Hugging Face's logo

FINAL-Bench
/
Darwin-36B-Opus

Text Generation
Transformers
Safetensors
qwen3_5_moe_text
darwin
darwin-v7
evolutionary-merge
reasoning
advanced-reasoning
chain-of-thought
thinking
qwen3.6
qwen
Mixture of Experts
mixture-of-experts
claude-opus
distillation
gpqa
benchmark
open-source
apache-2.0
hybrid-vigor
proto-agi
vidraft
Eval Results
conversational
Eval Results (legacy)
Model card Files
xet
 Community
7
SeaWolf-AI commited on
Commit
e56adcf
·
verified ·
1 Parent(s): 716148d

Darwin-36B-Opus: Qwen3.6-35B-A3B x hesamation Opus (SLERP merge, proxy 0.8403)

Browse files
Files changed (38) hide show
  1. .gitattributes +2 -0
  2. chat_template.jinja +154 -0
  3. config.json +96 -0
  4. darwin_v6_report.json +69 -0
  5. generation_config.json +12 -0
  6. merges.txt +0 -0
  7. model-00001-of-00026.safetensors +3 -0
  8. model-00002-of-00026.safetensors +3 -0
  9. model-00003-of-00026.safetensors +3 -0
  10. model-00004-of-00026.safetensors +3 -0
  11. model-00005-of-00026.safetensors +3 -0
  12. model-00006-of-00026.safetensors +3 -0
  13. model-00007-of-00026.safetensors +3 -0
  14. model-00008-of-00026.safetensors +3 -0
  15. model-00009-of-00026.safetensors +3 -0
  16. model-00010-of-00026.safetensors +3 -0
  17. model-00011-of-00026.safetensors +3 -0
  18. model-00012-of-00026.safetensors +3 -0
  19. model-00013-of-00026.safetensors +3 -0
  20. model-00014-of-00026.safetensors +3 -0
  21. model-00015-of-00026.safetensors +3 -0
  22. model-00016-of-00026.safetensors +3 -0
  23. model-00017-of-00026.safetensors +3 -0
  24. model-00018-of-00026.safetensors +3 -0
  25. model-00019-of-00026.safetensors +3 -0
  26. model-00020-of-00026.safetensors +3 -0
  27. model-00021-of-00026.safetensors +3 -0
  28. model-00022-of-00026.safetensors +3 -0
  29. model-00023-of-00026.safetensors +3 -0
  30. model-00024-of-00026.safetensors +3 -0
  31. model-00025-of-00026.safetensors +3 -0
  32. model-00026-of-00026.safetensors +3 -0
  33. model.safetensors.index.json +1052 -0
  34. parent_comparison.png +3 -0
  35. prescription_ratios.png +0 -0
  36. tokenizer.json +3 -0
  37. tokenizer_config.json +31 -0
  38. vocab.json +0 -0
.gitattributes CHANGED
@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ parent_comparison.png filter=lfs diff=lfs merge=lfs -text
37
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
chat_template.jinja ADDED
@@ -0,0 +1,154 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {%- set image_count = namespace(value=0) %}
2
+ {%- set video_count = namespace(value=0) %}
3
+ {%- macro render_content(content, do_vision_count, is_system_content=false) %}
4
+ {%- if content is string %}
5
+ {{- content }}
6
+ {%- elif content is iterable and content is not mapping %}
7
+ {%- for item in content %}
8
+ {%- if 'image' in item or 'image_url' in item or item.type == 'image' %}
9
+ {%- if is_system_content %}
10
+ {{- raise_exception('System message cannot contain images.') }}
11
+ {%- endif %}
12
+ {%- if do_vision_count %}
13
+ {%- set image_count.value = image_count.value + 1 %}
14
+ {%- endif %}
15
+ {%- if add_vision_id %}
16
+ {{- 'Picture ' ~ image_count.value ~ ': ' }}
17
+ {%- endif %}
18
+ {{- '<|vision_start|><|image_pad|><|vision_end|>' }}
19
+ {%- elif 'video' in item or item.type == 'video' %}
20
+ {%- if is_system_content %}
21
+ {{- raise_exception('System message cannot contain videos.') }}
22
+ {%- endif %}
23
+ {%- if do_vision_count %}
24
+ {%- set video_count.value = video_count.value + 1 %}
25
+ {%- endif %}
26
+ {%- if add_vision_id %}
27
+ {{- 'Video ' ~ video_count.value ~ ': ' }}
28
+ {%- endif %}
29
+ {{- '<|vision_start|><|video_pad|><|vision_end|>' }}
30
+ {%- elif 'text' in item %}
31
+ {{- item.text }}
32
+ {%- else %}
33
+ {{- raise_exception('Unexpected item type in content.') }}
34
+ {%- endif %}
35
+ {%- endfor %}
36
+ {%- elif content is none or content is undefined %}
37
+ {{- '' }}
38
+ {%- else %}
39
+ {{- raise_exception('Unexpected content type.') }}
40
+ {%- endif %}
41
+ {%- endmacro %}
42
+ {%- if not messages %}
43
+ {{- raise_exception('No messages provided.') }}
44
+ {%- endif %}
45
+ {%- if tools and tools is iterable and tools is not mapping %}
46
+ {{- '<|im_start|>system\n' }}
47
+ {{- "# Tools\n\nYou have access to the following functions:\n\n<tools>" }}
48
+ {%- for tool in tools %}
49
+ {{- "\n" }}
50
+ {{- tool | tojson }}
51
+ {%- endfor %}
52
+ {{- "\n</tools>" }}
53
+ {{- '\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n<tool_call>\n<function=example_function_name>\n<parameter=example_parameter_1>\nvalue_1\n</parameter>\n<parameter=example_parameter_2>\nThis is the value for the second parameter\nthat can span\nmultiple lines\n</parameter>\n</function>\n</tool_call>\n\n<IMPORTANT>\nReminder:\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\n- Required parameters MUST be specified\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\n</IMPORTANT>' }}
54
+ {%- if messages[0].role == 'system' %}
55
+ {%- set content = render_content(messages[0].content, false, true)|trim %}
56
+ {%- if content %}
57
+ {{- '\n\n' + content }}
58
+ {%- endif %}
59
+ {%- endif %}
60
+ {{- '<|im_end|>\n' }}
61
+ {%- else %}
62
+ {%- if messages[0].role == 'system' %}
63
+ {%- set content = render_content(messages[0].content, false, true)|trim %}
64
+ {{- '<|im_start|>system\n' + content + '<|im_end|>\n' }}
65
+ {%- endif %}
66
+ {%- endif %}
67
+ {%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
68
+ {%- for message in messages[::-1] %}
69
+ {%- set index = (messages|length - 1) - loop.index0 %}
70
+ {%- if ns.multi_step_tool and message.role == "user" %}
71
+ {%- set content = render_content(message.content, false)|trim %}
72
+ {%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}
73
+ {%- set ns.multi_step_tool = false %}
74
+ {%- set ns.last_query_index = index %}
75
+ {%- endif %}
76
+ {%- endif %}
77
+ {%- endfor %}
78
+ {%- if ns.multi_step_tool %}
79
+ {{- raise_exception('No user query found in messages.') }}
80
+ {%- endif %}
81
+ {%- for message in messages %}
82
+ {%- set content = render_content(message.content, true)|trim %}
83
+ {%- if message.role == "system" %}
84
+ {%- if not loop.first %}
85
+ {{- raise_exception('System message must be at the beginning.') }}
86
+ {%- endif %}
87
+ {%- elif message.role == "user" %}
88
+ {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
89
+ {%- elif message.role == "assistant" %}
90
+ {%- set reasoning_content = '' %}
91
+ {%- if message.reasoning_content is string %}
92
+ {%- set reasoning_content = message.reasoning_content %}
93
+ {%- else %}
94
+ {%- if '</think>' in content %}
95
+ {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
96
+ {%- set content = content.split('</think>')[-1].lstrip('\n') %}
97
+ {%- endif %}
98
+ {%- endif %}
99
+ {%- set reasoning_content = reasoning_content|trim %}
100
+ {%- if (preserve_thinking is defined and preserve_thinking is true) or (loop.index0 > ns.last_query_index) %}
101
+ {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content + '\n</think>\n\n' + content }}
102
+ {%- else %}
103
+ {{- '<|im_start|>' + message.role + '\n' + content }}
104
+ {%- endif %}
105
+ {%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}
106
+ {%- for tool_call in message.tool_calls %}
107
+ {%- if tool_call.function is defined %}
108
+ {%- set tool_call = tool_call.function %}
109
+ {%- endif %}
110
+ {%- if loop.first %}
111
+ {%- if content|trim %}
112
+ {{- '\n\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
113
+ {%- else %}
114
+ {{- '<tool_call>\n<function=' + tool_call.name + '>\n' }}
115
+ {%- endif %}
116
+ {%- else %}
117
+ {{- '\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
118
+ {%- endif %}
119
+ {%- if tool_call.arguments is defined %}
120
+ {%- for args_name, args_value in tool_call.arguments|items %}
121
+ {{- '<parameter=' + args_name + '>\n' }}
122
+ {%- set args_value = args_value | string if args_value is string else args_value | tojson | safe %}
123
+ {{- args_value }}
124
+ {{- '\n</parameter>\n' }}
125
+ {%- endfor %}
126
+ {%- endif %}
127
+ {{- '</function>\n</tool_call>' }}
128
+ {%- endfor %}
129
+ {%- endif %}
130
+ {{- '<|im_end|>\n' }}
131
+ {%- elif message.role == "tool" %}
132
+ {%- if loop.previtem and loop.previtem.role != "tool" %}
133
+ {{- '<|im_start|>user' }}
134
+ {%- endif %}
135
+ {{- '\n<tool_response>\n' }}
136
+ {{- content }}
137
+ {{- '\n</tool_response>' }}
138
+ {%- if not loop.last and loop.nextitem.role != "tool" %}
139
+ {{- '<|im_end|>\n' }}
140
+ {%- elif loop.last %}
141
+ {{- '<|im_end|>\n' }}
142
+ {%- endif %}
143
+ {%- else %}
144
+ {{- raise_exception('Unexpected message role.') }}
145
+ {%- endif %}
146
+ {%- endfor %}
147
+ {%- if add_generation_prompt %}
148
+ {{- '<|im_start|>assistant\n' }}
149
+ {%- if enable_thinking is defined and enable_thinking is false %}
150
+ {{- '<think>\n\n</think>\n\n' }}
151
+ {%- else %}
152
+ {{- '<think>\n' }}
153
+ {%- endif %}
154
+ {%- endif %}
config.json ADDED
@@ -0,0 +1,96 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "attention_bias": false,
3
+ "attention_dropout": 0.0,
4
+ "attn_output_gate": true,
5
+ "bos_token_id": 248044,
6
+ "dtype": "bfloat16",
7
+ "eos_token_id": 248044,
8
+ "full_attention_interval": 4,
9
+ "head_dim": 256,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 2048,
12
+ "initializer_range": 0.02,
13
+ "layer_types": [
14
+ "linear_attention",
15
+ "linear_attention",
16
+ "linear_attention",
17
+ "full_attention",
18
+ "linear_attention",
19
+ "linear_attention",
20
+ "linear_attention",
21
+ "full_attention",
22
+ "linear_attention",
23
+ "linear_attention",
24
+ "linear_attention",
25
+ "full_attention",
26
+ "linear_attention",
27
+ "linear_attention",
28
+ "linear_attention",
29
+ "full_attention",
30
+ "linear_attention",
31
+ "linear_attention",
32
+ "linear_attention",
33
+ "full_attention",
34
+ "linear_attention",
35
+ "linear_attention",
36
+ "linear_attention",
37
+ "full_attention",
38
+ "linear_attention",
39
+ "linear_attention",
40
+ "linear_attention",
41
+ "full_attention",
42
+ "linear_attention",
43
+ "linear_attention",
44
+ "linear_attention",
45
+ "full_attention",
46
+ "linear_attention",
47
+ "linear_attention",
48
+ "linear_attention",
49
+ "full_attention",
50
+ "linear_attention",
51
+ "linear_attention",
52
+ "linear_attention",
53
+ "full_attention"
54
+ ],
55
+ "linear_conv_kernel_dim": 4,
56
+ "linear_key_head_dim": 128,
57
+ "linear_num_key_heads": 16,
58
+ "linear_num_value_heads": 32,
59
+ "linear_value_head_dim": 128,
60
+ "mamba_ssm_dtype": "float32",
61
+ "max_position_embeddings": 262144,
62
+ "model_type": "qwen3_5_moe",
63
+ "moe_intermediate_size": 512,
64
+ "mtp_num_hidden_layers": 1,
65
+ "mtp_use_dedicated_embeddings": false,
66
+ "num_attention_heads": 16,
67
+ "num_experts": 256,
68
+ "num_experts_per_tok": 8,
69
+ "num_hidden_layers": 40,
70
+ "num_key_value_heads": 2,
71
+ "output_router_logits": false,
72
+ "pad_token_id": null,
73
+ "partial_rotary_factor": 0.25,
74
+ "rms_norm_eps": 1e-06,
75
+ "rope_parameters": {
76
+ "mrope_interleaved": true,
77
+ "mrope_section": [
78
+ 11,
79
+ 11,
80
+ 10
81
+ ],
82
+ "partial_rotary_factor": 0.25,
83
+ "rope_theta": 10000000,
84
+ "rope_type": "default"
85
+ },
86
+ "router_aux_loss_coef": 0.001,
87
+ "shared_expert_intermediate_size": 512,
88
+ "tie_word_embeddings": false,
89
+ "use_cache": true,
90
+ "vocab_size": 248320,
91
+ "architectures": [
92
+ "Qwen3_5MoeForCausalLM"
93
+ ],
94
+ "torch_dtype": "bfloat16",
95
+ "transformers_version": "4.57.1"
96
+ }
darwin_v6_report.json ADDED
@@ -0,0 +1,69 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "version": "darwin_v6",
3
+ "model_a": "Qwen/Qwen3.6-35B-A3B",
4
+ "model_b": "hesamation/Qwen3.6-35B-A3B-Claude-4.6-Opus-Reasoning-Distilled",
5
+ "scan_time_a": 161.1855502128601,
6
+ "scan_time_b": 149.11143231391907,
7
+ "prescription": {
8
+ "total_tensors": 1045,
9
+ "avg_ratio_b": 0.49999984425441674,
10
+ "avg_attn_ratio": 0.499985450760254,
11
+ "avg_ffn_ratio": 0.5000152414508509,
12
+ "avg_embed_ratio": 0.49999999999992895,
13
+ "transplant_a_count": 0,
14
+ "transplant_b_count": 0,
15
+ "blended_count": 1045
16
+ },
17
+ "recommended_genome": {
18
+ "global_ratio": 0.49999984425441674,
19
+ "attn_ratio": 0.499985450760254,
20
+ "ffn_ratio": 0.5000152414508509,
21
+ "embed_ratio": 0.49999999999992895,
22
+ "block_ratios": [
23
+ 0.5000721444413114,
24
+ 0.4998433134008189,
25
+ 0.499780888197006,
26
+ 0.4997929703763515,
27
+ 0.499771132051783,
28
+ 0.4997801248073877,
29
+ 0.499745996175545,
30
+ 0.5012345529552215
31
+ ],
32
+ "mri_trust": 0.7
33
+ },
34
+ "evolution": {
35
+ "best_score": 0.8402656748646429,
36
+ "best_genome": [
37
+ 0.4936662919610739,
38
+ 0.0815242519055706,
39
+ 0.9341507094494833,
40
+ 0.36828574975395845,
41
+ 0.9482560366006947,
42
+ 0.9930202372461144,
43
+ 0.6267934460397571,
44
+ 0.7804501296513594,
45
+ 0.5091179237088572,
46
+ 0.5273575416938678,
47
+ 0.3549558469479533,
48
+ 0.2945505642361962,
49
+ 0.7838544898184714,
50
+ 0.47445473021143214,
51
+ 0.7214881982362042,
52
+ 0.7737746038647229
53
+ ],
54
+ "elapsed_sec": 2909.7664647102356,
55
+ "merge_report": {
56
+ "total": 1045,
57
+ "transplant_a": 0,
58
+ "transplant_b": 0,
59
+ "blended": 1045,
60
+ "method": "slerp",
61
+ "genome_hash": "8fc46eeb"
62
+ }
63
+ },
64
+ "health": {
65
+ "status": "healthy",
66
+ "summary": "failed: Repo id must be in the form 'repo_name' or 'namespace/repo_name': '/home/gmail_be2j/darwin_merge_cache/merged_6edaacaf'. Use `repo_type` argument if needed.",
67
+ "issue_count": 0
68
+ }
69
+ }
generation_config.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 248044,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 248046,
6
+ 248044
7
+ ],
8
+ "pad_token_id": 248044,
9
+ "temperature": 1.0,
10
+ "top_k": 20,
11
+ "top_p": 0.95
12
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model-00001-of-00026.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd736d53f1ad547e5e2bf76056a85b7ef459aeabeac316841372cf3aae4c39f0
3
+ size 3996199680
model-00002-of-00026.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc2fa5ef1db267a0d1534b2bb883378beb7cf476c9e8169e5aeddc2a9962e9f0
3
+ size 1284907672
model-00003-of-00026.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f3101f11ccaa437fbeffdff97e053aa870fee5a8f676ff31e0c7da1720774be6
3
+ size 3357898328
model-00004-of-00026.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:53a154df2a6293fb8c773cfe2ad36a21ed6223f12efb074c425a6b3b0c4cfaa0
3
+ size 3370808680
model-00005-of-00026.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ff3d373f8ded18c007d29b20bd21dbc037da18d9cb0328a231eb6201401eee39
3
+ size 3357898328
model-00006-of-00026.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:208029410a96a742737d4facba86575cab27b3c63b6a46a2f9fea11561aad0db
3
+ size 3959424872
model-00007-of-00026.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:259097bd43725af329741b11e92b7bba43939ef8fe3cb3ada16ee6ef2ed8c30f
3
+ size 1096788200
model-00008-of-00026.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:69ded80f4cc677ad6afe978b0522e793d5954e375553ce819d60dcd8a9e552bc
3
+ size 3946841976
model-00009-of-00026.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:14e2daa1edbbf6df5f078f4325aa42c7e8906a6f7206307646b3d2179582cfef
3
+ size 1096460816
model-00010-of-00026.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e67ffdce4e3d58ca5ae03f7e4d96f8032b5cb26b74b0228b41b760875aff6811
3
+ size 3946841960
model-00011-of-00026.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d015def2200f5101aea3de1e655593e6606e91179fab7c60430a7475a561e8e
3
+ size 1096460720
model-00012-of-00026.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2043579ed722c46ac12f1de2df597b8899f543fd3f02dbc15be8809258190204
3
+ size 3409971048
model-00013-of-00026.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b17383078b7871c1260b5982190a15856547afdce73f65b3eb48d7bdd9af4733
3
+ size 1633331632
model-00014-of-00026.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c9548f87ccdc0fd23b61ff4d41d17fdbc9d2cf1ccb6e217b49a2e77e446cc36e
3
+ size 3422553840
model-00015-of-00026.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:07d6c595fa11ea86d1cf28b34162f1c1a0ba6395415141d8457bed8f1a69bd99
3
+ size 1633659192
model-00016-of-00026.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4bdcd920e97bf64d99cc095ed37e76b684071438feb1bd5168e2444d1f95241e
3
+ size 3946842104
model-00017-of-00026.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c7ad799298def5fe7f31f4142ee0f0ef938649592d28ce000db71e0ef962cb18
3
+ size 1096460576
model-00018-of-00026.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:487bc52558b53c05263ce89f40846501787fdc6e0e4486ce2a84006f02a62b0d
3
+ size 3946841960
model-00019-of-00026.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:792482237192b978e2030a8ec6750cd927d854ef4bf4dad08a33853aff535fa2
3
+ size 1096460776
model-00020-of-00026.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4db7e1192b69836e6782ddee88ce6d7c48bee3623f7419a96da8cc7e1f37a5ce
3
+ size 3409971040
model-00021-of-00026.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:43f7f62c0591d727fa69207be3bc88eb60f590d2674832e356ef2cebd7ffbb66
3
+ size 1633331712
model-00022-of-00026.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e3f8b8d497428abbe3008318e9ca7619132418f16e73560f4f6abfd7f62d0d10
3
+ size 3370808720
model-00023-of-00026.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5bb31679261a3ebf3e78fbc1b7a48dfdd3839dbcc729415602757523f7fd0e9c
3
+ size 3357898360
model-00024-of-00026.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:567a56a0309e57f3d2c9481df1a7a7d852bb1e18b1f37e5dbd26b4ef8d108edb
3
+ size 3370808720
model-00025-of-00026.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e692f8856ee8d96f826fe5e7dfdca85bdfeff918fd4ab6e6e17fc03dec04c3c2
3
+ size 3832888224
model-00026-of-00026.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:84320dec3f77619ab434f1ac56a8fe6c51610ac5d8e5191a91bd3c6472aa4e78
3
+ size 2231416816
model.safetensors.index.json ADDED
@@ -0,0 +1,1052 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 71903645408.0
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "model-00026-of-00026.safetensors",
7
+ "model.language_model.embed_tokens.weight": "model-00001-of-00026.safetensors",
8
+ "model.language_model.layers.0.input_layernorm.weight": "model-00002-of-00026.safetensors",
9
+ "model.language_model.layers.0.linear_attn.A_log": "model-00002-of-00026.safetensors",
10
+ "model.language_model.layers.0.linear_attn.conv1d.weight": "model-00002-of-00026.safetensors",
11
+ "model.language_model.layers.0.linear_attn.dt_bias": "model-00002-of-00026.safetensors",
12
+ "model.language_model.layers.0.linear_attn.in_proj_a.weight": "model-00002-of-00026.safetensors",
13
+ "model.language_model.layers.0.linear_attn.in_proj_b.weight": "model-00002-of-00026.safetensors",
14
+ "model.language_model.layers.0.linear_attn.in_proj_qkv.weight": "model-00001-of-00026.safetensors",
15
+ "model.language_model.layers.0.linear_attn.in_proj_z.weight": "model-00001-of-00026.safetensors",
16
+ "model.language_model.layers.0.linear_attn.norm.weight": "model-00002-of-00026.safetensors",
17
+ "model.language_model.layers.0.linear_attn.out_proj.weight": "model-00001-of-00026.safetensors",
18
+ "model.language_model.layers.0.mlp.experts.down_proj": "model-00002-of-00026.safetensors",
19
+ "model.language_model.layers.0.mlp.experts.gate_up_proj": "model-00001-of-00026.safetensors",
20
+ "model.language_model.layers.0.mlp.gate.weight": "model-00002-of-00026.safetensors",
21
+ "model.language_model.layers.0.mlp.shared_expert.down_proj.weight": "model-00002-of-00026.safetensors",
22
+ "model.language_model.layers.0.mlp.shared_expert.gate_proj.weight": "model-00002-of-00026.safetensors",
23
+ "model.language_model.layers.0.mlp.shared_expert.up_proj.weight": "model-00002-of-00026.safetensors",
24
+ "model.language_model.layers.0.mlp.shared_expert_gate.weight": "model-00002-of-00026.safetensors",
25
+ "model.language_model.layers.0.post_attention_layernorm.weight": "model-00002-of-00026.safetensors",
26
+ "model.language_model.layers.1.input_layernorm.weight": "model-00002-of-00026.safetensors",
27
+ "model.language_model.layers.1.linear_attn.A_log": "model-00002-of-00026.safetensors",
28
+ "model.language_model.layers.1.linear_attn.conv1d.weight": "model-00002-of-00026.safetensors",
29
+ "model.language_model.layers.1.linear_attn.dt_bias": "model-00002-of-00026.safetensors",
30
+ "model.language_model.layers.1.linear_attn.in_proj_a.weight": "model-00002-of-00026.safetensors",
31
+ "model.language_model.layers.1.linear_attn.in_proj_b.weight": "model-00002-of-00026.safetensors",
32
+ "model.language_model.layers.1.linear_attn.in_proj_qkv.weight": "model-00001-of-00026.safetensors",
33
+ "model.language_model.layers.1.linear_attn.in_proj_z.weight": "model-00001-of-00026.safetensors",
34
+ "model.language_model.layers.1.linear_attn.norm.weight": "model-00002-of-00026.safetensors",
35
+ "model.language_model.layers.1.linear_attn.out_proj.weight": "model-00001-of-00026.safetensors",
36
+ "model.language_model.layers.1.mlp.experts.down_proj": "model-00001-of-00026.safetensors",
37
+ "model.language_model.layers.1.mlp.experts.gate_up_proj": "model-00001-of-00026.safetensors",
38
+ "model.language_model.layers.1.mlp.gate.weight": "model-00002-of-00026.safetensors",
39
+ "model.language_model.layers.1.mlp.shared_expert.down_proj.weight": "model-00002-of-00026.safetensors",
40
+ "model.language_model.layers.1.mlp.shared_expert.gate_proj.weight": "model-00002-of-00026.safetensors",
41
+ "model.language_model.layers.1.mlp.shared_expert.up_proj.weight": "model-00002-of-00026.safetensors",
42
+ "model.language_model.layers.1.mlp.shared_expert_gate.weight": "model-00002-of-00026.safetensors",
43
+ "model.language_model.layers.1.post_attention_layernorm.weight": "model-00002-of-00026.safetensors",
44
+ "model.language_model.layers.10.input_layernorm.weight": "model-00007-of-00026.safetensors",
45
+ "model.language_model.layers.10.linear_attn.A_log": "model-00007-of-00026.safetensors",
46
+ "model.language_model.layers.10.linear_attn.conv1d.weight": "model-00007-of-00026.safetensors",
47
+ "model.language_model.layers.10.linear_attn.dt_bias": "model-00007-of-00026.safetensors",
48
+ "model.language_model.layers.10.linear_attn.in_proj_a.weight": "model-00007-of-00026.safetensors",
49
+ "model.language_model.layers.10.linear_attn.in_proj_b.weight": "model-00007-of-00026.safetensors",
50
+ "model.language_model.layers.10.linear_attn.in_proj_qkv.weight": "model-00006-of-00026.safetensors",
51
+ "model.language_model.layers.10.linear_attn.in_proj_z.weight": "model-00006-of-00026.safetensors",
52
+ "model.language_model.layers.10.linear_attn.norm.weight": "model-00007-of-00026.safetensors",
53
+ "model.language_model.layers.10.linear_attn.out_proj.weight": "model-00006-of-00026.safetensors",
54
+ "model.language_model.layers.10.mlp.experts.down_proj": "model-00006-of-00026.safetensors",
55
+ "model.language_model.layers.10.mlp.experts.gate_up_proj": "model-00007-of-00026.safetensors",
56
+ "model.language_model.layers.10.mlp.gate.weight": "model-00007-of-00026.safetensors",
57
+ "model.language_model.layers.10.mlp.shared_expert.down_proj.weight": "model-00007-of-00026.safetensors",
58
+ "model.language_model.layers.10.mlp.shared_expert.gate_proj.weight": "model-00007-of-00026.safetensors",
59
+ "model.language_model.layers.10.mlp.shared_expert.up_proj.weight": "model-00007-of-00026.safetensors",
60
+ "model.language_model.layers.10.mlp.shared_expert_gate.weight": "model-00007-of-00026.safetensors",
61
+ "model.language_model.layers.10.post_attention_layernorm.weight": "model-00007-of-00026.safetensors",
62
+ "model.language_model.layers.11.input_layernorm.weight": "model-00009-of-00026.safetensors",
63
+ "model.language_model.layers.11.mlp.experts.down_proj": "model-00009-of-00026.safetensors",
64
+ "model.language_model.layers.11.mlp.experts.gate_up_proj": "model-00008-of-00026.safetensors",
65
+ "model.language_model.layers.11.mlp.gate.weight": "model-00009-of-00026.safetensors",
66
+ "model.language_model.layers.11.mlp.shared_expert.down_proj.weight": "model-00009-of-00026.safetensors",
67
+ "model.language_model.layers.11.mlp.shared_expert.gate_proj.weight": "model-00009-of-00026.safetensors",
68
+ "model.language_model.layers.11.mlp.shared_expert.up_proj.weight": "model-00009-of-00026.safetensors",
69
+ "model.language_model.layers.11.mlp.shared_expert_gate.weight": "model-00009-of-00026.safetensors",
70
+ "model.language_model.layers.11.post_attention_layernorm.weight": "model-00009-of-00026.safetensors",
71
+ "model.language_model.layers.11.self_attn.k_norm.weight": "model-00009-of-00026.safetensors",
72
+ "model.language_model.layers.11.self_attn.k_proj.weight": "model-00008-of-00026.safetensors",
73
+ "model.language_model.layers.11.self_attn.o_proj.weight": "model-00008-of-00026.safetensors",
74
+ "model.language_model.layers.11.self_attn.q_norm.weight": "model-00009-of-00026.safetensors",
75
+ "model.language_model.layers.11.self_attn.q_proj.weight": "model-00008-of-00026.safetensors",
76
+ "model.language_model.layers.11.self_attn.v_proj.weight": "model-00008-of-00026.safetensors",
77
+ "model.language_model.layers.12.input_layernorm.weight": "model-00009-of-00026.safetensors",
78
+ "model.language_model.layers.12.linear_attn.A_log": "model-00009-of-00026.safetensors",
79
+ "model.language_model.layers.12.linear_attn.conv1d.weight": "model-00009-of-00026.safetensors",
80
+ "model.language_model.layers.12.linear_attn.dt_bias": "model-00009-of-00026.safetensors",
81
+ "model.language_model.layers.12.linear_attn.in_proj_a.weight": "model-00009-of-00026.safetensors",
82
+ "model.language_model.layers.12.linear_attn.in_proj_b.weight": "model-00009-of-00026.safetensors",
83
+ "model.language_model.layers.12.linear_attn.in_proj_qkv.weight": "model-00008-of-00026.safetensors",
84
+ "model.language_model.layers.12.linear_attn.in_proj_z.weight": "model-00008-of-00026.safetensors",
85
+ "model.language_model.layers.12.linear_attn.norm.weight": "model-00009-of-00026.safetensors",
86
+ "model.language_model.layers.12.linear_attn.out_proj.weight": "model-00008-of-00026.safetensors",
87
+ "model.language_model.layers.12.mlp.experts.down_proj": "model-00009-of-00026.safetensors",
88
+ "model.language_model.layers.12.mlp.experts.gate_up_proj": "model-00008-of-00026.safetensors",
89
+ "model.language_model.layers.12.mlp.gate.weight": "model-00009-of-00026.safetensors",
90
+ "model.language_model.layers.12.mlp.shared_expert.down_proj.weight": "model-00009-of-00026.safetensors",
91
+ "model.language_model.layers.12.mlp.shared_expert.gate_proj.weight": "model-00009-of-00026.safetensors",
92
+ "model.language_model.layers.12.mlp.shared_expert.up_proj.weight": "model-00009-of-00026.safetensors",
93
+ "model.language_model.layers.12.mlp.shared_expert_gate.weight": "model-00009-of-00026.safetensors",
94
+ "model.language_model.layers.12.post_attention_layernorm.weight": "model-00009-of-00026.safetensors",
95
+ "model.language_model.layers.13.input_layernorm.weight": "model-00009-of-00026.safetensors",
96
+ "model.language_model.layers.13.linear_attn.A_log": "model-00009-of-00026.safetensors",
97
+ "model.language_model.layers.13.linear_attn.conv1d.weight": "model-00009-of-00026.safetensors",
98
+ "model.language_model.layers.13.linear_attn.dt_bias": "model-00009-of-00026.safetensors",
99
+ "model.language_model.layers.13.linear_attn.in_proj_a.weight": "model-00009-of-00026.safetensors",
100
+ "model.language_model.layers.13.linear_attn.in_proj_b.weight": "model-00009-of-00026.safetensors",
101
+ "model.language_model.layers.13.linear_attn.in_proj_qkv.weight": "model-00008-of-00026.safetensors",
102
+ "model.language_model.layers.13.linear_attn.in_proj_z.weight": "model-00008-of-00026.safetensors",
103
+ "model.language_model.layers.13.linear_attn.norm.weight": "model-00009-of-00026.safetensors",
104
+ "model.language_model.layers.13.linear_attn.out_proj.weight": "model-00008-of-00026.safetensors",
105
+ "model.language_model.layers.13.mlp.experts.down_proj": "model-00008-of-00026.safetensors",
106
+ "model.language_model.layers.13.mlp.experts.gate_up_proj": "model-00008-of-00026.safetensors",
107
+ "model.language_model.layers.13.mlp.gate.weight": "model-00009-of-00026.safetensors",
108
+ "model.language_model.layers.13.mlp.shared_expert.down_proj.weight": "model-00009-of-00026.safetensors",
109
+ "model.language_model.layers.13.mlp.shared_expert.gate_proj.weight": "model-00009-of-00026.safetensors",
110
+ "model.language_model.layers.13.mlp.shared_expert.up_proj.weight": "model-00009-of-00026.safetensors",
111
+ "model.language_model.layers.13.mlp.shared_expert_gate.weight": "model-00009-of-00026.safetensors",
112
+ "model.language_model.layers.13.post_attention_layernorm.weight": "model-00009-of-00026.safetensors",
113
+ "model.language_model.layers.14.input_layernorm.weight": "model-00011-of-00026.safetensors",
114
+ "model.language_model.layers.14.linear_attn.A_log": "model-00011-of-00026.safetensors",
115
+ "model.language_model.layers.14.linear_attn.conv1d.weight": "model-00011-of-00026.safetensors",
116
+ "model.language_model.layers.14.linear_attn.dt_bias": "model-00011-of-00026.safetensors",
117
+ "model.language_model.layers.14.linear_attn.in_proj_a.weight": "model-00011-of-00026.safetensors",
118
+ "model.language_model.layers.14.linear_attn.in_proj_b.weight": "model-00011-of-00026.safetensors",
119
+ "model.language_model.layers.14.linear_attn.in_proj_qkv.weight": "model-00010-of-00026.safetensors",
120
+ "model.language_model.layers.14.linear_attn.in_proj_z.weight": "model-00010-of-00026.safetensors",
121
+ "model.language_model.layers.14.linear_attn.norm.weight": "model-00011-of-00026.safetensors",
122
+ "model.language_model.layers.14.linear_attn.out_proj.weight": "model-00010-of-00026.safetensors",
123
+ "model.language_model.layers.14.mlp.experts.down_proj": "model-00010-of-00026.safetensors",
124
+ "model.language_model.layers.14.mlp.experts.gate_up_proj": "model-00010-of-00026.safetensors",
125
+ "model.language_model.layers.14.mlp.gate.weight": "model-00011-of-00026.safetensors",
126
+ "model.language_model.layers.14.mlp.shared_expert.down_proj.weight": "model-00011-of-00026.safetensors",
127
+ "model.language_model.layers.14.mlp.shared_expert.gate_proj.weight": "model-00011-of-00026.safetensors",
128
+ "model.language_model.layers.14.mlp.shared_expert.up_proj.weight": "model-00011-of-00026.safetensors",
129
+ "model.language_model.layers.14.mlp.shared_expert_gate.weight": "model-00011-of-00026.safetensors",
130
+ "model.language_model.layers.14.post_attention_layernorm.weight": "model-00011-of-00026.safetensors",
131
+ "model.language_model.layers.15.input_layernorm.weight": "model-00011-of-00026.safetensors",
132
+ "model.language_model.layers.15.mlp.experts.down_proj": "model-00011-of-00026.safetensors",
133
+ "model.language_model.layers.15.mlp.experts.gate_up_proj": "model-00010-of-00026.safetensors",
134
+ "model.language_model.layers.15.mlp.gate.weight": "model-00011-of-00026.safetensors",
135
+ "model.language_model.layers.15.mlp.shared_expert.down_proj.weight": "model-00011-of-00026.safetensors",
136
+ "model.language_model.layers.15.mlp.shared_expert.gate_proj.weight": "model-00011-of-00026.safetensors",
137
+ "model.language_model.layers.15.mlp.shared_expert.up_proj.weight": "model-00011-of-00026.safetensors",
138
+ "model.language_model.layers.15.mlp.shared_expert_gate.weight": "model-00011-of-00026.safetensors",
139
+ "model.language_model.layers.15.post_attention_layernorm.weight": "model-00011-of-00026.safetensors",
140
+ "model.language_model.layers.15.self_attn.k_norm.weight": "model-00011-of-00026.safetensors",
141
+ "model.language_model.layers.15.self_attn.k_proj.weight": "model-00010-of-00026.safetensors",
142
+ "model.language_model.layers.15.self_attn.o_proj.weight": "model-00010-of-00026.safetensors",
143
+ "model.language_model.layers.15.self_attn.q_norm.weight": "model-00011-of-00026.safetensors",
144
+ "model.language_model.layers.15.self_attn.q_proj.weight": "model-00010-of-00026.safetensors",
145
+ "model.language_model.layers.15.self_attn.v_proj.weight": "model-00010-of-00026.safetensors",
146
+ "model.language_model.layers.16.input_layernorm.weight": "model-00011-of-00026.safetensors",
147
+ "model.language_model.layers.16.linear_attn.A_log": "model-00011-of-00026.safetensors",
148
+ "model.language_model.layers.16.linear_attn.conv1d.weight": "model-00011-of-00026.safetensors",
149
+ "model.language_model.layers.16.linear_attn.dt_bias": "model-00011-of-00026.safetensors",
150
+ "model.language_model.layers.16.linear_attn.in_proj_a.weight": "model-00011-of-00026.safetensors",
151
+ "model.language_model.layers.16.linear_attn.in_proj_b.weight": "model-00011-of-00026.safetensors",
152
+ "model.language_model.layers.16.linear_attn.in_proj_qkv.weight": "model-00010-of-00026.safetensors",
153
+ "model.language_model.layers.16.linear_attn.in_proj_z.weight": "model-00010-of-00026.safetensors",
154
+ "model.language_model.layers.16.linear_attn.norm.weight": "model-00011-of-00026.safetensors",
155
+ "model.language_model.layers.16.linear_attn.out_proj.weight": "model-00010-of-00026.safetensors",
156
+ "model.language_model.layers.16.mlp.experts.down_proj": "model-00011-of-00026.safetensors",
157
+ "model.language_model.layers.16.mlp.experts.gate_up_proj": "model-00010-of-00026.safetensors",
158
+ "model.language_model.layers.16.mlp.gate.weight": "model-00011-of-00026.safetensors",
159
+ "model.language_model.layers.16.mlp.shared_expert.down_proj.weight": "model-00011-of-00026.safetensors",
160
+ "model.language_model.layers.16.mlp.shared_expert.gate_proj.weight": "model-00011-of-00026.safetensors",
161
+ "model.language_model.layers.16.mlp.shared_expert.up_proj.weight": "model-00011-of-00026.safetensors",
162
+ "model.language_model.layers.16.mlp.shared_expert_gate.weight": "model-00011-of-00026.safetensors",
163
+ "model.language_model.layers.16.post_attention_layernorm.weight": "model-00011-of-00026.safetensors",
164
+ "model.language_model.layers.17.input_layernorm.weight": "model-00013-of-00026.safetensors",
165
+ "model.language_model.layers.17.linear_attn.A_log": "model-00013-of-00026.safetensors",
166
+ "model.language_model.layers.17.linear_attn.conv1d.weight": "model-00013-of-00026.safetensors",
167
+ "model.language_model.layers.17.linear_attn.dt_bias": "model-00013-of-00026.safetensors",
168
+ "model.language_model.layers.17.linear_attn.in_proj_a.weight": "model-00013-of-00026.safetensors",
169
+ "model.language_model.layers.17.linear_attn.in_proj_b.weight": "model-00013-of-00026.safetensors",
170
+ "model.language_model.layers.17.linear_attn.in_proj_qkv.weight": "model-00012-of-00026.safetensors",
171
+ "model.language_model.layers.17.linear_attn.in_proj_z.weight": "model-00012-of-00026.safetensors",
172
+ "model.language_model.layers.17.linear_attn.norm.weight": "model-00013-of-00026.safetensors",
173
+ "model.language_model.layers.17.linear_attn.out_proj.weight": "model-00012-of-00026.safetensors",
174
+ "model.language_model.layers.17.mlp.experts.down_proj": "model-00012-of-00026.safetensors",
175
+ "model.language_model.layers.17.mlp.experts.gate_up_proj": "model-00012-of-00026.safetensors",
176
+ "model.language_model.layers.17.mlp.gate.weight": "model-00013-of-00026.safetensors",
177
+ "model.language_model.layers.17.mlp.shared_expert.down_proj.weight": "model-00013-of-00026.safetensors",
178
+ "model.language_model.layers.17.mlp.shared_expert.gate_proj.weight": "model-00013-of-00026.safetensors",
179
+ "model.language_model.layers.17.mlp.shared_expert.up_proj.weight": "model-00013-of-00026.safetensors",
180
+ "model.language_model.layers.17.mlp.shared_expert_gate.weight": "model-00013-of-00026.safetensors",
181
+ "model.language_model.layers.17.post_attention_layernorm.weight": "model-00013-of-00026.safetensors",
182
+ "model.language_model.layers.18.input_layernorm.weight": "model-00013-of-00026.safetensors",
183
+ "model.language_model.layers.18.linear_attn.A_log": "model-00013-of-00026.safetensors",
184
+ "model.language_model.layers.18.linear_attn.conv1d.weight": "model-00013-of-00026.safetensors",
185
+ "model.language_model.layers.18.linear_attn.dt_bias": "model-00013-of-00026.safetensors",
186
+ "model.language_model.layers.18.linear_attn.in_proj_a.weight": "model-00013-of-00026.safetensors",
187
+ "model.language_model.layers.18.linear_attn.in_proj_b.weight": "model-00013-of-00026.safetensors",
188
+ "model.language_model.layers.18.linear_attn.in_proj_qkv.weight": "model-00012-of-00026.safetensors",
189
+ "model.language_model.layers.18.linear_attn.in_proj_z.weight": "model-00012-of-00026.safetensors",
190
+ "model.language_model.layers.18.linear_attn.norm.weight": "model-00013-of-00026.safetensors",
191
+ "model.language_model.layers.18.linear_attn.out_proj.weight": "model-00012-of-00026.safetensors",
192
+ "model.language_model.layers.18.mlp.experts.down_proj": "model-00012-of-00026.safetensors",
193
+ "model.language_model.layers.18.mlp.experts.gate_up_proj": "model-00013-of-00026.safetensors",
194
+ "model.language_model.layers.18.mlp.gate.weight": "model-00013-of-00026.safetensors",
195
+ "model.language_model.layers.18.mlp.shared_expert.down_proj.weight": "model-00013-of-00026.safetensors",
196
+ "model.language_model.layers.18.mlp.shared_expert.gate_proj.weight": "model-00013-of-00026.safetensors",
197
+ "model.language_model.layers.18.mlp.shared_expert.up_proj.weight": "model-00013-of-00026.safetensors",
198
+ "model.language_model.layers.18.mlp.shared_expert_gate.weight": "model-00013-of-00026.safetensors",
199
+ "model.language_model.layers.18.post_attention_layernorm.weight": "model-00013-of-00026.safetensors",
200
+ "model.language_model.layers.19.input_layernorm.weight": "model-00013-of-00026.safetensors",
201
+ "model.language_model.layers.19.mlp.experts.down_proj": "model-00013-of-00026.safetensors",
202
+ "model.language_model.layers.19.mlp.experts.gate_up_proj": "model-00012-of-00026.safetensors",
203
+ "model.language_model.layers.19.mlp.gate.weight": "model-00013-of-00026.safetensors",
204
+ "model.language_model.layers.19.mlp.shared_expert.down_proj.weight": "model-00013-of-00026.safetensors",
205
+ "model.language_model.layers.19.mlp.shared_expert.gate_proj.weight": "model-00013-of-00026.safetensors",
206
+ "model.language_model.layers.19.mlp.shared_expert.up_proj.weight": "model-00013-of-00026.safetensors",
207
+ "model.language_model.layers.19.mlp.shared_expert_gate.weight": "model-00013-of-00026.safetensors",
208
+ "model.language_model.layers.19.post_attention_layernorm.weight": "model-00013-of-00026.safetensors",
209
+ "model.language_model.layers.19.self_attn.k_norm.weight": "model-00013-of-00026.safetensors",
210
+ "model.language_model.layers.19.self_attn.k_proj.weight": "model-00012-of-00026.safetensors",
211
+ "model.language_model.layers.19.self_attn.o_proj.weight": "model-00012-of-00026.safetensors",
212
+ "model.language_model.layers.19.self_attn.q_norm.weight": "model-00013-of-00026.safetensors",
213
+ "model.language_model.layers.19.self_attn.q_proj.weight": "model-00012-of-00026.safetensors",
214
+ "model.language_model.layers.19.self_attn.v_proj.weight": "model-00012-of-00026.safetensors",
215
+ "model.language_model.layers.2.input_layernorm.weight": "model-00003-of-00026.safetensors",
216
+ "model.language_model.layers.2.linear_attn.A_log": "model-00003-of-00026.safetensors",
217
+ "model.language_model.layers.2.linear_attn.conv1d.weight": "model-00003-of-00026.safetensors",
218
+ "model.language_model.layers.2.linear_attn.dt_bias": "model-00003-of-00026.safetensors",
219
+ "model.language_model.layers.2.linear_attn.in_proj_a.weight": "model-00003-of-00026.safetensors",
220
+ "model.language_model.layers.2.linear_attn.in_proj_b.weight": "model-00003-of-00026.safetensors",
221
+ "model.language_model.layers.2.linear_attn.in_proj_qkv.weight": "model-00003-of-00026.safetensors",
222
+ "model.language_model.layers.2.linear_attn.in_proj_z.weight": "model-00003-of-00026.safetensors",
223
+ "model.language_model.layers.2.linear_attn.norm.weight": "model-00003-of-00026.safetensors",
224
+ "model.language_model.layers.2.linear_attn.out_proj.weight": "model-00003-of-00026.safetensors",
225
+ "model.language_model.layers.2.mlp.experts.down_proj": "model-00003-of-00026.safetensors",
226
+ "model.language_model.layers.2.mlp.experts.gate_up_proj": "model-00003-of-00026.safetensors",
227
+ "model.language_model.layers.2.mlp.gate.weight": "model-00003-of-00026.safetensors",
228
+ "model.language_model.layers.2.mlp.shared_expert.down_proj.weight": "model-00003-of-00026.safetensors",
229
+ "model.language_model.layers.2.mlp.shared_expert.gate_proj.weight": "model-00003-of-00026.safetensors",
230
+ "model.language_model.layers.2.mlp.shared_expert.up_proj.weight": "model-00003-of-00026.safetensors",
231
+ "model.language_model.layers.2.mlp.shared_expert_gate.weight": "model-00003-of-00026.safetensors",
232
+ "model.language_model.layers.2.post_attention_layernorm.weight": "model-00003-of-00026.safetensors",
233
+ "model.language_model.layers.20.input_layernorm.weight": "model-00015-of-00026.safetensors",
234
+ "model.language_model.layers.20.linear_attn.A_log": "model-00015-of-00026.safetensors",
235
+ "model.language_model.layers.20.linear_attn.conv1d.weight": "model-00015-of-00026.safetensors",
236
+ "model.language_model.layers.20.linear_attn.dt_bias": "model-00015-of-00026.safetensors",
237
+ "model.language_model.layers.20.linear_attn.in_proj_a.weight": "model-00015-of-00026.safetensors",
238
+ "model.language_model.layers.20.linear_attn.in_proj_b.weight": "model-00015-of-00026.safetensors",
239
+ "model.language_model.layers.20.linear_attn.in_proj_qkv.weight": "model-00014-of-00026.safetensors",
240
+ "model.language_model.layers.20.linear_attn.in_proj_z.weight": "model-00014-of-00026.safetensors",
241
+ "model.language_model.layers.20.linear_attn.norm.weight": "model-00015-of-00026.safetensors",
242
+ "model.language_model.layers.20.linear_attn.out_proj.weight": "model-00014-of-00026.safetensors",
243
+ "model.language_model.layers.20.mlp.experts.down_proj": "model-00014-of-00026.safetensors",
244
+ "model.language_model.layers.20.mlp.experts.gate_up_proj": "model-00014-of-00026.safetensors",
245
+ "model.language_model.layers.20.mlp.gate.weight": "model-00015-of-00026.safetensors",
246
+ "model.language_model.layers.20.mlp.shared_expert.down_proj.weight": "model-00015-of-00026.safetensors",
247
+ "model.language_model.layers.20.mlp.shared_expert.gate_proj.weight": "model-00015-of-00026.safetensors",
248
+ "model.language_model.layers.20.mlp.shared_expert.up_proj.weight": "model-00015-of-00026.safetensors",
249
+ "model.language_model.layers.20.mlp.shared_expert_gate.weight": "model-00015-of-00026.safetensors",
250
+ "model.language_model.layers.20.post_attention_layernorm.weight": "model-00015-of-00026.safetensors",
251
+ "model.language_model.layers.21.input_layernorm.weight": "model-00015-of-00026.safetensors",
252
+ "model.language_model.layers.21.linear_attn.A_log": "model-00015-of-00026.safetensors",
253
+ "model.language_model.layers.21.linear_attn.conv1d.weight": "model-00015-of-00026.safetensors",
254
+ "model.language_model.layers.21.linear_attn.dt_bias": "model-00015-of-00026.safetensors",
255
+ "model.language_model.layers.21.linear_attn.in_proj_a.weight": "model-00015-of-00026.safetensors",
256
+ "model.language_model.layers.21.linear_attn.in_proj_b.weight": "model-00015-of-00026.safetensors",
257
+ "model.language_model.layers.21.linear_attn.in_proj_qkv.weight": "model-00014-of-00026.safetensors",
258
+ "model.language_model.layers.21.linear_attn.in_proj_z.weight": "model-00014-of-00026.safetensors",
259
+ "model.language_model.layers.21.linear_attn.norm.weight": "model-00015-of-00026.safetensors",
260
+ "model.language_model.layers.21.linear_attn.out_proj.weight": "model-00014-of-00026.safetensors",
261
+ "model.language_model.layers.21.mlp.experts.down_proj": "model-00014-of-00026.safetensors",
262
+ "model.language_model.layers.21.mlp.experts.gate_up_proj": "model-00015-of-00026.safetensors",
263
+ "model.language_model.layers.21.mlp.gate.weight": "model-00015-of-00026.safetensors",
264
+ "model.language_model.layers.21.mlp.shared_expert.down_proj.weight": "model-00015-of-00026.safetensors",
265
+ "model.language_model.layers.21.mlp.shared_expert.gate_proj.weight": "model-00015-of-00026.safetensors",
266
+ "model.language_model.layers.21.mlp.shared_expert.up_proj.weight": "model-00015-of-00026.safetensors",
267
+ "model.language_model.layers.21.mlp.shared_expert_gate.weight": "model-00015-of-00026.safetensors",
268
+ "model.language_model.layers.21.post_attention_layernorm.weight": "model-00015-of-00026.safetensors",
269
+ "model.language_model.layers.22.input_layernorm.weight": "model-00015-of-00026.safetensors",
270
+ "model.language_model.layers.22.linear_attn.A_log": "model-00015-of-00026.safetensors",
271
+ "model.language_model.layers.22.linear_attn.conv1d.weight": "model-00015-of-00026.safetensors",
272
+ "model.language_model.layers.22.linear_attn.dt_bias": "model-00015-of-00026.safetensors",
273
+ "model.language_model.layers.22.linear_attn.in_proj_a.weight": "model-00015-of-00026.safetensors",
274
+ "model.language_model.layers.22.linear_attn.in_proj_b.weight": "model-00015-of-00026.safetensors",
275
+ "model.language_model.layers.22.linear_attn.in_proj_qkv.weight": "model-00014-of-00026.safetensors",
276
+ "model.language_model.layers.22.linear_attn.in_proj_z.weight": "model-00014-of-00026.safetensors",
277
+ "model.language_model.layers.22.linear_attn.norm.weight": "model-00015-of-00026.safetensors",
278
+ "model.language_model.layers.22.linear_attn.out_proj.weight": "model-00014-of-00026.safetensors",
279
+ "model.language_model.layers.22.mlp.experts.down_proj": "model-00015-of-00026.safetensors",
280
+ "model.language_model.layers.22.mlp.experts.gate_up_proj": "model-00014-of-00026.safetensors",
281
+ "model.language_model.layers.22.mlp.gate.weight": "model-00015-of-00026.safetensors",
282
+ "model.language_model.layers.22.mlp.shared_expert.down_proj.weight": "model-00015-of-00026.safetensors",
283
+ "model.language_model.layers.22.mlp.shared_expert.gate_proj.weight": "model-00015-of-00026.safetensors",
284
+ "model.language_model.layers.22.mlp.shared_expert.up_proj.weight": "model-00015-of-00026.safetensors",
285
+ "model.language_model.layers.22.mlp.shared_expert_gate.weight": "model-00015-of-00026.safetensors",
286
+ "model.language_model.layers.22.post_attention_layernorm.weight": "model-00015-of-00026.safetensors",
287
+ "model.language_model.layers.23.input_layernorm.weight": "model-00017-of-00026.safetensors",
288
+ "model.language_model.layers.23.mlp.experts.down_proj": "model-00016-of-00026.safetensors",
289
+ "model.language_model.layers.23.mlp.experts.gate_up_proj": "model-00016-of-00026.safetensors",
290
+ "model.language_model.layers.23.mlp.gate.weight": "model-00017-of-00026.safetensors",
291
+ "model.language_model.layers.23.mlp.shared_expert.down_proj.weight": "model-00017-of-00026.safetensors",
292
+ "model.language_model.layers.23.mlp.shared_expert.gate_proj.weight": "model-00017-of-00026.safetensors",
293
+ "model.language_model.layers.23.mlp.shared_expert.up_proj.weight": "model-00017-of-00026.safetensors",
294
+ "model.language_model.layers.23.mlp.shared_expert_gate.weight": "model-00017-of-00026.safetensors",
295
+ "model.language_model.layers.23.post_attention_layernorm.weight": "model-00017-of-00026.safetensors",
296
+ "model.language_model.layers.23.self_attn.k_norm.weight": "model-00017-of-00026.safetensors",
297
+ "model.language_model.layers.23.self_attn.k_proj.weight": "model-00016-of-00026.safetensors",
298
+ "model.language_model.layers.23.self_attn.o_proj.weight": "model-00016-of-00026.safetensors",
299
+ "model.language_model.layers.23.self_attn.q_norm.weight": "model-00017-of-00026.safetensors",
300
+ "model.language_model.layers.23.self_attn.q_proj.weight": "model-00016-of-00026.safetensors",
301
+ "model.language_model.layers.23.self_attn.v_proj.weight": "model-00016-of-00026.safetensors",
302
+ "model.language_model.layers.24.input_layernorm.weight": "model-00017-of-00026.safetensors",
303
+ "model.language_model.layers.24.linear_attn.A_log": "model-00017-of-00026.safetensors",
304
+ "model.language_model.layers.24.linear_attn.conv1d.weight": "model-00017-of-00026.safetensors",
305
+ "model.language_model.layers.24.linear_attn.dt_bias": "model-00017-of-00026.safetensors",
306
+ "model.language_model.layers.24.linear_attn.in_proj_a.weight": "model-00017-of-00026.safetensors",
307
+ "model.language_model.layers.24.linear_attn.in_proj_b.weight": "model-00017-of-00026.safetensors",
308
+ "model.language_model.layers.24.linear_attn.in_proj_qkv.weight": "model-00016-of-00026.safetensors",
309
+ "model.language_model.layers.24.linear_attn.in_proj_z.weight": "model-00016-of-00026.safetensors",
310
+ "model.language_model.layers.24.linear_attn.norm.weight": "model-00017-of-00026.safetensors",
311
+ "model.language_model.layers.24.linear_attn.out_proj.weight": "model-00016-of-00026.safetensors",
312
+ "model.language_model.layers.24.mlp.experts.down_proj": "model-00016-of-00026.safetensors",
313
+ "model.language_model.layers.24.mlp.experts.gate_up_proj": "model-00016-of-00026.safetensors",
314
+ "model.language_model.layers.24.mlp.gate.weight": "model-00017-of-00026.safetensors",
315
+ "model.language_model.layers.24.mlp.shared_expert.down_proj.weight": "model-00017-of-00026.safetensors",
316
+ "model.language_model.layers.24.mlp.shared_expert.gate_proj.weight": "model-00017-of-00026.safetensors",
317
+ "model.language_model.layers.24.mlp.shared_expert.up_proj.weight": "model-00017-of-00026.safetensors",
318
+ "model.language_model.layers.24.mlp.shared_expert_gate.weight": "model-00017-of-00026.safetensors",
319
+ "model.language_model.layers.24.post_attention_layernorm.weight": "model-00017-of-00026.safetensors",
320
+ "model.language_model.layers.25.input_layernorm.weight": "model-00017-of-00026.safetensors",
321
+ "model.language_model.layers.25.linear_attn.A_log": "model-00017-of-00026.safetensors",
322
+ "model.language_model.layers.25.linear_attn.conv1d.weight": "model-00017-of-00026.safetensors",
323
+ "model.language_model.layers.25.linear_attn.dt_bias": "model-00017-of-00026.safetensors",
324
+ "model.language_model.layers.25.linear_attn.in_proj_a.weight": "model-00017-of-00026.safetensors",
325
+ "model.language_model.layers.25.linear_attn.in_proj_b.weight": "model-00017-of-00026.safetensors",
326
+ "model.language_model.layers.25.linear_attn.in_proj_qkv.weight": "model-00016-of-00026.safetensors",
327
+ "model.language_model.layers.25.linear_attn.in_proj_z.weight": "model-00016-of-00026.safetensors",
328
+ "model.language_model.layers.25.linear_attn.norm.weight": "model-00017-of-00026.safetensors",
329
+ "model.language_model.layers.25.linear_attn.out_proj.weight": "model-00016-of-00026.safetensors",
330
+ "model.language_model.layers.25.mlp.experts.down_proj": "model-00016-of-00026.safetensors",
331
+ "model.language_model.layers.25.mlp.experts.gate_up_proj": "model-00017-of-00026.safetensors",
332
+ "model.language_model.layers.25.mlp.gate.weight": "model-00017-of-00026.safetensors",
333
+ "model.language_model.layers.25.mlp.shared_expert.down_proj.weight": "model-00017-of-00026.safetensors",
334
+ "model.language_model.layers.25.mlp.shared_expert.gate_proj.weight": "model-00017-of-00026.safetensors",
335
+ "model.language_model.layers.25.mlp.shared_expert.up_proj.weight": "model-00017-of-00026.safetensors",
336
+ "model.language_model.layers.25.mlp.shared_expert_gate.weight": "model-00017-of-00026.safetensors",
337
+ "model.language_model.layers.25.post_attention_layernorm.weight": "model-00017-of-00026.safetensors",
338
+ "model.language_model.layers.26.input_layernorm.weight": "model-00019-of-00026.safetensors",
339
+ "model.language_model.layers.26.linear_attn.A_log": "model-00019-of-00026.safetensors",
340
+ "model.language_model.layers.26.linear_attn.conv1d.weight": "model-00019-of-00026.safetensors",
341
+ "model.language_model.layers.26.linear_attn.dt_bias": "model-00019-of-00026.safetensors",
342
+ "model.language_model.layers.26.linear_attn.in_proj_a.weight": "model-00019-of-00026.safetensors",
343
+ "model.language_model.layers.26.linear_attn.in_proj_b.weight": "model-00019-of-00026.safetensors",
344
+ "model.language_model.layers.26.linear_attn.in_proj_qkv.weight": "model-00018-of-00026.safetensors",
345
+ "model.language_model.layers.26.linear_attn.in_proj_z.weight": "model-00018-of-00026.safetensors",
346
+ "model.language_model.layers.26.linear_attn.norm.weight": "model-00019-of-00026.safetensors",
347
+ "model.language_model.layers.26.linear_attn.out_proj.weight": "model-00018-of-00026.safetensors",
348
+ "model.language_model.layers.26.mlp.experts.down_proj": "model-00019-of-00026.safetensors",
349
+ "model.language_model.layers.26.mlp.experts.gate_up_proj": "model-00018-of-00026.safetensors",
350
+ "model.language_model.layers.26.mlp.gate.weight": "model-00019-of-00026.safetensors",
351
+ "model.language_model.layers.26.mlp.shared_expert.down_proj.weight": "model-00019-of-00026.safetensors",
352
+ "model.language_model.layers.26.mlp.shared_expert.gate_proj.weight": "model-00019-of-00026.safetensors",
353
+ "model.language_model.layers.26.mlp.shared_expert.up_proj.weight": "model-00019-of-00026.safetensors",
354
+ "model.language_model.layers.26.mlp.shared_expert_gate.weight": "model-00019-of-00026.safetensors",
355
+ "model.language_model.layers.26.post_attention_layernorm.weight": "model-00019-of-00026.safetensors",
356
+ "model.language_model.layers.27.input_layernorm.weight": "model-00019-of-00026.safetensors",
357
+ "model.language_model.layers.27.mlp.experts.down_proj": "model-00019-of-00026.safetensors",
358
+ "model.language_model.layers.27.mlp.experts.gate_up_proj": "model-00018-of-00026.safetensors",
359
+ "model.language_model.layers.27.mlp.gate.weight": "model-00019-of-00026.safetensors",
360
+ "model.language_model.layers.27.mlp.shared_expert.down_proj.weight": "model-00019-of-00026.safetensors",
361
+ "model.language_model.layers.27.mlp.shared_expert.gate_proj.weight": "model-00019-of-00026.safetensors",
362
+ "model.language_model.layers.27.mlp.shared_expert.up_proj.weight": "model-00019-of-00026.safetensors",
363
+ "model.language_model.layers.27.mlp.shared_expert_gate.weight": "model-00019-of-00026.safetensors",
364
+ "model.language_model.layers.27.post_attention_layernorm.weight": "model-00019-of-00026.safetensors",
365
+ "model.language_model.layers.27.self_attn.k_norm.weight": "model-00019-of-00026.safetensors",
366
+ "model.language_model.layers.27.self_attn.k_proj.weight": "model-00018-of-00026.safetensors",
367
+ "model.language_model.layers.27.self_attn.o_proj.weight": "model-00018-of-00026.safetensors",
368
+ "model.language_model.layers.27.self_attn.q_norm.weight": "model-00019-of-00026.safetensors",
369
+ "model.language_model.layers.27.self_attn.q_proj.weight": "model-00018-of-00026.safetensors",
370
+ "model.language_model.layers.27.self_attn.v_proj.weight": "model-00018-of-00026.safetensors",
371
+ "model.language_model.layers.28.input_layernorm.weight": "model-00019-of-00026.safetensors",
372
+ "model.language_model.layers.28.linear_attn.A_log": "model-00019-of-00026.safetensors",
373
+ "model.language_model.layers.28.linear_attn.conv1d.weight": "model-00019-of-00026.safetensors",
374
+ "model.language_model.layers.28.linear_attn.dt_bias": "model-00019-of-00026.safetensors",
375
+ "model.language_model.layers.28.linear_attn.in_proj_a.weight": "model-00019-of-00026.safetensors",
376
+ "model.language_model.layers.28.linear_attn.in_proj_b.weight": "model-00019-of-00026.safetensors",
377
+ "model.language_model.layers.28.linear_attn.in_proj_qkv.weight": "model-00018-of-00026.safetensors",
378
+ "model.language_model.layers.28.linear_attn.in_proj_z.weight": "model-00018-of-00026.safetensors",
379
+ "model.language_model.layers.28.linear_attn.norm.weight": "model-00019-of-00026.safetensors",
380
+ "model.language_model.layers.28.linear_attn.out_proj.weight": "model-00018-of-00026.safetensors",
381
+ "model.language_model.layers.28.mlp.experts.down_proj": "model-00018-of-00026.safetensors",
382
+ "model.language_model.layers.28.mlp.experts.gate_up_proj": "model-00018-of-00026.safetensors",
383
+ "model.language_model.layers.28.mlp.gate.weight": "model-00019-of-00026.safetensors",
384
+ "model.language_model.layers.28.mlp.shared_expert.down_proj.weight": "model-00019-of-00026.safetensors",
385
+ "model.language_model.layers.28.mlp.shared_expert.gate_proj.weight": "model-00019-of-00026.safetensors",
386
+ "model.language_model.layers.28.mlp.shared_expert.up_proj.weight": "model-00019-of-00026.safetensors",
387
+ "model.language_model.layers.28.mlp.shared_expert_gate.weight": "model-00019-of-00026.safetensors",
388
+ "model.language_model.layers.28.post_attention_layernorm.weight": "model-00019-of-00026.safetensors",
389
+ "model.language_model.layers.29.input_layernorm.weight": "model-00021-of-00026.safetensors",
390
+ "model.language_model.layers.29.linear_attn.A_log": "model-00021-of-00026.safetensors",
391
+ "model.language_model.layers.29.linear_attn.conv1d.weight": "model-00021-of-00026.safetensors",
392
+ "model.language_model.layers.29.linear_attn.dt_bias": "model-00021-of-00026.safetensors",
393
+ "model.language_model.layers.29.linear_attn.in_proj_a.weight": "model-00021-of-00026.safetensors",
394
+ "model.language_model.layers.29.linear_attn.in_proj_b.weight": "model-00021-of-00026.safetensors",
395
+ "model.language_model.layers.29.linear_attn.in_proj_qkv.weight": "model-00020-of-00026.safetensors",
396
+ "model.language_model.layers.29.linear_attn.in_proj_z.weight": "model-00020-of-00026.safetensors",
397
+ "model.language_model.layers.29.linear_attn.norm.weight": "model-00021-of-00026.safetensors",
398
+ "model.language_model.layers.29.linear_attn.out_proj.weight": "model-00020-of-00026.safetensors",
399
+ "model.language_model.layers.29.mlp.experts.down_proj": "model-00020-of-00026.safetensors",
400
+ "model.language_model.layers.29.mlp.experts.gate_up_proj": "model-00021-of-00026.safetensors",
401
+ "model.language_model.layers.29.mlp.gate.weight": "model-00021-of-00026.safetensors",
402
+ "model.language_model.layers.29.mlp.shared_expert.down_proj.weight": "model-00021-of-00026.safetensors",
403
+ "model.language_model.layers.29.mlp.shared_expert.gate_proj.weight": "model-00021-of-00026.safetensors",
404
+ "model.language_model.layers.29.mlp.shared_expert.up_proj.weight": "model-00021-of-00026.safetensors",
405
+ "model.language_model.layers.29.mlp.shared_expert_gate.weight": "model-00021-of-00026.safetensors",
406
+ "model.language_model.layers.29.post_attention_layernorm.weight": "model-00021-of-00026.safetensors",
407
+ "model.language_model.layers.3.input_layernorm.weight": "model-00003-of-00026.safetensors",
408
+ "model.language_model.layers.3.mlp.experts.down_proj": "model-00003-of-00026.safetensors",
409
+ "model.language_model.layers.3.mlp.experts.gate_up_proj": "model-00003-of-00026.safetensors",
410
+ "model.language_model.layers.3.mlp.gate.weight": "model-00003-of-00026.safetensors",
411
+ "model.language_model.layers.3.mlp.shared_expert.down_proj.weight": "model-00003-of-00026.safetensors",
412
+ "model.language_model.layers.3.mlp.shared_expert.gate_proj.weight": "model-00003-of-00026.safetensors",
413
+ "model.language_model.layers.3.mlp.shared_expert.up_proj.weight": "model-00003-of-00026.safetensors",
414
+ "model.language_model.layers.3.mlp.shared_expert_gate.weight": "model-00003-of-00026.safetensors",
415
+ "model.language_model.layers.3.post_attention_layernorm.weight": "model-00003-of-00026.safetensors",
416
+ "model.language_model.layers.3.self_attn.k_norm.weight": "model-00003-of-00026.safetensors",
417
+ "model.language_model.layers.3.self_attn.k_proj.weight": "model-00003-of-00026.safetensors",
418
+ "model.language_model.layers.3.self_attn.o_proj.weight": "model-00003-of-00026.safetensors",
419
+ "model.language_model.layers.3.self_attn.q_norm.weight": "model-00003-of-00026.safetensors",
420
+ "model.language_model.layers.3.self_attn.q_proj.weight": "model-00003-of-00026.safetensors",
421
+ "model.language_model.layers.3.self_attn.v_proj.weight": "model-00003-of-00026.safetensors",
422
+ "model.language_model.layers.30.input_layernorm.weight": "model-00021-of-00026.safetensors",
423
+ "model.language_model.layers.30.linear_attn.A_log": "model-00021-of-00026.safetensors",
424
+ "model.language_model.layers.30.linear_attn.conv1d.weight": "model-00021-of-00026.safetensors",
425
+ "model.language_model.layers.30.linear_attn.dt_bias": "model-00021-of-00026.safetensors",
426
+ "model.language_model.layers.30.linear_attn.in_proj_a.weight": "model-00021-of-00026.safetensors",
427
+ "model.language_model.layers.30.linear_attn.in_proj_b.weight": "model-00021-of-00026.safetensors",
428
+ "model.language_model.layers.30.linear_attn.in_proj_qkv.weight": "model-00020-of-00026.safetensors",
429
+ "model.language_model.layers.30.linear_attn.in_proj_z.weight": "model-00020-of-00026.safetensors",
430
+ "model.language_model.layers.30.linear_attn.norm.weight": "model-00021-of-00026.safetensors",
431
+ "model.language_model.layers.30.linear_attn.out_proj.weight": "model-00020-of-00026.safetensors",
432
+ "model.language_model.layers.30.mlp.experts.down_proj": "model-00021-of-00026.safetensors",
433
+ "model.language_model.layers.30.mlp.experts.gate_up_proj": "model-00020-of-00026.safetensors",
434
+ "model.language_model.layers.30.mlp.gate.weight": "model-00021-of-00026.safetensors",
435
+ "model.language_model.layers.30.mlp.shared_expert.down_proj.weight": "model-00021-of-00026.safetensors",
436
+ "model.language_model.layers.30.mlp.shared_expert.gate_proj.weight": "model-00021-of-00026.safetensors",
437
+ "model.language_model.layers.30.mlp.shared_expert.up_proj.weight": "model-00021-of-00026.safetensors",
438
+ "model.language_model.layers.30.mlp.shared_expert_gate.weight": "model-00021-of-00026.safetensors",
439
+ "model.language_model.layers.30.post_attention_layernorm.weight": "model-00021-of-00026.safetensors",
440
+ "model.language_model.layers.31.input_layernorm.weight": "model-00021-of-00026.safetensors",
441
+ "model.language_model.layers.31.mlp.experts.down_proj": "model-00020-of-00026.safetensors",
442
+ "model.language_model.layers.31.mlp.experts.gate_up_proj": "model-00020-of-00026.safetensors",
443
+ "model.language_model.layers.31.mlp.gate.weight": "model-00021-of-00026.safetensors",
444
+ "model.language_model.layers.31.mlp.shared_expert.down_proj.weight": "model-00021-of-00026.safetensors",
445
+ "model.language_model.layers.31.mlp.shared_expert.gate_proj.weight": "model-00021-of-00026.safetensors",
446
+ "model.language_model.layers.31.mlp.shared_expert.up_proj.weight": "model-00021-of-00026.safetensors",
447
+ "model.language_model.layers.31.mlp.shared_expert_gate.weight": "model-00021-of-00026.safetensors",
448
+ "model.language_model.layers.31.post_attention_layernorm.weight": "model-00021-of-00026.safetensors",
449
+ "model.language_model.layers.31.self_attn.k_norm.weight": "model-00021-of-00026.safetensors",
450
+ "model.language_model.layers.31.self_attn.k_proj.weight": "model-00020-of-00026.safetensors",
451
+ "model.language_model.layers.31.self_attn.o_proj.weight": "model-00020-of-00026.safetensors",
452
+ "model.language_model.layers.31.self_attn.q_norm.weight": "model-00021-of-00026.safetensors",
453
+ "model.language_model.layers.31.self_attn.q_proj.weight": "model-00020-of-00026.safetensors",
454
+ "model.language_model.layers.31.self_attn.v_proj.weight": "model-00020-of-00026.safetensors",
455
+ "model.language_model.layers.32.input_layernorm.weight": "model-00022-of-00026.safetensors",
456
+ "model.language_model.layers.32.linear_attn.A_log": "model-00022-of-00026.safetensors",
457
+ "model.language_model.layers.32.linear_attn.conv1d.weight": "model-00022-of-00026.safetensors",
458
+ "model.language_model.layers.32.linear_attn.dt_bias": "model-00022-of-00026.safetensors",
459
+ "model.language_model.layers.32.linear_attn.in_proj_a.weight": "model-00022-of-00026.safetensors",
460
+ "model.language_model.layers.32.linear_attn.in_proj_b.weight": "model-00022-of-00026.safetensors",
461
+ "model.language_model.layers.32.linear_attn.in_proj_qkv.weight": "model-00022-of-00026.safetensors",
462
+ "model.language_model.layers.32.linear_attn.in_proj_z.weight": "model-00022-of-00026.safetensors",
463
+ "model.language_model.layers.32.linear_attn.norm.weight": "model-00022-of-00026.safetensors",
464
+ "model.language_model.layers.32.linear_attn.out_proj.weight": "model-00022-of-00026.safetensors",
465
+ "model.language_model.layers.32.mlp.experts.down_proj": "model-00022-of-00026.safetensors",
466
+ "model.language_model.layers.32.mlp.experts.gate_up_proj": "model-00022-of-00026.safetensors",
467
+ "model.language_model.layers.32.mlp.gate.weight": "model-00022-of-00026.safetensors",
468
+ "model.language_model.layers.32.mlp.shared_expert.down_proj.weight": "model-00022-of-00026.safetensors",
469
+ "model.language_model.layers.32.mlp.shared_expert.gate_proj.weight": "model-00022-of-00026.safetensors",
470
+ "model.language_model.layers.32.mlp.shared_expert.up_proj.weight": "model-00022-of-00026.safetensors",
471
+ "model.language_model.layers.32.mlp.shared_expert_gate.weight": "model-00022-of-00026.safetensors",
472
+ "model.language_model.layers.32.post_attention_layernorm.weight": "model-00022-of-00026.safetensors",
473
+ "model.language_model.layers.33.input_layernorm.weight": "model-00022-of-00026.safetensors",
474
+ "model.language_model.layers.33.linear_attn.A_log": "model-00022-of-00026.safetensors",
475
+ "model.language_model.layers.33.linear_attn.conv1d.weight": "model-00022-of-00026.safetensors",
476
+ "model.language_model.layers.33.linear_attn.dt_bias": "model-00022-of-00026.safetensors",
477
+ "model.language_model.layers.33.linear_attn.in_proj_a.weight": "model-00022-of-00026.safetensors",
478
+ "model.language_model.layers.33.linear_attn.in_proj_b.weight": "model-00022-of-00026.safetensors",
479
+ "model.language_model.layers.33.linear_attn.in_proj_qkv.weight": "model-00022-of-00026.safetensors",
480
+ "model.language_model.layers.33.linear_attn.in_proj_z.weight": "model-00022-of-00026.safetensors",
481
+ "model.language_model.layers.33.linear_attn.norm.weight": "model-00022-of-00026.safetensors",
482
+ "model.language_model.layers.33.linear_attn.out_proj.weight": "model-00022-of-00026.safetensors",
483
+ "model.language_model.layers.33.mlp.experts.down_proj": "model-00022-of-00026.safetensors",
484
+ "model.language_model.layers.33.mlp.experts.gate_up_proj": "model-00022-of-00026.safetensors",
485
+ "model.language_model.layers.33.mlp.gate.weight": "model-00022-of-00026.safetensors",
486
+ "model.language_model.layers.33.mlp.shared_expert.down_proj.weight": "model-00022-of-00026.safetensors",
487
+ "model.language_model.layers.33.mlp.shared_expert.gate_proj.weight": "model-00022-of-00026.safetensors",
488
+ "model.language_model.layers.33.mlp.shared_expert.up_proj.weight": "model-00022-of-00026.safetensors",
489
+ "model.language_model.layers.33.mlp.shared_expert_gate.weight": "model-00022-of-00026.safetensors",
490
+ "model.language_model.layers.33.post_attention_layernorm.weight": "model-00022-of-00026.safetensors",
491
+ "model.language_model.layers.34.input_layernorm.weight": "model-00023-of-00026.safetensors",
492
+ "model.language_model.layers.34.linear_attn.A_log": "model-00023-of-00026.safetensors",
493
+ "model.language_model.layers.34.linear_attn.conv1d.weight": "model-00023-of-00026.safetensors",
494
+ "model.language_model.layers.34.linear_attn.dt_bias": "model-00023-of-00026.safetensors",
495
+ "model.language_model.layers.34.linear_attn.in_proj_a.weight": "model-00023-of-00026.safetensors",
496
+ "model.language_model.layers.34.linear_attn.in_proj_b.weight": "model-00023-of-00026.safetensors",
497
+ "model.language_model.layers.34.linear_attn.in_proj_qkv.weight": "model-00023-of-00026.safetensors",
498
+ "model.language_model.layers.34.linear_attn.in_proj_z.weight": "model-00023-of-00026.safetensors",
499
+ "model.language_model.layers.34.linear_attn.norm.weight": "model-00023-of-00026.safetensors",
500
+ "model.language_model.layers.34.linear_attn.out_proj.weight": "model-00023-of-00026.safetensors",
501
+ "model.language_model.layers.34.mlp.experts.down_proj": "model-00023-of-00026.safetensors",
502
+ "model.language_model.layers.34.mlp.experts.gate_up_proj": "model-00023-of-00026.safetensors",
503
+ "model.language_model.layers.34.mlp.gate.weight": "model-00023-of-00026.safetensors",
504
+ "model.language_model.layers.34.mlp.shared_expert.down_proj.weight": "model-00023-of-00026.safetensors",
505
+ "model.language_model.layers.34.mlp.shared_expert.gate_proj.weight": "model-00023-of-00026.safetensors",
506
+ "model.language_model.layers.34.mlp.shared_expert.up_proj.weight": "model-00023-of-00026.safetensors",
507
+ "model.language_model.layers.34.mlp.shared_expert_gate.weight": "model-00023-of-00026.safetensors",
508
+ "model.language_model.layers.34.post_attention_layernorm.weight": "model-00023-of-00026.safetensors",
509
+ "model.language_model.layers.35.input_layernorm.weight": "model-00023-of-00026.safetensors",
510
+ "model.language_model.layers.35.mlp.experts.down_proj": "model-00023-of-00026.safetensors",
511
+ "model.language_model.layers.35.mlp.experts.gate_up_proj": "model-00023-of-00026.safetensors",
512
+ "model.language_model.layers.35.mlp.gate.weight": "model-00023-of-00026.safetensors",
513
+ "model.language_model.layers.35.mlp.shared_expert.down_proj.weight": "model-00023-of-00026.safetensors",
514
+ "model.language_model.layers.35.mlp.shared_expert.gate_proj.weight": "model-00023-of-00026.safetensors",
515
+ "model.language_model.layers.35.mlp.shared_expert.up_proj.weight": "model-00023-of-00026.safetensors",
516
+ "model.language_model.layers.35.mlp.shared_expert_gate.weight": "model-00023-of-00026.safetensors",
517
+ "model.language_model.layers.35.post_attention_layernorm.weight": "model-00023-of-00026.safetensors",
518
+ "model.language_model.layers.35.self_attn.k_norm.weight": "model-00023-of-00026.safetensors",
519
+ "model.language_model.layers.35.self_attn.k_proj.weight": "model-00023-of-00026.safetensors",
520
+ "model.language_model.layers.35.self_attn.o_proj.weight": "model-00023-of-00026.safetensors",
521
+ "model.language_model.layers.35.self_attn.q_norm.weight": "model-00023-of-00026.safetensors",
522
+ "model.language_model.layers.35.self_attn.q_proj.weight": "model-00023-of-00026.safetensors",
523
+ "model.language_model.layers.35.self_attn.v_proj.weight": "model-00023-of-00026.safetensors",
524
+ "model.language_model.layers.36.input_layernorm.weight": "model-00024-of-00026.safetensors",
525
+ "model.language_model.layers.36.linear_attn.A_log": "model-00024-of-00026.safetensors",
526
+ "model.language_model.layers.36.linear_attn.conv1d.weight": "model-00024-of-00026.safetensors",
527
+ "model.language_model.layers.36.linear_attn.dt_bias": "model-00024-of-00026.safetensors",
528
+ "model.language_model.layers.36.linear_attn.in_proj_a.weight": "model-00024-of-00026.safetensors",
529
+ "model.language_model.layers.36.linear_attn.in_proj_b.weight": "model-00024-of-00026.safetensors",
530
+ "model.language_model.layers.36.linear_attn.in_proj_qkv.weight": "model-00024-of-00026.safetensors",
531
+ "model.language_model.layers.36.linear_attn.in_proj_z.weight": "model-00024-of-00026.safetensors",
532
+ "model.language_model.layers.36.linear_attn.norm.weight": "model-00024-of-00026.safetensors",
533
+ "model.language_model.layers.36.linear_attn.out_proj.weight": "model-00024-of-00026.safetensors",
534
+ "model.language_model.layers.36.mlp.experts.down_proj": "model-00024-of-00026.safetensors",
535
+ "model.language_model.layers.36.mlp.experts.gate_up_proj": "model-00024-of-00026.safetensors",
536
+ "model.language_model.layers.36.mlp.gate.weight": "model-00024-of-00026.safetensors",
537
+ "model.language_model.layers.36.mlp.shared_expert.down_proj.weight": "model-00024-of-00026.safetensors",
538
+ "model.language_model.layers.36.mlp.shared_expert.gate_proj.weight": "model-00024-of-00026.safetensors",
539
+ "model.language_model.layers.36.mlp.shared_expert.up_proj.weight": "model-00024-of-00026.safetensors",
540
+ "model.language_model.layers.36.mlp.shared_expert_gate.weight": "model-00024-of-00026.safetensors",
541
+ "model.language_model.layers.36.post_attention_layernorm.weight": "model-00024-of-00026.safetensors",
542
+ "model.language_model.layers.37.input_layernorm.weight": "model-00024-of-00026.safetensors",
543
+ "model.language_model.layers.37.linear_attn.A_log": "model-00024-of-00026.safetensors",
544
+ "model.language_model.layers.37.linear_attn.conv1d.weight": "model-00024-of-00026.safetensors",
545
+ "model.language_model.layers.37.linear_attn.dt_bias": "model-00024-of-00026.safetensors",
546
+ "model.language_model.layers.37.linear_attn.in_proj_a.weight": "model-00024-of-00026.safetensors",
547
+ "model.language_model.layers.37.linear_attn.in_proj_b.weight": "model-00024-of-00026.safetensors",
548
+ "model.language_model.layers.37.linear_attn.in_proj_qkv.weight": "model-00024-of-00026.safetensors",
549
+ "model.language_model.layers.37.linear_attn.in_proj_z.weight": "model-00024-of-00026.safetensors",
550
+ "model.language_model.layers.37.linear_attn.norm.weight": "model-00024-of-00026.safetensors",
551
+ "model.language_model.layers.37.linear_attn.out_proj.weight": "model-00024-of-00026.safetensors",
552
+ "model.language_model.layers.37.mlp.experts.down_proj": "model-00024-of-00026.safetensors",
553
+ "model.language_model.layers.37.mlp.experts.gate_up_proj": "model-00024-of-00026.safetensors",
554
+ "model.language_model.layers.37.mlp.gate.weight": "model-00024-of-00026.safetensors",
555
+ "model.language_model.layers.37.mlp.shared_expert.down_proj.weight": "model-00024-of-00026.safetensors",
556
+ "model.language_model.layers.37.mlp.shared_expert.gate_proj.weight": "model-00024-of-00026.safetensors",
557
+ "model.language_model.layers.37.mlp.shared_expert.up_proj.weight": "model-00024-of-00026.safetensors",
558
+ "model.language_model.layers.37.mlp.shared_expert_gate.weight": "model-00024-of-00026.safetensors",
559
+ "model.language_model.layers.37.post_attention_layernorm.weight": "model-00024-of-00026.safetensors",
560
+ "model.language_model.layers.38.input_layernorm.weight": "model-00025-of-00026.safetensors",
561
+ "model.language_model.layers.38.linear_attn.A_log": "model-00025-of-00026.safetensors",
562
+ "model.language_model.layers.38.linear_attn.conv1d.weight": "model-00025-of-00026.safetensors",
563
+ "model.language_model.layers.38.linear_attn.dt_bias": "model-00025-of-00026.safetensors",
564
+ "model.language_model.layers.38.linear_attn.in_proj_a.weight": "model-00025-of-00026.safetensors",
565
+ "model.language_model.layers.38.linear_attn.in_proj_b.weight": "model-00025-of-00026.safetensors",
566
+ "model.language_model.layers.38.linear_attn.in_proj_qkv.weight": "model-00025-of-00026.safetensors",
567
+ "model.language_model.layers.38.linear_attn.in_proj_z.weight": "model-00025-of-00026.safetensors",
568
+ "model.language_model.layers.38.linear_attn.norm.weight": "model-00025-of-00026.safetensors",
569
+ "model.language_model.layers.38.linear_attn.out_proj.weight": "model-00025-of-00026.safetensors",
570
+ "model.language_model.layers.38.mlp.experts.down_proj": "model-00025-of-00026.safetensors",
571
+ "model.language_model.layers.38.mlp.experts.gate_up_proj": "model-00025-of-00026.safetensors",
572
+ "model.language_model.layers.38.mlp.gate.weight": "model-00025-of-00026.safetensors",
573
+ "model.language_model.layers.38.mlp.shared_expert.down_proj.weight": "model-00025-of-00026.safetensors",
574
+ "model.language_model.layers.38.mlp.shared_expert.gate_proj.weight": "model-00025-of-00026.safetensors",
575
+ "model.language_model.layers.38.mlp.shared_expert.up_proj.weight": "model-00025-of-00026.safetensors",
576
+ "model.language_model.layers.38.mlp.shared_expert_gate.weight": "model-00025-of-00026.safetensors",
577
+ "model.language_model.layers.38.post_attention_layernorm.weight": "model-00025-of-00026.safetensors",
578
+ "model.language_model.layers.39.input_layernorm.weight": "model-00026-of-00026.safetensors",
579
+ "model.language_model.layers.39.mlp.experts.down_proj": "model-00026-of-00026.safetensors",
580
+ "model.language_model.layers.39.mlp.experts.gate_up_proj": "model-00025-of-00026.safetensors",
581
+ "model.language_model.layers.39.mlp.gate.weight": "model-00026-of-00026.safetensors",
582
+ "model.language_model.layers.39.mlp.shared_expert.down_proj.weight": "model-00026-of-00026.safetensors",
583
+ "model.language_model.layers.39.mlp.shared_expert.gate_proj.weight": "model-00026-of-00026.safetensors",
584
+ "model.language_model.layers.39.mlp.shared_expert.up_proj.weight": "model-00026-of-00026.safetensors",
585
+ "model.language_model.layers.39.mlp.shared_expert_gate.weight": "model-00026-of-00026.safetensors",
586
+ "model.language_model.layers.39.post_attention_layernorm.weight": "model-00026-of-00026.safetensors",
587
+ "model.language_model.layers.39.self_attn.k_norm.weight": "model-00026-of-00026.safetensors",
588
+ "model.language_model.layers.39.self_attn.k_proj.weight": "model-00026-of-00026.safetensors",
589
+ "model.language_model.layers.39.self_attn.o_proj.weight": "model-00026-of-00026.safetensors",
590
+ "model.language_model.layers.39.self_attn.q_norm.weight": "model-00026-of-00026.safetensors",
591
+ "model.language_model.layers.39.self_attn.q_proj.weight": "model-00026-of-00026.safetensors",
592
+ "model.language_model.layers.39.self_attn.v_proj.weight": "model-00026-of-00026.safetensors",
593
+ "model.language_model.layers.4.input_layernorm.weight": "model-00004-of-00026.safetensors",
594
+ "model.language_model.layers.4.linear_attn.A_log": "model-00004-of-00026.safetensors",
595
+ "model.language_model.layers.4.linear_attn.conv1d.weight": "model-00004-of-00026.safetensors",
596
+ "model.language_model.layers.4.linear_attn.dt_bias": "model-00004-of-00026.safetensors",
597
+ "model.language_model.layers.4.linear_attn.in_proj_a.weight": "model-00004-of-00026.safetensors",
598
+ "model.language_model.layers.4.linear_attn.in_proj_b.weight": "model-00004-of-00026.safetensors",
599
+ "model.language_model.layers.4.linear_attn.in_proj_qkv.weight": "model-00004-of-00026.safetensors",
600
+ "model.language_model.layers.4.linear_attn.in_proj_z.weight": "model-00004-of-00026.safetensors",
601
+ "model.language_model.layers.4.linear_attn.norm.weight": "model-00004-of-00026.safetensors",
602
+ "model.language_model.layers.4.linear_attn.out_proj.weight": "model-00004-of-00026.safetensors",
603
+ "model.language_model.layers.4.mlp.experts.down_proj": "model-00004-of-00026.safetensors",
604
+ "model.language_model.layers.4.mlp.experts.gate_up_proj": "model-00004-of-00026.safetensors",
605
+ "model.language_model.layers.4.mlp.gate.weight": "model-00004-of-00026.safetensors",
606
+ "model.language_model.layers.4.mlp.shared_expert.down_proj.weight": "model-00004-of-00026.safetensors",
607
+ "model.language_model.layers.4.mlp.shared_expert.gate_proj.weight": "model-00004-of-00026.safetensors",
608
+ "model.language_model.layers.4.mlp.shared_expert.up_proj.weight": "model-00004-of-00026.safetensors",
609
+ "model.language_model.layers.4.mlp.shared_expert_gate.weight": "model-00004-of-00026.safetensors",
610
+ "model.language_model.layers.4.post_attention_layernorm.weight": "model-00004-of-00026.safetensors",
611
+ "model.language_model.layers.5.input_layernorm.weight": "model-00004-of-00026.safetensors",
612
+ "model.language_model.layers.5.linear_attn.A_log": "model-00004-of-00026.safetensors",
613
+ "model.language_model.layers.5.linear_attn.conv1d.weight": "model-00004-of-00026.safetensors",
614
+ "model.language_model.layers.5.linear_attn.dt_bias": "model-00004-of-00026.safetensors",
615
+ "model.language_model.layers.5.linear_attn.in_proj_a.weight": "model-00004-of-00026.safetensors",
616
+ "model.language_model.layers.5.linear_attn.in_proj_b.weight": "model-00004-of-00026.safetensors",
617
+ "model.language_model.layers.5.linear_attn.in_proj_qkv.weight": "model-00004-of-00026.safetensors",
618
+ "model.language_model.layers.5.linear_attn.in_proj_z.weight": "model-00004-of-00026.safetensors",
619
+ "model.language_model.layers.5.linear_attn.norm.weight": "model-00004-of-00026.safetensors",
620
+ "model.language_model.layers.5.linear_attn.out_proj.weight": "model-00004-of-00026.safetensors",
621
+ "model.language_model.layers.5.mlp.experts.down_proj": "model-00004-of-00026.safetensors",
622
+ "model.language_model.layers.5.mlp.experts.gate_up_proj": "model-00004-of-00026.safetensors",
623
+ "model.language_model.layers.5.mlp.gate.weight": "model-00004-of-00026.safetensors",
624
+ "model.language_model.layers.5.mlp.shared_expert.down_proj.weight": "model-00004-of-00026.safetensors",
625
+ "model.language_model.layers.5.mlp.shared_expert.gate_proj.weight": "model-00004-of-00026.safetensors",
626
+ "model.language_model.layers.5.mlp.shared_expert.up_proj.weight": "model-00004-of-00026.safetensors",
627
+ "model.language_model.layers.5.mlp.shared_expert_gate.weight": "model-00004-of-00026.safetensors",
628
+ "model.language_model.layers.5.post_attention_layernorm.weight": "model-00004-of-00026.safetensors",
629
+ "model.language_model.layers.6.input_layernorm.weight": "model-00005-of-00026.safetensors",
630
+ "model.language_model.layers.6.linear_attn.A_log": "model-00005-of-00026.safetensors",
631
+ "model.language_model.layers.6.linear_attn.conv1d.weight": "model-00005-of-00026.safetensors",
632
+ "model.language_model.layers.6.linear_attn.dt_bias": "model-00005-of-00026.safetensors",
633
+ "model.language_model.layers.6.linear_attn.in_proj_a.weight": "model-00005-of-00026.safetensors",
634
+ "model.language_model.layers.6.linear_attn.in_proj_b.weight": "model-00005-of-00026.safetensors",
635
+ "model.language_model.layers.6.linear_attn.in_proj_qkv.weight": "model-00005-of-00026.safetensors",
636
+ "model.language_model.layers.6.linear_attn.in_proj_z.weight": "model-00005-of-00026.safetensors",
637
+ "model.language_model.layers.6.linear_attn.norm.weight": "model-00005-of-00026.safetensors",
638
+ "model.language_model.layers.6.linear_attn.out_proj.weight": "model-00005-of-00026.safetensors",
639
+ "model.language_model.layers.6.mlp.experts.down_proj": "model-00005-of-00026.safetensors",
640
+ "model.language_model.layers.6.mlp.experts.gate_up_proj": "model-00005-of-00026.safetensors",
641
+ "model.language_model.layers.6.mlp.gate.weight": "model-00005-of-00026.safetensors",
642
+ "model.language_model.layers.6.mlp.shared_expert.down_proj.weight": "model-00005-of-00026.safetensors",
643
+ "model.language_model.layers.6.mlp.shared_expert.gate_proj.weight": "model-00005-of-00026.safetensors",
644
+ "model.language_model.layers.6.mlp.shared_expert.up_proj.weight": "model-00005-of-00026.safetensors",
645
+ "model.language_model.layers.6.mlp.shared_expert_gate.weight": "model-00005-of-00026.safetensors",
646
+ "model.language_model.layers.6.post_attention_layernorm.weight": "model-00005-of-00026.safetensors",
647
+ "model.language_model.layers.7.input_layernorm.weight": "model-00005-of-00026.safetensors",
648
+ "model.language_model.layers.7.mlp.experts.down_proj": "model-00005-of-00026.safetensors",
649
+ "model.language_model.layers.7.mlp.experts.gate_up_proj": "model-00005-of-00026.safetensors",
650
+ "model.language_model.layers.7.mlp.gate.weight": "model-00005-of-00026.safetensors",
651
+ "model.language_model.layers.7.mlp.shared_expert.down_proj.weight": "model-00005-of-00026.safetensors",
652
+ "model.language_model.layers.7.mlp.shared_expert.gate_proj.weight": "model-00005-of-00026.safetensors",
653
+ "model.language_model.layers.7.mlp.shared_expert.up_proj.weight": "model-00005-of-00026.safetensors",
654
+ "model.language_model.layers.7.mlp.shared_expert_gate.weight": "model-00005-of-00026.safetensors",
655
+ "model.language_model.layers.7.post_attention_layernorm.weight": "model-00005-of-00026.safetensors",
656
+ "model.language_model.layers.7.self_attn.k_norm.weight": "model-00005-of-00026.safetensors",
657
+ "model.language_model.layers.7.self_attn.k_proj.weight": "model-00005-of-00026.safetensors",
658
+ "model.language_model.layers.7.self_attn.o_proj.weight": "model-00005-of-00026.safetensors",
659
+ "model.language_model.layers.7.self_attn.q_norm.weight": "model-00005-of-00026.safetensors",
660
+ "model.language_model.layers.7.self_attn.q_proj.weight": "model-00005-of-00026.safetensors",
661
+ "model.language_model.layers.7.self_attn.v_proj.weight": "model-00005-of-00026.safetensors",
662
+ "model.language_model.layers.8.input_layernorm.weight": "model-00007-of-00026.safetensors",
663
+ "model.language_model.layers.8.linear_attn.A_log": "model-00007-of-00026.safetensors",
664
+ "model.language_model.layers.8.linear_attn.conv1d.weight": "model-00007-of-00026.safetensors",
665
+ "model.language_model.layers.8.linear_attn.dt_bias": "model-00007-of-00026.safetensors",
666
+ "model.language_model.layers.8.linear_attn.in_proj_a.weight": "model-00007-of-00026.safetensors",
667
+ "model.language_model.layers.8.linear_attn.in_proj_b.weight": "model-00007-of-00026.safetensors",
668
+ "model.language_model.layers.8.linear_attn.in_proj_qkv.weight": "model-00006-of-00026.safetensors",
669
+ "model.language_model.layers.8.linear_attn.in_proj_z.weight": "model-00006-of-00026.safetensors",
670
+ "model.language_model.layers.8.linear_attn.norm.weight": "model-00007-of-00026.safetensors",
671
+ "model.language_model.layers.8.linear_attn.out_proj.weight": "model-00006-of-00026.safetensors",
672
+ "model.language_model.layers.8.mlp.experts.down_proj": "model-00006-of-00026.safetensors",
673
+ "model.language_model.layers.8.mlp.experts.gate_up_proj": "model-00006-of-00026.safetensors",
674
+ "model.language_model.layers.8.mlp.gate.weight": "model-00007-of-00026.safetensors",
675
+ "model.language_model.layers.8.mlp.shared_expert.down_proj.weight": "model-00007-of-00026.safetensors",
676
+ "model.language_model.layers.8.mlp.shared_expert.gate_proj.weight": "model-00007-of-00026.safetensors",
677
+ "model.language_model.layers.8.mlp.shared_expert.up_proj.weight": "model-00007-of-00026.safetensors",
678
+ "model.language_model.layers.8.mlp.shared_expert_gate.weight": "model-00007-of-00026.safetensors",
679
+ "model.language_model.layers.8.post_attention_layernorm.weight": "model-00007-of-00026.safetensors",
680
+ "model.language_model.layers.9.input_layernorm.weight": "model-00007-of-00026.safetensors",
681
+ "model.language_model.layers.9.linear_attn.A_log": "model-00007-of-00026.safetensors",
682
+ "model.language_model.layers.9.linear_attn.conv1d.weight": "model-00007-of-00026.safetensors",
683
+ "model.language_model.layers.9.linear_attn.dt_bias": "model-00007-of-00026.safetensors",
684
+ "model.language_model.layers.9.linear_attn.in_proj_a.weight": "model-00007-of-00026.safetensors",
685
+ "model.language_model.layers.9.linear_attn.in_proj_b.weight": "model-00007-of-00026.safetensors",
686
+ "model.language_model.layers.9.linear_attn.in_proj_qkv.weight": "model-00006-of-00026.safetensors",
687
+ "model.language_model.layers.9.linear_attn.in_proj_z.weight": "model-00006-of-00026.safetensors",
688
+ "model.language_model.layers.9.linear_attn.norm.weight": "model-00007-of-00026.safetensors",
689
+ "model.language_model.layers.9.linear_attn.out_proj.weight": "model-00006-of-00026.safetensors",
690
+ "model.language_model.layers.9.mlp.experts.down_proj": "model-00006-of-00026.safetensors",
691
+ "model.language_model.layers.9.mlp.experts.gate_up_proj": "model-00006-of-00026.safetensors",
692
+ "model.language_model.layers.9.mlp.gate.weight": "model-00007-of-00026.safetensors",
693
+ "model.language_model.layers.9.mlp.shared_expert.down_proj.weight": "model-00007-of-00026.safetensors",
694
+ "model.language_model.layers.9.mlp.shared_expert.gate_proj.weight": "model-00007-of-00026.safetensors",
695
+ "model.language_model.layers.9.mlp.shared_expert.up_proj.weight": "model-00007-of-00026.safetensors",
696
+ "model.language_model.layers.9.mlp.shared_expert_gate.weight": "model-00007-of-00026.safetensors",
697
+ "model.language_model.layers.9.post_attention_layernorm.weight": "model-00007-of-00026.safetensors",
698
+ "model.language_model.norm.weight": "model-00026-of-00026.safetensors",
699
+ "model.visual.blocks.0.attn.proj.bias": "model-00002-of-00026.safetensors",
700
+ "model.visual.blocks.0.attn.proj.weight": "model-00002-of-00026.safetensors",
701
+ "model.visual.blocks.0.attn.qkv.bias": "model-00002-of-00026.safetensors",
702
+ "model.visual.blocks.0.attn.qkv.weight": "model-00002-of-00026.safetensors",
703
+ "model.visual.blocks.0.mlp.linear_fc1.bias": "model-00002-of-00026.safetensors",
704
+ "model.visual.blocks.0.mlp.linear_fc1.weight": "model-00001-of-00026.safetensors",
705
+ "model.visual.blocks.0.mlp.linear_fc2.bias": "model-00002-of-00026.safetensors",
706
+ "model.visual.blocks.0.mlp.linear_fc2.weight": "model-00001-of-00026.safetensors",
707
+ "model.visual.blocks.0.norm1.bias": "model-00002-of-00026.safetensors",
708
+ "model.visual.blocks.0.norm1.weight": "model-00002-of-00026.safetensors",
709
+ "model.visual.blocks.0.norm2.bias": "model-00002-of-00026.safetensors",
710
+ "model.visual.blocks.0.norm2.weight": "model-00002-of-00026.safetensors",
711
+ "model.visual.blocks.1.attn.proj.bias": "model-00002-of-00026.safetensors",
712
+ "model.visual.blocks.1.attn.proj.weight": "model-00002-of-00026.safetensors",
713
+ "model.visual.blocks.1.attn.qkv.bias": "model-00002-of-00026.safetensors",
714
+ "model.visual.blocks.1.attn.qkv.weight": "model-00002-of-00026.safetensors",
715
+ "model.visual.blocks.1.mlp.linear_fc1.bias": "model-00002-of-00026.safetensors",
716
+ "model.visual.blocks.1.mlp.linear_fc1.weight": "model-00001-of-00026.safetensors",
717
+ "model.visual.blocks.1.mlp.linear_fc2.bias": "model-00002-of-00026.safetensors",
718
+ "model.visual.blocks.1.mlp.linear_fc2.weight": "model-00001-of-00026.safetensors",
719
+ "model.visual.blocks.1.norm1.bias": "model-00002-of-00026.safetensors",
720
+ "model.visual.blocks.1.norm1.weight": "model-00002-of-00026.safetensors",
721
+ "model.visual.blocks.1.norm2.bias": "model-00002-of-00026.safetensors",
722
+ "model.visual.blocks.1.norm2.weight": "model-00002-of-00026.safetensors",
723
+ "model.visual.blocks.10.attn.proj.bias": "model-00002-of-00026.safetensors",
724
+ "model.visual.blocks.10.attn.proj.weight": "model-00002-of-00026.safetensors",
725
+ "model.visual.blocks.10.attn.qkv.bias": "model-00002-of-00026.safetensors",
726
+ "model.visual.blocks.10.attn.qkv.weight": "model-00002-of-00026.safetensors",
727
+ "model.visual.blocks.10.mlp.linear_fc1.bias": "model-00002-of-00026.safetensors",
728
+ "model.visual.blocks.10.mlp.linear_fc1.weight": "model-00001-of-00026.safetensors",
729
+ "model.visual.blocks.10.mlp.linear_fc2.bias": "model-00002-of-00026.safetensors",
730
+ "model.visual.blocks.10.mlp.linear_fc2.weight": "model-00001-of-00026.safetensors",
731
+ "model.visual.blocks.10.norm1.bias": "model-00002-of-00026.safetensors",
732
+ "model.visual.blocks.10.norm1.weight": "model-00002-of-00026.safetensors",
733
+ "model.visual.blocks.10.norm2.bias": "model-00002-of-00026.safetensors",
734
+ "model.visual.blocks.10.norm2.weight": "model-00002-of-00026.safetensors",
735
+ "model.visual.blocks.11.attn.proj.bias": "model-00002-of-00026.safetensors",
736
+ "model.visual.blocks.11.attn.proj.weight": "model-00002-of-00026.safetensors",
737
+ "model.visual.blocks.11.attn.qkv.bias": "model-00002-of-00026.safetensors",
738
+ "model.visual.blocks.11.attn.qkv.weight": "model-00002-of-00026.safetensors",
739
+ "model.visual.blocks.11.mlp.linear_fc1.bias": "model-00002-of-00026.safetensors",
740
+ "model.visual.blocks.11.mlp.linear_fc1.weight": "model-00001-of-00026.safetensors",
741
+ "model.visual.blocks.11.mlp.linear_fc2.bias": "model-00002-of-00026.safetensors",
742
+ "model.visual.blocks.11.mlp.linear_fc2.weight": "model-00001-of-00026.safetensors",
743
+ "model.visual.blocks.11.norm1.bias": "model-00002-of-00026.safetensors",
744
+ "model.visual.blocks.11.norm1.weight": "model-00002-of-00026.safetensors",
745
+ "model.visual.blocks.11.norm2.bias": "model-00002-of-00026.safetensors",
746
+ "model.visual.blocks.11.norm2.weight": "model-00002-of-00026.safetensors",
747
+ "model.visual.blocks.12.attn.proj.bias": "model-00002-of-00026.safetensors",
748
+ "model.visual.blocks.12.attn.proj.weight": "model-00002-of-00026.safetensors",
749
+ "model.visual.blocks.12.attn.qkv.bias": "model-00002-of-00026.safetensors",
750
+ "model.visual.blocks.12.attn.qkv.weight": "model-00002-of-00026.safetensors",
751
+ "model.visual.blocks.12.mlp.linear_fc1.bias": "model-00002-of-00026.safetensors",
752
+ "model.visual.blocks.12.mlp.linear_fc1.weight": "model-00001-of-00026.safetensors",
753
+ "model.visual.blocks.12.mlp.linear_fc2.bias": "model-00002-of-00026.safetensors",
754
+ "model.visual.blocks.12.mlp.linear_fc2.weight": "model-00001-of-00026.safetensors",
755
+ "model.visual.blocks.12.norm1.bias": "model-00002-of-00026.safetensors",
756
+ "model.visual.blocks.12.norm1.weight": "model-00002-of-00026.safetensors",
757
+ "model.visual.blocks.12.norm2.bias": "model-00002-of-00026.safetensors",
758
+ "model.visual.blocks.12.norm2.weight": "model-00002-of-00026.safetensors",
759
+ "model.visual.blocks.13.attn.proj.bias": "model-00002-of-00026.safetensors",
760
+ "model.visual.blocks.13.attn.proj.weight": "model-00002-of-00026.safetensors",
761
+ "model.visual.blocks.13.attn.qkv.bias": "model-00002-of-00026.safetensors",
762
+ "model.visual.blocks.13.attn.qkv.weight": "model-00002-of-00026.safetensors",
763
+ "model.visual.blocks.13.mlp.linear_fc1.bias": "model-00002-of-00026.safetensors",
764
+ "model.visual.blocks.13.mlp.linear_fc1.weight": "model-00002-of-00026.safetensors",
765
+ "model.visual.blocks.13.mlp.linear_fc2.bias": "model-00002-of-00026.safetensors",
766
+ "model.visual.blocks.13.mlp.linear_fc2.weight": "model-00002-of-00026.safetensors",
767
+ "model.visual.blocks.13.norm1.bias": "model-00002-of-00026.safetensors",
768
+ "model.visual.blocks.13.norm1.weight": "model-00002-of-00026.safetensors",
769
+ "model.visual.blocks.13.norm2.bias": "model-00002-of-00026.safetensors",
770
+ "model.visual.blocks.13.norm2.weight": "model-00002-of-00026.safetensors",
771
+ "model.visual.blocks.14.attn.proj.bias": "model-00002-of-00026.safetensors",
772
+ "model.visual.blocks.14.attn.proj.weight": "model-00002-of-00026.safetensors",
773
+ "model.visual.blocks.14.attn.qkv.bias": "model-00002-of-00026.safetensors",
774
+ "model.visual.blocks.14.attn.qkv.weight": "model-00002-of-00026.safetensors",
775
+ "model.visual.blocks.14.mlp.linear_fc1.bias": "model-00002-of-00026.safetensors",
776
+ "model.visual.blocks.14.mlp.linear_fc1.weight": "model-00002-of-00026.safetensors",
777
+ "model.visual.blocks.14.mlp.linear_fc2.bias": "model-00002-of-00026.safetensors",
778
+ "model.visual.blocks.14.mlp.linear_fc2.weight": "model-00002-of-00026.safetensors",
779
+ "model.visual.blocks.14.norm1.bias": "model-00002-of-00026.safetensors",
780
+ "model.visual.blocks.14.norm1.weight": "model-00002-of-00026.safetensors",
781
+ "model.visual.blocks.14.norm2.bias": "model-00002-of-00026.safetensors",
782
+ "model.visual.blocks.14.norm2.weight": "model-00002-of-00026.safetensors",
783
+ "model.visual.blocks.15.attn.proj.bias": "model-00002-of-00026.safetensors",
784
+ "model.visual.blocks.15.attn.proj.weight": "model-00002-of-00026.safetensors",
785
+ "model.visual.blocks.15.attn.qkv.bias": "model-00002-of-00026.safetensors",
786
+ "model.visual.blocks.15.attn.qkv.weight": "model-00002-of-00026.safetensors",
787
+ "model.visual.blocks.15.mlp.linear_fc1.bias": "model-00002-of-00026.safetensors",
788
+ "model.visual.blocks.15.mlp.linear_fc1.weight": "model-00002-of-00026.safetensors",
789
+ "model.visual.blocks.15.mlp.linear_fc2.bias": "model-00002-of-00026.safetensors",
790
+ "model.visual.blocks.15.mlp.linear_fc2.weight": "model-00002-of-00026.safetensors",
791
+ "model.visual.blocks.15.norm1.bias": "model-00002-of-00026.safetensors",
792
+ "model.visual.blocks.15.norm1.weight": "model-00002-of-00026.safetensors",
793
+ "model.visual.blocks.15.norm2.bias": "model-00002-of-00026.safetensors",
794
+ "model.visual.blocks.15.norm2.weight": "model-00002-of-00026.safetensors",
795
+ "model.visual.blocks.16.attn.proj.bias": "model-00002-of-00026.safetensors",
796
+ "model.visual.blocks.16.attn.proj.weight": "model-00002-of-00026.safetensors",
797
+ "model.visual.blocks.16.attn.qkv.bias": "model-00002-of-00026.safetensors",
798
+ "model.visual.blocks.16.attn.qkv.weight": "model-00002-of-00026.safetensors",
799
+ "model.visual.blocks.16.mlp.linear_fc1.bias": "model-00002-of-00026.safetensors",
800
+ "model.visual.blocks.16.mlp.linear_fc1.weight": "model-00002-of-00026.safetensors",
801
+ "model.visual.blocks.16.mlp.linear_fc2.bias": "model-00002-of-00026.safetensors",
802
+ "model.visual.blocks.16.mlp.linear_fc2.weight": "model-00002-of-00026.safetensors",
803
+ "model.visual.blocks.16.norm1.bias": "model-00002-of-00026.safetensors",
804
+ "model.visual.blocks.16.norm1.weight": "model-00002-of-00026.safetensors",
805
+ "model.visual.blocks.16.norm2.bias": "model-00002-of-00026.safetensors",
806
+ "model.visual.blocks.16.norm2.weight": "model-00002-of-00026.safetensors",
807
+ "model.visual.blocks.17.attn.proj.bias": "model-00002-of-00026.safetensors",
808
+ "model.visual.blocks.17.attn.proj.weight": "model-00002-of-00026.safetensors",
809
+ "model.visual.blocks.17.attn.qkv.bias": "model-00002-of-00026.safetensors",
810
+ "model.visual.blocks.17.attn.qkv.weight": "model-00002-of-00026.safetensors",
811
+ "model.visual.blocks.17.mlp.linear_fc1.bias": "model-00002-of-00026.safetensors",
812
+ "model.visual.blocks.17.mlp.linear_fc1.weight": "model-00002-of-00026.safetensors",
813
+ "model.visual.blocks.17.mlp.linear_fc2.bias": "model-00002-of-00026.safetensors",
814
+ "model.visual.blocks.17.mlp.linear_fc2.weight": "model-00002-of-00026.safetensors",
815
+ "model.visual.blocks.17.norm1.bias": "model-00002-of-00026.safetensors",
816
+ "model.visual.blocks.17.norm1.weight": "model-00002-of-00026.safetensors",
817
+ "model.visual.blocks.17.norm2.bias": "model-00002-of-00026.safetensors",
818
+ "model.visual.blocks.17.norm2.weight": "model-00002-of-00026.safetensors",
819
+ "model.visual.blocks.18.attn.proj.bias": "model-00002-of-00026.safetensors",
820
+ "model.visual.blocks.18.attn.proj.weight": "model-00002-of-00026.safetensors",
821
+ "model.visual.blocks.18.attn.qkv.bias": "model-00002-of-00026.safetensors",
822
+ "model.visual.blocks.18.attn.qkv.weight": "model-00002-of-00026.safetensors",
823
+ "model.visual.blocks.18.mlp.linear_fc1.bias": "model-00002-of-00026.safetensors",
824
+ "model.visual.blocks.18.mlp.linear_fc1.weight": "model-00002-of-00026.safetensors",
825
+ "model.visual.blocks.18.mlp.linear_fc2.bias": "model-00002-of-00026.safetensors",
826
+ "model.visual.blocks.18.mlp.linear_fc2.weight": "model-00002-of-00026.safetensors",
827
+ "model.visual.blocks.18.norm1.bias": "model-00002-of-00026.safetensors",
828
+ "model.visual.blocks.18.norm1.weight": "model-00002-of-00026.safetensors",
829
+ "model.visual.blocks.18.norm2.bias": "model-00002-of-00026.safetensors",
830
+ "model.visual.blocks.18.norm2.weight": "model-00002-of-00026.safetensors",
831
+ "model.visual.blocks.19.attn.proj.bias": "model-00002-of-00026.safetensors",
832
+ "model.visual.blocks.19.attn.proj.weight": "model-00002-of-00026.safetensors",
833
+ "model.visual.blocks.19.attn.qkv.bias": "model-00002-of-00026.safetensors",
834
+ "model.visual.blocks.19.attn.qkv.weight": "model-00002-of-00026.safetensors",
835
+ "model.visual.blocks.19.mlp.linear_fc1.bias": "model-00002-of-00026.safetensors",
836
+ "model.visual.blocks.19.mlp.linear_fc1.weight": "model-00002-of-00026.safetensors",
837
+ "model.visual.blocks.19.mlp.linear_fc2.bias": "model-00002-of-00026.safetensors",
838
+ "model.visual.blocks.19.mlp.linear_fc2.weight": "model-00002-of-00026.safetensors",
839
+ "model.visual.blocks.19.norm1.bias": "model-00002-of-00026.safetensors",
840
+ "model.visual.blocks.19.norm1.weight": "model-00002-of-00026.safetensors",
841
+ "model.visual.blocks.19.norm2.bias": "model-00002-of-00026.safetensors",
842
+ "model.visual.blocks.19.norm2.weight": "model-00002-of-00026.safetensors",
843
+ "model.visual.blocks.2.attn.proj.bias": "model-00002-of-00026.safetensors",
844
+ "model.visual.blocks.2.attn.proj.weight": "model-00002-of-00026.safetensors",
845
+ "model.visual.blocks.2.attn.qkv.bias": "model-00002-of-00026.safetensors",
846
+ "model.visual.blocks.2.attn.qkv.weight": "model-00002-of-00026.safetensors",
847
+ "model.visual.blocks.2.mlp.linear_fc1.bias": "model-00002-of-00026.safetensors",
848
+ "model.visual.blocks.2.mlp.linear_fc1.weight": "model-00002-of-00026.safetensors",
849
+ "model.visual.blocks.2.mlp.linear_fc2.bias": "model-00002-of-00026.safetensors",
850
+ "model.visual.blocks.2.mlp.linear_fc2.weight": "model-00002-of-00026.safetensors",
851
+ "model.visual.blocks.2.norm1.bias": "model-00002-of-00026.safetensors",
852
+ "model.visual.blocks.2.norm1.weight": "model-00002-of-00026.safetensors",
853
+ "model.visual.blocks.2.norm2.bias": "model-00002-of-00026.safetensors",
854
+ "model.visual.blocks.2.norm2.weight": "model-00002-of-00026.safetensors",
855
+ "model.visual.blocks.20.attn.proj.bias": "model-00002-of-00026.safetensors",
856
+ "model.visual.blocks.20.attn.proj.weight": "model-00002-of-00026.safetensors",
857
+ "model.visual.blocks.20.attn.qkv.bias": "model-00002-of-00026.safetensors",
858
+ "model.visual.blocks.20.attn.qkv.weight": "model-00002-of-00026.safetensors",
859
+ "model.visual.blocks.20.mlp.linear_fc1.bias": "model-00002-of-00026.safetensors",
860
+ "model.visual.blocks.20.mlp.linear_fc1.weight": "model-00002-of-00026.safetensors",
861
+ "model.visual.blocks.20.mlp.linear_fc2.bias": "model-00002-of-00026.safetensors",
862
+ "model.visual.blocks.20.mlp.linear_fc2.weight": "model-00002-of-00026.safetensors",
863
+ "model.visual.blocks.20.norm1.bias": "model-00002-of-00026.safetensors",
864
+ "model.visual.blocks.20.norm1.weight": "model-00002-of-00026.safetensors",
865
+ "model.visual.blocks.20.norm2.bias": "model-00002-of-00026.safetensors",
866
+ "model.visual.blocks.20.norm2.weight": "model-00002-of-00026.safetensors",
867
+ "model.visual.blocks.21.attn.proj.bias": "model-00002-of-00026.safetensors",
868
+ "model.visual.blocks.21.attn.proj.weight": "model-00002-of-00026.safetensors",
869
+ "model.visual.blocks.21.attn.qkv.bias": "model-00002-of-00026.safetensors",
870
+ "model.visual.blocks.21.attn.qkv.weight": "model-00002-of-00026.safetensors",
871
+ "model.visual.blocks.21.mlp.linear_fc1.bias": "model-00002-of-00026.safetensors",
872
+ "model.visual.blocks.21.mlp.linear_fc1.weight": "model-00002-of-00026.safetensors",
873
+ "model.visual.blocks.21.mlp.linear_fc2.bias": "model-00002-of-00026.safetensors",
874
+ "model.visual.blocks.21.mlp.linear_fc2.weight": "model-00002-of-00026.safetensors",
875
+ "model.visual.blocks.21.norm1.bias": "model-00002-of-00026.safetensors",
876
+ "model.visual.blocks.21.norm1.weight": "model-00002-of-00026.safetensors",
877
+ "model.visual.blocks.21.norm2.bias": "model-00002-of-00026.safetensors",
878
+ "model.visual.blocks.21.norm2.weight": "model-00002-of-00026.safetensors",
879
+ "model.visual.blocks.22.attn.proj.bias": "model-00002-of-00026.safetensors",
880
+ "model.visual.blocks.22.attn.proj.weight": "model-00002-of-00026.safetensors",
881
+ "model.visual.blocks.22.attn.qkv.bias": "model-00002-of-00026.safetensors",
882
+ "model.visual.blocks.22.attn.qkv.weight": "model-00002-of-00026.safetensors",
883
+ "model.visual.blocks.22.mlp.linear_fc1.bias": "model-00002-of-00026.safetensors",
884
+ "model.visual.blocks.22.mlp.linear_fc1.weight": "model-00002-of-00026.safetensors",
885
+ "model.visual.blocks.22.mlp.linear_fc2.bias": "model-00002-of-00026.safetensors",
886
+ "model.visual.blocks.22.mlp.linear_fc2.weight": "model-00002-of-00026.safetensors",
887
+ "model.visual.blocks.22.norm1.bias": "model-00002-of-00026.safetensors",
888
+ "model.visual.blocks.22.norm1.weight": "model-00002-of-00026.safetensors",
889
+ "model.visual.blocks.22.norm2.bias": "model-00002-of-00026.safetensors",
890
+ "model.visual.blocks.22.norm2.weight": "model-00002-of-00026.safetensors",
891
+ "model.visual.blocks.23.attn.proj.bias": "model-00002-of-00026.safetensors",
892
+ "model.visual.blocks.23.attn.proj.weight": "model-00002-of-00026.safetensors",
893
+ "model.visual.blocks.23.attn.qkv.bias": "model-00002-of-00026.safetensors",
894
+ "model.visual.blocks.23.attn.qkv.weight": "model-00002-of-00026.safetensors",
895
+ "model.visual.blocks.23.mlp.linear_fc1.bias": "model-00002-of-00026.safetensors",
896
+ "model.visual.blocks.23.mlp.linear_fc1.weight": "model-00002-of-00026.safetensors",
897
+ "model.visual.blocks.23.mlp.linear_fc2.bias": "model-00002-of-00026.safetensors",
898
+ "model.visual.blocks.23.mlp.linear_fc2.weight": "model-00002-of-00026.safetensors",
899
+ "model.visual.blocks.23.norm1.bias": "model-00002-of-00026.safetensors",
900
+ "model.visual.blocks.23.norm1.weight": "model-00002-of-00026.safetensors",
901
+ "model.visual.blocks.23.norm2.bias": "model-00002-of-00026.safetensors",
902
+ "model.visual.blocks.23.norm2.weight": "model-00002-of-00026.safetensors",
903
+ "model.visual.blocks.24.attn.proj.bias": "model-00002-of-00026.safetensors",
904
+ "model.visual.blocks.24.attn.proj.weight": "model-00002-of-00026.safetensors",
905
+ "model.visual.blocks.24.attn.qkv.bias": "model-00002-of-00026.safetensors",
906
+ "model.visual.blocks.24.attn.qkv.weight": "model-00002-of-00026.safetensors",
907
+ "model.visual.blocks.24.mlp.linear_fc1.bias": "model-00002-of-00026.safetensors",
908
+ "model.visual.blocks.24.mlp.linear_fc1.weight": "model-00002-of-00026.safetensors",
909
+ "model.visual.blocks.24.mlp.linear_fc2.bias": "model-00002-of-00026.safetensors",
910
+ "model.visual.blocks.24.mlp.linear_fc2.weight": "model-00002-of-00026.safetensors",
911
+ "model.visual.blocks.24.norm1.bias": "model-00002-of-00026.safetensors",
912
+ "model.visual.blocks.24.norm1.weight": "model-00002-of-00026.safetensors",
913
+ "model.visual.blocks.24.norm2.bias": "model-00002-of-00026.safetensors",
914
+ "model.visual.blocks.24.norm2.weight": "model-00002-of-00026.safetensors",
915
+ "model.visual.blocks.25.attn.proj.bias": "model-00002-of-00026.safetensors",
916
+ "model.visual.blocks.25.attn.proj.weight": "model-00002-of-00026.safetensors",
917
+ "model.visual.blocks.25.attn.qkv.bias": "model-00002-of-00026.safetensors",
918
+ "model.visual.blocks.25.attn.qkv.weight": "model-00002-of-00026.safetensors",
919
+ "model.visual.blocks.25.mlp.linear_fc1.bias": "model-00002-of-00026.safetensors",
920
+ "model.visual.blocks.25.mlp.linear_fc1.weight": "model-00002-of-00026.safetensors",
921
+ "model.visual.blocks.25.mlp.linear_fc2.bias": "model-00002-of-00026.safetensors",
922
+ "model.visual.blocks.25.mlp.linear_fc2.weight": "model-00002-of-00026.safetensors",
923
+ "model.visual.blocks.25.norm1.bias": "model-00002-of-00026.safetensors",
924
+ "model.visual.blocks.25.norm1.weight": "model-00002-of-00026.safetensors",
925
+ "model.visual.blocks.25.norm2.bias": "model-00002-of-00026.safetensors",
926
+ "model.visual.blocks.25.norm2.weight": "model-00002-of-00026.safetensors",
927
+ "model.visual.blocks.26.attn.proj.bias": "model-00002-of-00026.safetensors",
928
+ "model.visual.blocks.26.attn.proj.weight": "model-00002-of-00026.safetensors",
929
+ "model.visual.blocks.26.attn.qkv.bias": "model-00002-of-00026.safetensors",
930
+ "model.visual.blocks.26.attn.qkv.weight": "model-00002-of-00026.safetensors",
931
+ "model.visual.blocks.26.mlp.linear_fc1.bias": "model-00002-of-00026.safetensors",
932
+ "model.visual.blocks.26.mlp.linear_fc1.weight": "model-00002-of-00026.safetensors",
933
+ "model.visual.blocks.26.mlp.linear_fc2.bias": "model-00002-of-00026.safetensors",
934
+ "model.visual.blocks.26.mlp.linear_fc2.weight": "model-00002-of-00026.safetensors",
935
+ "model.visual.blocks.26.norm1.bias": "model-00002-of-00026.safetensors",
936
+ "model.visual.blocks.26.norm1.weight": "model-00002-of-00026.safetensors",
937
+ "model.visual.blocks.26.norm2.bias": "model-00002-of-00026.safetensors",
938
+ "model.visual.blocks.26.norm2.weight": "model-00002-of-00026.safetensors",
939
+ "model.visual.blocks.3.attn.proj.bias": "model-00002-of-00026.safetensors",
940
+ "model.visual.blocks.3.attn.proj.weight": "model-00002-of-00026.safetensors",
941
+ "model.visual.blocks.3.attn.qkv.bias": "model-00002-of-00026.safetensors",
942
+ "model.visual.blocks.3.attn.qkv.weight": "model-00002-of-00026.safetensors",
943
+ "model.visual.blocks.3.mlp.linear_fc1.bias": "model-00002-of-00026.safetensors",
944
+ "model.visual.blocks.3.mlp.linear_fc1.weight": "model-00002-of-00026.safetensors",
945
+ "model.visual.blocks.3.mlp.linear_fc2.bias": "model-00002-of-00026.safetensors",
946
+ "model.visual.blocks.3.mlp.linear_fc2.weight": "model-00002-of-00026.safetensors",
947
+ "model.visual.blocks.3.norm1.bias": "model-00002-of-00026.safetensors",
948
+ "model.visual.blocks.3.norm1.weight": "model-00002-of-00026.safetensors",
949
+ "model.visual.blocks.3.norm2.bias": "model-00002-of-00026.safetensors",
950
+ "model.visual.blocks.3.norm2.weight": "model-00002-of-00026.safetensors",
951
+ "model.visual.blocks.4.attn.proj.bias": "model-00002-of-00026.safetensors",
952
+ "model.visual.blocks.4.attn.proj.weight": "model-00002-of-00026.safetensors",
953
+ "model.visual.blocks.4.attn.qkv.bias": "model-00002-of-00026.safetensors",
954
+ "model.visual.blocks.4.attn.qkv.weight": "model-00002-of-00026.safetensors",
955
+ "model.visual.blocks.4.mlp.linear_fc1.bias": "model-00002-of-00026.safetensors",
956
+ "model.visual.blocks.4.mlp.linear_fc1.weight": "model-00002-of-00026.safetensors",
957
+ "model.visual.blocks.4.mlp.linear_fc2.bias": "model-00002-of-00026.safetensors",
958
+ "model.visual.blocks.4.mlp.linear_fc2.weight": "model-00002-of-00026.safetensors",
959
+ "model.visual.blocks.4.norm1.bias": "model-00002-of-00026.safetensors",
960
+ "model.visual.blocks.4.norm1.weight": "model-00002-of-00026.safetensors",
961
+ "model.visual.blocks.4.norm2.bias": "model-00002-of-00026.safetensors",
962
+ "model.visual.blocks.4.norm2.weight": "model-00002-of-00026.safetensors",
963
+ "model.visual.blocks.5.attn.proj.bias": "model-00002-of-00026.safetensors",
964
+ "model.visual.blocks.5.attn.proj.weight": "model-00002-of-00026.safetensors",
965
+ "model.visual.blocks.5.attn.qkv.bias": "model-00002-of-00026.safetensors",
966
+ "model.visual.blocks.5.attn.qkv.weight": "model-00002-of-00026.safetensors",
967
+ "model.visual.blocks.5.mlp.linear_fc1.bias": "model-00002-of-00026.safetensors",
968
+ "model.visual.blocks.5.mlp.linear_fc1.weight": "model-00002-of-00026.safetensors",
969
+ "model.visual.blocks.5.mlp.linear_fc2.bias": "model-00002-of-00026.safetensors",
970
+ "model.visual.blocks.5.mlp.linear_fc2.weight": "model-00002-of-00026.safetensors",
971
+ "model.visual.blocks.5.norm1.bias": "model-00002-of-00026.safetensors",
972
+ "model.visual.blocks.5.norm1.weight": "model-00002-of-00026.safetensors",
973
+ "model.visual.blocks.5.norm2.bias": "model-00002-of-00026.safetensors",
974
+ "model.visual.blocks.5.norm2.weight": "model-00002-of-00026.safetensors",
975
+ "model.visual.blocks.6.attn.proj.bias": "model-00002-of-00026.safetensors",
976
+ "model.visual.blocks.6.attn.proj.weight": "model-00002-of-00026.safetensors",
977
+ "model.visual.blocks.6.attn.qkv.bias": "model-00002-of-00026.safetensors",
978
+ "model.visual.blocks.6.attn.qkv.weight": "model-00002-of-00026.safetensors",
979
+ "model.visual.blocks.6.mlp.linear_fc1.bias": "model-00002-of-00026.safetensors",
980
+ "model.visual.blocks.6.mlp.linear_fc1.weight": "model-00002-of-00026.safetensors",
981
+ "model.visual.blocks.6.mlp.linear_fc2.bias": "model-00002-of-00026.safetensors",
982
+ "model.visual.blocks.6.mlp.linear_fc2.weight": "model-00002-of-00026.safetensors",
983
+ "model.visual.blocks.6.norm1.bias": "model-00002-of-00026.safetensors",
984
+ "model.visual.blocks.6.norm1.weight": "model-00002-of-00026.safetensors",
985
+ "model.visual.blocks.6.norm2.bias": "model-00002-of-00026.safetensors",
986
+ "model.visual.blocks.6.norm2.weight": "model-00002-of-00026.safetensors",
987
+ "model.visual.blocks.7.attn.proj.bias": "model-00002-of-00026.safetensors",
988
+ "model.visual.blocks.7.attn.proj.weight": "model-00002-of-00026.safetensors",
989
+ "model.visual.blocks.7.attn.qkv.bias": "model-00002-of-00026.safetensors",
990
+ "model.visual.blocks.7.attn.qkv.weight": "model-00002-of-00026.safetensors",
991
+ "model.visual.blocks.7.mlp.linear_fc1.bias": "model-00002-of-00026.safetensors",
992
+ "model.visual.blocks.7.mlp.linear_fc1.weight": "model-00002-of-00026.safetensors",
993
+ "model.visual.blocks.7.mlp.linear_fc2.bias": "model-00002-of-00026.safetensors",
994
+ "model.visual.blocks.7.mlp.linear_fc2.weight": "model-00002-of-00026.safetensors",
995
+ "model.visual.blocks.7.norm1.bias": "model-00002-of-00026.safetensors",
996
+ "model.visual.blocks.7.norm1.weight": "model-00002-of-00026.safetensors",
997
+ "model.visual.blocks.7.norm2.bias": "model-00002-of-00026.safetensors",
998
+ "model.visual.blocks.7.norm2.weight": "model-00002-of-00026.safetensors",
999
+ "model.visual.blocks.8.attn.proj.bias": "model-00002-of-00026.safetensors",
1000
+ "model.visual.blocks.8.attn.proj.weight": "model-00002-of-00026.safetensors",
1001
+ "model.visual.blocks.8.attn.qkv.bias": "model-00002-of-00026.safetensors",
1002
+ "model.visual.blocks.8.attn.qkv.weight": "model-00002-of-00026.safetensors",
1003
+ "model.visual.blocks.8.mlp.linear_fc1.bias": "model-00002-of-00026.safetensors",
1004
+ "model.visual.blocks.8.mlp.linear_fc1.weight": "model-00002-of-00026.safetensors",
1005
+ "model.visual.blocks.8.mlp.linear_fc2.bias": "model-00002-of-00026.safetensors",
1006
+ "model.visual.blocks.8.mlp.linear_fc2.weight": "model-00002-of-00026.safetensors",
1007
+ "model.visual.blocks.8.norm1.bias": "model-00002-of-00026.safetensors",
1008
+ "model.visual.blocks.8.norm1.weight": "model-00002-of-00026.safetensors",
1009
+ "model.visual.blocks.8.norm2.bias": "model-00002-of-00026.safetensors",
1010
+ "model.visual.blocks.8.norm2.weight": "model-00002-of-00026.safetensors",
1011
+ "model.visual.blocks.9.attn.proj.bias": "model-00002-of-00026.safetensors",
1012
+ "model.visual.blocks.9.attn.proj.weight": "model-00002-of-00026.safetensors",
1013
+ "model.visual.blocks.9.attn.qkv.bias": "model-00002-of-00026.safetensors",
1014
+ "model.visual.blocks.9.attn.qkv.weight": "model-00002-of-00026.safetensors",
1015
+ "model.visual.blocks.9.mlp.linear_fc1.bias": "model-00002-of-00026.safetensors",
1016
+ "model.visual.blocks.9.mlp.linear_fc1.weight": "model-00002-of-00026.safetensors",
1017
+ "model.visual.blocks.9.mlp.linear_fc2.bias": "model-00002-of-00026.safetensors",
1018
+ "model.visual.blocks.9.mlp.linear_fc2.weight": "model-00002-of-00026.safetensors",
1019
+ "model.visual.blocks.9.norm1.bias": "model-00002-of-00026.safetensors",
1020
+ "model.visual.blocks.9.norm1.weight": "model-00002-of-00026.safetensors",
1021
+ "model.visual.blocks.9.norm2.bias": "model-00002-of-00026.safetensors",
1022
+ "model.visual.blocks.9.norm2.weight": "model-00002-of-00026.safetensors",
1023
+ "model.visual.merger.linear_fc1.bias": "model-00002-of-00026.safetensors",
1024
+ "model.visual.merger.linear_fc1.weight": "model-00001-of-00026.safetensors",
1025
+ "model.visual.merger.linear_fc2.bias": "model-00002-of-00026.safetensors",
1026
+ "model.visual.merger.linear_fc2.weight": "model-00001-of-00026.safetensors",
1027
+ "model.visual.merger.norm.bias": "model-00002-of-00026.safetensors",
1028
+ "model.visual.merger.norm.weight": "model-00002-of-00026.safetensors",
1029
+ "model.visual.patch_embed.proj.bias": "model-00002-of-00026.safetensors",
1030
+ "model.visual.patch_embed.proj.weight": "model-00002-of-00026.safetensors",
1031
+ "model.visual.pos_embed.weight": "model-00002-of-00026.safetensors",
1032
+ "mtp.fc.weight": "model-00026-of-00026.safetensors",
1033
+ "mtp.layers.0.input_layernorm.weight": "model-00026-of-00026.safetensors",
1034
+ "mtp.layers.0.mlp.experts.down_proj": "model-00026-of-00026.safetensors",
1035
+ "mtp.layers.0.mlp.experts.gate_up_proj": "model-00025-of-00026.safetensors",
1036
+ "mtp.layers.0.mlp.gate.weight": "model-00026-of-00026.safetensors",
1037
+ "mtp.layers.0.mlp.shared_expert.down_proj.weight": "model-00026-of-00026.safetensors",
1038
+ "mtp.layers.0.mlp.shared_expert.gate_proj.weight": "model-00026-of-00026.safetensors",
1039
+ "mtp.layers.0.mlp.shared_expert.up_proj.weight": "model-00026-of-00026.safetensors",
1040
+ "mtp.layers.0.mlp.shared_expert_gate.weight": "model-00026-of-00026.safetensors",
1041
+ "mtp.layers.0.post_attention_layernorm.weight": "model-00026-of-00026.safetensors",
1042
+ "mtp.layers.0.self_attn.k_norm.weight": "model-00026-of-00026.safetensors",
1043
+ "mtp.layers.0.self_attn.k_proj.weight": "model-00026-of-00026.safetensors",
1044
+ "mtp.layers.0.self_attn.o_proj.weight": "model-00026-of-00026.safetensors",
1045
+ "mtp.layers.0.self_attn.q_norm.weight": "model-00026-of-00026.safetensors",
1046
+ "mtp.layers.0.self_attn.q_proj.weight": "model-00026-of-00026.safetensors",
1047
+ "mtp.layers.0.self_attn.v_proj.weight": "model-00026-of-00026.safetensors",
1048
+ "mtp.norm.weight": "model-00026-of-00026.safetensors",
1049
+ "mtp.pre_fc_norm_embedding.weight": "model-00026-of-00026.safetensors",
1050
+ "mtp.pre_fc_norm_hidden.weight": "model-00026-of-00026.safetensors"
1051
+ }
1052
+ }
parent_comparison.png ADDED

Git LFS Details

  • SHA256: 9961329b9efecba3e90bccb9b07409692f8a5f4ea6ec6055dde72123c195e471
  • Pointer size: 131 Bytes
  • Size of remote file: 181 kB
prescription_ratios.png ADDED
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:87a7830d63fcf43bf241c3c5242e96e62dd3fdc29224ca26fed8ea333db72de4
3
+ size 19989343
tokenizer_config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "audio_bos_token": "<|audio_start|>",
4
+ "audio_eos_token": "<|audio_end|>",
5
+ "audio_token": "<|audio_pad|>",
6
+ "backend": "tokenizers",
7
+ "bos_token": null,
8
+ "clean_up_tokenization_spaces": false,
9
+ "eos_token": "<|im_end|>",
10
+ "errors": "replace",
11
+ "image_token": "<|image_pad|>",
12
+ "is_local": true,
13
+ "model_max_length": 262144,
14
+ "model_specific_special_tokens": {
15
+ "audio_bos_token": "<|audio_start|>",
16
+ "audio_eos_token": "<|audio_end|>",
17
+ "audio_token": "<|audio_pad|>",
18
+ "image_token": "<|image_pad|>",
19
+ "video_token": "<|video_pad|>",
20
+ "vision_bos_token": "<|vision_start|>",
21
+ "vision_eos_token": "<|vision_end|>"
22
+ },
23
+ "pad_token": "<|endoftext|>",
24
+ "pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
25
+ "split_special_tokens": false,
26
+ "tokenizer_class": "TokenizersBackend",
27
+ "unk_token": null,
28
+ "video_token": "<|video_pad|>",
29
+ "vision_bos_token": "<|vision_start|>",
30
+ "vision_eos_token": "<|vision_end|>"
31
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff