Hugging Face's logo

Sh2425
/
Dolphy-1.2-Base

Transformers
Safetensors
English
dolphy_moe
text-generation-inference
unsloth
qwen3
trl
Model card Files
xet
Community
Sh2425 commited on
Commit
cd216de
·
verified ·
1 Parent(s): e65adfe

Upload folder using huggingface_hub

Browse files
Files changed (9) hide show
  1. chat_template.jinja +1 -26
  2. config.json +59 -33
  3. generation_config.json +1 -2
  4. model-00001-of-00003.safetensors +3 -0
  5. model-00002-of-00003.safetensors +3 -0
  6. model-00003-of-00003.safetensors +3 -0
  7. model.safetensors.index.json +316 -316
  8. special_tokens_map.json +1 -1
  9. tokenizer_config.json +2 -3
chat_template.jinja CHANGED
@@ -14,14 +14,6 @@
14
  {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
15
  {%- endif %}
16
  {%- endif %}
17
- {%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
18
- {%- for message in messages[::-1] %}
19
- {%- set index = (messages|length - 1) - loop.index0 %}
20
- {%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
21
- {%- set ns.multi_step_tool = false %}
22
- {%- set ns.last_query_index = index %}
23
- {%- endif %}
24
- {%- endfor %}
25
  {%- for message in messages %}
26
  {%- if message.content is string %}
27
  {%- set content = message.content %}
@@ -31,24 +23,7 @@
31
  {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
32
  {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
33
  {%- elif message.role == "assistant" %}
34
- {%- set reasoning_content = '' %}
35
- {%- if message.reasoning_content is string %}
36
- {%- set reasoning_content = message.reasoning_content %}
37
- {%- else %}
38
- {%- if '</think>' in content %}
39
- {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
40
- {%- set content = content.split('</think>')[-1].lstrip('\n') %}
41
- {%- endif %}
42
- {%- endif %}
43
- {%- if loop.index0 > ns.last_query_index %}
44
- {%- if loop.last or (not loop.last and reasoning_content) %}
45
- {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
46
- {%- else %}
47
- {{- '<|im_start|>' + message.role + '\n' + content }}
48
- {%- endif %}
49
- {%- else %}
50
- {{- '<|im_start|>' + message.role + '\n' + content }}
51
- {%- endif %}
52
  {%- if message.tool_calls %}
53
  {%- for tool_call in message.tool_calls %}
54
  {%- if (loop.first and content) or (not loop.first) %}
 
14
  {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
15
  {%- endif %}
16
  {%- endif %}
 
 
 
 
 
 
 
 
17
  {%- for message in messages %}
18
  {%- if message.content is string %}
19
  {%- set content = message.content %}
 
23
  {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
24
  {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
25
  {%- elif message.role == "assistant" %}
26
+ {{- '<|im_start|>' + message.role + '\n' + content }}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
27
  {%- if message.tool_calls %}
28
  {%- for tool_call in message.tool_calls %}
29
  {%- if (loop.first and content) or (not loop.first) %}
config.json CHANGED
@@ -1,42 +1,68 @@
1
  {
2
- "architectures": ["Dolphy1ForCausalLM"],
3
- "model_type": "qwen3",
4
- "moe_fused": true,
5
- "vocab_size": 151936,
6
- "hidden_size": 2560,
7
- "intermediate_size": 9728,
8
- "num_hidden_layers": 36,
9
- "num_attention_heads": 32,
10
- "num_key_value_heads": 8,
11
  "head_dim": 128,
12
  "hidden_act": "silu",
13
- "attention_dropout": 0.0,
14
- "attention_bias": false,
15
- "rms_norm_eps": 1e-6,
16
  "initializer_range": 0.02,
17
- "max_position_embeddings": 262144,
18
- "eos_token_id": 151645,
19
- "pad_token_id": 151654,
20
- "tie_word_embeddings": true,
21
- "use_cache": true,
22
- "use_sliding_window": false,
23
- "sliding_window": null,
24
  "layer_types": [
25
- "full_attention", "full_attention", "full_attention", "full_attention",
26
- "full_attention", "full_attention", "full_attention", "full_attention",
27
- "full_attention", "full_attention", "full_attention", "full_attention",
28
- "full_attention", "full_attention", "full_attention", "full_attention",
29
- "full_attention", "full_attention", "full_attention", "full_attention",
30
- "full_attention", "full_attention", "full_attention", "full_attention",
31
- "full_attention", "full_attention", "full_attention", "full_attention",
32
- "full_attention", "full_attention", "full_attention", "full_attention",
33
- "full_attention", "full_attention", "full_attention", "full_attention"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
34
  ],
35
- "rope_theta": 5000000,
36
- "rope_scaling": null,
37
  "max_window_layers": 36,
38
- "dtype": "float16",
 
 
 
 
 
 
 
 
39
  "transformers_version": "4.57.1",
40
- "unsloth_fixed": true,
41
- "unsloth_version": "2025.10.11"
 
42
  }
 
1
  {
2
+ "architectures": [
3
+ "Qwen3ForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 151643,
8
+ "dtype": "float16",
9
+ "eos_token_id": 151645,
 
10
  "head_dim": 128,
11
  "hidden_act": "silu",
12
+ "hidden_size": 2560,
 
 
13
  "initializer_range": 0.02,
14
+ "intermediate_size": 9728,
 
 
 
 
 
 
15
  "layer_types": [
16
+ "full_attention",
17
+ "full_attention",
18
+ "full_attention",
19
+ "full_attention",
20
+ "full_attention",
21
+ "full_attention",
22
+ "full_attention",
23
+ "full_attention",
24
+ "full_attention",
25
+ "full_attention",
26
+ "full_attention",
27
+ "full_attention",
28
+ "full_attention",
29
+ "full_attention",
30
+ "full_attention",
31
+ "full_attention",
32
+ "full_attention",
33
+ "full_attention",
34
+ "full_attention",
35
+ "full_attention",
36
+ "full_attention",
37
+ "full_attention",
38
+ "full_attention",
39
+ "full_attention",
40
+ "full_attention",
41
+ "full_attention",
42
+ "full_attention",
43
+ "full_attention",
44
+ "full_attention",
45
+ "full_attention",
46
+ "full_attention",
47
+ "full_attention",
48
+ "full_attention",
49
+ "full_attention",
50
+ "full_attention",
51
+ "full_attention"
52
  ],
53
+ "max_position_embeddings": 262144,
 
54
  "max_window_layers": 36,
55
+ "model_type": "qwen3",
56
+ "num_attention_heads": 32,
57
+ "num_hidden_layers": 36,
58
+ "num_key_value_heads": 8,
59
+ "rms_norm_eps": 1e-06,
60
+ "rope_scaling": null,
61
+ "rope_theta": 5000000,
62
+ "sliding_window": null,
63
+ "tie_word_embeddings": true,
64
  "transformers_version": "4.57.1",
65
+ "use_cache": true,
66
+ "use_sliding_window": false,
67
+ "vocab_size": 151936
68
  }
generation_config.json CHANGED
@@ -5,8 +5,7 @@
5
  151645,
6
  151643
7
  ],
8
- "max_length": 262144,
9
- "pad_token_id": 151654,
10
  "temperature": 0.7,
11
  "top_k": 20,
12
  "top_p": 0.8,
 
5
  151645,
6
  151643
7
  ],
8
+ "pad_token_id": 151643,
 
9
  "temperature": 0.7,
10
  "top_k": 20,
11
  "top_p": 0.8,
model-00001-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ff1827d7da07d723e2bed552d37790e7d7be3f6e59337035f7ea2da6bf819d8
3
+ size 4919817072
model-00002-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b9ba3b9579c46fa7e5d1912e2d49d5b6e84401c1f800af8acd6f15c641952e6c
3
+ size 4973065720
model-00003-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ea8d1fe1ce9191a0c4a8c3abcf8f855311dec26460b0fcc698ef0c709952a080
3
+ size 1108986136
model.safetensors.index.json CHANGED
@@ -4,321 +4,321 @@
4
  "total_size": 11001832464
5
  },
6
  "weight_map": {
7
- "model.embed_tokens.weight": "model-00001-of-00008.safetensors",
8
- "model.layers.0.input_layernorm.weight": "model-00002-of-00008.safetensors",
9
- "model.layers.0.mlp.experts.0.down_proj.weight": "model-00001-of-00008.safetensors",
10
- "model.layers.0.mlp.experts.0.gate_proj.weight": "model-00001-of-00008.safetensors",
11
- "model.layers.0.mlp.experts.0.up_proj.weight": "model-00001-of-00008.safetensors",
12
- "model.layers.0.mlp.experts.1.down_proj.weight": "model-00001-of-00008.safetensors",
13
- "model.layers.0.mlp.experts.1.gate_proj.weight": "model-00001-of-00008.safetensors",
14
- "model.layers.0.mlp.experts.1.up_proj.weight": "model-00001-of-00008.safetensors",
15
- "model.layers.0.mlp.experts.2.down_proj.weight": "model-00002-of-00008.safetensors",
16
- "model.layers.0.mlp.experts.2.gate_proj.weight": "model-00002-of-00008.safetensors",
17
- "model.layers.0.mlp.experts.2.up_proj.weight": "model-00002-of-00008.safetensors",
18
- "model.layers.0.mlp.experts.3.down_proj.weight": "model-00002-of-00008.safetensors",
19
- "model.layers.0.mlp.experts.3.gate_proj.weight": "model-00002-of-00008.safetensors",
20
- "model.layers.0.mlp.experts.3.up_proj.weight": "model-00002-of-00008.safetensors",
21
- "model.layers.0.mlp.ffn_fallback.down_proj.weight": "model-00002-of-00008.safetensors",
22
- "model.layers.0.mlp.ffn_fallback.gate_proj.weight": "model-00002-of-00008.safetensors",
23
- "model.layers.0.mlp.ffn_fallback.up_proj.weight": "model-00002-of-00008.safetensors",
24
- "model.layers.0.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
25
- "model.layers.0.self_attn.k_norm.weight": "model-00001-of-00008.safetensors",
26
- "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00008.safetensors",
27
- "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00008.safetensors",
28
- "model.layers.0.self_attn.q_norm.weight": "model-00001-of-00008.safetensors",
29
- "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00008.safetensors",
30
- "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00008.safetensors",
31
- "model.layers.1.input_layernorm.weight": "model-00003-of-00008.safetensors",
32
- "model.layers.1.mlp.experts.0.down_proj.weight": "model-00002-of-00008.safetensors",
33
- "model.layers.1.mlp.experts.0.gate_proj.weight": "model-00002-of-00008.safetensors",
34
- "model.layers.1.mlp.experts.0.up_proj.weight": "model-00002-of-00008.safetensors",
35
- "model.layers.1.mlp.experts.1.down_proj.weight": "model-00003-of-00008.safetensors",
36
- "model.layers.1.mlp.experts.1.gate_proj.weight": "model-00002-of-00008.safetensors",
37
- "model.layers.1.mlp.experts.1.up_proj.weight": "model-00002-of-00008.safetensors",
38
- "model.layers.1.mlp.experts.2.down_proj.weight": "model-00003-of-00008.safetensors",
39
- "model.layers.1.mlp.experts.2.gate_proj.weight": "model-00003-of-00008.safetensors",
40
- "model.layers.1.mlp.experts.2.up_proj.weight": "model-00003-of-00008.safetensors",
41
- "model.layers.1.mlp.experts.3.down_proj.weight": "model-00003-of-00008.safetensors",
42
- "model.layers.1.mlp.experts.3.gate_proj.weight": "model-00003-of-00008.safetensors",
43
- "model.layers.1.mlp.experts.3.up_proj.weight": "model-00003-of-00008.safetensors",
44
- "model.layers.1.mlp.ffn_fallback.down_proj.weight": "model-00003-of-00008.safetensors",
45
- "model.layers.1.mlp.ffn_fallback.gate_proj.weight": "model-00003-of-00008.safetensors",
46
- "model.layers.1.mlp.ffn_fallback.up_proj.weight": "model-00003-of-00008.safetensors",
47
- "model.layers.1.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
48
- "model.layers.1.self_attn.k_norm.weight": "model-00002-of-00008.safetensors",
49
- "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00008.safetensors",
50
- "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00008.safetensors",
51
- "model.layers.1.self_attn.q_norm.weight": "model-00002-of-00008.safetensors",
52
- "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00008.safetensors",
53
- "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00008.safetensors",
54
- "model.layers.10.input_layernorm.weight": "model-00006-of-00008.safetensors",
55
- "model.layers.10.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
56
- "model.layers.10.mlp.gate_proj.weight": "model-00006-of-00008.safetensors",
57
- "model.layers.10.mlp.up_proj.weight": "model-00006-of-00008.safetensors",
58
- "model.layers.10.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
59
- "model.layers.10.self_attn.k_norm.weight": "model-00006-of-00008.safetensors",
60
- "model.layers.10.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
61
- "model.layers.10.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
62
- "model.layers.10.self_attn.q_norm.weight": "model-00006-of-00008.safetensors",
63
- "model.layers.10.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
64
- "model.layers.10.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
65
- "model.layers.11.input_layernorm.weight": "model-00006-of-00008.safetensors",
66
- "model.layers.11.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
67
- "model.layers.11.mlp.gate_proj.weight": "model-00006-of-00008.safetensors",
68
- "model.layers.11.mlp.up_proj.weight": "model-00006-of-00008.safetensors",
69
- "model.layers.11.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
70
- "model.layers.11.self_attn.k_norm.weight": "model-00006-of-00008.safetensors",
71
- "model.layers.11.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
72
- "model.layers.11.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
73
- "model.layers.11.self_attn.q_norm.weight": "model-00006-of-00008.safetensors",
74
- "model.layers.11.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
75
- "model.layers.11.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
76
- "model.layers.12.input_layernorm.weight": "model-00007-of-00008.safetensors",
77
- "model.layers.12.mlp.down_proj.weight": "model-00007-of-00008.safetensors",
78
- "model.layers.12.mlp.gate_proj.weight": "model-00006-of-00008.safetensors",
79
- "model.layers.12.mlp.up_proj.weight": "model-00006-of-00008.safetensors",
80
- "model.layers.12.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
81
- "model.layers.12.self_attn.k_norm.weight": "model-00006-of-00008.safetensors",
82
- "model.layers.12.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
83
- "model.layers.12.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
84
- "model.layers.12.self_attn.q_norm.weight": "model-00006-of-00008.safetensors",
85
- "model.layers.12.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
86
- "model.layers.12.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
87
- "model.layers.13.input_layernorm.weight": "model-00007-of-00008.safetensors",
88
- "model.layers.13.mlp.down_proj.weight": "model-00007-of-00008.safetensors",
89
- "model.layers.13.mlp.gate_proj.weight": "model-00007-of-00008.safetensors",
90
- "model.layers.13.mlp.up_proj.weight": "model-00007-of-00008.safetensors",
91
- "model.layers.13.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
92
- "model.layers.13.self_attn.k_norm.weight": "model-00007-of-00008.safetensors",
93
- "model.layers.13.self_attn.k_proj.weight": "model-00007-of-00008.safetensors",
94
- "model.layers.13.self_attn.o_proj.weight": "model-00007-of-00008.safetensors",
95
- "model.layers.13.self_attn.q_norm.weight": "model-00007-of-00008.safetensors",
96
- "model.layers.13.self_attn.q_proj.weight": "model-00007-of-00008.safetensors",
97
- "model.layers.13.self_attn.v_proj.weight": "model-00007-of-00008.safetensors",
98
- "model.layers.14.input_layernorm.weight": "model-00007-of-00008.safetensors",
99
- "model.layers.14.mlp.down_proj.weight": "model-00007-of-00008.safetensors",
100
- "model.layers.14.mlp.gate_proj.weight": "model-00007-of-00008.safetensors",
101
- "model.layers.14.mlp.up_proj.weight": "model-00007-of-00008.safetensors",
102
- "model.layers.14.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
103
- "model.layers.14.self_attn.k_norm.weight": "model-00007-of-00008.safetensors",
104
- "model.layers.14.self_attn.k_proj.weight": "model-00007-of-00008.safetensors",
105
- "model.layers.14.self_attn.o_proj.weight": "model-00007-of-00008.safetensors",
106
- "model.layers.14.self_attn.q_norm.weight": "model-00007-of-00008.safetensors",
107
- "model.layers.14.self_attn.q_proj.weight": "model-00007-of-00008.safetensors",
108
- "model.layers.14.self_attn.v_proj.weight": "model-00007-of-00008.safetensors",
109
- "model.layers.15.input_layernorm.weight": "model-00007-of-00008.safetensors",
110
- "model.layers.15.mlp.down_proj.weight": "model-00007-of-00008.safetensors",
111
- "model.layers.15.mlp.gate_proj.weight": "model-00007-of-00008.safetensors",
112
- "model.layers.15.mlp.up_proj.weight": "model-00007-of-00008.safetensors",
113
- "model.layers.15.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
114
- "model.layers.15.self_attn.k_norm.weight": "model-00007-of-00008.safetensors",
115
- "model.layers.15.self_attn.k_proj.weight": "model-00007-of-00008.safetensors",
116
- "model.layers.15.self_attn.o_proj.weight": "model-00007-of-00008.safetensors",
117
- "model.layers.15.self_attn.q_norm.weight": "model-00007-of-00008.safetensors",
118
- "model.layers.15.self_attn.q_proj.weight": "model-00007-of-00008.safetensors",
119
- "model.layers.15.self_attn.v_proj.weight": "model-00007-of-00008.safetensors",
120
- "model.layers.16.input_layernorm.weight": "model-00007-of-00008.safetensors",
121
- "model.layers.16.mlp.down_proj.weight": "model-00007-of-00008.safetensors",
122
- "model.layers.16.mlp.gate_proj.weight": "model-00007-of-00008.safetensors",
123
- "model.layers.16.mlp.up_proj.weight": "model-00007-of-00008.safetensors",
124
- "model.layers.16.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
125
- "model.layers.16.self_attn.k_norm.weight": "model-00007-of-00008.safetensors",
126
- "model.layers.16.self_attn.k_proj.weight": "model-00007-of-00008.safetensors",
127
- "model.layers.16.self_attn.o_proj.weight": "model-00007-of-00008.safetensors",
128
- "model.layers.16.self_attn.q_norm.weight": "model-00007-of-00008.safetensors",
129
- "model.layers.16.self_attn.q_proj.weight": "model-00007-of-00008.safetensors",
130
- "model.layers.16.self_attn.v_proj.weight": "model-00007-of-00008.safetensors",
131
- "model.layers.17.input_layernorm.weight": "model-00007-of-00008.safetensors",
132
- "model.layers.17.mlp.down_proj.weight": "model-00007-of-00008.safetensors",
133
- "model.layers.17.mlp.gate_proj.weight": "model-00007-of-00008.safetensors",
134
- "model.layers.17.mlp.up_proj.weight": "model-00007-of-00008.safetensors",
135
- "model.layers.17.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
136
- "model.layers.17.self_attn.k_norm.weight": "model-00007-of-00008.safetensors",
137
- "model.layers.17.self_attn.k_proj.weight": "model-00007-of-00008.safetensors",
138
- "model.layers.17.self_attn.o_proj.weight": "model-00007-of-00008.safetensors",
139
- "model.layers.17.self_attn.q_norm.weight": "model-00007-of-00008.safetensors",
140
- "model.layers.17.self_attn.q_proj.weight": "model-00007-of-00008.safetensors",
141
- "model.layers.17.self_attn.v_proj.weight": "model-00007-of-00008.safetensors",
142
- "model.layers.18.input_layernorm.weight": "model-00007-of-00008.safetensors",
143
- "model.layers.18.mlp.down_proj.weight": "model-00007-of-00008.safetensors",
144
- "model.layers.18.mlp.gate_proj.weight": "model-00007-of-00008.safetensors",
145
- "model.layers.18.mlp.up_proj.weight": "model-00007-of-00008.safetensors",
146
- "model.layers.18.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
147
- "model.layers.18.self_attn.k_norm.weight": "model-00007-of-00008.safetensors",
148
- "model.layers.18.self_attn.k_proj.weight": "model-00007-of-00008.safetensors",
149
- "model.layers.18.self_attn.o_proj.weight": "model-00007-of-00008.safetensors",
150
- "model.layers.18.self_attn.q_norm.weight": "model-00007-of-00008.safetensors",
151
- "model.layers.18.self_attn.q_proj.weight": "model-00007-of-00008.safetensors",
152
- "model.layers.18.self_attn.v_proj.weight": "model-00007-of-00008.safetensors",
153
- "model.layers.19.input_layernorm.weight": "model-00007-of-00008.safetensors",
154
- "model.layers.19.mlp.down_proj.weight": "model-00007-of-00008.safetensors",
155
- "model.layers.19.mlp.gate_proj.weight": "model-00007-of-00008.safetensors",
156
- "model.layers.19.mlp.up_proj.weight": "model-00007-of-00008.safetensors",
157
- "model.layers.19.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
158
- "model.layers.19.self_attn.k_norm.weight": "model-00007-of-00008.safetensors",
159
- "model.layers.19.self_attn.k_proj.weight": "model-00007-of-00008.safetensors",
160
- "model.layers.19.self_attn.o_proj.weight": "model-00007-of-00008.safetensors",
161
- "model.layers.19.self_attn.q_norm.weight": "model-00007-of-00008.safetensors",
162
- "model.layers.19.self_attn.q_proj.weight": "model-00007-of-00008.safetensors",
163
- "model.layers.19.self_attn.v_proj.weight": "model-00007-of-00008.safetensors",
164
- "model.layers.2.input_layernorm.weight": "model-00004-of-00008.safetensors",
165
- "model.layers.2.mlp.experts.0.down_proj.weight": "model-00003-of-00008.safetensors",
166
- "model.layers.2.mlp.experts.0.gate_proj.weight": "model-00003-of-00008.safetensors",
167
- "model.layers.2.mlp.experts.0.up_proj.weight": "model-00003-of-00008.safetensors",
168
- "model.layers.2.mlp.experts.1.down_proj.weight": "model-00004-of-00008.safetensors",
169
- "model.layers.2.mlp.experts.1.gate_proj.weight": "model-00003-of-00008.safetensors",
170
- "model.layers.2.mlp.experts.1.up_proj.weight": "model-00004-of-00008.safetensors",
171
- "model.layers.2.mlp.experts.2.down_proj.weight": "model-00004-of-00008.safetensors",
172
- "model.layers.2.mlp.experts.2.gate_proj.weight": "model-00004-of-00008.safetensors",
173
- "model.layers.2.mlp.experts.2.up_proj.weight": "model-00004-of-00008.safetensors",
174
- "model.layers.2.mlp.experts.3.down_proj.weight": "model-00004-of-00008.safetensors",
175
- "model.layers.2.mlp.experts.3.gate_proj.weight": "model-00004-of-00008.safetensors",
176
- "model.layers.2.mlp.experts.3.up_proj.weight": "model-00004-of-00008.safetensors",
177
- "model.layers.2.mlp.ffn_fallback.down_proj.weight": "model-00004-of-00008.safetensors",
178
- "model.layers.2.mlp.ffn_fallback.gate_proj.weight": "model-00004-of-00008.safetensors",
179
- "model.layers.2.mlp.ffn_fallback.up_proj.weight": "model-00004-of-00008.safetensors",
180
- "model.layers.2.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
181
- "model.layers.2.self_attn.k_norm.weight": "model-00003-of-00008.safetensors",
182
- "model.layers.2.self_attn.k_proj.weight": "model-00003-of-00008.safetensors",
183
- "model.layers.2.self_attn.o_proj.weight": "model-00003-of-00008.safetensors",
184
- "model.layers.2.self_attn.q_norm.weight": "model-00003-of-00008.safetensors",
185
- "model.layers.2.self_attn.q_proj.weight": "model-00003-of-00008.safetensors",
186
- "model.layers.2.self_attn.v_proj.weight": "model-00003-of-00008.safetensors",
187
- "model.layers.20.input_layernorm.weight": "model-00008-of-00008.safetensors",
188
- "model.layers.20.mlp.down_proj.weight": "model-00008-of-00008.safetensors",
189
- "model.layers.20.mlp.gate_proj.weight": "model-00008-of-00008.safetensors",
190
- "model.layers.20.mlp.up_proj.weight": "model-00008-of-00008.safetensors",
191
- "model.layers.20.post_attention_layernorm.weight": "model-00008-of-00008.safetensors",
192
- "model.layers.20.self_attn.k_norm.weight": "model-00008-of-00008.safetensors",
193
- "model.layers.20.self_attn.k_proj.weight": "model-00007-of-00008.safetensors",
194
- "model.layers.20.self_attn.o_proj.weight": "model-00008-of-00008.safetensors",
195
- "model.layers.20.self_attn.q_norm.weight": "model-00008-of-00008.safetensors",
196
- "model.layers.20.self_attn.q_proj.weight": "model-00007-of-00008.safetensors",
197
- "model.layers.20.self_attn.v_proj.weight": "model-00007-of-00008.safetensors",
198
- "model.layers.21.input_layernorm.weight": "model-00008-of-00008.safetensors",
199
- "model.layers.21.mlp.down_proj.weight": "model-00008-of-00008.safetensors",
200
- "model.layers.21.mlp.gate_proj.weight": "model-00008-of-00008.safetensors",
201
- "model.layers.21.mlp.up_proj.weight": "model-00008-of-00008.safetensors",
202
- "model.layers.21.post_attention_layernorm.weight": "model-00008-of-00008.safetensors",
203
- "model.layers.21.self_attn.k_norm.weight": "model-00008-of-00008.safetensors",
204
- "model.layers.21.self_attn.k_proj.weight": "model-00008-of-00008.safetensors",
205
- "model.layers.21.self_attn.o_proj.weight": "model-00008-of-00008.safetensors",
206
- "model.layers.21.self_attn.q_norm.weight": "model-00008-of-00008.safetensors",
207
- "model.layers.21.self_attn.q_proj.weight": "model-00008-of-00008.safetensors",
208
- "model.layers.21.self_attn.v_proj.weight": "model-00008-of-00008.safetensors",
209
- "model.layers.22.input_layernorm.weight": "model-00008-of-00008.safetensors",
210
- "model.layers.22.mlp.down_proj.weight": "model-00008-of-00008.safetensors",
211
- "model.layers.22.mlp.gate_proj.weight": "model-00008-of-00008.safetensors",
212
- "model.layers.22.mlp.up_proj.weight": "model-00008-of-00008.safetensors",
213
- "model.layers.22.post_attention_layernorm.weight": "model-00008-of-00008.safetensors",
214
- "model.layers.22.self_attn.k_norm.weight": "model-00008-of-00008.safetensors",
215
- "model.layers.22.self_attn.k_proj.weight": "model-00008-of-00008.safetensors",
216
- "model.layers.22.self_attn.o_proj.weight": "model-00008-of-00008.safetensors",
217
- "model.layers.22.self_attn.q_norm.weight": "model-00008-of-00008.safetensors",
218
- "model.layers.22.self_attn.q_proj.weight": "model-00008-of-00008.safetensors",
219
- "model.layers.22.self_attn.v_proj.weight": "model-00008-of-00008.safetensors",
220
- "model.layers.23.input_layernorm.weight": "model-00008-of-00008.safetensors",
221
- "model.layers.23.mlp.down_proj.weight": "model-00008-of-00008.safetensors",
222
- "model.layers.23.mlp.gate_proj.weight": "model-00008-of-00008.safetensors",
223
- "model.layers.23.mlp.up_proj.weight": "model-00008-of-00008.safetensors",
224
- "model.layers.23.post_attention_layernorm.weight": "model-00008-of-00008.safetensors",
225
- "model.layers.23.self_attn.k_norm.weight": "model-00008-of-00008.safetensors",
226
- "model.layers.23.self_attn.k_proj.weight": "model-00008-of-00008.safetensors",
227
- "model.layers.23.self_attn.o_proj.weight": "model-00008-of-00008.safetensors",
228
- "model.layers.23.self_attn.q_norm.weight": "model-00008-of-00008.safetensors",
229
- "model.layers.23.self_attn.q_proj.weight": "model-00008-of-00008.safetensors",
230
- "model.layers.23.self_attn.v_proj.weight": "model-00008-of-00008.safetensors",
231
- "model.layers.3.input_layernorm.weight": "model-00005-of-00008.safetensors",
232
- "model.layers.3.mlp.experts.0.down_proj.weight": "model-00004-of-00008.safetensors",
233
- "model.layers.3.mlp.experts.0.gate_proj.weight": "model-00004-of-00008.safetensors",
234
- "model.layers.3.mlp.experts.0.up_proj.weight": "model-00004-of-00008.safetensors",
235
- "model.layers.3.mlp.experts.1.down_proj.weight": "model-00005-of-00008.safetensors",
236
- "model.layers.3.mlp.experts.1.gate_proj.weight": "model-00005-of-00008.safetensors",
237
- "model.layers.3.mlp.experts.1.up_proj.weight": "model-00005-of-00008.safetensors",
238
- "model.layers.3.mlp.experts.2.down_proj.weight": "model-00005-of-00008.safetensors",
239
- "model.layers.3.mlp.experts.2.gate_proj.weight": "model-00005-of-00008.safetensors",
240
- "model.layers.3.mlp.experts.2.up_proj.weight": "model-00005-of-00008.safetensors",
241
- "model.layers.3.mlp.experts.3.down_proj.weight": "model-00005-of-00008.safetensors",
242
- "model.layers.3.mlp.experts.3.gate_proj.weight": "model-00005-of-00008.safetensors",
243
- "model.layers.3.mlp.experts.3.up_proj.weight": "model-00005-of-00008.safetensors",
244
- "model.layers.3.mlp.ffn_fallback.down_proj.weight": "model-00005-of-00008.safetensors",
245
- "model.layers.3.mlp.ffn_fallback.gate_proj.weight": "model-00005-of-00008.safetensors",
246
- "model.layers.3.mlp.ffn_fallback.up_proj.weight": "model-00005-of-00008.safetensors",
247
- "model.layers.3.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
248
- "model.layers.3.self_attn.k_norm.weight": "model-00004-of-00008.safetensors",
249
- "model.layers.3.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
250
- "model.layers.3.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
251
- "model.layers.3.self_attn.q_norm.weight": "model-00004-of-00008.safetensors",
252
- "model.layers.3.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
253
- "model.layers.3.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
254
- "model.layers.4.input_layernorm.weight": "model-00005-of-00008.safetensors",
255
- "model.layers.4.mlp.down_proj.weight": "model-00005-of-00008.safetensors",
256
- "model.layers.4.mlp.gate_proj.weight": "model-00005-of-00008.safetensors",
257
- "model.layers.4.mlp.up_proj.weight": "model-00005-of-00008.safetensors",
258
- "model.layers.4.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
259
- "model.layers.4.self_attn.k_norm.weight": "model-00005-of-00008.safetensors",
260
- "model.layers.4.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
261
- "model.layers.4.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
262
- "model.layers.4.self_attn.q_norm.weight": "model-00005-of-00008.safetensors",
263
- "model.layers.4.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
264
- "model.layers.4.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
265
- "model.layers.5.input_layernorm.weight": "model-00006-of-00008.safetensors",
266
- "model.layers.5.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
267
- "model.layers.5.mlp.gate_proj.weight": "model-00005-of-00008.safetensors",
268
- "model.layers.5.mlp.up_proj.weight": "model-00006-of-00008.safetensors",
269
- "model.layers.5.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
270
- "model.layers.5.self_attn.k_norm.weight": "model-00005-of-00008.safetensors",
271
- "model.layers.5.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
272
- "model.layers.5.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
273
- "model.layers.5.self_attn.q_norm.weight": "model-00005-of-00008.safetensors",
274
- "model.layers.5.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
275
- "model.layers.5.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
276
- "model.layers.6.input_layernorm.weight": "model-00006-of-00008.safetensors",
277
- "model.layers.6.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
278
- "model.layers.6.mlp.gate_proj.weight": "model-00006-of-00008.safetensors",
279
- "model.layers.6.mlp.up_proj.weight": "model-00006-of-00008.safetensors",
280
- "model.layers.6.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
281
- "model.layers.6.self_attn.k_norm.weight": "model-00006-of-00008.safetensors",
282
- "model.layers.6.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
283
- "model.layers.6.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
284
- "model.layers.6.self_attn.q_norm.weight": "model-00006-of-00008.safetensors",
285
- "model.layers.6.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
286
- "model.layers.6.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
287
- "model.layers.7.input_layernorm.weight": "model-00006-of-00008.safetensors",
288
- "model.layers.7.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
289
- "model.layers.7.mlp.gate_proj.weight": "model-00006-of-00008.safetensors",
290
- "model.layers.7.mlp.up_proj.weight": "model-00006-of-00008.safetensors",
291
- "model.layers.7.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
292
- "model.layers.7.self_attn.k_norm.weight": "model-00006-of-00008.safetensors",
293
- "model.layers.7.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
294
- "model.layers.7.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
295
- "model.layers.7.self_attn.q_norm.weight": "model-00006-of-00008.safetensors",
296
- "model.layers.7.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
297
- "model.layers.7.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
298
- "model.layers.8.input_layernorm.weight": "model-00006-of-00008.safetensors",
299
- "model.layers.8.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
300
- "model.layers.8.mlp.gate_proj.weight": "model-00006-of-00008.safetensors",
301
- "model.layers.8.mlp.up_proj.weight": "model-00006-of-00008.safetensors",
302
- "model.layers.8.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
303
- "model.layers.8.self_attn.k_norm.weight": "model-00006-of-00008.safetensors",
304
- "model.layers.8.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
305
- "model.layers.8.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
306
- "model.layers.8.self_attn.q_norm.weight": "model-00006-of-00008.safetensors",
307
- "model.layers.8.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
308
- "model.layers.8.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
309
- "model.layers.9.input_layernorm.weight": "model-00006-of-00008.safetensors",
310
- "model.layers.9.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
311
- "model.layers.9.mlp.gate_proj.weight": "model-00006-of-00008.safetensors",
312
- "model.layers.9.mlp.up_proj.weight": "model-00006-of-00008.safetensors",
313
- "model.layers.9.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
314
- "model.layers.9.self_attn.k_norm.weight": "model-00006-of-00008.safetensors",
315
- "model.layers.9.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
316
- "model.layers.9.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
317
- "model.layers.9.self_attn.q_norm.weight": "model-00006-of-00008.safetensors",
318
- "model.layers.9.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
319
- "model.layers.9.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
320
- "model.norm.weight": "model-00008-of-00008.safetensors",
321
- "router.gate.bias": "model-00008-of-00008.safetensors",
322
- "router.gate.weight": "model-00008-of-00008.safetensors"
323
  }
324
  }
 
4
  "total_size": 11001832464
5
  },
6
  "weight_map": {
7
+ "model.embed_tokens.weight": "model-00001-of-00003.safetensors",
8
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
9
+ "model.layers.0.mlp.experts.0.down_proj.weight": "model-00001-of-00003.safetensors",
10
+ "model.layers.0.mlp.experts.0.gate_proj.weight": "model-00001-of-00003.safetensors",
11
+ "model.layers.0.mlp.experts.0.up_proj.weight": "model-00001-of-00003.safetensors",
12
+ "model.layers.0.mlp.experts.1.down_proj.weight": "model-00001-of-00003.safetensors",
13
+ "model.layers.0.mlp.experts.1.gate_proj.weight": "model-00001-of-00003.safetensors",
14
+ "model.layers.0.mlp.experts.1.up_proj.weight": "model-00001-of-00003.safetensors",
15
+ "model.layers.0.mlp.experts.2.down_proj.weight": "model-00001-of-00003.safetensors",
16
+ "model.layers.0.mlp.experts.2.gate_proj.weight": "model-00001-of-00003.safetensors",
17
+ "model.layers.0.mlp.experts.2.up_proj.weight": "model-00001-of-00003.safetensors",
18
+ "model.layers.0.mlp.experts.3.down_proj.weight": "model-00001-of-00003.safetensors",
19
+ "model.layers.0.mlp.experts.3.gate_proj.weight": "model-00001-of-00003.safetensors",
20
+ "model.layers.0.mlp.experts.3.up_proj.weight": "model-00001-of-00003.safetensors",
21
+ "model.layers.0.mlp.ffn_fallback.down_proj.weight": "model-00001-of-00003.safetensors",
22
+ "model.layers.0.mlp.ffn_fallback.gate_proj.weight": "model-00001-of-00003.safetensors",
23
+ "model.layers.0.mlp.ffn_fallback.up_proj.weight": "model-00001-of-00003.safetensors",
24
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
25
+ "model.layers.0.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
26
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
27
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
28
+ "model.layers.0.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
29
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
30
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
31
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
32
+ "model.layers.1.mlp.experts.0.down_proj.weight": "model-00001-of-00003.safetensors",
33
+ "model.layers.1.mlp.experts.0.gate_proj.weight": "model-00001-of-00003.safetensors",
34
+ "model.layers.1.mlp.experts.0.up_proj.weight": "model-00001-of-00003.safetensors",
35
+ "model.layers.1.mlp.experts.1.down_proj.weight": "model-00001-of-00003.safetensors",
36
+ "model.layers.1.mlp.experts.1.gate_proj.weight": "model-00001-of-00003.safetensors",
37
+ "model.layers.1.mlp.experts.1.up_proj.weight": "model-00001-of-00003.safetensors",
38
+ "model.layers.1.mlp.experts.2.down_proj.weight": "model-00001-of-00003.safetensors",
39
+ "model.layers.1.mlp.experts.2.gate_proj.weight": "model-00001-of-00003.safetensors",
40
+ "model.layers.1.mlp.experts.2.up_proj.weight": "model-00001-of-00003.safetensors",
41
+ "model.layers.1.mlp.experts.3.down_proj.weight": "model-00001-of-00003.safetensors",
42
+ "model.layers.1.mlp.experts.3.gate_proj.weight": "model-00001-of-00003.safetensors",
43
+ "model.layers.1.mlp.experts.3.up_proj.weight": "model-00001-of-00003.safetensors",
44
+ "model.layers.1.mlp.ffn_fallback.down_proj.weight": "model-00001-of-00003.safetensors",
45
+ "model.layers.1.mlp.ffn_fallback.gate_proj.weight": "model-00001-of-00003.safetensors",
46
+ "model.layers.1.mlp.ffn_fallback.up_proj.weight": "model-00001-of-00003.safetensors",
47
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
48
+ "model.layers.1.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
49
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
50
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
51
+ "model.layers.1.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
52
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
53
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
54
+ "model.layers.10.input_layernorm.weight": "model-00002-of-00003.safetensors",
55
+ "model.layers.10.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
56
+ "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
57
+ "model.layers.10.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
58
+ "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
59
+ "model.layers.10.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
60
+ "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
61
+ "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
62
+ "model.layers.10.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
63
+ "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
64
+ "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
65
+ "model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors",
66
+ "model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
67
+ "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
68
+ "model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
69
+ "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
70
+ "model.layers.11.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
71
+ "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
72
+ "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
73
+ "model.layers.11.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
74
+ "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
75
+ "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
76
+ "model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
77
+ "model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
78
+ "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
79
+ "model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
80
+ "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
81
+ "model.layers.12.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
82
+ "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
83
+ "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
84
+ "model.layers.12.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
85
+ "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
86
+ "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
87
+ "model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
88
+ "model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
89
+ "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
90
+ "model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
91
+ "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
92
+ "model.layers.13.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
93
+ "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
94
+ "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
95
+ "model.layers.13.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
96
+ "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
97
+ "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
98
+ "model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
99
+ "model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
100
+ "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
101
+ "model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
102
+ "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
103
+ "model.layers.14.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
104
+ "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
105
+ "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
106
+ "model.layers.14.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
107
+ "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
108
+ "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
109
+ "model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
110
+ "model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
111
+ "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
112
+ "model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
113
+ "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
114
+ "model.layers.15.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
115
+ "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
116
+ "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
117
+ "model.layers.15.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
118
+ "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
119
+ "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
120
+ "model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
121
+ "model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
122
+ "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
123
+ "model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
124
+ "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
125
+ "model.layers.16.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
126
+ "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
127
+ "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
128
+ "model.layers.16.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
129
+ "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
130
+ "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
131
+ "model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
132
+ "model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
133
+ "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
134
+ "model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
135
+ "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
136
+ "model.layers.17.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
137
+ "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
138
+ "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
139
+ "model.layers.17.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
140
+ "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
141
+ "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
142
+ "model.layers.18.input_layernorm.weight": "model-00003-of-00003.safetensors",
143
+ "model.layers.18.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
144
+ "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
145
+ "model.layers.18.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
146
+ "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
147
+ "model.layers.18.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
148
+ "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
149
+ "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
150
+ "model.layers.18.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
151
+ "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
152
+ "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
153
+ "model.layers.19.input_layernorm.weight": "model-00003-of-00003.safetensors",
154
+ "model.layers.19.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
155
+ "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
156
+ "model.layers.19.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
157
+ "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
158
+ "model.layers.19.self_attn.k_norm.weight": "model-00003-of-00003.safetensors",
159
+ "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
160
+ "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
161
+ "model.layers.19.self_attn.q_norm.weight": "model-00003-of-00003.safetensors",
162
+ "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
163
+ "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
164
+ "model.layers.2.input_layernorm.weight": "model-00002-of-00003.safetensors",
165
+ "model.layers.2.mlp.experts.0.down_proj.weight": "model-00001-of-00003.safetensors",
166
+ "model.layers.2.mlp.experts.0.gate_proj.weight": "model-00001-of-00003.safetensors",
167
+ "model.layers.2.mlp.experts.0.up_proj.weight": "model-00001-of-00003.safetensors",
168
+ "model.layers.2.mlp.experts.1.down_proj.weight": "model-00001-of-00003.safetensors",
169
+ "model.layers.2.mlp.experts.1.gate_proj.weight": "model-00001-of-00003.safetensors",
170
+ "model.layers.2.mlp.experts.1.up_proj.weight": "model-00001-of-00003.safetensors",
171
+ "model.layers.2.mlp.experts.2.down_proj.weight": "model-00001-of-00003.safetensors",
172
+ "model.layers.2.mlp.experts.2.gate_proj.weight": "model-00001-of-00003.safetensors",
173
+ "model.layers.2.mlp.experts.2.up_proj.weight": "model-00001-of-00003.safetensors",
174
+ "model.layers.2.mlp.experts.3.down_proj.weight": "model-00002-of-00003.safetensors",
175
+ "model.layers.2.mlp.experts.3.gate_proj.weight": "model-00001-of-00003.safetensors",
176
+ "model.layers.2.mlp.experts.3.up_proj.weight": "model-00002-of-00003.safetensors",
177
+ "model.layers.2.mlp.ffn_fallback.down_proj.weight": "model-00002-of-00003.safetensors",
178
+ "model.layers.2.mlp.ffn_fallback.gate_proj.weight": "model-00002-of-00003.safetensors",
179
+ "model.layers.2.mlp.ffn_fallback.up_proj.weight": "model-00002-of-00003.safetensors",
180
+ "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
181
+ "model.layers.2.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
182
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
183
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
184
+ "model.layers.2.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
185
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
186
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
187
+ "model.layers.20.input_layernorm.weight": "model-00003-of-00003.safetensors",
188
+ "model.layers.20.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
189
+ "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
190
+ "model.layers.20.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
191
+ "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
192
+ "model.layers.20.self_attn.k_norm.weight": "model-00003-of-00003.safetensors",
193
+ "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
194
+ "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
195
+ "model.layers.20.self_attn.q_norm.weight": "model-00003-of-00003.safetensors",
196
+ "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
197
+ "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
198
+ "model.layers.21.input_layernorm.weight": "model-00003-of-00003.safetensors",
199
+ "model.layers.21.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
200
+ "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
201
+ "model.layers.21.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
202
+ "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
203
+ "model.layers.21.self_attn.k_norm.weight": "model-00003-of-00003.safetensors",
204
+ "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
205
+ "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
206
+ "model.layers.21.self_attn.q_norm.weight": "model-00003-of-00003.safetensors",
207
+ "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
208
+ "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
209
+ "model.layers.22.input_layernorm.weight": "model-00003-of-00003.safetensors",
210
+ "model.layers.22.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
211
+ "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
212
+ "model.layers.22.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
213
+ "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
214
+ "model.layers.22.self_attn.k_norm.weight": "model-00003-of-00003.safetensors",
215
+ "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
216
+ "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
217
+ "model.layers.22.self_attn.q_norm.weight": "model-00003-of-00003.safetensors",
218
+ "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
219
+ "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
220
+ "model.layers.23.input_layernorm.weight": "model-00003-of-00003.safetensors",
221
+ "model.layers.23.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
222
+ "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
223
+ "model.layers.23.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
224
+ "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
225
+ "model.layers.23.self_attn.k_norm.weight": "model-00003-of-00003.safetensors",
226
+ "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
227
+ "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
228
+ "model.layers.23.self_attn.q_norm.weight": "model-00003-of-00003.safetensors",
229
+ "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
230
+ "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
231
+ "model.layers.3.input_layernorm.weight": "model-00002-of-00003.safetensors",
232
+ "model.layers.3.mlp.experts.0.down_proj.weight": "model-00002-of-00003.safetensors",
233
+ "model.layers.3.mlp.experts.0.gate_proj.weight": "model-00002-of-00003.safetensors",
234
+ "model.layers.3.mlp.experts.0.up_proj.weight": "model-00002-of-00003.safetensors",
235
+ "model.layers.3.mlp.experts.1.down_proj.weight": "model-00002-of-00003.safetensors",
236
+ "model.layers.3.mlp.experts.1.gate_proj.weight": "model-00002-of-00003.safetensors",
237
+ "model.layers.3.mlp.experts.1.up_proj.weight": "model-00002-of-00003.safetensors",
238
+ "model.layers.3.mlp.experts.2.down_proj.weight": "model-00002-of-00003.safetensors",
239
+ "model.layers.3.mlp.experts.2.gate_proj.weight": "model-00002-of-00003.safetensors",
240
+ "model.layers.3.mlp.experts.2.up_proj.weight": "model-00002-of-00003.safetensors",
241
+ "model.layers.3.mlp.experts.3.down_proj.weight": "model-00002-of-00003.safetensors",
242
+ "model.layers.3.mlp.experts.3.gate_proj.weight": "model-00002-of-00003.safetensors",
243
+ "model.layers.3.mlp.experts.3.up_proj.weight": "model-00002-of-00003.safetensors",
244
+ "model.layers.3.mlp.ffn_fallback.down_proj.weight": "model-00002-of-00003.safetensors",
245
+ "model.layers.3.mlp.ffn_fallback.gate_proj.weight": "model-00002-of-00003.safetensors",
246
+ "model.layers.3.mlp.ffn_fallback.up_proj.weight": "model-00002-of-00003.safetensors",
247
+ "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
248
+ "model.layers.3.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
249
+ "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
250
+ "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
251
+ "model.layers.3.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
252
+ "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
253
+ "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
254
+ "model.layers.4.input_layernorm.weight": "model-00002-of-00003.safetensors",
255
+ "model.layers.4.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
256
+ "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
257
+ "model.layers.4.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
258
+ "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
259
+ "model.layers.4.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
260
+ "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
261
+ "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
262
+ "model.layers.4.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
263
+ "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
264
+ "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
265
+ "model.layers.5.input_layernorm.weight": "model-00002-of-00003.safetensors",
266
+ "model.layers.5.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
267
+ "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
268
+ "model.layers.5.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
269
+ "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
270
+ "model.layers.5.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
271
+ "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
272
+ "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
273
+ "model.layers.5.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
274
+ "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
275
+ "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
276
+ "model.layers.6.input_layernorm.weight": "model-00002-of-00003.safetensors",
277
+ "model.layers.6.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
278
+ "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
279
+ "model.layers.6.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
280
+ "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
281
+ "model.layers.6.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
282
+ "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
283
+ "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
284
+ "model.layers.6.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
285
+ "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
286
+ "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
287
+ "model.layers.7.input_layernorm.weight": "model-00002-of-00003.safetensors",
288
+ "model.layers.7.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
289
+ "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
290
+ "model.layers.7.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
291
+ "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
292
+ "model.layers.7.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
293
+ "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
294
+ "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
295
+ "model.layers.7.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
296
+ "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
297
+ "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
298
+ "model.layers.8.input_layernorm.weight": "model-00002-of-00003.safetensors",
299
+ "model.layers.8.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
300
+ "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
301
+ "model.layers.8.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
302
+ "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
303
+ "model.layers.8.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
304
+ "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
305
+ "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
306
+ "model.layers.8.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
307
+ "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
308
+ "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
309
+ "model.layers.9.input_layernorm.weight": "model-00002-of-00003.safetensors",
310
+ "model.layers.9.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
311
+ "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
312
+ "model.layers.9.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
313
+ "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
314
+ "model.layers.9.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
315
+ "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
316
+ "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
317
+ "model.layers.9.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
318
+ "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
319
+ "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
320
+ "model.norm.weight": "model-00003-of-00003.safetensors",
321
+ "router.gate.bias": "model-00003-of-00003.safetensors",
322
+ "router.gate.weight": "model-00003-of-00003.safetensors"
323
  }
324
  }
special_tokens_map.json CHANGED
@@ -22,7 +22,7 @@
22
  "single_word": false
23
  },
24
  "pad_token": {
25
- "content": "<|vision_pad|>",
26
  "lstrip": false,
27
  "normalized": false,
28
  "rstrip": false,
 
22
  "single_word": false
23
  },
24
  "pad_token": {
25
+ "content": "<|endoftext|>",
26
  "lstrip": false,
27
  "normalized": false,
28
  "rstrip": false,
tokenizer_config.json CHANGED
@@ -231,9 +231,8 @@
231
  "eos_token": "<|im_end|>",
232
  "errors": "replace",
233
  "extra_special_tokens": {},
234
- "model_max_length": 262144,
235
- "pad_token": "<|vision_pad|>",
236
- "padding_side": "left",
237
  "split_special_tokens": false,
238
  "tokenizer_class": "Qwen2Tokenizer",
239
  "unk_token": null
 
231
  "eos_token": "<|im_end|>",
232
  "errors": "replace",
233
  "extra_special_tokens": {},
234
+ "model_max_length": 1010000,
235
+ "pad_token": "<|endoftext|>",
 
236
  "split_special_tokens": false,
237
  "tokenizer_class": "Qwen2Tokenizer",
238
  "unk_token": null