Upload folder using huggingface_hub
Browse files- added_tokens.json +1 -20
- chat_template.jinja +6 -54
- config.json +9 -17
- model-00001-of-00004.safetensors +3 -0
- model-00002-of-00004.safetensors +3 -0
- model-00003-of-00004.safetensors +3 -0
- model-00004-of-00004.safetensors +3 -0
- model.safetensors.index.json +341 -436
- special_tokens_map.json +1 -12
- tokenizer.json +2 -2
- tokenizer_config.json +1 -165
added_tokens.json
CHANGED
|
@@ -1,24 +1,5 @@
|
|
| 1 |
{
|
| 2 |
-
"</tool_call>": 151658,
|
| 3 |
-
"<tool_call>": 151657,
|
| 4 |
-
"<|box_end|>": 151649,
|
| 5 |
-
"<|box_start|>": 151648,
|
| 6 |
"<|endoftext|>": 151643,
|
| 7 |
-
"<|file_sep|>": 151664,
|
| 8 |
-
"<|fim_middle|>": 151660,
|
| 9 |
-
"<|fim_pad|>": 151662,
|
| 10 |
-
"<|fim_prefix|>": 151659,
|
| 11 |
-
"<|fim_suffix|>": 151661,
|
| 12 |
"<|im_end|>": 151645,
|
| 13 |
-
"<|im_start|>": 151644
|
| 14 |
-
"<|image_pad|>": 151655,
|
| 15 |
-
"<|object_ref_end|>": 151647,
|
| 16 |
-
"<|object_ref_start|>": 151646,
|
| 17 |
-
"<|quad_end|>": 151651,
|
| 18 |
-
"<|quad_start|>": 151650,
|
| 19 |
-
"<|repo_name|>": 151663,
|
| 20 |
-
"<|video_pad|>": 151656,
|
| 21 |
-
"<|vision_end|>": 151653,
|
| 22 |
-
"<|vision_pad|>": 151654,
|
| 23 |
-
"<|vision_start|>": 151652
|
| 24 |
}
|
|
|
|
| 1 |
{
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2 |
"<|endoftext|>": 151643,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
"<|im_end|>": 151645,
|
| 4 |
+
"<|im_start|>": 151644
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5 |
}
|
chat_template.jinja
CHANGED
|
@@ -1,54 +1,6 @@
|
|
| 1 |
-
{
|
| 2 |
-
|
| 3 |
-
|
| 4 |
-
|
| 5 |
-
|
| 6 |
-
|
| 7 |
-
{%- endif %}
|
| 8 |
-
{{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
|
| 9 |
-
{%- for tool in tools %}
|
| 10 |
-
{{- "\n" }}
|
| 11 |
-
{{- tool | tojson }}
|
| 12 |
-
{%- endfor %}
|
| 13 |
-
{{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
|
| 14 |
-
{%- else %}
|
| 15 |
-
{%- if messages[0]['role'] == 'system' %}
|
| 16 |
-
{{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
|
| 17 |
-
{%- else %}
|
| 18 |
-
{{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
|
| 19 |
-
{%- endif %}
|
| 20 |
-
{%- endif %}
|
| 21 |
-
{%- for message in messages %}
|
| 22 |
-
{%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
|
| 23 |
-
{{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
|
| 24 |
-
{%- elif message.role == "assistant" %}
|
| 25 |
-
{{- '<|im_start|>' + message.role }}
|
| 26 |
-
{%- if message.content %}
|
| 27 |
-
{{- '\n' + message.content }}
|
| 28 |
-
{%- endif %}
|
| 29 |
-
{%- for tool_call in message.tool_calls %}
|
| 30 |
-
{%- if tool_call.function is defined %}
|
| 31 |
-
{%- set tool_call = tool_call.function %}
|
| 32 |
-
{%- endif %}
|
| 33 |
-
{{- '\n<tool_call>\n{"name": "' }}
|
| 34 |
-
{{- tool_call.name }}
|
| 35 |
-
{{- '", "arguments": ' }}
|
| 36 |
-
{{- tool_call.arguments | tojson }}
|
| 37 |
-
{{- '}\n</tool_call>' }}
|
| 38 |
-
{%- endfor %}
|
| 39 |
-
{{- '<|im_end|>\n' }}
|
| 40 |
-
{%- elif message.role == "tool" %}
|
| 41 |
-
{%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
|
| 42 |
-
{{- '<|im_start|>user' }}
|
| 43 |
-
{%- endif %}
|
| 44 |
-
{{- '\n<tool_response>\n' }}
|
| 45 |
-
{{- message.content }}
|
| 46 |
-
{{- '\n</tool_response>' }}
|
| 47 |
-
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
|
| 48 |
-
{{- '<|im_end|>\n' }}
|
| 49 |
-
{%- endif %}
|
| 50 |
-
{%- endif %}
|
| 51 |
-
{%- endfor %}
|
| 52 |
-
{%- if add_generation_prompt %}
|
| 53 |
-
{{- '<|im_start|>assistant\n' }}
|
| 54 |
-
{%- endif %}
|
|
|
|
| 1 |
+
{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system
|
| 2 |
+
You are a helpful assistant.<|im_end|>
|
| 3 |
+
' }}{% endif %}{{'<|im_start|>' + message['role'] + '
|
| 4 |
+
' + message['content'] + '<|im_end|>' + '
|
| 5 |
+
'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant
|
| 6 |
+
' }}{% endif %}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
config.json
CHANGED
|
@@ -4,12 +4,12 @@
|
|
| 4 |
],
|
| 5 |
"attention_dropout": 0.0,
|
| 6 |
"bos_token_id": 151643,
|
| 7 |
-
"dtype": "
|
| 8 |
"eos_token_id": 151645,
|
| 9 |
"hidden_act": "silu",
|
| 10 |
-
"hidden_size":
|
| 11 |
"initializer_range": 0.02,
|
| 12 |
-
"intermediate_size":
|
| 13 |
"layer_types": [
|
| 14 |
"full_attention",
|
| 15 |
"full_attention",
|
|
@@ -38,29 +38,21 @@
|
|
| 38 |
"full_attention",
|
| 39 |
"full_attention",
|
| 40 |
"full_attention",
|
| 41 |
-
"full_attention",
|
| 42 |
-
"full_attention",
|
| 43 |
-
"full_attention",
|
| 44 |
-
"full_attention",
|
| 45 |
-
"full_attention",
|
| 46 |
-
"full_attention",
|
| 47 |
-
"full_attention",
|
| 48 |
-
"full_attention",
|
| 49 |
"full_attention"
|
| 50 |
],
|
| 51 |
"max_position_embeddings": 32768,
|
| 52 |
-
"max_window_layers":
|
| 53 |
"model_type": "qwen2",
|
| 54 |
-
"num_attention_heads":
|
| 55 |
-
"num_hidden_layers":
|
| 56 |
-
"num_key_value_heads":
|
| 57 |
"rms_norm_eps": 1e-06,
|
| 58 |
"rope_scaling": null,
|
| 59 |
"rope_theta": 1000000.0,
|
| 60 |
"sliding_window": null,
|
| 61 |
-
"tie_word_embeddings":
|
| 62 |
"transformers_version": "4.57.3",
|
| 63 |
"use_cache": true,
|
| 64 |
"use_sliding_window": false,
|
| 65 |
-
"vocab_size":
|
| 66 |
}
|
|
|
|
| 4 |
],
|
| 5 |
"attention_dropout": 0.0,
|
| 6 |
"bos_token_id": 151643,
|
| 7 |
+
"dtype": "float16",
|
| 8 |
"eos_token_id": 151645,
|
| 9 |
"hidden_act": "silu",
|
| 10 |
+
"hidden_size": 3584,
|
| 11 |
"initializer_range": 0.02,
|
| 12 |
+
"intermediate_size": 18944,
|
| 13 |
"layer_types": [
|
| 14 |
"full_attention",
|
| 15 |
"full_attention",
|
|
|
|
| 38 |
"full_attention",
|
| 39 |
"full_attention",
|
| 40 |
"full_attention",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 41 |
"full_attention"
|
| 42 |
],
|
| 43 |
"max_position_embeddings": 32768,
|
| 44 |
+
"max_window_layers": 28,
|
| 45 |
"model_type": "qwen2",
|
| 46 |
+
"num_attention_heads": 28,
|
| 47 |
+
"num_hidden_layers": 28,
|
| 48 |
+
"num_key_value_heads": 4,
|
| 49 |
"rms_norm_eps": 1e-06,
|
| 50 |
"rope_scaling": null,
|
| 51 |
"rope_theta": 1000000.0,
|
| 52 |
"sliding_window": null,
|
| 53 |
+
"tie_word_embeddings": false,
|
| 54 |
"transformers_version": "4.57.3",
|
| 55 |
"use_cache": true,
|
| 56 |
"use_sliding_window": false,
|
| 57 |
+
"vocab_size": 151646
|
| 58 |
}
|
model-00001-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c2b7977127db1b0ae87a923b9fb0bfe57b0db8a14b0f9ede38e9371c875c5bfa
|
| 3 |
+
size 4874664448
|
model-00002-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:618d70797997842aa0dbe359125538a97679e0a3083285805f1eec93f2801a73
|
| 3 |
+
size 4932750888
|
model-00003-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0fea862373a9ba6b09f1f3ae761d6fa1af6e77dc76213b7a06cc67440bc550a7
|
| 3 |
+
size 4330865088
|
model-00004-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:99892716124143226976e1640e490a611085690dd4acbbe1fdf1bf8d79e1c52b
|
| 3 |
+
size 1086998656
|
model.safetensors.index.json
CHANGED
|
@@ -1,442 +1,347 @@
|
|
| 1 |
{
|
| 2 |
"metadata": {
|
| 3 |
-
"total_parameters":
|
| 4 |
-
"total_size":
|
| 5 |
},
|
| 6 |
"weight_map": {
|
| 7 |
-
"
|
| 8 |
-
"model.
|
| 9 |
-
"model.layers.0.
|
| 10 |
-
"model.layers.0.mlp.
|
| 11 |
-
"model.layers.0.mlp.
|
| 12 |
-
"model.layers.0.
|
| 13 |
-
"model.layers.0.
|
| 14 |
-
"model.layers.0.self_attn.k_proj.
|
| 15 |
-
"model.layers.0.self_attn.
|
| 16 |
-
"model.layers.0.self_attn.
|
| 17 |
-
"model.layers.0.self_attn.q_proj.
|
| 18 |
-
"model.layers.0.self_attn.
|
| 19 |
-
"model.layers.0.self_attn.v_proj.
|
| 20 |
-
"model.layers.
|
| 21 |
-
"model.layers.1.
|
| 22 |
-
"model.layers.1.mlp.
|
| 23 |
-
"model.layers.1.mlp.
|
| 24 |
-
"model.layers.1.
|
| 25 |
-
"model.layers.1.
|
| 26 |
-
"model.layers.1.self_attn.k_proj.
|
| 27 |
-
"model.layers.1.self_attn.
|
| 28 |
-
"model.layers.1.self_attn.
|
| 29 |
-
"model.layers.1.self_attn.q_proj.
|
| 30 |
-
"model.layers.1.self_attn.
|
| 31 |
-
"model.layers.1.self_attn.v_proj.
|
| 32 |
-
"model.layers.
|
| 33 |
-
"model.layers.10.
|
| 34 |
-
"model.layers.10.mlp.
|
| 35 |
-
"model.layers.10.mlp.
|
| 36 |
-
"model.layers.10.
|
| 37 |
-
"model.layers.10.
|
| 38 |
-
"model.layers.10.self_attn.k_proj.
|
| 39 |
-
"model.layers.10.self_attn.
|
| 40 |
-
"model.layers.10.self_attn.
|
| 41 |
-
"model.layers.10.self_attn.q_proj.
|
| 42 |
-
"model.layers.10.self_attn.
|
| 43 |
-
"model.layers.10.self_attn.v_proj.
|
| 44 |
-
"model.layers.
|
| 45 |
-
"model.layers.11.
|
| 46 |
-
"model.layers.11.mlp.
|
| 47 |
-
"model.layers.11.mlp.
|
| 48 |
-
"model.layers.11.
|
| 49 |
-
"model.layers.11.
|
| 50 |
-
"model.layers.11.self_attn.k_proj.
|
| 51 |
-
"model.layers.11.self_attn.
|
| 52 |
-
"model.layers.11.self_attn.
|
| 53 |
-
"model.layers.11.self_attn.q_proj.
|
| 54 |
-
"model.layers.11.self_attn.
|
| 55 |
-
"model.layers.11.self_attn.v_proj.
|
| 56 |
-
"model.layers.
|
| 57 |
-
"model.layers.12.
|
| 58 |
-
"model.layers.12.mlp.
|
| 59 |
-
"model.layers.12.mlp.
|
| 60 |
-
"model.layers.12.
|
| 61 |
-
"model.layers.12.
|
| 62 |
-
"model.layers.12.self_attn.k_proj.
|
| 63 |
-
"model.layers.12.self_attn.
|
| 64 |
-
"model.layers.12.self_attn.
|
| 65 |
-
"model.layers.12.self_attn.q_proj.
|
| 66 |
-
"model.layers.12.self_attn.
|
| 67 |
-
"model.layers.12.self_attn.v_proj.
|
| 68 |
-
"model.layers.
|
| 69 |
-
"model.layers.13.
|
| 70 |
-
"model.layers.13.mlp.
|
| 71 |
-
"model.layers.13.mlp.
|
| 72 |
-
"model.layers.13.
|
| 73 |
-
"model.layers.13.
|
| 74 |
-
"model.layers.13.self_attn.k_proj.
|
| 75 |
-
"model.layers.13.self_attn.
|
| 76 |
-
"model.layers.13.self_attn.
|
| 77 |
-
"model.layers.13.self_attn.q_proj.
|
| 78 |
-
"model.layers.13.self_attn.
|
| 79 |
-
"model.layers.13.self_attn.v_proj.
|
| 80 |
-
"model.layers.
|
| 81 |
-
"model.layers.14.
|
| 82 |
-
"model.layers.14.mlp.
|
| 83 |
-
"model.layers.14.mlp.
|
| 84 |
-
"model.layers.14.
|
| 85 |
-
"model.layers.14.
|
| 86 |
-
"model.layers.14.self_attn.k_proj.
|
| 87 |
-
"model.layers.14.self_attn.
|
| 88 |
-
"model.layers.14.self_attn.
|
| 89 |
-
"model.layers.14.self_attn.q_proj.
|
| 90 |
-
"model.layers.14.self_attn.
|
| 91 |
-
"model.layers.14.self_attn.v_proj.
|
| 92 |
-
"model.layers.
|
| 93 |
-
"model.layers.15.
|
| 94 |
-
"model.layers.15.mlp.
|
| 95 |
-
"model.layers.15.mlp.
|
| 96 |
-
"model.layers.15.
|
| 97 |
-
"model.layers.15.
|
| 98 |
-
"model.layers.15.self_attn.k_proj.
|
| 99 |
-
"model.layers.15.self_attn.
|
| 100 |
-
"model.layers.15.self_attn.
|
| 101 |
-
"model.layers.15.self_attn.q_proj.
|
| 102 |
-
"model.layers.15.self_attn.
|
| 103 |
-
"model.layers.15.self_attn.v_proj.
|
| 104 |
-
"model.layers.
|
| 105 |
-
"model.layers.16.
|
| 106 |
-
"model.layers.16.mlp.
|
| 107 |
-
"model.layers.16.mlp.
|
| 108 |
-
"model.layers.16.
|
| 109 |
-
"model.layers.16.
|
| 110 |
-
"model.layers.16.self_attn.k_proj.
|
| 111 |
-
"model.layers.16.self_attn.
|
| 112 |
-
"model.layers.16.self_attn.
|
| 113 |
-
"model.layers.16.self_attn.q_proj.
|
| 114 |
-
"model.layers.16.self_attn.
|
| 115 |
-
"model.layers.16.self_attn.v_proj.
|
| 116 |
-
"model.layers.
|
| 117 |
-
"model.layers.17.
|
| 118 |
-
"model.layers.17.mlp.
|
| 119 |
-
"model.layers.17.mlp.
|
| 120 |
-
"model.layers.17.
|
| 121 |
-
"model.layers.17.
|
| 122 |
-
"model.layers.17.self_attn.k_proj.
|
| 123 |
-
"model.layers.17.self_attn.
|
| 124 |
-
"model.layers.17.self_attn.
|
| 125 |
-
"model.layers.17.self_attn.q_proj.
|
| 126 |
-
"model.layers.17.self_attn.
|
| 127 |
-
"model.layers.17.self_attn.v_proj.
|
| 128 |
-
"model.layers.
|
| 129 |
-
"model.layers.18.
|
| 130 |
-
"model.layers.18.mlp.
|
| 131 |
-
"model.layers.18.mlp.
|
| 132 |
-
"model.layers.18.
|
| 133 |
-
"model.layers.18.
|
| 134 |
-
"model.layers.18.self_attn.k_proj.
|
| 135 |
-
"model.layers.18.self_attn.
|
| 136 |
-
"model.layers.18.self_attn.
|
| 137 |
-
"model.layers.18.self_attn.q_proj.
|
| 138 |
-
"model.layers.18.self_attn.
|
| 139 |
-
"model.layers.18.self_attn.v_proj.
|
| 140 |
-
"model.layers.
|
| 141 |
-
"model.layers.19.
|
| 142 |
-
"model.layers.19.mlp.
|
| 143 |
-
"model.layers.19.mlp.
|
| 144 |
-
"model.layers.19.
|
| 145 |
-
"model.layers.19.
|
| 146 |
-
"model.layers.19.self_attn.k_proj.
|
| 147 |
-
"model.layers.19.self_attn.
|
| 148 |
-
"model.layers.19.self_attn.
|
| 149 |
-
"model.layers.19.self_attn.q_proj.
|
| 150 |
-
"model.layers.19.self_attn.
|
| 151 |
-
"model.layers.19.self_attn.v_proj.
|
| 152 |
-
"model.layers.
|
| 153 |
-
"model.layers.2.
|
| 154 |
-
"model.layers.2.mlp.
|
| 155 |
-
"model.layers.2.mlp.
|
| 156 |
-
"model.layers.2.
|
| 157 |
-
"model.layers.2.
|
| 158 |
-
"model.layers.2.self_attn.k_proj.
|
| 159 |
-
"model.layers.2.self_attn.
|
| 160 |
-
"model.layers.2.self_attn.
|
| 161 |
-
"model.layers.2.self_attn.q_proj.
|
| 162 |
-
"model.layers.2.self_attn.
|
| 163 |
-
"model.layers.2.self_attn.v_proj.
|
| 164 |
-
"model.layers.
|
| 165 |
-
"model.layers.20.
|
| 166 |
-
"model.layers.20.mlp.
|
| 167 |
-
"model.layers.20.mlp.
|
| 168 |
-
"model.layers.20.
|
| 169 |
-
"model.layers.20.
|
| 170 |
-
"model.layers.20.self_attn.k_proj.
|
| 171 |
-
"model.layers.20.self_attn.
|
| 172 |
-
"model.layers.20.self_attn.
|
| 173 |
-
"model.layers.20.self_attn.q_proj.
|
| 174 |
-
"model.layers.20.self_attn.
|
| 175 |
-
"model.layers.20.self_attn.v_proj.
|
| 176 |
-
"model.layers.
|
| 177 |
-
"model.layers.21.
|
| 178 |
-
"model.layers.21.mlp.
|
| 179 |
-
"model.layers.21.mlp.
|
| 180 |
-
"model.layers.21.
|
| 181 |
-
"model.layers.21.
|
| 182 |
-
"model.layers.21.self_attn.k_proj.
|
| 183 |
-
"model.layers.21.self_attn.
|
| 184 |
-
"model.layers.21.self_attn.
|
| 185 |
-
"model.layers.21.self_attn.q_proj.
|
| 186 |
-
"model.layers.21.self_attn.
|
| 187 |
-
"model.layers.21.self_attn.v_proj.
|
| 188 |
-
"model.layers.
|
| 189 |
-
"model.layers.22.
|
| 190 |
-
"model.layers.22.mlp.
|
| 191 |
-
"model.layers.22.mlp.
|
| 192 |
-
"model.layers.22.
|
| 193 |
-
"model.layers.22.
|
| 194 |
-
"model.layers.22.self_attn.k_proj.
|
| 195 |
-
"model.layers.22.self_attn.
|
| 196 |
-
"model.layers.22.self_attn.
|
| 197 |
-
"model.layers.22.self_attn.q_proj.
|
| 198 |
-
"model.layers.22.self_attn.
|
| 199 |
-
"model.layers.22.self_attn.v_proj.
|
| 200 |
-
"model.layers.
|
| 201 |
-
"model.layers.23.
|
| 202 |
-
"model.layers.23.mlp.
|
| 203 |
-
"model.layers.23.mlp.
|
| 204 |
-
"model.layers.23.
|
| 205 |
-
"model.layers.23.
|
| 206 |
-
"model.layers.23.self_attn.k_proj.
|
| 207 |
-
"model.layers.23.self_attn.
|
| 208 |
-
"model.layers.23.self_attn.
|
| 209 |
-
"model.layers.23.self_attn.q_proj.
|
| 210 |
-
"model.layers.23.self_attn.
|
| 211 |
-
"model.layers.23.self_attn.v_proj.
|
| 212 |
-
"model.layers.
|
| 213 |
-
"model.layers.24.
|
| 214 |
-
"model.layers.24.mlp.
|
| 215 |
-
"model.layers.24.mlp.
|
| 216 |
-
"model.layers.24.
|
| 217 |
-
"model.layers.24.
|
| 218 |
-
"model.layers.24.self_attn.k_proj.
|
| 219 |
-
"model.layers.24.self_attn.
|
| 220 |
-
"model.layers.24.self_attn.
|
| 221 |
-
"model.layers.24.self_attn.q_proj.
|
| 222 |
-
"model.layers.24.self_attn.
|
| 223 |
-
"model.layers.24.self_attn.v_proj.
|
| 224 |
-
"model.layers.
|
| 225 |
-
"model.layers.25.
|
| 226 |
-
"model.layers.25.mlp.
|
| 227 |
-
"model.layers.25.mlp.
|
| 228 |
-
"model.layers.25.
|
| 229 |
-
"model.layers.25.
|
| 230 |
-
"model.layers.25.self_attn.k_proj.
|
| 231 |
-
"model.layers.25.self_attn.
|
| 232 |
-
"model.layers.25.self_attn.
|
| 233 |
-
"model.layers.25.self_attn.q_proj.
|
| 234 |
-
"model.layers.25.self_attn.
|
| 235 |
-
"model.layers.25.self_attn.v_proj.
|
| 236 |
-
"model.layers.
|
| 237 |
-
"model.layers.26.
|
| 238 |
-
"model.layers.26.mlp.
|
| 239 |
-
"model.layers.26.mlp.
|
| 240 |
-
"model.layers.26.
|
| 241 |
-
"model.layers.26.
|
| 242 |
-
"model.layers.26.self_attn.k_proj.
|
| 243 |
-
"model.layers.26.self_attn.
|
| 244 |
-
"model.layers.26.self_attn.
|
| 245 |
-
"model.layers.26.self_attn.q_proj.
|
| 246 |
-
"model.layers.26.self_attn.
|
| 247 |
-
"model.layers.26.self_attn.v_proj.
|
| 248 |
-
"model.layers.
|
| 249 |
-
"model.layers.27.
|
| 250 |
-
"model.layers.27.mlp.
|
| 251 |
-
"model.layers.27.mlp.
|
| 252 |
-
"model.layers.27.
|
| 253 |
-
"model.layers.27.
|
| 254 |
-
"model.layers.27.self_attn.k_proj.
|
| 255 |
-
"model.layers.27.self_attn.
|
| 256 |
-
"model.layers.27.self_attn.
|
| 257 |
-
"model.layers.27.self_attn.q_proj.
|
| 258 |
-
"model.layers.27.self_attn.
|
| 259 |
-
"model.layers.27.self_attn.v_proj.
|
| 260 |
-
"model.layers.
|
| 261 |
-
"model.layers.
|
| 262 |
-
"model.layers.
|
| 263 |
-
"model.layers.
|
| 264 |
-
"model.layers.
|
| 265 |
-
"model.layers.
|
| 266 |
-
"model.layers.
|
| 267 |
-
"model.layers.
|
| 268 |
-
"model.layers.
|
| 269 |
-
"model.layers.
|
| 270 |
-
"model.layers.
|
| 271 |
-
"model.layers.
|
| 272 |
-
"model.layers.
|
| 273 |
-
"model.layers.
|
| 274 |
-
"model.layers.
|
| 275 |
-
"model.layers.
|
| 276 |
-
"model.layers.
|
| 277 |
-
"model.layers.
|
| 278 |
-
"model.layers.
|
| 279 |
-
"model.layers.
|
| 280 |
-
"model.layers.
|
| 281 |
-
"model.layers.
|
| 282 |
-
"model.layers.
|
| 283 |
-
"model.layers.
|
| 284 |
-
"model.layers.
|
| 285 |
-
"model.layers.
|
| 286 |
-
"model.layers.
|
| 287 |
-
"model.layers.
|
| 288 |
-
"model.layers.
|
| 289 |
-
"model.layers.
|
| 290 |
-
"model.layers.
|
| 291 |
-
"model.layers.
|
| 292 |
-
"model.layers.
|
| 293 |
-
"model.layers.
|
| 294 |
-
"model.layers.
|
| 295 |
-
"model.layers.
|
| 296 |
-
"model.layers.
|
| 297 |
-
"model.layers.
|
| 298 |
-
"model.layers.
|
| 299 |
-
"model.layers.
|
| 300 |
-
"model.layers.
|
| 301 |
-
"model.layers.
|
| 302 |
-
"model.layers.
|
| 303 |
-
"model.layers.
|
| 304 |
-
"model.layers.
|
| 305 |
-
"model.layers.
|
| 306 |
-
"model.layers.
|
| 307 |
-
"model.layers.
|
| 308 |
-
"model.layers.
|
| 309 |
-
"model.layers.
|
| 310 |
-
"model.layers.
|
| 311 |
-
"model.layers.
|
| 312 |
-
"model.layers.
|
| 313 |
-
"model.layers.
|
| 314 |
-
"model.layers.
|
| 315 |
-
"model.layers.
|
| 316 |
-
"model.layers.
|
| 317 |
-
"model.layers.
|
| 318 |
-
"model.layers.
|
| 319 |
-
"model.layers.
|
| 320 |
-
"model.layers.
|
| 321 |
-
"model.layers.
|
| 322 |
-
"model.layers.
|
| 323 |
-
"model.layers.
|
| 324 |
-
"model.layers.
|
| 325 |
-
"model.layers.
|
| 326 |
-
"model.layers.
|
| 327 |
-
"model.layers.
|
| 328 |
-
"model.layers.
|
| 329 |
-
"model.layers.
|
| 330 |
-
"model.layers.
|
| 331 |
-
"model.layers.
|
| 332 |
-
"model.layers.
|
| 333 |
-
"model.layers.
|
| 334 |
-
"model.layers.
|
| 335 |
-
"model.layers.
|
| 336 |
-
"model.layers.
|
| 337 |
-
"model.layers.
|
| 338 |
-
"model.layers.
|
| 339 |
-
"model.layers.
|
| 340 |
-
"model.layers.
|
| 341 |
-
"model.layers.
|
| 342 |
-
"model.layers.
|
| 343 |
-
"model.layers.
|
| 344 |
-
"model.layers.
|
| 345 |
-
"model.
|
| 346 |
-
"model.layers.34.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
| 347 |
-
"model.layers.34.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
| 348 |
-
"model.layers.34.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 349 |
-
"model.layers.34.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 350 |
-
"model.layers.34.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 351 |
-
"model.layers.34.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
| 352 |
-
"model.layers.34.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 353 |
-
"model.layers.34.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 354 |
-
"model.layers.34.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 355 |
-
"model.layers.34.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 356 |
-
"model.layers.35.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 357 |
-
"model.layers.35.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
| 358 |
-
"model.layers.35.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
| 359 |
-
"model.layers.35.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
| 360 |
-
"model.layers.35.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 361 |
-
"model.layers.35.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 362 |
-
"model.layers.35.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 363 |
-
"model.layers.35.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
| 364 |
-
"model.layers.35.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 365 |
-
"model.layers.35.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 366 |
-
"model.layers.35.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 367 |
-
"model.layers.35.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 368 |
-
"model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 369 |
-
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 370 |
-
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 371 |
-
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 372 |
-
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 373 |
-
"model.layers.4.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 374 |
-
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 375 |
-
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 376 |
-
"model.layers.4.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 377 |
-
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 378 |
-
"model.layers.4.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 379 |
-
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 380 |
-
"model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 381 |
-
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 382 |
-
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 383 |
-
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 384 |
-
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 385 |
-
"model.layers.5.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 386 |
-
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 387 |
-
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 388 |
-
"model.layers.5.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 389 |
-
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 390 |
-
"model.layers.5.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 391 |
-
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 392 |
-
"model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 393 |
-
"model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 394 |
-
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 395 |
-
"model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 396 |
-
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 397 |
-
"model.layers.6.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 398 |
-
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 399 |
-
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 400 |
-
"model.layers.6.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 401 |
-
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 402 |
-
"model.layers.6.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 403 |
-
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 404 |
-
"model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 405 |
-
"model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 406 |
-
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 407 |
-
"model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 408 |
-
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 409 |
-
"model.layers.7.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 410 |
-
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 411 |
-
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 412 |
-
"model.layers.7.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 413 |
-
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 414 |
-
"model.layers.7.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 415 |
-
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 416 |
-
"model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 417 |
-
"model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 418 |
-
"model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 419 |
-
"model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 420 |
-
"model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 421 |
-
"model.layers.8.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 422 |
-
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 423 |
-
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 424 |
-
"model.layers.8.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 425 |
-
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 426 |
-
"model.layers.8.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 427 |
-
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 428 |
-
"model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 429 |
-
"model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 430 |
-
"model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 431 |
-
"model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 432 |
-
"model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 433 |
-
"model.layers.9.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 434 |
-
"model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 435 |
-
"model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 436 |
-
"model.layers.9.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 437 |
-
"model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 438 |
-
"model.layers.9.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 439 |
-
"model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 440 |
-
"model.norm.weight": "model-00003-of-00003.safetensors"
|
| 441 |
}
|
| 442 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"metadata": {
|
| 3 |
+
"total_parameters": 7612620288,
|
| 4 |
+
"total_size": 15225240576
|
| 5 |
},
|
| 6 |
"weight_map": {
|
| 7 |
+
"lm_head.weight": "model-00004-of-00004.safetensors",
|
| 8 |
+
"model.embed_tokens.weight": "model-00001-of-00004.safetensors",
|
| 9 |
+
"model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 10 |
+
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 11 |
+
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 12 |
+
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 13 |
+
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 14 |
+
"model.layers.0.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
| 15 |
+
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 16 |
+
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 17 |
+
"model.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
| 18 |
+
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 19 |
+
"model.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
| 20 |
+
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 21 |
+
"model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 22 |
+
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 23 |
+
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 24 |
+
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 25 |
+
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 26 |
+
"model.layers.1.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
| 27 |
+
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 28 |
+
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 29 |
+
"model.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
| 30 |
+
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 31 |
+
"model.layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
| 32 |
+
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 33 |
+
"model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 34 |
+
"model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 35 |
+
"model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 36 |
+
"model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 37 |
+
"model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 38 |
+
"model.layers.10.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
| 39 |
+
"model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 40 |
+
"model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 41 |
+
"model.layers.10.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
| 42 |
+
"model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 43 |
+
"model.layers.10.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
| 44 |
+
"model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 45 |
+
"model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 46 |
+
"model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 47 |
+
"model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 48 |
+
"model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 49 |
+
"model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 50 |
+
"model.layers.11.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
| 51 |
+
"model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 52 |
+
"model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 53 |
+
"model.layers.11.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
| 54 |
+
"model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 55 |
+
"model.layers.11.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
| 56 |
+
"model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 57 |
+
"model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 58 |
+
"model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 59 |
+
"model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 60 |
+
"model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 61 |
+
"model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 62 |
+
"model.layers.12.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
| 63 |
+
"model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 64 |
+
"model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 65 |
+
"model.layers.12.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
| 66 |
+
"model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 67 |
+
"model.layers.12.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
| 68 |
+
"model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 69 |
+
"model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 70 |
+
"model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 71 |
+
"model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 72 |
+
"model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 73 |
+
"model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 74 |
+
"model.layers.13.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
| 75 |
+
"model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 76 |
+
"model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 77 |
+
"model.layers.13.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
| 78 |
+
"model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 79 |
+
"model.layers.13.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
| 80 |
+
"model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 81 |
+
"model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 82 |
+
"model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 83 |
+
"model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 84 |
+
"model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 85 |
+
"model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 86 |
+
"model.layers.14.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
| 87 |
+
"model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 88 |
+
"model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 89 |
+
"model.layers.14.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
| 90 |
+
"model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 91 |
+
"model.layers.14.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
| 92 |
+
"model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 93 |
+
"model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 94 |
+
"model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 95 |
+
"model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 96 |
+
"model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 97 |
+
"model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 98 |
+
"model.layers.15.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
| 99 |
+
"model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 100 |
+
"model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 101 |
+
"model.layers.15.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
| 102 |
+
"model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 103 |
+
"model.layers.15.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
| 104 |
+
"model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 105 |
+
"model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 106 |
+
"model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 107 |
+
"model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 108 |
+
"model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 109 |
+
"model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 110 |
+
"model.layers.16.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
| 111 |
+
"model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 112 |
+
"model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 113 |
+
"model.layers.16.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
| 114 |
+
"model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 115 |
+
"model.layers.16.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
| 116 |
+
"model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 117 |
+
"model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 118 |
+
"model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 119 |
+
"model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 120 |
+
"model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 121 |
+
"model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 122 |
+
"model.layers.17.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
| 123 |
+
"model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 124 |
+
"model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 125 |
+
"model.layers.17.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
| 126 |
+
"model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 127 |
+
"model.layers.17.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
| 128 |
+
"model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 129 |
+
"model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 130 |
+
"model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 131 |
+
"model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 132 |
+
"model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 133 |
+
"model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 134 |
+
"model.layers.18.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
| 135 |
+
"model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 136 |
+
"model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 137 |
+
"model.layers.18.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
| 138 |
+
"model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 139 |
+
"model.layers.18.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
| 140 |
+
"model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 141 |
+
"model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 142 |
+
"model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 143 |
+
"model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 144 |
+
"model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 145 |
+
"model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 146 |
+
"model.layers.19.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 147 |
+
"model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 148 |
+
"model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 149 |
+
"model.layers.19.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 150 |
+
"model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 151 |
+
"model.layers.19.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 152 |
+
"model.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 153 |
+
"model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 154 |
+
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 155 |
+
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 156 |
+
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 157 |
+
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 158 |
+
"model.layers.2.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
| 159 |
+
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 160 |
+
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 161 |
+
"model.layers.2.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
| 162 |
+
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 163 |
+
"model.layers.2.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
| 164 |
+
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 165 |
+
"model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 166 |
+
"model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 167 |
+
"model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 168 |
+
"model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 169 |
+
"model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 170 |
+
"model.layers.20.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 171 |
+
"model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 172 |
+
"model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 173 |
+
"model.layers.20.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 174 |
+
"model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 175 |
+
"model.layers.20.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 176 |
+
"model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 177 |
+
"model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 178 |
+
"model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 179 |
+
"model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 180 |
+
"model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 181 |
+
"model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 182 |
+
"model.layers.21.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 183 |
+
"model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 184 |
+
"model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 185 |
+
"model.layers.21.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 186 |
+
"model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 187 |
+
"model.layers.21.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 188 |
+
"model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 189 |
+
"model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 190 |
+
"model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 191 |
+
"model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 192 |
+
"model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 193 |
+
"model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 194 |
+
"model.layers.22.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 195 |
+
"model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 196 |
+
"model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 197 |
+
"model.layers.22.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 198 |
+
"model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 199 |
+
"model.layers.22.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 200 |
+
"model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 201 |
+
"model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 202 |
+
"model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 203 |
+
"model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 204 |
+
"model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 205 |
+
"model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 206 |
+
"model.layers.23.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 207 |
+
"model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 208 |
+
"model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 209 |
+
"model.layers.23.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 210 |
+
"model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 211 |
+
"model.layers.23.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 212 |
+
"model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 213 |
+
"model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 214 |
+
"model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 215 |
+
"model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 216 |
+
"model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 217 |
+
"model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 218 |
+
"model.layers.24.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 219 |
+
"model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 220 |
+
"model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 221 |
+
"model.layers.24.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 222 |
+
"model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 223 |
+
"model.layers.24.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 224 |
+
"model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 225 |
+
"model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 226 |
+
"model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 227 |
+
"model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 228 |
+
"model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 229 |
+
"model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 230 |
+
"model.layers.25.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 231 |
+
"model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 232 |
+
"model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 233 |
+
"model.layers.25.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 234 |
+
"model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 235 |
+
"model.layers.25.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 236 |
+
"model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 237 |
+
"model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 238 |
+
"model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 239 |
+
"model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 240 |
+
"model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 241 |
+
"model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 242 |
+
"model.layers.26.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 243 |
+
"model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 244 |
+
"model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 245 |
+
"model.layers.26.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 246 |
+
"model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 247 |
+
"model.layers.26.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 248 |
+
"model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 249 |
+
"model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 250 |
+
"model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 251 |
+
"model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 252 |
+
"model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 253 |
+
"model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 254 |
+
"model.layers.27.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 255 |
+
"model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 256 |
+
"model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 257 |
+
"model.layers.27.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 258 |
+
"model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 259 |
+
"model.layers.27.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 260 |
+
"model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 261 |
+
"model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 262 |
+
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 263 |
+
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 264 |
+
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 265 |
+
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 266 |
+
"model.layers.3.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
| 267 |
+
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 268 |
+
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 269 |
+
"model.layers.3.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
| 270 |
+
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 271 |
+
"model.layers.3.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
| 272 |
+
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 273 |
+
"model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 274 |
+
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 275 |
+
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 276 |
+
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 277 |
+
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 278 |
+
"model.layers.4.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
| 279 |
+
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 280 |
+
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 281 |
+
"model.layers.4.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
| 282 |
+
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 283 |
+
"model.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
| 284 |
+
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 285 |
+
"model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 286 |
+
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 287 |
+
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 288 |
+
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 289 |
+
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 290 |
+
"model.layers.5.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
| 291 |
+
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 292 |
+
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 293 |
+
"model.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
| 294 |
+
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 295 |
+
"model.layers.5.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
| 296 |
+
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 297 |
+
"model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 298 |
+
"model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 299 |
+
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 300 |
+
"model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 301 |
+
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 302 |
+
"model.layers.6.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
| 303 |
+
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 304 |
+
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 305 |
+
"model.layers.6.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
| 306 |
+
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 307 |
+
"model.layers.6.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
| 308 |
+
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 309 |
+
"model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 310 |
+
"model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 311 |
+
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 312 |
+
"model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 313 |
+
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 314 |
+
"model.layers.7.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
| 315 |
+
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 316 |
+
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 317 |
+
"model.layers.7.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
| 318 |
+
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 319 |
+
"model.layers.7.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
| 320 |
+
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 321 |
+
"model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 322 |
+
"model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 323 |
+
"model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 324 |
+
"model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 325 |
+
"model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 326 |
+
"model.layers.8.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
| 327 |
+
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 328 |
+
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 329 |
+
"model.layers.8.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
| 330 |
+
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 331 |
+
"model.layers.8.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
| 332 |
+
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 333 |
+
"model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 334 |
+
"model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 335 |
+
"model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 336 |
+
"model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 337 |
+
"model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 338 |
+
"model.layers.9.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
| 339 |
+
"model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 340 |
+
"model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 341 |
+
"model.layers.9.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
| 342 |
+
"model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 343 |
+
"model.layers.9.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
| 344 |
+
"model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 345 |
+
"model.norm.weight": "model-00003-of-00004.safetensors"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 346 |
}
|
| 347 |
}
|
special_tokens_map.json
CHANGED
|
@@ -1,18 +1,7 @@
|
|
| 1 |
{
|
| 2 |
"additional_special_tokens": [
|
| 3 |
"<|im_start|>",
|
| 4 |
-
"<|im_end|>"
|
| 5 |
-
"<|object_ref_start|>",
|
| 6 |
-
"<|object_ref_end|>",
|
| 7 |
-
"<|box_start|>",
|
| 8 |
-
"<|box_end|>",
|
| 9 |
-
"<|quad_start|>",
|
| 10 |
-
"<|quad_end|>",
|
| 11 |
-
"<|vision_start|>",
|
| 12 |
-
"<|vision_end|>",
|
| 13 |
-
"<|vision_pad|>",
|
| 14 |
-
"<|image_pad|>",
|
| 15 |
-
"<|video_pad|>"
|
| 16 |
],
|
| 17 |
"eos_token": {
|
| 18 |
"content": "<|im_end|>",
|
|
|
|
| 1 |
{
|
| 2 |
"additional_special_tokens": [
|
| 3 |
"<|im_start|>",
|
| 4 |
+
"<|im_end|>"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5 |
],
|
| 6 |
"eos_token": {
|
| 7 |
"content": "<|im_end|>",
|
tokenizer.json
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bcfe42da0a4497e8b2b172c1f9f4ec423a46dc12907f4349c55025f670422ba9
|
| 3 |
+
size 11418266
|
tokenizer_config.json
CHANGED
|
@@ -1,5 +1,4 @@
|
|
| 1 |
{
|
| 2 |
-
"add_bos_token": false,
|
| 3 |
"add_prefix_space": false,
|
| 4 |
"added_tokens_decoder": {
|
| 5 |
"151643": {
|
|
@@ -25,174 +24,11 @@
|
|
| 25 |
"rstrip": false,
|
| 26 |
"single_word": false,
|
| 27 |
"special": true
|
| 28 |
-
},
|
| 29 |
-
"151646": {
|
| 30 |
-
"content": "<|object_ref_start|>",
|
| 31 |
-
"lstrip": false,
|
| 32 |
-
"normalized": false,
|
| 33 |
-
"rstrip": false,
|
| 34 |
-
"single_word": false,
|
| 35 |
-
"special": true
|
| 36 |
-
},
|
| 37 |
-
"151647": {
|
| 38 |
-
"content": "<|object_ref_end|>",
|
| 39 |
-
"lstrip": false,
|
| 40 |
-
"normalized": false,
|
| 41 |
-
"rstrip": false,
|
| 42 |
-
"single_word": false,
|
| 43 |
-
"special": true
|
| 44 |
-
},
|
| 45 |
-
"151648": {
|
| 46 |
-
"content": "<|box_start|>",
|
| 47 |
-
"lstrip": false,
|
| 48 |
-
"normalized": false,
|
| 49 |
-
"rstrip": false,
|
| 50 |
-
"single_word": false,
|
| 51 |
-
"special": true
|
| 52 |
-
},
|
| 53 |
-
"151649": {
|
| 54 |
-
"content": "<|box_end|>",
|
| 55 |
-
"lstrip": false,
|
| 56 |
-
"normalized": false,
|
| 57 |
-
"rstrip": false,
|
| 58 |
-
"single_word": false,
|
| 59 |
-
"special": true
|
| 60 |
-
},
|
| 61 |
-
"151650": {
|
| 62 |
-
"content": "<|quad_start|>",
|
| 63 |
-
"lstrip": false,
|
| 64 |
-
"normalized": false,
|
| 65 |
-
"rstrip": false,
|
| 66 |
-
"single_word": false,
|
| 67 |
-
"special": true
|
| 68 |
-
},
|
| 69 |
-
"151651": {
|
| 70 |
-
"content": "<|quad_end|>",
|
| 71 |
-
"lstrip": false,
|
| 72 |
-
"normalized": false,
|
| 73 |
-
"rstrip": false,
|
| 74 |
-
"single_word": false,
|
| 75 |
-
"special": true
|
| 76 |
-
},
|
| 77 |
-
"151652": {
|
| 78 |
-
"content": "<|vision_start|>",
|
| 79 |
-
"lstrip": false,
|
| 80 |
-
"normalized": false,
|
| 81 |
-
"rstrip": false,
|
| 82 |
-
"single_word": false,
|
| 83 |
-
"special": true
|
| 84 |
-
},
|
| 85 |
-
"151653": {
|
| 86 |
-
"content": "<|vision_end|>",
|
| 87 |
-
"lstrip": false,
|
| 88 |
-
"normalized": false,
|
| 89 |
-
"rstrip": false,
|
| 90 |
-
"single_word": false,
|
| 91 |
-
"special": true
|
| 92 |
-
},
|
| 93 |
-
"151654": {
|
| 94 |
-
"content": "<|vision_pad|>",
|
| 95 |
-
"lstrip": false,
|
| 96 |
-
"normalized": false,
|
| 97 |
-
"rstrip": false,
|
| 98 |
-
"single_word": false,
|
| 99 |
-
"special": true
|
| 100 |
-
},
|
| 101 |
-
"151655": {
|
| 102 |
-
"content": "<|image_pad|>",
|
| 103 |
-
"lstrip": false,
|
| 104 |
-
"normalized": false,
|
| 105 |
-
"rstrip": false,
|
| 106 |
-
"single_word": false,
|
| 107 |
-
"special": true
|
| 108 |
-
},
|
| 109 |
-
"151656": {
|
| 110 |
-
"content": "<|video_pad|>",
|
| 111 |
-
"lstrip": false,
|
| 112 |
-
"normalized": false,
|
| 113 |
-
"rstrip": false,
|
| 114 |
-
"single_word": false,
|
| 115 |
-
"special": true
|
| 116 |
-
},
|
| 117 |
-
"151657": {
|
| 118 |
-
"content": "<tool_call>",
|
| 119 |
-
"lstrip": false,
|
| 120 |
-
"normalized": false,
|
| 121 |
-
"rstrip": false,
|
| 122 |
-
"single_word": false,
|
| 123 |
-
"special": false
|
| 124 |
-
},
|
| 125 |
-
"151658": {
|
| 126 |
-
"content": "</tool_call>",
|
| 127 |
-
"lstrip": false,
|
| 128 |
-
"normalized": false,
|
| 129 |
-
"rstrip": false,
|
| 130 |
-
"single_word": false,
|
| 131 |
-
"special": false
|
| 132 |
-
},
|
| 133 |
-
"151659": {
|
| 134 |
-
"content": "<|fim_prefix|>",
|
| 135 |
-
"lstrip": false,
|
| 136 |
-
"normalized": false,
|
| 137 |
-
"rstrip": false,
|
| 138 |
-
"single_word": false,
|
| 139 |
-
"special": false
|
| 140 |
-
},
|
| 141 |
-
"151660": {
|
| 142 |
-
"content": "<|fim_middle|>",
|
| 143 |
-
"lstrip": false,
|
| 144 |
-
"normalized": false,
|
| 145 |
-
"rstrip": false,
|
| 146 |
-
"single_word": false,
|
| 147 |
-
"special": false
|
| 148 |
-
},
|
| 149 |
-
"151661": {
|
| 150 |
-
"content": "<|fim_suffix|>",
|
| 151 |
-
"lstrip": false,
|
| 152 |
-
"normalized": false,
|
| 153 |
-
"rstrip": false,
|
| 154 |
-
"single_word": false,
|
| 155 |
-
"special": false
|
| 156 |
-
},
|
| 157 |
-
"151662": {
|
| 158 |
-
"content": "<|fim_pad|>",
|
| 159 |
-
"lstrip": false,
|
| 160 |
-
"normalized": false,
|
| 161 |
-
"rstrip": false,
|
| 162 |
-
"single_word": false,
|
| 163 |
-
"special": false
|
| 164 |
-
},
|
| 165 |
-
"151663": {
|
| 166 |
-
"content": "<|repo_name|>",
|
| 167 |
-
"lstrip": false,
|
| 168 |
-
"normalized": false,
|
| 169 |
-
"rstrip": false,
|
| 170 |
-
"single_word": false,
|
| 171 |
-
"special": false
|
| 172 |
-
},
|
| 173 |
-
"151664": {
|
| 174 |
-
"content": "<|file_sep|>",
|
| 175 |
-
"lstrip": false,
|
| 176 |
-
"normalized": false,
|
| 177 |
-
"rstrip": false,
|
| 178 |
-
"single_word": false,
|
| 179 |
-
"special": false
|
| 180 |
}
|
| 181 |
},
|
| 182 |
"additional_special_tokens": [
|
| 183 |
"<|im_start|>",
|
| 184 |
-
"<|im_end|>"
|
| 185 |
-
"<|object_ref_start|>",
|
| 186 |
-
"<|object_ref_end|>",
|
| 187 |
-
"<|box_start|>",
|
| 188 |
-
"<|box_end|>",
|
| 189 |
-
"<|quad_start|>",
|
| 190 |
-
"<|quad_end|>",
|
| 191 |
-
"<|vision_start|>",
|
| 192 |
-
"<|vision_end|>",
|
| 193 |
-
"<|vision_pad|>",
|
| 194 |
-
"<|image_pad|>",
|
| 195 |
-
"<|video_pad|>"
|
| 196 |
],
|
| 197 |
"bos_token": null,
|
| 198 |
"clean_up_tokenization_spaces": false,
|
|
|
|
| 1 |
{
|
|
|
|
| 2 |
"add_prefix_space": false,
|
| 3 |
"added_tokens_decoder": {
|
| 4 |
"151643": {
|
|
|
|
| 24 |
"rstrip": false,
|
| 25 |
"single_word": false,
|
| 26 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 27 |
}
|
| 28 |
},
|
| 29 |
"additional_special_tokens": [
|
| 30 |
"<|im_start|>",
|
| 31 |
+
"<|im_end|>"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 32 |
],
|
| 33 |
"bos_token": null,
|
| 34 |
"clean_up_tokenization_spaces": false,
|