norm2.weight": "model-00004-of-00004.safetensors",
689
+ "model.visual.blocks.23.attn.qkv.weight": "model-00004-of-00004.safetensors",
690
+ "model.visual.blocks.23.attn.proj.weight": "model-00004-of-00004.safetensors",
691
+ "model.visual.blocks.23.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
692
+ "model.visual.blocks.23.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
693
+ "model.visual.blocks.23.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
694
+ "model.language_model.embed_tokens.weight": "model-00004-of-00004.safetensors",
695
+ "lm_head.weight": "model-00004-of-00004.safetensors",
696
+ "model.language_model.norm.weight": "model-00004-of-00004.safetensors",
697
+ "model.visual.downsample.weight": "model-00004-of-00004.safetensors",
698
+ "model.visual.downsample.bias": "model-00004-of-00004.safetensors",
699
+ "model.visual.merger.gate_proj.weight": "model-00004-of-00004.safetensors",
700
+ "model.visual.merger.up_proj.weight": "model-00004-of-00004.safetensors",
701
+ "model.visual.merger.down_proj.weight": "model-00004-of-00004.safetensors",
702
+ "model.visual.merger.proj.weight": "model-00004-of-00004.safetensors",
703
+ "model.visual.merger.post_projection_norm.weight": "model-00004-of-00004.safetensors",
704
+ "model.visual.merger.post_projection_norm.bias": "model-00004-of-00004.safetensors",
705
+ "model.visual.embeddings.position_embedding.weight": "model-00004-of-00004.safetensors",
706
+ "model.visual.patch_embed.proj.weight": "model-00004-of-00004.safetensors",
707
+ "model.visual.patch_embed.proj.bias": "model-00004-of-00004.safetensors",
708
+ "model.visual.post_conv_layernorm.weight": "model-00004-of-00004.safetensors",
709
+ "model.visual.post_layernorm.weight": "model-00004-of-00004.safetensors"
710
+ }
711
+ }
notebook.ipynb ADDED
The diff for this file is too large to render. See raw diff
 
preprocessor_config.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "size": {"shortest_edge": 12544, "longest_edge": 9633792},
3
+ "do_rescale": true,
4
+ "patch_size": 14,
5
+ "temporal_patch_size": 2,
6
+ "merge_size": 2,
7
+ "image_mean": [0.48145466, 0.4578275, 0.40821073],
8
+ "image_std": [0.26862954, 0.26130258, 0.27577711],
9
+ "image_processor_type": "Glm4vImageProcessor",
10
+ "processor_class": "Glm4vProcessor"
11
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:76ebeac0d8bd7879ead7b43c16b44981f277e47225de2bd7de9ae1a6cc664a8c
3
+ size 19966496
tokenizer_config.json ADDED
@@ -0,0 +1,218 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "151329": {
4
+ "content": "<|endoftext|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "151330": {
12
+ "content": "[MASK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "151331": {
20
+ "content": "[gMASK]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "151332": {
28
+ "content": "[sMASK]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "151333": {
36
+ "content": "<sop>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "151334": {
44
+ "content": "<eop>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "151335": {
52
+ "content": "<|system|>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "151336": {
60
+ "content": "<|user|>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "151337": {
68
+ "content": "<|assistant|>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "151338": {
76
+ "content": "<|observation|>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "151339": {
84
+ "content": "<|begin_of_image|>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "151340": {
92
+ "content": "<|end_of_image|>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "151341": {
100
+ "content": "<|begin_of_video|>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "151342": {
108
+ "content": "<|end_of_video|>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "151343": {
116
+ "content": "<|image|>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "151344": {
124
+ "content": "<|video|>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "151345": {
132
+ "content": "<think>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": false
138
+ },
139
+ "151346": {
140
+ "content": "</think>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": false
146
+ },
147
+ "151347": {
148
+ "content": "<answer>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": false
154
+ },
155
+ "151348": {
156
+ "content": "</answer>",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": false
162
+ },
163
+ "151349": {
164
+ "content": "<|begin_of_box|>",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": false
170
+ },
171
+ "151350": {
172
+ "content": "<|end_of_box|>",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": false
178
+ },
179
+ "151351": {
180
+ "content": "<|sep|>",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": false
186
+ }
187
+ },
188
+ "additional_special_tokens": [
189
+ "<|endoftext|>",
190
+ "[MASK]",
191
+ "[gMASK]",
192
+ "[sMASK]",
193
+ "<sop>",
194
+ "<eop>",
195
+ "<|system|>",
196
+ "<|user|>",
197
+ "<|assistant|>",
198
+ "<|observation|>",
199
+ "<|begin_of_image|>",
200
+ "<|end_of_image|>",
201
+ "<|begin_of_video|>",
202
+ "<|end_of_video|>",
203
+ "<|image|>",
204
+ "<|video|>"
205
+ ],
206
+ "clean_up_tokenization_spaces": false,
207
+ "do_lower_case": false,
208
+ "eos_token": "<|endoftext|>",
209
+ "pad_token": "<|endoftext|>",
210
+ "model_input_names": [
211
+ "input_ids",
212
+ "attention_mask"
213
+ ],
214
+ "model_max_length": 65536,
215
+ "padding_side": "left",
216
+ "remove_space": false,
217
+ "tokenizer_class": "PreTrainedTokenizer"
218
+ }
video_preprocessor_config.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "size": {"shortest_edge": 12544, "longest_edge": 47040000},
3
+ "do_rescale": true,
4
+ "patch_size": 14,
5
+ "temporal_patch_size": 2,
6
+ "merge_size": 2,
7
+ "image_mean": [0.48145466, 0.4578275, 0.40821073],
8
+ "image_std": [0.26862954, 0.26130258, 0.27577711],
9
+ "video_processor_type": "Glm4vVideoProcessor",
10
+ "processor_class": "Glm4vProcessor"
11
+ }