Training in progress, step 10
Browse files- chat_template.jinja +1 -89
- config.json +17 -14
- model-00001-of-00003.safetensors +3 -0
- model-00002-of-00003.safetensors +3 -0
- model-00003-of-00003.safetensors +3 -0
- model.safetensors.index.json +292 -400
- special_tokens_map.json +11 -19
- tokenizer.json +2 -2
- tokenizer_config.json +90 -135
- training_args.bin +2 -2
chat_template.jinja
CHANGED
|
@@ -1,89 +1 @@
|
|
| 1 |
-
{%- if
|
| 2 |
-
{{- '<|im_start|>system\n' }}
|
| 3 |
-
{%- if messages[0].role == 'system' %}
|
| 4 |
-
{{- messages[0].content + '\n\n' }}
|
| 5 |
-
{%- endif %}
|
| 6 |
-
{{- "# 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>" }}
|
| 7 |
-
{%- for tool in tools %}
|
| 8 |
-
{{- "\n" }}
|
| 9 |
-
{{- tool | tojson }}
|
| 10 |
-
{%- endfor %}
|
| 11 |
-
{{- "\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" }}
|
| 12 |
-
{%- else %}
|
| 13 |
-
{%- if messages[0].role == 'system' %}
|
| 14 |
-
{{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
|
| 15 |
-
{%- endif %}
|
| 16 |
-
{%- endif %}
|
| 17 |
-
{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
|
| 18 |
-
{%- for message in messages[::-1] %}
|
| 19 |
-
{%- set index = (messages|length - 1) - loop.index0 %}
|
| 20 |
-
{%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
|
| 21 |
-
{%- set ns.multi_step_tool = false %}
|
| 22 |
-
{%- set ns.last_query_index = index %}
|
| 23 |
-
{%- endif %}
|
| 24 |
-
{%- endfor %}
|
| 25 |
-
{%- for message in messages %}
|
| 26 |
-
{%- if message.content is string %}
|
| 27 |
-
{%- set content = message.content %}
|
| 28 |
-
{%- else %}
|
| 29 |
-
{%- set content = '' %}
|
| 30 |
-
{%- endif %}
|
| 31 |
-
{%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
|
| 32 |
-
{{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
|
| 33 |
-
{%- elif message.role == "assistant" %}
|
| 34 |
-
{%- set reasoning_content = '' %}
|
| 35 |
-
{%- if message.reasoning_content is string %}
|
| 36 |
-
{%- set reasoning_content = message.reasoning_content %}
|
| 37 |
-
{%- else %}
|
| 38 |
-
{%- if '</think>' in content %}
|
| 39 |
-
{%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
|
| 40 |
-
{%- set content = content.split('</think>')[-1].lstrip('\n') %}
|
| 41 |
-
{%- endif %}
|
| 42 |
-
{%- endif %}
|
| 43 |
-
{%- if loop.index0 > ns.last_query_index %}
|
| 44 |
-
{%- if loop.last or (not loop.last and reasoning_content) %}
|
| 45 |
-
{{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
|
| 46 |
-
{%- else %}
|
| 47 |
-
{{- '<|im_start|>' + message.role + '\n' + content }}
|
| 48 |
-
{%- endif %}
|
| 49 |
-
{%- else %}
|
| 50 |
-
{{- '<|im_start|>' + message.role + '\n' + content }}
|
| 51 |
-
{%- endif %}
|
| 52 |
-
{%- if message.tool_calls %}
|
| 53 |
-
{%- for tool_call in message.tool_calls %}
|
| 54 |
-
{%- if (loop.first and content) or (not loop.first) %}
|
| 55 |
-
{{- '\n' }}
|
| 56 |
-
{%- endif %}
|
| 57 |
-
{%- if tool_call.function %}
|
| 58 |
-
{%- set tool_call = tool_call.function %}
|
| 59 |
-
{%- endif %}
|
| 60 |
-
{{- '<tool_call>\n{"name": "' }}
|
| 61 |
-
{{- tool_call.name }}
|
| 62 |
-
{{- '", "arguments": ' }}
|
| 63 |
-
{%- if tool_call.arguments is string %}
|
| 64 |
-
{{- tool_call.arguments }}
|
| 65 |
-
{%- else %}
|
| 66 |
-
{{- tool_call.arguments | tojson }}
|
| 67 |
-
{%- endif %}
|
| 68 |
-
{{- '}\n</tool_call>' }}
|
| 69 |
-
{%- endfor %}
|
| 70 |
-
{%- endif %}
|
| 71 |
-
{{- '<|im_end|>\n' }}
|
| 72 |
-
{%- elif message.role == "tool" %}
|
| 73 |
-
{%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
|
| 74 |
-
{{- '<|im_start|>user' }}
|
| 75 |
-
{%- endif %}
|
| 76 |
-
{{- '\n<tool_response>\n' }}
|
| 77 |
-
{{- content }}
|
| 78 |
-
{{- '\n</tool_response>' }}
|
| 79 |
-
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
|
| 80 |
-
{{- '<|im_end|>\n' }}
|
| 81 |
-
{%- endif %}
|
| 82 |
-
{%- endif %}
|
| 83 |
-
{%- endfor %}
|
| 84 |
-
{%- if add_generation_prompt %}
|
| 85 |
-
{{- '<|im_start|>assistant\n' }}
|
| 86 |
-
{%- if enable_thinking is defined and enable_thinking is false %}
|
| 87 |
-
{{- '<think>\n\n</think>\n\n' }}
|
| 88 |
-
{%- endif %}
|
| 89 |
-
{%- endif %}
|
|
|
|
| 1 |
+
{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='') %}{%- for message in messages %}{%- if message['role'] == 'system' %}{% set ns.system_prompt = message['content'] %}{%- endif %}{%- endfor %}{{bos_token}}{{ns.system_prompt}}{%- for message in messages %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{{'<｜User｜>' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is none %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls']%}{%- if not ns.is_first %}{{'<｜Assistant｜><｜tool▁calls▁begin｜><｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\n' + '```json' + '\n' + tool['function']['arguments'] + '\n' + '```' + '<｜tool▁call▁end｜>'}}{%- set ns.is_first = true -%}{%- else %}{{'\n' + '<｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\n' + '```json' + '\n' + tool['function']['arguments'] + '\n' + '```' + '<｜tool▁call▁end｜>'}}{{'<｜tool▁calls▁end｜><｜end▁of▁sentence｜>'}}{%- endif %}{%- endfor %}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is not none %}{%- if ns.is_tool %}{{'<｜tool▁outputs▁end｜>' + message['content'] + '<｜end▁of▁sentence｜>'}}{%- set ns.is_tool = false -%}{%- else %}{% set content = message['content'] %}{{'<｜Assistant｜>' + content + '<｜end▁of▁sentence｜>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<｜tool▁outputs▁begin｜><｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- set ns.is_output_first = false %}{%- else %}{{'\n<｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<｜tool▁outputs▁end｜>'}}{% endif %}{% if add_generation_prompt and not ns.is_tool %}{{'<｜Assistant｜>'}}{% endif %}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
config.json
CHANGED
|
@@ -1,30 +1,33 @@
|
|
| 1 |
{
|
| 2 |
"architectures": [
|
| 3 |
-
"
|
| 4 |
],
|
| 5 |
"attention_bias": false,
|
| 6 |
"attention_dropout": 0.0,
|
| 7 |
-
"bos_token_id":
|
| 8 |
-
"eos_token_id":
|
| 9 |
"head_dim": 128,
|
| 10 |
"hidden_act": "silu",
|
| 11 |
"hidden_size": 4096,
|
| 12 |
"initializer_range": 0.02,
|
| 13 |
-
"intermediate_size":
|
| 14 |
-
"max_position_embeddings":
|
| 15 |
-
"
|
| 16 |
-
"model_type": "
|
| 17 |
"num_attention_heads": 32,
|
| 18 |
-
"num_hidden_layers":
|
| 19 |
-
"num_key_value_heads":
|
|
|
|
| 20 |
"rms_norm_eps": 1e-06,
|
| 21 |
-
"rope_scaling":
|
| 22 |
-
|
| 23 |
-
|
|
|
|
|
|
|
|
|
|
| 24 |
"tie_word_embeddings": false,
|
| 25 |
"torch_dtype": "bfloat16",
|
| 26 |
"transformers_version": "4.52.3",
|
| 27 |
"use_cache": false,
|
| 28 |
-
"
|
| 29 |
-
"vocab_size": 151936
|
| 30 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"architectures": [
|
| 3 |
+
"LlamaForCausalLM"
|
| 4 |
],
|
| 5 |
"attention_bias": false,
|
| 6 |
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": 32013,
|
| 8 |
+
"eos_token_id": 32014,
|
| 9 |
"head_dim": 128,
|
| 10 |
"hidden_act": "silu",
|
| 11 |
"hidden_size": 4096,
|
| 12 |
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 11008,
|
| 14 |
+
"max_position_embeddings": 16384,
|
| 15 |
+
"mlp_bias": false,
|
| 16 |
+
"model_type": "llama",
|
| 17 |
"num_attention_heads": 32,
|
| 18 |
+
"num_hidden_layers": 32,
|
| 19 |
+
"num_key_value_heads": 32,
|
| 20 |
+
"pretraining_tp": 1,
|
| 21 |
"rms_norm_eps": 1e-06,
|
| 22 |
+
"rope_scaling": {
|
| 23 |
+
"factor": 4.0,
|
| 24 |
+
"rope_type": "linear",
|
| 25 |
+
"type": "linear"
|
| 26 |
+
},
|
| 27 |
+
"rope_theta": 100000,
|
| 28 |
"tie_word_embeddings": false,
|
| 29 |
"torch_dtype": "bfloat16",
|
| 30 |
"transformers_version": "4.52.3",
|
| 31 |
"use_cache": false,
|
| 32 |
+
"vocab_size": 32256
|
|
|
|
| 33 |
}
|
model-00001-of-00003.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ecbb5834354f9357f0c75ec656e7b55720a0f2d956626c95f9d72e3675ba5871
|
| 3 |
+
size 4941082504
|
model-00002-of-00003.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:13b3fd2d44cac3deece215dde55668b430d707c3ea595a6c3361416e111e423f
|
| 3 |
+
size 4947390880
|
model-00003-of-00003.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d50dbe9ee4d11f9ab9b1c0b1ef0fab678f1ba20e579966c5fb69da6527e11377
|
| 3 |
+
size 3592585968
|
model.safetensors.index.json
CHANGED
|
@@ -1,406 +1,298 @@
|
|
| 1 |
{
|
| 2 |
"metadata": {
|
| 3 |
-
"total_size":
|
| 4 |
},
|
| 5 |
"weight_map": {
|
| 6 |
-
"lm_head.weight": "model-
|
| 7 |
-
"model.embed_tokens.weight": "model-00001-of-
|
| 8 |
-
"model.layers.0.input_layernorm.weight": "model-00001-of-
|
| 9 |
-
"model.layers.0.mlp.down_proj.weight": "model-00001-of-
|
| 10 |
-
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-
|
| 11 |
-
"model.layers.0.mlp.up_proj.weight": "model-00001-of-
|
| 12 |
-
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-
|
| 13 |
-
"model.layers.0.self_attn.
|
| 14 |
-
"model.layers.0.self_attn.
|
| 15 |
-
"model.layers.0.self_attn.
|
| 16 |
-
"model.layers.0.self_attn.
|
| 17 |
-
"model.layers.
|
| 18 |
-
"model.layers.
|
| 19 |
-
"model.layers.1.
|
| 20 |
-
"model.layers.1.mlp.
|
| 21 |
-
"model.layers.1.
|
| 22 |
-
"model.layers.1.
|
| 23 |
-
"model.layers.1.
|
| 24 |
-
"model.layers.1.self_attn.
|
| 25 |
-
"model.layers.1.self_attn.
|
| 26 |
-
"model.layers.
|
| 27 |
-
"model.layers.
|
| 28 |
-
"model.layers.
|
| 29 |
-
"model.layers.
|
| 30 |
-
"model.layers.10.
|
| 31 |
-
"model.layers.10.
|
| 32 |
-
"model.layers.10.
|
| 33 |
-
"model.layers.10.
|
| 34 |
-
"model.layers.10.
|
| 35 |
-
"model.layers.
|
| 36 |
-
"model.layers.
|
| 37 |
-
"model.layers.
|
| 38 |
-
"model.layers.
|
| 39 |
-
"model.layers.
|
| 40 |
-
"model.layers.
|
| 41 |
-
"model.layers.11.
|
| 42 |
-
"model.layers.11.
|
| 43 |
-
"model.layers.11.
|
| 44 |
-
"model.layers.
|
| 45 |
-
"model.layers.
|
| 46 |
-
"model.layers.
|
| 47 |
-
"model.layers.
|
| 48 |
-
"model.layers.
|
| 49 |
-
"model.layers.
|
| 50 |
-
"model.layers.
|
| 51 |
-
"model.layers.
|
| 52 |
-
"model.layers.12.
|
| 53 |
-
"model.layers.
|
| 54 |
-
"model.layers.
|
| 55 |
-
"model.layers.
|
| 56 |
-
"model.layers.
|
| 57 |
-
"model.layers.
|
| 58 |
-
"model.layers.
|
| 59 |
-
"model.layers.
|
| 60 |
-
"model.layers.
|
| 61 |
-
"model.layers.
|
| 62 |
-
"model.layers.
|
| 63 |
-
"model.layers.
|
| 64 |
-
"model.layers.
|
| 65 |
-
"model.layers.
|
| 66 |
-
"model.layers.
|
| 67 |
-
"model.layers.
|
| 68 |
-
"model.layers.
|
| 69 |
-
"model.layers.
|
| 70 |
-
"model.layers.
|
| 71 |
-
"model.layers.
|
| 72 |
-
"model.layers.
|
| 73 |
-
"model.layers.
|
| 74 |
-
"model.layers.
|
| 75 |
-
"model.layers.
|
| 76 |
-
"model.layers.
|
| 77 |
-
"model.layers.
|
| 78 |
-
"model.layers.
|
| 79 |
-
"model.layers.
|
| 80 |
-
"model.layers.
|
| 81 |
-
"model.layers.
|
| 82 |
-
"model.layers.
|
| 83 |
-
"model.layers.
|
| 84 |
-
"model.layers.
|
| 85 |
-
"model.layers.
|
| 86 |
-
"model.layers.
|
| 87 |
-
"model.layers.
|
| 88 |
-
"model.layers.
|
| 89 |
-
"model.layers.
|
| 90 |
-
"model.layers.
|
| 91 |
-
"model.layers.
|
| 92 |
-
"model.layers.
|
| 93 |
-
"model.layers.
|
| 94 |
-
"model.layers.
|
| 95 |
-
"model.layers.
|
| 96 |
-
"model.layers.
|
| 97 |
-
"model.layers.
|
| 98 |
-
"model.layers.
|
| 99 |
-
"model.layers.
|
| 100 |
-
"model.layers.
|
| 101 |
-
"model.layers.
|
| 102 |
-
"model.layers.
|
| 103 |
-
"model.layers.
|
| 104 |
-
"model.layers.
|
| 105 |
-
"model.layers.
|
| 106 |
-
"model.layers.
|
| 107 |
-
"model.layers.
|
| 108 |
-
"model.layers.
|
| 109 |
-
"model.layers.
|
| 110 |
-
"model.layers.
|
| 111 |
-
"model.layers.
|
| 112 |
-
"model.layers.
|
| 113 |
-
"model.layers.
|
| 114 |
-
"model.layers.
|
| 115 |
-
"model.layers.
|
| 116 |
-
"model.layers.
|
| 117 |
-
"model.layers.
|
| 118 |
-
"model.layers.
|
| 119 |
-
"model.layers.
|
| 120 |
-
"model.layers.
|
| 121 |
-
"model.layers.
|
| 122 |
-
"model.layers.
|
| 123 |
-
"model.layers.
|
| 124 |
-
"model.layers.
|
| 125 |
-
"model.layers.
|
| 126 |
-
"model.layers.
|
| 127 |
-
"model.layers.
|
| 128 |
-
"model.layers.
|
| 129 |
-
"model.layers.
|
| 130 |
-
"model.layers.
|
| 131 |
-
"model.layers.
|
| 132 |
-
"model.layers.
|
| 133 |
-
"model.layers.
|
| 134 |
-
"model.layers.
|
| 135 |
-
"model.layers.
|
| 136 |
-
"model.layers.
|
| 137 |
-
"model.layers.
|
| 138 |
-
"model.layers.
|
| 139 |
-
"model.layers.
|
| 140 |
-
"model.layers.
|
| 141 |
-
"model.layers.
|
| 142 |
-
"model.layers.
|
| 143 |
-
"model.layers.
|
| 144 |
-
"model.layers.
|
| 145 |
-
"model.layers.
|
| 146 |
-
"model.layers.
|
| 147 |
-
"model.layers.
|
| 148 |
-
"model.layers.
|
| 149 |
-
"model.layers.
|
| 150 |
-
"model.layers.
|
| 151 |
-
"model.layers.
|
| 152 |
-
"model.layers.
|
| 153 |
-
"model.layers.
|
| 154 |
-
"model.layers.
|
| 155 |
-
"model.layers.
|
| 156 |
-
"model.layers.
|
| 157 |
-
"model.layers.
|
| 158 |
-
"model.layers.
|
| 159 |
-
"model.layers.
|
| 160 |
-
"model.layers.
|
| 161 |
-
"model.layers.
|
| 162 |
-
"model.layers.
|
| 163 |
-
"model.layers.
|
| 164 |
-
"model.layers.
|
| 165 |
-
"model.layers.
|
| 166 |
-
"model.layers.
|
| 167 |
-
"model.layers.
|
| 168 |
-
"model.layers.
|
| 169 |
-
"model.layers.
|
| 170 |
-
"model.layers.
|
| 171 |
-
"model.layers.
|
| 172 |
-
"model.layers.
|
| 173 |
-
"model.layers.
|
| 174 |
-
"model.layers.
|
| 175 |
-
"model.layers.
|
| 176 |
-
"model.layers.
|
| 177 |
-
"model.layers.
|
| 178 |
-
"model.layers.
|
| 179 |
-
"model.layers.
|
| 180 |
-
"model.layers.
|
| 181 |
-
"model.layers.
|
| 182 |
-
"model.layers.
|
| 183 |
-
"model.layers.
|
| 184 |
-
"model.layers.
|
| 185 |
-
"model.layers.
|
| 186 |
-
"model.layers.
|
| 187 |
-
"model.layers.
|
| 188 |
-
"model.layers.
|
| 189 |
-
"model.layers.
|
| 190 |
-
"model.layers.
|
| 191 |
-
"model.layers.
|
| 192 |
-
"model.layers.
|
| 193 |
-
"model.layers.
|
| 194 |
-
"model.layers.
|
| 195 |
-
"model.layers.
|
| 196 |
-
"model.layers.
|
| 197 |
-
"model.layers.
|
| 198 |
-
"model.layers.
|
| 199 |
-
"model.layers.
|
| 200 |
-
"model.layers.
|
| 201 |
-
"model.layers.
|
| 202 |
-
"model.layers.
|
| 203 |
-
"model.layers.
|
| 204 |
-
"model.layers.
|
| 205 |
-
"model.layers.
|
| 206 |
-
"model.layers.
|
| 207 |
-
"model.layers.
|
| 208 |
-
"model.layers.
|
| 209 |
-
"model.layers.
|
| 210 |
-
"model.layers.
|
| 211 |
-
"model.layers.
|
| 212 |
-
"model.layers.
|
| 213 |
-
"model.layers.
|
| 214 |
-
"model.layers.
|
| 215 |
-
"model.layers.
|
| 216 |
-
"model.layers.
|
| 217 |
-
"model.layers.
|
| 218 |
-
"model.layers.
|
| 219 |
-
"model.layers.
|
| 220 |
-
"model.layers.
|
| 221 |
-
"model.layers.
|
| 222 |
-
"model.layers.
|
| 223 |
-
"model.layers.
|
| 224 |
-
"model.layers.
|
| 225 |
-
"model.layers.
|
| 226 |
-
"model.layers.
|
| 227 |
-
"model.layers.
|
| 228 |
-
"model.layers.
|
| 229 |
-
"model.layers.
|
| 230 |
-
"model.layers.
|
| 231 |
-
"model.layers.
|
| 232 |
-
"model.layers.
|
| 233 |
-
"model.layers.
|
| 234 |
-
"model.layers.
|
| 235 |
-
"model.layers.
|
| 236 |
-
"model.layers.
|
| 237 |
-
"model.layers.
|
| 238 |
-
"model.layers.
|
| 239 |
-
"model.layers.
|
| 240 |
-
"model.layers.
|
| 241 |
-
"model.layers.
|
| 242 |
-
"model.layers.
|
| 243 |
-
"model.layers.
|
| 244 |
-
"model.layers.
|
| 245 |
-
"model.layers.
|
| 246 |
-
"model.layers.
|
| 247 |
-
"model.layers.
|
| 248 |
-
"model.layers.
|
| 249 |
-
"model.layers.
|
| 250 |
-
"model.layers.
|
| 251 |
-
"model.layers.
|
| 252 |
-
"model.layers.
|
| 253 |
-
"model.layers.
|
| 254 |
-
"model.layers.
|
| 255 |
-
"model.layers.
|
| 256 |
-
"model.layers.
|
| 257 |
-
"model.layers.
|
| 258 |
-
"model.layers.
|
| 259 |
-
"model.layers.
|
| 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.
|
| 297 |
-
"model.layers.32.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 298 |
-
"model.layers.32.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 299 |
-
"model.layers.32.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
| 300 |
-
"model.layers.32.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 301 |
-
"model.layers.32.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 302 |
-
"model.layers.32.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 303 |
-
"model.layers.32.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 304 |
-
"model.layers.32.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 305 |
-
"model.layers.33.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 306 |
-
"model.layers.33.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 307 |
-
"model.layers.33.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 308 |
-
"model.layers.33.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 309 |
-
"model.layers.33.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 310 |
-
"model.layers.33.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
| 311 |
-
"model.layers.33.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 312 |
-
"model.layers.33.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 313 |
-
"model.layers.33.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 314 |
-
"model.layers.33.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 315 |
-
"model.layers.33.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 316 |
-
"model.layers.34.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 317 |
-
"model.layers.34.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 318 |
-
"model.layers.34.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 319 |
-
"model.layers.34.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 320 |
-
"model.layers.34.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 321 |
-
"model.layers.34.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
| 322 |
-
"model.layers.34.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 323 |
-
"model.layers.34.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 324 |
-
"model.layers.34.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 325 |
-
"model.layers.34.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 326 |
-
"model.layers.34.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 327 |
-
"model.layers.35.input_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 328 |
-
"model.layers.35.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
| 329 |
-
"model.layers.35.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
| 330 |
-
"model.layers.35.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
| 331 |
-
"model.layers.35.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 332 |
-
"model.layers.35.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
|
| 333 |
-
"model.layers.35.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 334 |
-
"model.layers.35.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
|
| 335 |
-
"model.layers.35.self_attn.q_norm.weight": "model-00004-of-00004.safetensors",
|
| 336 |
-
"model.layers.35.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 337 |
-
"model.layers.35.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 338 |
-
"model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 339 |
-
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 340 |
-
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 341 |
-
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 342 |
-
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 343 |
-
"model.layers.4.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
| 344 |
-
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 345 |
-
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 346 |
-
"model.layers.4.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
| 347 |
-
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 348 |
-
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 349 |
-
"model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 350 |
-
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 351 |
-
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 352 |
-
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 353 |
-
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 354 |
-
"model.layers.5.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
| 355 |
-
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 356 |
-
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 357 |
-
"model.layers.5.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
| 358 |
-
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 359 |
-
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 360 |
-
"model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 361 |
-
"model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 362 |
-
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 363 |
-
"model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 364 |
-
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 365 |
-
"model.layers.6.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
| 366 |
-
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 367 |
-
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 368 |
-
"model.layers.6.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
| 369 |
-
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 370 |
-
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 371 |
-
"model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 372 |
-
"model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 373 |
-
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 374 |
-
"model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 375 |
-
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 376 |
-
"model.layers.7.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
| 377 |
-
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 378 |
-
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 379 |
-
"model.layers.7.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
| 380 |
-
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 381 |
-
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 382 |
-
"model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 383 |
-
"model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 384 |
-
"model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 385 |
-
"model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 386 |
-
"model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 387 |
-
"model.layers.8.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
| 388 |
-
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 389 |
-
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 390 |
-
"model.layers.8.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
| 391 |
-
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 392 |
-
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 393 |
-
"model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 394 |
-
"model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 395 |
-
"model.layers.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 396 |
-
"model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 397 |
-
"model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 398 |
-
"model.layers.9.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
| 399 |
-
"model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 400 |
-
"model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 401 |
-
"model.layers.9.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
| 402 |
-
"model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 403 |
-
"model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 404 |
-
"model.norm.weight": "model-00004-of-00004.safetensors"
|
| 405 |
}
|
| 406 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"metadata": {
|
| 3 |
+
"total_size": 13481025536
|
| 4 |
},
|
| 5 |
"weight_map": {
|
| 6 |
+
"lm_head.weight": "model-00003-of-00003.safetensors",
|
| 7 |
+
"model.embed_tokens.weight": "model-00001-of-00003.safetensors",
|
| 8 |
+
"model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 9 |
+
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 10 |
+
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 11 |
+
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 12 |
+
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 13 |
+
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 14 |
+
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 15 |
+
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 16 |
+
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 17 |
+
"model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 18 |
+
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 19 |
+
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 20 |
+
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 21 |
+
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 22 |
+
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 23 |
+
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 24 |
+
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 25 |
+
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 26 |
+
"model.layers.10.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 27 |
+
"model.layers.10.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 28 |
+
"model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 29 |
+
"model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 30 |
+
"model.layers.10.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 31 |
+
"model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 32 |
+
"model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 33 |
+
"model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 34 |
+
"model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 35 |
+
"model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 36 |
+
"model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 37 |
+
"model.layers.11.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 38 |
+
"model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 39 |
+
"model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 40 |
+
"model.layers.11.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 41 |
+
"model.layers.11.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 42 |
+
"model.layers.11.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 43 |
+
"model.layers.11.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 44 |
+
"model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 45 |
+
"model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 46 |
+
"model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 47 |
+
"model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 48 |
+
"model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 49 |
+
"model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 50 |
+
"model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 51 |
+
"model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 52 |
+
"model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 53 |
+
"model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 54 |
+
"model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 55 |
+
"model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 56 |
+
"model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 57 |
+
"model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 58 |
+
"model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 59 |
+
"model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 60 |
+
"model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 61 |
+
"model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 62 |
+
"model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 63 |
+
"model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 64 |
+
"model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 65 |
+
"model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 66 |
+
"model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 67 |
+
"model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 68 |
+
"model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 69 |
+
"model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 70 |
+
"model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 71 |
+
"model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 72 |
+
"model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 73 |
+
"model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 74 |
+
"model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 75 |
+
"model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 76 |
+
"model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 77 |
+
"model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 78 |
+
"model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 79 |
+
"model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 80 |
+
"model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 81 |
+
"model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 82 |
+
"model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 83 |
+
"model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 84 |
+
"model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 85 |
+
"model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 86 |
+
"model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 87 |
+
"model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 88 |
+
"model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 89 |
+
"model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 90 |
+
"model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 91 |
+
"model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 92 |
+
"model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 93 |
+
"model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 94 |
+
"model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 95 |
+
"model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 96 |
+
"model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 97 |
+
"model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 98 |
+
"model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 99 |
+
"model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 100 |
+
"model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 101 |
+
"model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 102 |
+
"model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 103 |
+
"model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 104 |
+
"model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 105 |
+
"model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 106 |
+
"model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 107 |
+
"model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 108 |
+
"model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 109 |
+
"model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 110 |
+
"model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 111 |
+
"model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 112 |
+
"model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 113 |
+
"model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 114 |
+
"model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 115 |
+
"model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 116 |
+
"model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 117 |
+
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 118 |
+
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 119 |
+
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 120 |
+
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 121 |
+
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 122 |
+
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 123 |
+
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 124 |
+
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 125 |
+
"model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 126 |
+
"model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 127 |
+
"model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 128 |
+
"model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 129 |
+
"model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 130 |
+
"model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 131 |
+
"model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 132 |
+
"model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 133 |
+
"model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 134 |
+
"model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 135 |
+
"model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 136 |
+
"model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 137 |
+
"model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 138 |
+
"model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 139 |
+
"model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 140 |
+
"model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 141 |
+
"model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 142 |
+
"model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 143 |
+
"model.layers.22.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 144 |
+
"model.layers.22.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 145 |
+
"model.layers.22.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 146 |
+
"model.layers.22.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 147 |
+
"model.layers.22.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 148 |
+
"model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 149 |
+
"model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 150 |
+
"model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 151 |
+
"model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 152 |
+
"model.layers.23.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 153 |
+
"model.layers.23.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
| 154 |
+
"model.layers.23.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 155 |
+
"model.layers.23.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 156 |
+
"model.layers.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 157 |
+
"model.layers.23.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 158 |
+
"model.layers.23.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 159 |
+
"model.layers.23.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 160 |
+
"model.layers.23.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 161 |
+
"model.layers.24.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 162 |
+
"model.layers.24.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
| 163 |
+
"model.layers.24.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
| 164 |
+
"model.layers.24.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
| 165 |
+
"model.layers.24.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 166 |
+
"model.layers.24.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 167 |
+
"model.layers.24.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
| 168 |
+
"model.layers.24.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 169 |
+
"model.layers.24.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 170 |
+
"model.layers.25.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 171 |
+
"model.layers.25.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
| 172 |
+
"model.layers.25.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
| 173 |
+
"model.layers.25.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
| 174 |
+
"model.layers.25.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 175 |
+
"model.layers.25.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 176 |
+
"model.layers.25.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
| 177 |
+
"model.layers.25.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 178 |
+
"model.layers.25.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 179 |
+
"model.layers.26.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 180 |
+
"model.layers.26.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
| 181 |
+
"model.layers.26.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
| 182 |
+
"model.layers.26.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
| 183 |
+
"model.layers.26.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 184 |
+
"model.layers.26.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 185 |
+
"model.layers.26.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
| 186 |
+
"model.layers.26.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 187 |
+
"model.layers.26.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 188 |
+
"model.layers.27.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 189 |
+
"model.layers.27.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
| 190 |
+
"model.layers.27.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
| 191 |
+
"model.layers.27.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
| 192 |
+
"model.layers.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 193 |
+
"model.layers.27.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 194 |
+
"model.layers.27.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
| 195 |
+
"model.layers.27.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 196 |
+
"model.layers.27.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 197 |
+
"model.layers.28.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 198 |
+
"model.layers.28.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
| 199 |
+
"model.layers.28.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
| 200 |
+
"model.layers.28.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
| 201 |
+
"model.layers.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 202 |
+
"model.layers.28.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 203 |
+
"model.layers.28.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
| 204 |
+
"model.layers.28.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 205 |
+
"model.layers.28.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 206 |
+
"model.layers.29.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 207 |
+
"model.layers.29.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
| 208 |
+
"model.layers.29.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
| 209 |
+
"model.layers.29.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
| 210 |
+
"model.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 211 |
+
"model.layers.29.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 212 |
+
"model.layers.29.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
| 213 |
+
"model.layers.29.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 214 |
+
"model.layers.29.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 215 |
+
"model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 216 |
+
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 217 |
+
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 218 |
+
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 219 |
+
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 220 |
+
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 221 |
+
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 222 |
+
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 223 |
+
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 224 |
+
"model.layers.30.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 225 |
+
"model.layers.30.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
| 226 |
+
"model.layers.30.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
| 227 |
+
"model.layers.30.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
| 228 |
+
"model.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 229 |
+
"model.layers.30.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 230 |
+
"model.layers.30.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
| 231 |
+
"model.layers.30.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 232 |
+
"model.layers.30.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 233 |
+
"model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 234 |
+
"model.layers.31.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
| 235 |
+
"model.layers.31.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
| 236 |
+
"model.layers.31.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
| 237 |
+
"model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 238 |
+
"model.layers.31.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 239 |
+
"model.layers.31.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
| 240 |
+
"model.layers.31.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 241 |
+
"model.layers.31.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 242 |
+
"model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 243 |
+
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 244 |
+
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 245 |
+
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 246 |
+
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 247 |
+
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 248 |
+
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 249 |
+
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 250 |
+
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 251 |
+
"model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 252 |
+
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 253 |
+
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 254 |
+
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 255 |
+
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 256 |
+
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 257 |
+
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 258 |
+
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 259 |
+
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 260 |
+
"model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 261 |
+
"model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 262 |
+
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 263 |
+
"model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 264 |
+
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 265 |
+
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 266 |
+
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 267 |
+
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 268 |
+
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 269 |
+
"model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 270 |
+
"model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 271 |
+
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 272 |
+
"model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 273 |
+
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 274 |
+
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 275 |
+
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 276 |
+
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 277 |
+
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 278 |
+
"model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 279 |
+
"model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 280 |
+
"model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 281 |
+
"model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 282 |
+
"model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 283 |
+
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 284 |
+
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 285 |
+
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 286 |
+
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 287 |
+
"model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 288 |
+
"model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 289 |
+
"model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 290 |
+
"model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 291 |
+
"model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 292 |
+
"model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 293 |
+
"model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 294 |
+
"model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 295 |
+
"model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 296 |
+
"model.norm.weight": "model-00003-of-00003.safetensors"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 297 |
}
|
| 298 |
}
|
special_tokens_map.json
CHANGED
|
@@ -1,30 +1,22 @@
|
|
| 1 |
{
|
| 2 |
-
"
|
| 3 |
-
"
|
| 4 |
-
"
|
| 5 |
-
"
|
| 6 |
-
"
|
| 7 |
-
"
|
| 8 |
-
|
| 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": "
|
| 19 |
"lstrip": false,
|
| 20 |
-
"normalized":
|
| 21 |
"rstrip": false,
|
| 22 |
"single_word": false
|
| 23 |
},
|
| 24 |
"pad_token": {
|
| 25 |
-
"content": "
|
| 26 |
"lstrip": false,
|
| 27 |
-
"normalized":
|
| 28 |
"rstrip": false,
|
| 29 |
"single_word": false
|
| 30 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<｜begin▁of▁sentence｜>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": true,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 9 |
"eos_token": {
|
| 10 |
+
"content": "<｜end▁of▁sentence｜>",
|
| 11 |
"lstrip": false,
|
| 12 |
+
"normalized": true,
|
| 13 |
"rstrip": false,
|
| 14 |
"single_word": false
|
| 15 |
},
|
| 16 |
"pad_token": {
|
| 17 |
+
"content": "<｜end▁of▁sentence｜>",
|
| 18 |
"lstrip": false,
|
| 19 |
+
"normalized": true,
|
| 20 |
"rstrip": false,
|
| 21 |
"single_word": false
|
| 22 |
}
|
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 sha256:4b5dd76abf0eaa4908573b3d78ec0594df007e2db110c8b873539d8f7b77b0e5
|
| 3 |
+
size 2289991
|
tokenizer_config.json
CHANGED
|
@@ -1,239 +1,194 @@
|
|
| 1 |
{
|
| 2 |
-
"add_bos_token":
|
| 3 |
-
"
|
|
|
|
| 4 |
"added_tokens_decoder": {
|
| 5 |
-
"
|
| 6 |
-
"content": "
|
| 7 |
"lstrip": false,
|
| 8 |
-
"normalized":
|
| 9 |
"rstrip": false,
|
| 10 |
"single_word": false,
|
| 11 |
-
"special":
|
| 12 |
-
},
|
| 13 |
-
"151644": {
|
| 14 |
-
"content": "<|im_start|>",
|
| 15 |
-
"lstrip": false,
|
| 16 |
-
"normalized": false,
|
| 17 |
-
"rstrip": false,
|
| 18 |
-
"single_word": false,
|
| 19 |
-
"special": true
|
| 20 |
-
},
|
| 21 |
-
"151645": {
|
| 22 |
-
"content": "<|im_end|>",
|
| 23 |
-
"lstrip": false,
|
| 24 |
-
"normalized": false,
|
| 25 |
-
"rstrip": false,
|
| 26 |
-
"single_word": false,
|
| 27 |
-
"special": true
|
| 28 |
-
},
|
| 29 |
-
"151646": {
|
| 30 |
-
"content": "<|object_ref_start|>",
|
| 31 |
-
"lstrip": false,
|
| 32 |
-
"normalized": false,
|
| 33 |
-
"rstrip": false,
|
| 34 |
-
"single_word": false,
|
| 35 |
-
"special": true
|
| 36 |
-
},
|
| 37 |
-
"151647": {
|
| 38 |
-
"content": "<|object_ref_end|>",
|
| 39 |
-
"lstrip": false,
|
| 40 |
-
"normalized": false,
|
| 41 |
-
"rstrip": false,
|
| 42 |
-
"single_word": false,
|
| 43 |
-
"special": true
|
| 44 |
},
|
| 45 |
-
"
|
| 46 |
-
"content": "
|
| 47 |
"lstrip": false,
|
| 48 |
-
"normalized":
|
| 49 |
"rstrip": false,
|
| 50 |
"single_word": false,
|
| 51 |
-
"special":
|
| 52 |
},
|
| 53 |
-
"
|
| 54 |
-
"content": "
|
| 55 |
"lstrip": false,
|
| 56 |
-
"normalized":
|
| 57 |
"rstrip": false,
|
| 58 |
"single_word": false,
|
| 59 |
-
"special":
|
| 60 |
},
|
| 61 |
-
"
|
| 62 |
-
"content": "
|
| 63 |
"lstrip": false,
|
| 64 |
-
"normalized":
|
| 65 |
"rstrip": false,
|
| 66 |
"single_word": false,
|
| 67 |
-
"special":
|
| 68 |
},
|
| 69 |
-
"
|
| 70 |
-
"content": "
|
| 71 |
"lstrip": false,
|
| 72 |
-
"normalized":
|
| 73 |
"rstrip": false,
|
| 74 |
"single_word": false,
|
| 75 |
-
"special":
|
| 76 |
},
|
| 77 |
-
"
|
| 78 |
-
"content": "
|
| 79 |
"lstrip": false,
|
| 80 |
-
"normalized":
|
| 81 |
"rstrip": false,
|
| 82 |
"single_word": false,
|
| 83 |
-
"special":
|
| 84 |
},
|
| 85 |
-
"
|
| 86 |
-
"content": "
|
| 87 |
"lstrip": false,
|
| 88 |
-
"normalized":
|
| 89 |
"rstrip": false,
|
| 90 |
"single_word": false,
|
| 91 |
-
"special":
|
| 92 |
},
|
| 93 |
-
"
|
| 94 |
-
"content": "
|
| 95 |
"lstrip": false,
|
| 96 |
-
"normalized":
|
| 97 |
"rstrip": false,
|
| 98 |
"single_word": false,
|
| 99 |
-
"special":
|
| 100 |
},
|
| 101 |
-
"
|
| 102 |
-
"content": "
|
| 103 |
"lstrip": false,
|
| 104 |
-
"normalized":
|
| 105 |
"rstrip": false,
|
| 106 |
"single_word": false,
|
| 107 |
-
"special":
|
| 108 |
},
|
| 109 |
-
"
|
| 110 |
-
"content": "
|
| 111 |
"lstrip": false,
|
| 112 |
-
"normalized":
|
| 113 |
"rstrip": false,
|
| 114 |
"single_word": false,
|
| 115 |
-
"special":
|
| 116 |
},
|
| 117 |
-
"
|
| 118 |
-
"content": "
|
| 119 |
"lstrip": false,
|
| 120 |
-
"normalized":
|
| 121 |
"rstrip": false,
|
| 122 |
"single_word": false,
|
| 123 |
"special": false
|
| 124 |
},
|
| 125 |
-
"
|
| 126 |
-
"content": "
|
| 127 |
"lstrip": false,
|
| 128 |
-
"normalized":
|
| 129 |
"rstrip": false,
|
| 130 |
"single_word": false,
|
| 131 |
"special": false
|
| 132 |
},
|
| 133 |
-
"
|
| 134 |
-
"content": "
|
| 135 |
"lstrip": false,
|
| 136 |
-
"normalized":
|
| 137 |
"rstrip": false,
|
| 138 |
"single_word": false,
|
| 139 |
"special": false
|
| 140 |
},
|
| 141 |
-
"
|
| 142 |
-
"content": "
|
| 143 |
"lstrip": false,
|
| 144 |
-
"normalized":
|
| 145 |
"rstrip": false,
|
| 146 |
"single_word": false,
|
| 147 |
-
"special":
|
| 148 |
},
|
| 149 |
-
"
|
| 150 |
-
"content": "
|
| 151 |
"lstrip": false,
|
| 152 |
-
"normalized":
|
| 153 |
"rstrip": false,
|
| 154 |
"single_word": false,
|
| 155 |
-
"special":
|
| 156 |
},
|
| 157 |
-
"
|
| 158 |
-
"content": "
|
| 159 |
"lstrip": false,
|
| 160 |
-
"normalized":
|
| 161 |
"rstrip": false,
|
| 162 |
"single_word": false,
|
| 163 |
"special": false
|
| 164 |
},
|
| 165 |
-
"
|
| 166 |
-
"content": "
|
| 167 |
"lstrip": false,
|
| 168 |
-
"normalized":
|
| 169 |
"rstrip": false,
|
| 170 |
"single_word": false,
|
| 171 |
"special": false
|
| 172 |
},
|
| 173 |
-
"
|
| 174 |
-
"content": "
|
| 175 |
"lstrip": false,
|
| 176 |
-
"normalized":
|
| 177 |
"rstrip": false,
|
| 178 |
"single_word": false,
|
| 179 |
"special": false
|
| 180 |
},
|
| 181 |
-
"
|
| 182 |
-
"content": "<
|
| 183 |
"lstrip": false,
|
| 184 |
-
"normalized":
|
| 185 |
"rstrip": false,
|
| 186 |
"single_word": false,
|
| 187 |
"special": false
|
| 188 |
},
|
| 189 |
-
"
|
| 190 |
-
"content": "
|
| 191 |
"lstrip": false,
|
| 192 |
-
"normalized":
|
| 193 |
"rstrip": false,
|
| 194 |
"single_word": false,
|
| 195 |
"special": false
|
| 196 |
},
|
| 197 |
-
"
|
| 198 |
-
"content": "
|
| 199 |
"lstrip": false,
|
| 200 |
-
"normalized":
|
| 201 |
"rstrip": false,
|
| 202 |
"single_word": false,
|
| 203 |
"special": false
|
| 204 |
},
|
| 205 |
-
"
|
| 206 |
-
"content": "
|
| 207 |
"lstrip": false,
|
| 208 |
-
"normalized":
|
| 209 |
"rstrip": false,
|
| 210 |
"single_word": false,
|
| 211 |
"special": false
|
| 212 |
}
|
| 213 |
},
|
| 214 |
-
"
|
| 215 |
-
"<|im_start|>",
|
| 216 |
-
"<|im_end|>",
|
| 217 |
-
"<|object_ref_start|>",
|
| 218 |
-
"<|object_ref_end|>",
|
| 219 |
-
"<|box_start|>",
|
| 220 |
-
"<|box_end|>",
|
| 221 |
-
"<|quad_start|>",
|
| 222 |
-
"<|quad_end|>",
|
| 223 |
-
"<|vision_start|>",
|
| 224 |
-
"<|vision_end|>",
|
| 225 |
-
"<|vision_pad|>",
|
| 226 |
-
"<|image_pad|>",
|
| 227 |
-
"<|video_pad|>"
|
| 228 |
-
],
|
| 229 |
-
"bos_token": null,
|
| 230 |
"clean_up_tokenization_spaces": false,
|
| 231 |
-
"eos_token": "
|
| 232 |
-
"errors": "replace",
|
| 233 |
"extra_special_tokens": {},
|
| 234 |
-
"
|
| 235 |
-
"
|
| 236 |
-
"
|
| 237 |
-
"
|
| 238 |
-
"
|
|
|
|
|
|
|
| 239 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"add_prefix_space": null,
|
| 5 |
"added_tokens_decoder": {
|
| 6 |
+
"32000": {
|
| 7 |
+
"content": "õ",
|
| 8 |
"lstrip": false,
|
| 9 |
+
"normalized": true,
|
| 10 |
"rstrip": false,
|
| 11 |
"single_word": false,
|
| 12 |
+
"special": false
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 13 |
},
|
| 14 |
+
"32001": {
|
| 15 |
+
"content": "÷",
|
| 16 |
"lstrip": false,
|
| 17 |
+
"normalized": true,
|
| 18 |
"rstrip": false,
|
| 19 |
"single_word": false,
|
| 20 |
+
"special": false
|
| 21 |
},
|
| 22 |
+
"32002": {
|
| 23 |
+
"content": "Á",
|
| 24 |
"lstrip": false,
|
| 25 |
+
"normalized": true,
|
| 26 |
"rstrip": false,
|
| 27 |
"single_word": false,
|
| 28 |
+
"special": false
|
| 29 |
},
|
| 30 |
+
"32003": {
|
| 31 |
+
"content": "ý",
|
| 32 |
"lstrip": false,
|
| 33 |
+
"normalized": true,
|
| 34 |
"rstrip": false,
|
| 35 |
"single_word": false,
|
| 36 |
+
"special": false
|
| 37 |
},
|
| 38 |
+
"32004": {
|
| 39 |
+
"content": "À",
|
| 40 |
"lstrip": false,
|
| 41 |
+
"normalized": true,
|
| 42 |
"rstrip": false,
|
| 43 |
"single_word": false,
|
| 44 |
+
"special": false
|
| 45 |
},
|
| 46 |
+
"32005": {
|
| 47 |
+
"content": "ÿ",
|
| 48 |
"lstrip": false,
|
| 49 |
+
"normalized": true,
|
| 50 |
"rstrip": false,
|
| 51 |
"single_word": false,
|
| 52 |
+
"special": false
|
| 53 |
},
|
| 54 |
+
"32006": {
|
| 55 |
+
"content": "ø",
|
| 56 |
"lstrip": false,
|
| 57 |
+
"normalized": true,
|
| 58 |
"rstrip": false,
|
| 59 |
"single_word": false,
|
| 60 |
+
"special": false
|
| 61 |
},
|
| 62 |
+
"32007": {
|
| 63 |
+
"content": "ú",
|
| 64 |
"lstrip": false,
|
| 65 |
+
"normalized": true,
|
| 66 |
"rstrip": false,
|
| 67 |
"single_word": false,
|
| 68 |
+
"special": false
|
| 69 |
},
|
| 70 |
+
"32008": {
|
| 71 |
+
"content": "þ",
|
| 72 |
"lstrip": false,
|
| 73 |
+
"normalized": true,
|
| 74 |
"rstrip": false,
|
| 75 |
"single_word": false,
|
| 76 |
+
"special": false
|
| 77 |
},
|
| 78 |
+
"32009": {
|
| 79 |
+
"content": "ü",
|
| 80 |
"lstrip": false,
|
| 81 |
+
"normalized": true,
|
| 82 |
"rstrip": false,
|
| 83 |
"single_word": false,
|
| 84 |
+
"special": false
|
| 85 |
},
|
| 86 |
+
"32010": {
|
| 87 |
+
"content": "ù",
|
| 88 |
"lstrip": false,
|
| 89 |
+
"normalized": true,
|
| 90 |
"rstrip": false,
|
| 91 |
"single_word": false,
|
| 92 |
"special": false
|
| 93 |
},
|
| 94 |
+
"32011": {
|
| 95 |
+
"content": "ö",
|
| 96 |
"lstrip": false,
|
| 97 |
+
"normalized": true,
|
| 98 |
"rstrip": false,
|
| 99 |
"single_word": false,
|
| 100 |
"special": false
|
| 101 |
},
|
| 102 |
+
"32012": {
|
| 103 |
+
"content": "û",
|
| 104 |
"lstrip": false,
|
| 105 |
+
"normalized": true,
|
| 106 |
"rstrip": false,
|
| 107 |
"single_word": false,
|
| 108 |
"special": false
|
| 109 |
},
|
| 110 |
+
"32013": {
|
| 111 |
+
"content": "<｜begin▁of▁sentence｜>",
|
| 112 |
"lstrip": false,
|
| 113 |
+
"normalized": true,
|
| 114 |
"rstrip": false,
|
| 115 |
"single_word": false,
|
| 116 |
+
"special": true
|
| 117 |
},
|
| 118 |
+
"32014": {
|
| 119 |
+
"content": "<｜end▁of▁sentence｜>",
|
| 120 |
"lstrip": false,
|
| 121 |
+
"normalized": true,
|
| 122 |
"rstrip": false,
|
| 123 |
"single_word": false,
|
| 124 |
+
"special": true
|
| 125 |
},
|
| 126 |
+
"32015": {
|
| 127 |
+
"content": "<｜fim▁hole｜>",
|
| 128 |
"lstrip": false,
|
| 129 |
+
"normalized": true,
|
| 130 |
"rstrip": false,
|
| 131 |
"single_word": false,
|
| 132 |
"special": false
|
| 133 |
},
|
| 134 |
+
"32016": {
|
| 135 |
+
"content": "<｜fim▁begin｜>",
|
| 136 |
"lstrip": false,
|
| 137 |
+
"normalized": true,
|
| 138 |
"rstrip": false,
|
| 139 |
"single_word": false,
|
| 140 |
"special": false
|
| 141 |
},
|
| 142 |
+
"32017": {
|
| 143 |
+
"content": "<｜fim▁end｜>",
|
| 144 |
"lstrip": false,
|
| 145 |
+
"normalized": true,
|
| 146 |
"rstrip": false,
|
| 147 |
"single_word": false,
|
| 148 |
"special": false
|
| 149 |
},
|
| 150 |
+
"32018": {
|
| 151 |
+
"content": "<pad>",
|
| 152 |
"lstrip": false,
|
| 153 |
+
"normalized": true,
|
| 154 |
"rstrip": false,
|
| 155 |
"single_word": false,
|
| 156 |
"special": false
|
| 157 |
},
|
| 158 |
+
"32019": {
|
| 159 |
+
"content": "<|User|>",
|
| 160 |
"lstrip": false,
|
| 161 |
+
"normalized": true,
|
| 162 |
"rstrip": false,
|
| 163 |
"single_word": false,
|
| 164 |
"special": false
|
| 165 |
},
|
| 166 |
+
"32020": {
|
| 167 |
+
"content": "<|Assistant|>",
|
| 168 |
"lstrip": false,
|
| 169 |
+
"normalized": true,
|
| 170 |
"rstrip": false,
|
| 171 |
"single_word": false,
|
| 172 |
"special": false
|
| 173 |
},
|
| 174 |
+
"32021": {
|
| 175 |
+
"content": "<|EOT|>",
|
| 176 |
"lstrip": false,
|
| 177 |
+
"normalized": true,
|
| 178 |
"rstrip": false,
|
| 179 |
"single_word": false,
|
| 180 |
"special": false
|
| 181 |
}
|
| 182 |
},
|
| 183 |
+
"bos_token": "<｜begin▁of▁sentence｜>",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 184 |
"clean_up_tokenization_spaces": false,
|
| 185 |
+
"eos_token": "<｜end▁of▁sentence｜>",
|
|
|
|
| 186 |
"extra_special_tokens": {},
|
| 187 |
+
"legacy": true,
|
| 188 |
+
"model_max_length": 16384,
|
| 189 |
+
"pad_token": "<｜end▁of▁sentence｜>",
|
| 190 |
+
"sp_model_kwargs": {},
|
| 191 |
+
"tokenizer_class": "LlamaTokenizerFast",
|
| 192 |
+
"unk_token": null,
|
| 193 |
+
"use_default_system_prompt": false
|
| 194 |
}
|
training_args.bin
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:f337615735392684cbb3c767957ab62e301966bae77289f9574aceb61c2464a7
|
| 3 |
+
size 10104
|