Upload RegTech-32B-Instruct
Browse files- .gitattributes +1 -0
- added_tokens.json +24 -0
- chat_template.jinja +54 -0
- config.json +94 -0
- generation_config.json +14 -0
- merges.txt +0 -0
- model-00001-of-00014.safetensors +3 -0
- model-00002-of-00014.safetensors +3 -0
- model-00003-of-00014.safetensors +3 -0
- model-00004-of-00014.safetensors +3 -0
- model-00005-of-00014.safetensors +3 -0
- model-00006-of-00014.safetensors +3 -0
- model-00007-of-00014.safetensors +3 -0
- model-00008-of-00014.safetensors +3 -0
- model-00009-of-00014.safetensors +3 -0
- model-00010-of-00014.safetensors +3 -0
- model-00011-of-00014.safetensors +3 -0
- model-00012-of-00014.safetensors +3 -0
- model-00013-of-00014.safetensors +3 -0
- model-00014-of-00014.safetensors +3 -0
- model.safetensors.index.json +779 -0
- special_tokens_map.json +31 -0
- tokenizer.json +3 -0
- tokenizer_config.json +207 -0
- training_report.json +661 -0
- vocab.json +0 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
added_tokens.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
}
|
chat_template.jinja
ADDED
|
@@ -0,0 +1,54 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{%- if tools %}
|
| 2 |
+
{{- '<|im_start|>system\n' }}
|
| 3 |
+
{%- if messages[0]['role'] == 'system' %}
|
| 4 |
+
{{- messages[0]['content'] }}
|
| 5 |
+
{%- else %}
|
| 6 |
+
{{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
|
| 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 %}
|
config.json
ADDED
|
@@ -0,0 +1,94 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Qwen2ForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_dropout": 0.0,
|
| 6 |
+
"bos_token_id": 151643,
|
| 7 |
+
"dtype": "bfloat16",
|
| 8 |
+
"eos_token_id": 151645,
|
| 9 |
+
"hidden_act": "silu",
|
| 10 |
+
"hidden_size": 5120,
|
| 11 |
+
"initializer_range": 0.02,
|
| 12 |
+
"intermediate_size": 27648,
|
| 13 |
+
"layer_types": [
|
| 14 |
+
"full_attention",
|
| 15 |
+
"full_attention",
|
| 16 |
+
"full_attention",
|
| 17 |
+
"full_attention",
|
| 18 |
+
"full_attention",
|
| 19 |
+
"full_attention",
|
| 20 |
+
"full_attention",
|
| 21 |
+
"full_attention",
|
| 22 |
+
"full_attention",
|
| 23 |
+
"full_attention",
|
| 24 |
+
"full_attention",
|
| 25 |
+
"full_attention",
|
| 26 |
+
"full_attention",
|
| 27 |
+
"full_attention",
|
| 28 |
+
"full_attention",
|
| 29 |
+
"full_attention",
|
| 30 |
+
"full_attention",
|
| 31 |
+
"full_attention",
|
| 32 |
+
"full_attention",
|
| 33 |
+
"full_attention",
|
| 34 |
+
"full_attention",
|
| 35 |
+
"full_attention",
|
| 36 |
+
"full_attention",
|
| 37 |
+
"full_attention",
|
| 38 |
+
"full_attention",
|
| 39 |
+
"full_attention",
|
| 40 |
+
"full_attention",
|
| 41 |
+
"full_attention",
|
| 42 |
+
"full_attention",
|
| 43 |
+
"full_attention",
|
| 44 |
+
"full_attention",
|
| 45 |
+
"full_attention",
|
| 46 |
+
"full_attention",
|
| 47 |
+
"full_attention",
|
| 48 |
+
"full_attention",
|
| 49 |
+
"full_attention",
|
| 50 |
+
"full_attention",
|
| 51 |
+
"full_attention",
|
| 52 |
+
"full_attention",
|
| 53 |
+
"full_attention",
|
| 54 |
+
"full_attention",
|
| 55 |
+
"full_attention",
|
| 56 |
+
"full_attention",
|
| 57 |
+
"full_attention",
|
| 58 |
+
"full_attention",
|
| 59 |
+
"full_attention",
|
| 60 |
+
"full_attention",
|
| 61 |
+
"full_attention",
|
| 62 |
+
"full_attention",
|
| 63 |
+
"full_attention",
|
| 64 |
+
"full_attention",
|
| 65 |
+
"full_attention",
|
| 66 |
+
"full_attention",
|
| 67 |
+
"full_attention",
|
| 68 |
+
"full_attention",
|
| 69 |
+
"full_attention",
|
| 70 |
+
"full_attention",
|
| 71 |
+
"full_attention",
|
| 72 |
+
"full_attention",
|
| 73 |
+
"full_attention",
|
| 74 |
+
"full_attention",
|
| 75 |
+
"full_attention",
|
| 76 |
+
"full_attention",
|
| 77 |
+
"full_attention"
|
| 78 |
+
],
|
| 79 |
+
"max_position_embeddings": 32768,
|
| 80 |
+
"max_window_layers": 70,
|
| 81 |
+
"model_type": "qwen2",
|
| 82 |
+
"num_attention_heads": 40,
|
| 83 |
+
"num_hidden_layers": 64,
|
| 84 |
+
"num_key_value_heads": 8,
|
| 85 |
+
"rms_norm_eps": 1e-06,
|
| 86 |
+
"rope_scaling": null,
|
| 87 |
+
"rope_theta": 1000000.0,
|
| 88 |
+
"sliding_window": null,
|
| 89 |
+
"tie_word_embeddings": false,
|
| 90 |
+
"transformers_version": "4.57.3",
|
| 91 |
+
"use_cache": true,
|
| 92 |
+
"use_sliding_window": false,
|
| 93 |
+
"vocab_size": 152064
|
| 94 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 151643,
|
| 3 |
+
"do_sample": true,
|
| 4 |
+
"eos_token_id": [
|
| 5 |
+
151645,
|
| 6 |
+
151643
|
| 7 |
+
],
|
| 8 |
+
"pad_token_id": 151643,
|
| 9 |
+
"repetition_penalty": 1.05,
|
| 10 |
+
"temperature": 0.7,
|
| 11 |
+
"top_k": 20,
|
| 12 |
+
"top_p": 0.8,
|
| 13 |
+
"transformers_version": "4.57.3"
|
| 14 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
model-00001-of-00014.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:672d4e0856b3c59ca1ccee5e40388c5f94b18ce8f156e246af5e6075a9ad1165
|
| 3 |
+
size 4891730992
|
model-00002-of-00014.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b3937ce227317bc348a8bf3830462fffb7bd208995d72b7afb7e5fd2d727231c
|
| 3 |
+
size 4876059352
|
model-00003-of-00014.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e9845cd0ab8033da4b06a90def811d0788da233ba2e9e58656e6739e8d65ea00
|
| 3 |
+
size 4876059384
|
model-00004-of-00014.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:032ff3e7cdc8ad51e69758cb144d91024a262d15b16fdb29253c56e11f208279
|
| 3 |
+
size 4876059416
|
model-00005-of-00014.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:79fa75d0adc7cfa576aa9d80203158e3b5d52ef6ed4638cb82dc6181434cbb33
|
| 3 |
+
size 4876059416
|
model-00006-of-00014.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e82eee13d0ab0349bb4d77d49cd57acc15e18c515016a01471ce621478d51241
|
| 3 |
+
size 4876059416
|
model-00007-of-00014.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f8b737489b6eef459122dec9c9547496e6d11343de27c208ccd5cd3d103a70d3
|
| 3 |
+
size 4876059416
|
model-00008-of-00014.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4c75a17f65b2d74753c40a2b1f2129a6a8ab0a7b7595d3d22e841ea011d5f37d
|
| 3 |
+
size 4876059416
|
model-00009-of-00014.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:522d24a8a1224e10da0574c70f00b10765e71e4338fa6b70e5efb2e9d8a62702
|
| 3 |
+
size 4876059416
|
model-00010-of-00014.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:598c40086c6b5d8ad88746d190c876a5788410b42e6bfcf8b3532a950749ddf3
|
| 3 |
+
size 4876059416
|
model-00011-of-00014.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ca0310d57c47b9c5e6a8a7e9d6de99f033e24d63471bce2b4788ddadf6cfa230
|
| 3 |
+
size 4876059416
|
model-00012-of-00014.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b5ea59ab9897864d68975ddc5a78d57a13550a7a48e11f8cf6c6d4cedc10f9b0
|
| 3 |
+
size 4876059416
|
model-00013-of-00014.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e3dac52ec3aa4213ecedba02104aebcf1e6bed1700ad8c9d382e8e681dffc02f
|
| 3 |
+
size 4876059416
|
model-00014-of-00014.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7303c78552379c19725ef06ad5b1d460c406749b261f6c5bc4a47cd8607149fa
|
| 3 |
+
size 2123397800
|
model.safetensors.index.json
ADDED
|
@@ -0,0 +1,779 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_parameters": 32763876352,
|
| 4 |
+
"total_size": 65527752704
|
| 5 |
+
},
|
| 6 |
+
"weight_map": {
|
| 7 |
+
"lm_head.weight": "model-00014-of-00014.safetensors",
|
| 8 |
+
"model.embed_tokens.weight": "model-00001-of-00014.safetensors",
|
| 9 |
+
"model.layers.0.input_layernorm.weight": "model-00001-of-00014.safetensors",
|
| 10 |
+
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
|
| 11 |
+
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
|
| 12 |
+
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
|
| 13 |
+
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00014.safetensors",
|
| 14 |
+
"model.layers.0.self_attn.k_proj.bias": "model-00001-of-00014.safetensors",
|
| 15 |
+
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00014.safetensors",
|
| 16 |
+
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00014.safetensors",
|
| 17 |
+
"model.layers.0.self_attn.q_proj.bias": "model-00001-of-00014.safetensors",
|
| 18 |
+
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00014.safetensors",
|
| 19 |
+
"model.layers.0.self_attn.v_proj.bias": "model-00001-of-00014.safetensors",
|
| 20 |
+
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00014.safetensors",
|
| 21 |
+
"model.layers.1.input_layernorm.weight": "model-00001-of-00014.safetensors",
|
| 22 |
+
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
|
| 23 |
+
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
|
| 24 |
+
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
|
| 25 |
+
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00014.safetensors",
|
| 26 |
+
"model.layers.1.self_attn.k_proj.bias": "model-00001-of-00014.safetensors",
|
| 27 |
+
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00014.safetensors",
|
| 28 |
+
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00014.safetensors",
|
| 29 |
+
"model.layers.1.self_attn.q_proj.bias": "model-00001-of-00014.safetensors",
|
| 30 |
+
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00014.safetensors",
|
| 31 |
+
"model.layers.1.self_attn.v_proj.bias": "model-00001-of-00014.safetensors",
|
| 32 |
+
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00014.safetensors",
|
| 33 |
+
"model.layers.10.input_layernorm.weight": "model-00003-of-00014.safetensors",
|
| 34 |
+
"model.layers.10.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
|
| 35 |
+
"model.layers.10.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
|
| 36 |
+
"model.layers.10.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
|
| 37 |
+
"model.layers.10.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
|
| 38 |
+
"model.layers.10.self_attn.k_proj.bias": "model-00003-of-00014.safetensors",
|
| 39 |
+
"model.layers.10.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
|
| 40 |
+
"model.layers.10.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
|
| 41 |
+
"model.layers.10.self_attn.q_proj.bias": "model-00003-of-00014.safetensors",
|
| 42 |
+
"model.layers.10.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
|
| 43 |
+
"model.layers.10.self_attn.v_proj.bias": "model-00003-of-00014.safetensors",
|
| 44 |
+
"model.layers.10.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
|
| 45 |
+
"model.layers.11.input_layernorm.weight": "model-00003-of-00014.safetensors",
|
| 46 |
+
"model.layers.11.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
|
| 47 |
+
"model.layers.11.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
|
| 48 |
+
"model.layers.11.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
|
| 49 |
+
"model.layers.11.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
|
| 50 |
+
"model.layers.11.self_attn.k_proj.bias": "model-00003-of-00014.safetensors",
|
| 51 |
+
"model.layers.11.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
|
| 52 |
+
"model.layers.11.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
|
| 53 |
+
"model.layers.11.self_attn.q_proj.bias": "model-00003-of-00014.safetensors",
|
| 54 |
+
"model.layers.11.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
|
| 55 |
+
"model.layers.11.self_attn.v_proj.bias": "model-00003-of-00014.safetensors",
|
| 56 |
+
"model.layers.11.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
|
| 57 |
+
"model.layers.12.input_layernorm.weight": "model-00003-of-00014.safetensors",
|
| 58 |
+
"model.layers.12.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
|
| 59 |
+
"model.layers.12.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
|
| 60 |
+
"model.layers.12.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
|
| 61 |
+
"model.layers.12.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
|
| 62 |
+
"model.layers.12.self_attn.k_proj.bias": "model-00003-of-00014.safetensors",
|
| 63 |
+
"model.layers.12.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
|
| 64 |
+
"model.layers.12.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
|
| 65 |
+
"model.layers.12.self_attn.q_proj.bias": "model-00003-of-00014.safetensors",
|
| 66 |
+
"model.layers.12.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
|
| 67 |
+
"model.layers.12.self_attn.v_proj.bias": "model-00003-of-00014.safetensors",
|
| 68 |
+
"model.layers.12.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
|
| 69 |
+
"model.layers.13.input_layernorm.weight": "model-00004-of-00014.safetensors",
|
| 70 |
+
"model.layers.13.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
|
| 71 |
+
"model.layers.13.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
|
| 72 |
+
"model.layers.13.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
|
| 73 |
+
"model.layers.13.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
|
| 74 |
+
"model.layers.13.self_attn.k_proj.bias": "model-00003-of-00014.safetensors",
|
| 75 |
+
"model.layers.13.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
|
| 76 |
+
"model.layers.13.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
|
| 77 |
+
"model.layers.13.self_attn.q_proj.bias": "model-00003-of-00014.safetensors",
|
| 78 |
+
"model.layers.13.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
|
| 79 |
+
"model.layers.13.self_attn.v_proj.bias": "model-00003-of-00014.safetensors",
|
| 80 |
+
"model.layers.13.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
|
| 81 |
+
"model.layers.14.input_layernorm.weight": "model-00004-of-00014.safetensors",
|
| 82 |
+
"model.layers.14.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
|
| 83 |
+
"model.layers.14.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
|
| 84 |
+
"model.layers.14.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
|
| 85 |
+
"model.layers.14.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
|
| 86 |
+
"model.layers.14.self_attn.k_proj.bias": "model-00004-of-00014.safetensors",
|
| 87 |
+
"model.layers.14.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
|
| 88 |
+
"model.layers.14.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
|
| 89 |
+
"model.layers.14.self_attn.q_proj.bias": "model-00004-of-00014.safetensors",
|
| 90 |
+
"model.layers.14.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
|
| 91 |
+
"model.layers.14.self_attn.v_proj.bias": "model-00004-of-00014.safetensors",
|
| 92 |
+
"model.layers.14.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
|
| 93 |
+
"model.layers.15.input_layernorm.weight": "model-00004-of-00014.safetensors",
|
| 94 |
+
"model.layers.15.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
|
| 95 |
+
"model.layers.15.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
|
| 96 |
+
"model.layers.15.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
|
| 97 |
+
"model.layers.15.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
|
| 98 |
+
"model.layers.15.self_attn.k_proj.bias": "model-00004-of-00014.safetensors",
|
| 99 |
+
"model.layers.15.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
|
| 100 |
+
"model.layers.15.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
|
| 101 |
+
"model.layers.15.self_attn.q_proj.bias": "model-00004-of-00014.safetensors",
|
| 102 |
+
"model.layers.15.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
|
| 103 |
+
"model.layers.15.self_attn.v_proj.bias": "model-00004-of-00014.safetensors",
|
| 104 |
+
"model.layers.15.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
|
| 105 |
+
"model.layers.16.input_layernorm.weight": "model-00004-of-00014.safetensors",
|
| 106 |
+
"model.layers.16.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
|
| 107 |
+
"model.layers.16.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
|
| 108 |
+
"model.layers.16.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
|
| 109 |
+
"model.layers.16.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
|
| 110 |
+
"model.layers.16.self_attn.k_proj.bias": "model-00004-of-00014.safetensors",
|
| 111 |
+
"model.layers.16.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
|
| 112 |
+
"model.layers.16.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
|
| 113 |
+
"model.layers.16.self_attn.q_proj.bias": "model-00004-of-00014.safetensors",
|
| 114 |
+
"model.layers.16.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
|
| 115 |
+
"model.layers.16.self_attn.v_proj.bias": "model-00004-of-00014.safetensors",
|
| 116 |
+
"model.layers.16.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
|
| 117 |
+
"model.layers.17.input_layernorm.weight": "model-00004-of-00014.safetensors",
|
| 118 |
+
"model.layers.17.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
|
| 119 |
+
"model.layers.17.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
|
| 120 |
+
"model.layers.17.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
|
| 121 |
+
"model.layers.17.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
|
| 122 |
+
"model.layers.17.self_attn.k_proj.bias": "model-00004-of-00014.safetensors",
|
| 123 |
+
"model.layers.17.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
|
| 124 |
+
"model.layers.17.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
|
| 125 |
+
"model.layers.17.self_attn.q_proj.bias": "model-00004-of-00014.safetensors",
|
| 126 |
+
"model.layers.17.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
|
| 127 |
+
"model.layers.17.self_attn.v_proj.bias": "model-00004-of-00014.safetensors",
|
| 128 |
+
"model.layers.17.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
|
| 129 |
+
"model.layers.18.input_layernorm.weight": "model-00005-of-00014.safetensors",
|
| 130 |
+
"model.layers.18.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
|
| 131 |
+
"model.layers.18.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
|
| 132 |
+
"model.layers.18.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
|
| 133 |
+
"model.layers.18.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
|
| 134 |
+
"model.layers.18.self_attn.k_proj.bias": "model-00004-of-00014.safetensors",
|
| 135 |
+
"model.layers.18.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
|
| 136 |
+
"model.layers.18.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
|
| 137 |
+
"model.layers.18.self_attn.q_proj.bias": "model-00004-of-00014.safetensors",
|
| 138 |
+
"model.layers.18.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
|
| 139 |
+
"model.layers.18.self_attn.v_proj.bias": "model-00004-of-00014.safetensors",
|
| 140 |
+
"model.layers.18.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
|
| 141 |
+
"model.layers.19.input_layernorm.weight": "model-00005-of-00014.safetensors",
|
| 142 |
+
"model.layers.19.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
|
| 143 |
+
"model.layers.19.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
|
| 144 |
+
"model.layers.19.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
|
| 145 |
+
"model.layers.19.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
|
| 146 |
+
"model.layers.19.self_attn.k_proj.bias": "model-00005-of-00014.safetensors",
|
| 147 |
+
"model.layers.19.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
|
| 148 |
+
"model.layers.19.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
|
| 149 |
+
"model.layers.19.self_attn.q_proj.bias": "model-00005-of-00014.safetensors",
|
| 150 |
+
"model.layers.19.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
|
| 151 |
+
"model.layers.19.self_attn.v_proj.bias": "model-00005-of-00014.safetensors",
|
| 152 |
+
"model.layers.19.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
|
| 153 |
+
"model.layers.2.input_layernorm.weight": "model-00001-of-00014.safetensors",
|
| 154 |
+
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
|
| 155 |
+
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
|
| 156 |
+
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
|
| 157 |
+
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00014.safetensors",
|
| 158 |
+
"model.layers.2.self_attn.k_proj.bias": "model-00001-of-00014.safetensors",
|
| 159 |
+
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00014.safetensors",
|
| 160 |
+
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00014.safetensors",
|
| 161 |
+
"model.layers.2.self_attn.q_proj.bias": "model-00001-of-00014.safetensors",
|
| 162 |
+
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00014.safetensors",
|
| 163 |
+
"model.layers.2.self_attn.v_proj.bias": "model-00001-of-00014.safetensors",
|
| 164 |
+
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00014.safetensors",
|
| 165 |
+
"model.layers.20.input_layernorm.weight": "model-00005-of-00014.safetensors",
|
| 166 |
+
"model.layers.20.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
|
| 167 |
+
"model.layers.20.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
|
| 168 |
+
"model.layers.20.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
|
| 169 |
+
"model.layers.20.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
|
| 170 |
+
"model.layers.20.self_attn.k_proj.bias": "model-00005-of-00014.safetensors",
|
| 171 |
+
"model.layers.20.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
|
| 172 |
+
"model.layers.20.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
|
| 173 |
+
"model.layers.20.self_attn.q_proj.bias": "model-00005-of-00014.safetensors",
|
| 174 |
+
"model.layers.20.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
|
| 175 |
+
"model.layers.20.self_attn.v_proj.bias": "model-00005-of-00014.safetensors",
|
| 176 |
+
"model.layers.20.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
|
| 177 |
+
"model.layers.21.input_layernorm.weight": "model-00005-of-00014.safetensors",
|
| 178 |
+
"model.layers.21.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
|
| 179 |
+
"model.layers.21.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
|
| 180 |
+
"model.layers.21.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
|
| 181 |
+
"model.layers.21.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
|
| 182 |
+
"model.layers.21.self_attn.k_proj.bias": "model-00005-of-00014.safetensors",
|
| 183 |
+
"model.layers.21.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
|
| 184 |
+
"model.layers.21.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
|
| 185 |
+
"model.layers.21.self_attn.q_proj.bias": "model-00005-of-00014.safetensors",
|
| 186 |
+
"model.layers.21.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
|
| 187 |
+
"model.layers.21.self_attn.v_proj.bias": "model-00005-of-00014.safetensors",
|
| 188 |
+
"model.layers.21.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
|
| 189 |
+
"model.layers.22.input_layernorm.weight": "model-00005-of-00014.safetensors",
|
| 190 |
+
"model.layers.22.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
|
| 191 |
+
"model.layers.22.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
|
| 192 |
+
"model.layers.22.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
|
| 193 |
+
"model.layers.22.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
|
| 194 |
+
"model.layers.22.self_attn.k_proj.bias": "model-00005-of-00014.safetensors",
|
| 195 |
+
"model.layers.22.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
|
| 196 |
+
"model.layers.22.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
|
| 197 |
+
"model.layers.22.self_attn.q_proj.bias": "model-00005-of-00014.safetensors",
|
| 198 |
+
"model.layers.22.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
|
| 199 |
+
"model.layers.22.self_attn.v_proj.bias": "model-00005-of-00014.safetensors",
|
| 200 |
+
"model.layers.22.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
|
| 201 |
+
"model.layers.23.input_layernorm.weight": "model-00006-of-00014.safetensors",
|
| 202 |
+
"model.layers.23.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
|
| 203 |
+
"model.layers.23.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
|
| 204 |
+
"model.layers.23.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
|
| 205 |
+
"model.layers.23.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
|
| 206 |
+
"model.layers.23.self_attn.k_proj.bias": "model-00005-of-00014.safetensors",
|
| 207 |
+
"model.layers.23.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
|
| 208 |
+
"model.layers.23.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
|
| 209 |
+
"model.layers.23.self_attn.q_proj.bias": "model-00005-of-00014.safetensors",
|
| 210 |
+
"model.layers.23.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
|
| 211 |
+
"model.layers.23.self_attn.v_proj.bias": "model-00005-of-00014.safetensors",
|
| 212 |
+
"model.layers.23.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
|
| 213 |
+
"model.layers.24.input_layernorm.weight": "model-00006-of-00014.safetensors",
|
| 214 |
+
"model.layers.24.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
|
| 215 |
+
"model.layers.24.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
|
| 216 |
+
"model.layers.24.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
|
| 217 |
+
"model.layers.24.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
|
| 218 |
+
"model.layers.24.self_attn.k_proj.bias": "model-00006-of-00014.safetensors",
|
| 219 |
+
"model.layers.24.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
|
| 220 |
+
"model.layers.24.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
|
| 221 |
+
"model.layers.24.self_attn.q_proj.bias": "model-00006-of-00014.safetensors",
|
| 222 |
+
"model.layers.24.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
|
| 223 |
+
"model.layers.24.self_attn.v_proj.bias": "model-00006-of-00014.safetensors",
|
| 224 |
+
"model.layers.24.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
|
| 225 |
+
"model.layers.25.input_layernorm.weight": "model-00006-of-00014.safetensors",
|
| 226 |
+
"model.layers.25.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
|
| 227 |
+
"model.layers.25.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
|
| 228 |
+
"model.layers.25.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
|
| 229 |
+
"model.layers.25.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
|
| 230 |
+
"model.layers.25.self_attn.k_proj.bias": "model-00006-of-00014.safetensors",
|
| 231 |
+
"model.layers.25.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
|
| 232 |
+
"model.layers.25.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
|
| 233 |
+
"model.layers.25.self_attn.q_proj.bias": "model-00006-of-00014.safetensors",
|
| 234 |
+
"model.layers.25.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
|
| 235 |
+
"model.layers.25.self_attn.v_proj.bias": "model-00006-of-00014.safetensors",
|
| 236 |
+
"model.layers.25.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
|
| 237 |
+
"model.layers.26.input_layernorm.weight": "model-00006-of-00014.safetensors",
|
| 238 |
+
"model.layers.26.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
|
| 239 |
+
"model.layers.26.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
|
| 240 |
+
"model.layers.26.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
|
| 241 |
+
"model.layers.26.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
|
| 242 |
+
"model.layers.26.self_attn.k_proj.bias": "model-00006-of-00014.safetensors",
|
| 243 |
+
"model.layers.26.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
|
| 244 |
+
"model.layers.26.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
|
| 245 |
+
"model.layers.26.self_attn.q_proj.bias": "model-00006-of-00014.safetensors",
|
| 246 |
+
"model.layers.26.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
|
| 247 |
+
"model.layers.26.self_attn.v_proj.bias": "model-00006-of-00014.safetensors",
|
| 248 |
+
"model.layers.26.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
|
| 249 |
+
"model.layers.27.input_layernorm.weight": "model-00006-of-00014.safetensors",
|
| 250 |
+
"model.layers.27.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
|
| 251 |
+
"model.layers.27.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
|
| 252 |
+
"model.layers.27.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
|
| 253 |
+
"model.layers.27.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
|
| 254 |
+
"model.layers.27.self_attn.k_proj.bias": "model-00006-of-00014.safetensors",
|
| 255 |
+
"model.layers.27.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
|
| 256 |
+
"model.layers.27.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
|
| 257 |
+
"model.layers.27.self_attn.q_proj.bias": "model-00006-of-00014.safetensors",
|
| 258 |
+
"model.layers.27.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
|
| 259 |
+
"model.layers.27.self_attn.v_proj.bias": "model-00006-of-00014.safetensors",
|
| 260 |
+
"model.layers.27.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
|
| 261 |
+
"model.layers.28.input_layernorm.weight": "model-00007-of-00014.safetensors",
|
| 262 |
+
"model.layers.28.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
|
| 263 |
+
"model.layers.28.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
|
| 264 |
+
"model.layers.28.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
|
| 265 |
+
"model.layers.28.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
|
| 266 |
+
"model.layers.28.self_attn.k_proj.bias": "model-00006-of-00014.safetensors",
|
| 267 |
+
"model.layers.28.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
|
| 268 |
+
"model.layers.28.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
|
| 269 |
+
"model.layers.28.self_attn.q_proj.bias": "model-00006-of-00014.safetensors",
|
| 270 |
+
"model.layers.28.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
|
| 271 |
+
"model.layers.28.self_attn.v_proj.bias": "model-00006-of-00014.safetensors",
|
| 272 |
+
"model.layers.28.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
|
| 273 |
+
"model.layers.29.input_layernorm.weight": "model-00007-of-00014.safetensors",
|
| 274 |
+
"model.layers.29.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
|
| 275 |
+
"model.layers.29.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
|
| 276 |
+
"model.layers.29.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
|
| 277 |
+
"model.layers.29.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
|
| 278 |
+
"model.layers.29.self_attn.k_proj.bias": "model-00007-of-00014.safetensors",
|
| 279 |
+
"model.layers.29.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
|
| 280 |
+
"model.layers.29.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
|
| 281 |
+
"model.layers.29.self_attn.q_proj.bias": "model-00007-of-00014.safetensors",
|
| 282 |
+
"model.layers.29.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
|
| 283 |
+
"model.layers.29.self_attn.v_proj.bias": "model-00007-of-00014.safetensors",
|
| 284 |
+
"model.layers.29.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
|
| 285 |
+
"model.layers.3.input_layernorm.weight": "model-00002-of-00014.safetensors",
|
| 286 |
+
"model.layers.3.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
|
| 287 |
+
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
|
| 288 |
+
"model.layers.3.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
|
| 289 |
+
"model.layers.3.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
|
| 290 |
+
"model.layers.3.self_attn.k_proj.bias": "model-00001-of-00014.safetensors",
|
| 291 |
+
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00014.safetensors",
|
| 292 |
+
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00014.safetensors",
|
| 293 |
+
"model.layers.3.self_attn.q_proj.bias": "model-00001-of-00014.safetensors",
|
| 294 |
+
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00014.safetensors",
|
| 295 |
+
"model.layers.3.self_attn.v_proj.bias": "model-00001-of-00014.safetensors",
|
| 296 |
+
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00014.safetensors",
|
| 297 |
+
"model.layers.30.input_layernorm.weight": "model-00007-of-00014.safetensors",
|
| 298 |
+
"model.layers.30.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
|
| 299 |
+
"model.layers.30.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
|
| 300 |
+
"model.layers.30.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
|
| 301 |
+
"model.layers.30.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
|
| 302 |
+
"model.layers.30.self_attn.k_proj.bias": "model-00007-of-00014.safetensors",
|
| 303 |
+
"model.layers.30.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
|
| 304 |
+
"model.layers.30.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
|
| 305 |
+
"model.layers.30.self_attn.q_proj.bias": "model-00007-of-00014.safetensors",
|
| 306 |
+
"model.layers.30.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
|
| 307 |
+
"model.layers.30.self_attn.v_proj.bias": "model-00007-of-00014.safetensors",
|
| 308 |
+
"model.layers.30.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
|
| 309 |
+
"model.layers.31.input_layernorm.weight": "model-00007-of-00014.safetensors",
|
| 310 |
+
"model.layers.31.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
|
| 311 |
+
"model.layers.31.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
|
| 312 |
+
"model.layers.31.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
|
| 313 |
+
"model.layers.31.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
|
| 314 |
+
"model.layers.31.self_attn.k_proj.bias": "model-00007-of-00014.safetensors",
|
| 315 |
+
"model.layers.31.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
|
| 316 |
+
"model.layers.31.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
|
| 317 |
+
"model.layers.31.self_attn.q_proj.bias": "model-00007-of-00014.safetensors",
|
| 318 |
+
"model.layers.31.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
|
| 319 |
+
"model.layers.31.self_attn.v_proj.bias": "model-00007-of-00014.safetensors",
|
| 320 |
+
"model.layers.31.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
|
| 321 |
+
"model.layers.32.input_layernorm.weight": "model-00007-of-00014.safetensors",
|
| 322 |
+
"model.layers.32.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
|
| 323 |
+
"model.layers.32.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
|
| 324 |
+
"model.layers.32.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
|
| 325 |
+
"model.layers.32.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
|
| 326 |
+
"model.layers.32.self_attn.k_proj.bias": "model-00007-of-00014.safetensors",
|
| 327 |
+
"model.layers.32.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
|
| 328 |
+
"model.layers.32.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
|
| 329 |
+
"model.layers.32.self_attn.q_proj.bias": "model-00007-of-00014.safetensors",
|
| 330 |
+
"model.layers.32.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
|
| 331 |
+
"model.layers.32.self_attn.v_proj.bias": "model-00007-of-00014.safetensors",
|
| 332 |
+
"model.layers.32.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
|
| 333 |
+
"model.layers.33.input_layernorm.weight": "model-00008-of-00014.safetensors",
|
| 334 |
+
"model.layers.33.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
|
| 335 |
+
"model.layers.33.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
|
| 336 |
+
"model.layers.33.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
|
| 337 |
+
"model.layers.33.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
|
| 338 |
+
"model.layers.33.self_attn.k_proj.bias": "model-00007-of-00014.safetensors",
|
| 339 |
+
"model.layers.33.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
|
| 340 |
+
"model.layers.33.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
|
| 341 |
+
"model.layers.33.self_attn.q_proj.bias": "model-00007-of-00014.safetensors",
|
| 342 |
+
"model.layers.33.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
|
| 343 |
+
"model.layers.33.self_attn.v_proj.bias": "model-00007-of-00014.safetensors",
|
| 344 |
+
"model.layers.33.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
|
| 345 |
+
"model.layers.34.input_layernorm.weight": "model-00008-of-00014.safetensors",
|
| 346 |
+
"model.layers.34.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
|
| 347 |
+
"model.layers.34.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
|
| 348 |
+
"model.layers.34.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
|
| 349 |
+
"model.layers.34.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
|
| 350 |
+
"model.layers.34.self_attn.k_proj.bias": "model-00008-of-00014.safetensors",
|
| 351 |
+
"model.layers.34.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
|
| 352 |
+
"model.layers.34.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
|
| 353 |
+
"model.layers.34.self_attn.q_proj.bias": "model-00008-of-00014.safetensors",
|
| 354 |
+
"model.layers.34.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
|
| 355 |
+
"model.layers.34.self_attn.v_proj.bias": "model-00008-of-00014.safetensors",
|
| 356 |
+
"model.layers.34.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
|
| 357 |
+
"model.layers.35.input_layernorm.weight": "model-00008-of-00014.safetensors",
|
| 358 |
+
"model.layers.35.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
|
| 359 |
+
"model.layers.35.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
|
| 360 |
+
"model.layers.35.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
|
| 361 |
+
"model.layers.35.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
|
| 362 |
+
"model.layers.35.self_attn.k_proj.bias": "model-00008-of-00014.safetensors",
|
| 363 |
+
"model.layers.35.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
|
| 364 |
+
"model.layers.35.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
|
| 365 |
+
"model.layers.35.self_attn.q_proj.bias": "model-00008-of-00014.safetensors",
|
| 366 |
+
"model.layers.35.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
|
| 367 |
+
"model.layers.35.self_attn.v_proj.bias": "model-00008-of-00014.safetensors",
|
| 368 |
+
"model.layers.35.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
|
| 369 |
+
"model.layers.36.input_layernorm.weight": "model-00008-of-00014.safetensors",
|
| 370 |
+
"model.layers.36.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
|
| 371 |
+
"model.layers.36.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
|
| 372 |
+
"model.layers.36.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
|
| 373 |
+
"model.layers.36.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
|
| 374 |
+
"model.layers.36.self_attn.k_proj.bias": "model-00008-of-00014.safetensors",
|
| 375 |
+
"model.layers.36.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
|
| 376 |
+
"model.layers.36.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
|
| 377 |
+
"model.layers.36.self_attn.q_proj.bias": "model-00008-of-00014.safetensors",
|
| 378 |
+
"model.layers.36.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
|
| 379 |
+
"model.layers.36.self_attn.v_proj.bias": "model-00008-of-00014.safetensors",
|
| 380 |
+
"model.layers.36.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
|
| 381 |
+
"model.layers.37.input_layernorm.weight": "model-00008-of-00014.safetensors",
|
| 382 |
+
"model.layers.37.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
|
| 383 |
+
"model.layers.37.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
|
| 384 |
+
"model.layers.37.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
|
| 385 |
+
"model.layers.37.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
|
| 386 |
+
"model.layers.37.self_attn.k_proj.bias": "model-00008-of-00014.safetensors",
|
| 387 |
+
"model.layers.37.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
|
| 388 |
+
"model.layers.37.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
|
| 389 |
+
"model.layers.37.self_attn.q_proj.bias": "model-00008-of-00014.safetensors",
|
| 390 |
+
"model.layers.37.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
|
| 391 |
+
"model.layers.37.self_attn.v_proj.bias": "model-00008-of-00014.safetensors",
|
| 392 |
+
"model.layers.37.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
|
| 393 |
+
"model.layers.38.input_layernorm.weight": "model-00009-of-00014.safetensors",
|
| 394 |
+
"model.layers.38.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
|
| 395 |
+
"model.layers.38.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
|
| 396 |
+
"model.layers.38.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
|
| 397 |
+
"model.layers.38.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
|
| 398 |
+
"model.layers.38.self_attn.k_proj.bias": "model-00008-of-00014.safetensors",
|
| 399 |
+
"model.layers.38.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
|
| 400 |
+
"model.layers.38.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
|
| 401 |
+
"model.layers.38.self_attn.q_proj.bias": "model-00008-of-00014.safetensors",
|
| 402 |
+
"model.layers.38.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
|
| 403 |
+
"model.layers.38.self_attn.v_proj.bias": "model-00008-of-00014.safetensors",
|
| 404 |
+
"model.layers.38.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
|
| 405 |
+
"model.layers.39.input_layernorm.weight": "model-00009-of-00014.safetensors",
|
| 406 |
+
"model.layers.39.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
|
| 407 |
+
"model.layers.39.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
|
| 408 |
+
"model.layers.39.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
|
| 409 |
+
"model.layers.39.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
|
| 410 |
+
"model.layers.39.self_attn.k_proj.bias": "model-00009-of-00014.safetensors",
|
| 411 |
+
"model.layers.39.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
|
| 412 |
+
"model.layers.39.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
|
| 413 |
+
"model.layers.39.self_attn.q_proj.bias": "model-00009-of-00014.safetensors",
|
| 414 |
+
"model.layers.39.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
|
| 415 |
+
"model.layers.39.self_attn.v_proj.bias": "model-00009-of-00014.safetensors",
|
| 416 |
+
"model.layers.39.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
|
| 417 |
+
"model.layers.4.input_layernorm.weight": "model-00002-of-00014.safetensors",
|
| 418 |
+
"model.layers.4.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
|
| 419 |
+
"model.layers.4.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
|
| 420 |
+
"model.layers.4.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
|
| 421 |
+
"model.layers.4.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
|
| 422 |
+
"model.layers.4.self_attn.k_proj.bias": "model-00002-of-00014.safetensors",
|
| 423 |
+
"model.layers.4.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
|
| 424 |
+
"model.layers.4.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
|
| 425 |
+
"model.layers.4.self_attn.q_proj.bias": "model-00002-of-00014.safetensors",
|
| 426 |
+
"model.layers.4.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
|
| 427 |
+
"model.layers.4.self_attn.v_proj.bias": "model-00002-of-00014.safetensors",
|
| 428 |
+
"model.layers.4.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
|
| 429 |
+
"model.layers.40.input_layernorm.weight": "model-00009-of-00014.safetensors",
|
| 430 |
+
"model.layers.40.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
|
| 431 |
+
"model.layers.40.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
|
| 432 |
+
"model.layers.40.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
|
| 433 |
+
"model.layers.40.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
|
| 434 |
+
"model.layers.40.self_attn.k_proj.bias": "model-00009-of-00014.safetensors",
|
| 435 |
+
"model.layers.40.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
|
| 436 |
+
"model.layers.40.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
|
| 437 |
+
"model.layers.40.self_attn.q_proj.bias": "model-00009-of-00014.safetensors",
|
| 438 |
+
"model.layers.40.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
|
| 439 |
+
"model.layers.40.self_attn.v_proj.bias": "model-00009-of-00014.safetensors",
|
| 440 |
+
"model.layers.40.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
|
| 441 |
+
"model.layers.41.input_layernorm.weight": "model-00009-of-00014.safetensors",
|
| 442 |
+
"model.layers.41.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
|
| 443 |
+
"model.layers.41.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
|
| 444 |
+
"model.layers.41.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
|
| 445 |
+
"model.layers.41.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
|
| 446 |
+
"model.layers.41.self_attn.k_proj.bias": "model-00009-of-00014.safetensors",
|
| 447 |
+
"model.layers.41.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
|
| 448 |
+
"model.layers.41.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
|
| 449 |
+
"model.layers.41.self_attn.q_proj.bias": "model-00009-of-00014.safetensors",
|
| 450 |
+
"model.layers.41.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
|
| 451 |
+
"model.layers.41.self_attn.v_proj.bias": "model-00009-of-00014.safetensors",
|
| 452 |
+
"model.layers.41.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
|
| 453 |
+
"model.layers.42.input_layernorm.weight": "model-00009-of-00014.safetensors",
|
| 454 |
+
"model.layers.42.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
|
| 455 |
+
"model.layers.42.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
|
| 456 |
+
"model.layers.42.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
|
| 457 |
+
"model.layers.42.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
|
| 458 |
+
"model.layers.42.self_attn.k_proj.bias": "model-00009-of-00014.safetensors",
|
| 459 |
+
"model.layers.42.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
|
| 460 |
+
"model.layers.42.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
|
| 461 |
+
"model.layers.42.self_attn.q_proj.bias": "model-00009-of-00014.safetensors",
|
| 462 |
+
"model.layers.42.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
|
| 463 |
+
"model.layers.42.self_attn.v_proj.bias": "model-00009-of-00014.safetensors",
|
| 464 |
+
"model.layers.42.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
|
| 465 |
+
"model.layers.43.input_layernorm.weight": "model-00010-of-00014.safetensors",
|
| 466 |
+
"model.layers.43.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
|
| 467 |
+
"model.layers.43.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
|
| 468 |
+
"model.layers.43.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
|
| 469 |
+
"model.layers.43.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
|
| 470 |
+
"model.layers.43.self_attn.k_proj.bias": "model-00009-of-00014.safetensors",
|
| 471 |
+
"model.layers.43.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
|
| 472 |
+
"model.layers.43.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
|
| 473 |
+
"model.layers.43.self_attn.q_proj.bias": "model-00009-of-00014.safetensors",
|
| 474 |
+
"model.layers.43.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
|
| 475 |
+
"model.layers.43.self_attn.v_proj.bias": "model-00009-of-00014.safetensors",
|
| 476 |
+
"model.layers.43.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
|
| 477 |
+
"model.layers.44.input_layernorm.weight": "model-00010-of-00014.safetensors",
|
| 478 |
+
"model.layers.44.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
|
| 479 |
+
"model.layers.44.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
|
| 480 |
+
"model.layers.44.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
|
| 481 |
+
"model.layers.44.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
|
| 482 |
+
"model.layers.44.self_attn.k_proj.bias": "model-00010-of-00014.safetensors",
|
| 483 |
+
"model.layers.44.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
|
| 484 |
+
"model.layers.44.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
|
| 485 |
+
"model.layers.44.self_attn.q_proj.bias": "model-00010-of-00014.safetensors",
|
| 486 |
+
"model.layers.44.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
|
| 487 |
+
"model.layers.44.self_attn.v_proj.bias": "model-00010-of-00014.safetensors",
|
| 488 |
+
"model.layers.44.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
|
| 489 |
+
"model.layers.45.input_layernorm.weight": "model-00010-of-00014.safetensors",
|
| 490 |
+
"model.layers.45.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
|
| 491 |
+
"model.layers.45.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
|
| 492 |
+
"model.layers.45.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
|
| 493 |
+
"model.layers.45.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
|
| 494 |
+
"model.layers.45.self_attn.k_proj.bias": "model-00010-of-00014.safetensors",
|
| 495 |
+
"model.layers.45.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
|
| 496 |
+
"model.layers.45.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
|
| 497 |
+
"model.layers.45.self_attn.q_proj.bias": "model-00010-of-00014.safetensors",
|
| 498 |
+
"model.layers.45.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
|
| 499 |
+
"model.layers.45.self_attn.v_proj.bias": "model-00010-of-00014.safetensors",
|
| 500 |
+
"model.layers.45.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
|
| 501 |
+
"model.layers.46.input_layernorm.weight": "model-00010-of-00014.safetensors",
|
| 502 |
+
"model.layers.46.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
|
| 503 |
+
"model.layers.46.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
|
| 504 |
+
"model.layers.46.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
|
| 505 |
+
"model.layers.46.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
|
| 506 |
+
"model.layers.46.self_attn.k_proj.bias": "model-00010-of-00014.safetensors",
|
| 507 |
+
"model.layers.46.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
|
| 508 |
+
"model.layers.46.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
|
| 509 |
+
"model.layers.46.self_attn.q_proj.bias": "model-00010-of-00014.safetensors",
|
| 510 |
+
"model.layers.46.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
|
| 511 |
+
"model.layers.46.self_attn.v_proj.bias": "model-00010-of-00014.safetensors",
|
| 512 |
+
"model.layers.46.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
|
| 513 |
+
"model.layers.47.input_layernorm.weight": "model-00010-of-00014.safetensors",
|
| 514 |
+
"model.layers.47.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
|
| 515 |
+
"model.layers.47.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
|
| 516 |
+
"model.layers.47.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
|
| 517 |
+
"model.layers.47.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
|
| 518 |
+
"model.layers.47.self_attn.k_proj.bias": "model-00010-of-00014.safetensors",
|
| 519 |
+
"model.layers.47.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
|
| 520 |
+
"model.layers.47.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
|
| 521 |
+
"model.layers.47.self_attn.q_proj.bias": "model-00010-of-00014.safetensors",
|
| 522 |
+
"model.layers.47.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
|
| 523 |
+
"model.layers.47.self_attn.v_proj.bias": "model-00010-of-00014.safetensors",
|
| 524 |
+
"model.layers.47.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
|
| 525 |
+
"model.layers.48.input_layernorm.weight": "model-00011-of-00014.safetensors",
|
| 526 |
+
"model.layers.48.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
|
| 527 |
+
"model.layers.48.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
|
| 528 |
+
"model.layers.48.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
|
| 529 |
+
"model.layers.48.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
|
| 530 |
+
"model.layers.48.self_attn.k_proj.bias": "model-00010-of-00014.safetensors",
|
| 531 |
+
"model.layers.48.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
|
| 532 |
+
"model.layers.48.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
|
| 533 |
+
"model.layers.48.self_attn.q_proj.bias": "model-00010-of-00014.safetensors",
|
| 534 |
+
"model.layers.48.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
|
| 535 |
+
"model.layers.48.self_attn.v_proj.bias": "model-00010-of-00014.safetensors",
|
| 536 |
+
"model.layers.48.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
|
| 537 |
+
"model.layers.49.input_layernorm.weight": "model-00011-of-00014.safetensors",
|
| 538 |
+
"model.layers.49.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
|
| 539 |
+
"model.layers.49.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
|
| 540 |
+
"model.layers.49.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
|
| 541 |
+
"model.layers.49.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
|
| 542 |
+
"model.layers.49.self_attn.k_proj.bias": "model-00011-of-00014.safetensors",
|
| 543 |
+
"model.layers.49.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
|
| 544 |
+
"model.layers.49.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
|
| 545 |
+
"model.layers.49.self_attn.q_proj.bias": "model-00011-of-00014.safetensors",
|
| 546 |
+
"model.layers.49.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
|
| 547 |
+
"model.layers.49.self_attn.v_proj.bias": "model-00011-of-00014.safetensors",
|
| 548 |
+
"model.layers.49.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
|
| 549 |
+
"model.layers.5.input_layernorm.weight": "model-00002-of-00014.safetensors",
|
| 550 |
+
"model.layers.5.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
|
| 551 |
+
"model.layers.5.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
|
| 552 |
+
"model.layers.5.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
|
| 553 |
+
"model.layers.5.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
|
| 554 |
+
"model.layers.5.self_attn.k_proj.bias": "model-00002-of-00014.safetensors",
|
| 555 |
+
"model.layers.5.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
|
| 556 |
+
"model.layers.5.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
|
| 557 |
+
"model.layers.5.self_attn.q_proj.bias": "model-00002-of-00014.safetensors",
|
| 558 |
+
"model.layers.5.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
|
| 559 |
+
"model.layers.5.self_attn.v_proj.bias": "model-00002-of-00014.safetensors",
|
| 560 |
+
"model.layers.5.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
|
| 561 |
+
"model.layers.50.input_layernorm.weight": "model-00011-of-00014.safetensors",
|
| 562 |
+
"model.layers.50.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
|
| 563 |
+
"model.layers.50.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
|
| 564 |
+
"model.layers.50.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
|
| 565 |
+
"model.layers.50.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
|
| 566 |
+
"model.layers.50.self_attn.k_proj.bias": "model-00011-of-00014.safetensors",
|
| 567 |
+
"model.layers.50.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
|
| 568 |
+
"model.layers.50.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
|
| 569 |
+
"model.layers.50.self_attn.q_proj.bias": "model-00011-of-00014.safetensors",
|
| 570 |
+
"model.layers.50.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
|
| 571 |
+
"model.layers.50.self_attn.v_proj.bias": "model-00011-of-00014.safetensors",
|
| 572 |
+
"model.layers.50.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
|
| 573 |
+
"model.layers.51.input_layernorm.weight": "model-00011-of-00014.safetensors",
|
| 574 |
+
"model.layers.51.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
|
| 575 |
+
"model.layers.51.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
|
| 576 |
+
"model.layers.51.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
|
| 577 |
+
"model.layers.51.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
|
| 578 |
+
"model.layers.51.self_attn.k_proj.bias": "model-00011-of-00014.safetensors",
|
| 579 |
+
"model.layers.51.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
|
| 580 |
+
"model.layers.51.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
|
| 581 |
+
"model.layers.51.self_attn.q_proj.bias": "model-00011-of-00014.safetensors",
|
| 582 |
+
"model.layers.51.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
|
| 583 |
+
"model.layers.51.self_attn.v_proj.bias": "model-00011-of-00014.safetensors",
|
| 584 |
+
"model.layers.51.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
|
| 585 |
+
"model.layers.52.input_layernorm.weight": "model-00011-of-00014.safetensors",
|
| 586 |
+
"model.layers.52.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
|
| 587 |
+
"model.layers.52.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
|
| 588 |
+
"model.layers.52.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
|
| 589 |
+
"model.layers.52.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
|
| 590 |
+
"model.layers.52.self_attn.k_proj.bias": "model-00011-of-00014.safetensors",
|
| 591 |
+
"model.layers.52.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
|
| 592 |
+
"model.layers.52.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
|
| 593 |
+
"model.layers.52.self_attn.q_proj.bias": "model-00011-of-00014.safetensors",
|
| 594 |
+
"model.layers.52.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
|
| 595 |
+
"model.layers.52.self_attn.v_proj.bias": "model-00011-of-00014.safetensors",
|
| 596 |
+
"model.layers.52.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
|
| 597 |
+
"model.layers.53.input_layernorm.weight": "model-00012-of-00014.safetensors",
|
| 598 |
+
"model.layers.53.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
|
| 599 |
+
"model.layers.53.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
|
| 600 |
+
"model.layers.53.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
|
| 601 |
+
"model.layers.53.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
|
| 602 |
+
"model.layers.53.self_attn.k_proj.bias": "model-00011-of-00014.safetensors",
|
| 603 |
+
"model.layers.53.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
|
| 604 |
+
"model.layers.53.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
|
| 605 |
+
"model.layers.53.self_attn.q_proj.bias": "model-00011-of-00014.safetensors",
|
| 606 |
+
"model.layers.53.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
|
| 607 |
+
"model.layers.53.self_attn.v_proj.bias": "model-00011-of-00014.safetensors",
|
| 608 |
+
"model.layers.53.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
|
| 609 |
+
"model.layers.54.input_layernorm.weight": "model-00012-of-00014.safetensors",
|
| 610 |
+
"model.layers.54.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
|
| 611 |
+
"model.layers.54.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
|
| 612 |
+
"model.layers.54.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
|
| 613 |
+
"model.layers.54.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
|
| 614 |
+
"model.layers.54.self_attn.k_proj.bias": "model-00012-of-00014.safetensors",
|
| 615 |
+
"model.layers.54.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
|
| 616 |
+
"model.layers.54.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
|
| 617 |
+
"model.layers.54.self_attn.q_proj.bias": "model-00012-of-00014.safetensors",
|
| 618 |
+
"model.layers.54.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
|
| 619 |
+
"model.layers.54.self_attn.v_proj.bias": "model-00012-of-00014.safetensors",
|
| 620 |
+
"model.layers.54.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
|
| 621 |
+
"model.layers.55.input_layernorm.weight": "model-00012-of-00014.safetensors",
|
| 622 |
+
"model.layers.55.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
|
| 623 |
+
"model.layers.55.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
|
| 624 |
+
"model.layers.55.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
|
| 625 |
+
"model.layers.55.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
|
| 626 |
+
"model.layers.55.self_attn.k_proj.bias": "model-00012-of-00014.safetensors",
|
| 627 |
+
"model.layers.55.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
|
| 628 |
+
"model.layers.55.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
|
| 629 |
+
"model.layers.55.self_attn.q_proj.bias": "model-00012-of-00014.safetensors",
|
| 630 |
+
"model.layers.55.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
|
| 631 |
+
"model.layers.55.self_attn.v_proj.bias": "model-00012-of-00014.safetensors",
|
| 632 |
+
"model.layers.55.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
|
| 633 |
+
"model.layers.56.input_layernorm.weight": "model-00012-of-00014.safetensors",
|
| 634 |
+
"model.layers.56.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
|
| 635 |
+
"model.layers.56.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
|
| 636 |
+
"model.layers.56.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
|
| 637 |
+
"model.layers.56.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
|
| 638 |
+
"model.layers.56.self_attn.k_proj.bias": "model-00012-of-00014.safetensors",
|
| 639 |
+
"model.layers.56.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
|
| 640 |
+
"model.layers.56.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
|
| 641 |
+
"model.layers.56.self_attn.q_proj.bias": "model-00012-of-00014.safetensors",
|
| 642 |
+
"model.layers.56.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
|
| 643 |
+
"model.layers.56.self_attn.v_proj.bias": "model-00012-of-00014.safetensors",
|
| 644 |
+
"model.layers.56.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
|
| 645 |
+
"model.layers.57.input_layernorm.weight": "model-00012-of-00014.safetensors",
|
| 646 |
+
"model.layers.57.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
|
| 647 |
+
"model.layers.57.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
|
| 648 |
+
"model.layers.57.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
|
| 649 |
+
"model.layers.57.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
|
| 650 |
+
"model.layers.57.self_attn.k_proj.bias": "model-00012-of-00014.safetensors",
|
| 651 |
+
"model.layers.57.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
|
| 652 |
+
"model.layers.57.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
|
| 653 |
+
"model.layers.57.self_attn.q_proj.bias": "model-00012-of-00014.safetensors",
|
| 654 |
+
"model.layers.57.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
|
| 655 |
+
"model.layers.57.self_attn.v_proj.bias": "model-00012-of-00014.safetensors",
|
| 656 |
+
"model.layers.57.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
|
| 657 |
+
"model.layers.58.input_layernorm.weight": "model-00013-of-00014.safetensors",
|
| 658 |
+
"model.layers.58.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
|
| 659 |
+
"model.layers.58.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
|
| 660 |
+
"model.layers.58.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
|
| 661 |
+
"model.layers.58.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
|
| 662 |
+
"model.layers.58.self_attn.k_proj.bias": "model-00012-of-00014.safetensors",
|
| 663 |
+
"model.layers.58.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
|
| 664 |
+
"model.layers.58.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
|
| 665 |
+
"model.layers.58.self_attn.q_proj.bias": "model-00012-of-00014.safetensors",
|
| 666 |
+
"model.layers.58.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
|
| 667 |
+
"model.layers.58.self_attn.v_proj.bias": "model-00012-of-00014.safetensors",
|
| 668 |
+
"model.layers.58.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
|
| 669 |
+
"model.layers.59.input_layernorm.weight": "model-00013-of-00014.safetensors",
|
| 670 |
+
"model.layers.59.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
|
| 671 |
+
"model.layers.59.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
|
| 672 |
+
"model.layers.59.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
|
| 673 |
+
"model.layers.59.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
|
| 674 |
+
"model.layers.59.self_attn.k_proj.bias": "model-00013-of-00014.safetensors",
|
| 675 |
+
"model.layers.59.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
|
| 676 |
+
"model.layers.59.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
|
| 677 |
+
"model.layers.59.self_attn.q_proj.bias": "model-00013-of-00014.safetensors",
|
| 678 |
+
"model.layers.59.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
|
| 679 |
+
"model.layers.59.self_attn.v_proj.bias": "model-00013-of-00014.safetensors",
|
| 680 |
+
"model.layers.59.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
|
| 681 |
+
"model.layers.6.input_layernorm.weight": "model-00002-of-00014.safetensors",
|
| 682 |
+
"model.layers.6.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
|
| 683 |
+
"model.layers.6.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
|
| 684 |
+
"model.layers.6.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
|
| 685 |
+
"model.layers.6.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
|
| 686 |
+
"model.layers.6.self_attn.k_proj.bias": "model-00002-of-00014.safetensors",
|
| 687 |
+
"model.layers.6.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
|
| 688 |
+
"model.layers.6.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
|
| 689 |
+
"model.layers.6.self_attn.q_proj.bias": "model-00002-of-00014.safetensors",
|
| 690 |
+
"model.layers.6.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
|
| 691 |
+
"model.layers.6.self_attn.v_proj.bias": "model-00002-of-00014.safetensors",
|
| 692 |
+
"model.layers.6.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
|
| 693 |
+
"model.layers.60.input_layernorm.weight": "model-00013-of-00014.safetensors",
|
| 694 |
+
"model.layers.60.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
|
| 695 |
+
"model.layers.60.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
|
| 696 |
+
"model.layers.60.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
|
| 697 |
+
"model.layers.60.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
|
| 698 |
+
"model.layers.60.self_attn.k_proj.bias": "model-00013-of-00014.safetensors",
|
| 699 |
+
"model.layers.60.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
|
| 700 |
+
"model.layers.60.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
|
| 701 |
+
"model.layers.60.self_attn.q_proj.bias": "model-00013-of-00014.safetensors",
|
| 702 |
+
"model.layers.60.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
|
| 703 |
+
"model.layers.60.self_attn.v_proj.bias": "model-00013-of-00014.safetensors",
|
| 704 |
+
"model.layers.60.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
|
| 705 |
+
"model.layers.61.input_layernorm.weight": "model-00013-of-00014.safetensors",
|
| 706 |
+
"model.layers.61.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
|
| 707 |
+
"model.layers.61.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
|
| 708 |
+
"model.layers.61.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
|
| 709 |
+
"model.layers.61.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
|
| 710 |
+
"model.layers.61.self_attn.k_proj.bias": "model-00013-of-00014.safetensors",
|
| 711 |
+
"model.layers.61.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
|
| 712 |
+
"model.layers.61.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
|
| 713 |
+
"model.layers.61.self_attn.q_proj.bias": "model-00013-of-00014.safetensors",
|
| 714 |
+
"model.layers.61.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
|
| 715 |
+
"model.layers.61.self_attn.v_proj.bias": "model-00013-of-00014.safetensors",
|
| 716 |
+
"model.layers.61.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
|
| 717 |
+
"model.layers.62.input_layernorm.weight": "model-00013-of-00014.safetensors",
|
| 718 |
+
"model.layers.62.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
|
| 719 |
+
"model.layers.62.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
|
| 720 |
+
"model.layers.62.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
|
| 721 |
+
"model.layers.62.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
|
| 722 |
+
"model.layers.62.self_attn.k_proj.bias": "model-00013-of-00014.safetensors",
|
| 723 |
+
"model.layers.62.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
|
| 724 |
+
"model.layers.62.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
|
| 725 |
+
"model.layers.62.self_attn.q_proj.bias": "model-00013-of-00014.safetensors",
|
| 726 |
+
"model.layers.62.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
|
| 727 |
+
"model.layers.62.self_attn.v_proj.bias": "model-00013-of-00014.safetensors",
|
| 728 |
+
"model.layers.62.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
|
| 729 |
+
"model.layers.63.input_layernorm.weight": "model-00014-of-00014.safetensors",
|
| 730 |
+
"model.layers.63.mlp.down_proj.weight": "model-00014-of-00014.safetensors",
|
| 731 |
+
"model.layers.63.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
|
| 732 |
+
"model.layers.63.mlp.up_proj.weight": "model-00014-of-00014.safetensors",
|
| 733 |
+
"model.layers.63.post_attention_layernorm.weight": "model-00014-of-00014.safetensors",
|
| 734 |
+
"model.layers.63.self_attn.k_proj.bias": "model-00013-of-00014.safetensors",
|
| 735 |
+
"model.layers.63.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
|
| 736 |
+
"model.layers.63.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
|
| 737 |
+
"model.layers.63.self_attn.q_proj.bias": "model-00013-of-00014.safetensors",
|
| 738 |
+
"model.layers.63.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
|
| 739 |
+
"model.layers.63.self_attn.v_proj.bias": "model-00013-of-00014.safetensors",
|
| 740 |
+
"model.layers.63.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
|
| 741 |
+
"model.layers.7.input_layernorm.weight": "model-00002-of-00014.safetensors",
|
| 742 |
+
"model.layers.7.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
|
| 743 |
+
"model.layers.7.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
|
| 744 |
+
"model.layers.7.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
|
| 745 |
+
"model.layers.7.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
|
| 746 |
+
"model.layers.7.self_attn.k_proj.bias": "model-00002-of-00014.safetensors",
|
| 747 |
+
"model.layers.7.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
|
| 748 |
+
"model.layers.7.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
|
| 749 |
+
"model.layers.7.self_attn.q_proj.bias": "model-00002-of-00014.safetensors",
|
| 750 |
+
"model.layers.7.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
|
| 751 |
+
"model.layers.7.self_attn.v_proj.bias": "model-00002-of-00014.safetensors",
|
| 752 |
+
"model.layers.7.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
|
| 753 |
+
"model.layers.8.input_layernorm.weight": "model-00003-of-00014.safetensors",
|
| 754 |
+
"model.layers.8.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
|
| 755 |
+
"model.layers.8.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
|
| 756 |
+
"model.layers.8.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
|
| 757 |
+
"model.layers.8.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
|
| 758 |
+
"model.layers.8.self_attn.k_proj.bias": "model-00002-of-00014.safetensors",
|
| 759 |
+
"model.layers.8.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
|
| 760 |
+
"model.layers.8.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
|
| 761 |
+
"model.layers.8.self_attn.q_proj.bias": "model-00002-of-00014.safetensors",
|
| 762 |
+
"model.layers.8.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
|
| 763 |
+
"model.layers.8.self_attn.v_proj.bias": "model-00002-of-00014.safetensors",
|
| 764 |
+
"model.layers.8.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
|
| 765 |
+
"model.layers.9.input_layernorm.weight": "model-00003-of-00014.safetensors",
|
| 766 |
+
"model.layers.9.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
|
| 767 |
+
"model.layers.9.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
|
| 768 |
+
"model.layers.9.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
|
| 769 |
+
"model.layers.9.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
|
| 770 |
+
"model.layers.9.self_attn.k_proj.bias": "model-00003-of-00014.safetensors",
|
| 771 |
+
"model.layers.9.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
|
| 772 |
+
"model.layers.9.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
|
| 773 |
+
"model.layers.9.self_attn.q_proj.bias": "model-00003-of-00014.safetensors",
|
| 774 |
+
"model.layers.9.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
|
| 775 |
+
"model.layers.9.self_attn.v_proj.bias": "model-00003-of-00014.safetensors",
|
| 776 |
+
"model.layers.9.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
|
| 777 |
+
"model.norm.weight": "model-00014-of-00014.safetensors"
|
| 778 |
+
}
|
| 779 |
+
}
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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|>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": false,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
},
|
| 24 |
+
"pad_token": {
|
| 25 |
+
"content": "<|endoftext|>",
|
| 26 |
+
"lstrip": false,
|
| 27 |
+
"normalized": false,
|
| 28 |
+
"rstrip": false,
|
| 29 |
+
"single_word": false
|
| 30 |
+
}
|
| 31 |
+
}
|
tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
|
| 3 |
+
size 11421896
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,207 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": false,
|
| 3 |
+
"add_prefix_space": false,
|
| 4 |
+
"added_tokens_decoder": {
|
| 5 |
+
"151643": {
|
| 6 |
+
"content": "<|endoftext|>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false,
|
| 11 |
+
"special": true
|
| 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 |
+
"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,
|
| 199 |
+
"eos_token": "<|im_end|>",
|
| 200 |
+
"errors": "replace",
|
| 201 |
+
"extra_special_tokens": {},
|
| 202 |
+
"model_max_length": 131072,
|
| 203 |
+
"pad_token": "<|endoftext|>",
|
| 204 |
+
"split_special_tokens": false,
|
| 205 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 206 |
+
"unk_token": null
|
| 207 |
+
}
|
training_report.json
ADDED
|
@@ -0,0 +1,661 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"model_base": "Qwen/Qwen2.5-32B-Instruct",
|
| 3 |
+
"model_name": "RegTech-32B-Instruct",
|
| 4 |
+
"dataset": "./train.jsonl",
|
| 5 |
+
"env_file": "/home/ubuntu/sophia-core-server/.tuning/.env.32B",
|
| 6 |
+
"train_samples": 923,
|
| 7 |
+
"eval_samples": 102,
|
| 8 |
+
"params": {
|
| 9 |
+
"rank": 16,
|
| 10 |
+
"alpha": 32,
|
| 11 |
+
"dropout": 0.1,
|
| 12 |
+
"lr": 1e-05,
|
| 13 |
+
"scheduler": "cosine",
|
| 14 |
+
"epochs": 3,
|
| 15 |
+
"effective_batch": 4,
|
| 16 |
+
"max_seq_length": 4096,
|
| 17 |
+
"neftune_alpha": 5.0,
|
| 18 |
+
"target_modules": [
|
| 19 |
+
"q_proj",
|
| 20 |
+
"k_proj",
|
| 21 |
+
"v_proj",
|
| 22 |
+
"o_proj",
|
| 23 |
+
"gate_proj",
|
| 24 |
+
"up_proj",
|
| 25 |
+
"down_proj"
|
| 26 |
+
]
|
| 27 |
+
},
|
| 28 |
+
"results": {
|
| 29 |
+
"total_steps": 693,
|
| 30 |
+
"final_train_loss": 0.8432,
|
| 31 |
+
"best_eval_loss": 0.8133148550987244,
|
| 32 |
+
"best_eval_step": 640,
|
| 33 |
+
"elapsed_minutes": 40.0
|
| 34 |
+
},
|
| 35 |
+
"loss_history": {
|
| 36 |
+
"train": [
|
| 37 |
+
[
|
| 38 |
+
5,
|
| 39 |
+
1.7606
|
| 40 |
+
],
|
| 41 |
+
[
|
| 42 |
+
10,
|
| 43 |
+
1.8257
|
| 44 |
+
],
|
| 45 |
+
[
|
| 46 |
+
15,
|
| 47 |
+
2.0366
|
| 48 |
+
],
|
| 49 |
+
[
|
| 50 |
+
20,
|
| 51 |
+
1.8063
|
| 52 |
+
],
|
| 53 |
+
[
|
| 54 |
+
25,
|
| 55 |
+
1.9763
|
| 56 |
+
],
|
| 57 |
+
[
|
| 58 |
+
30,
|
| 59 |
+
1.9014
|
| 60 |
+
],
|
| 61 |
+
[
|
| 62 |
+
35,
|
| 63 |
+
1.8005
|
| 64 |
+
],
|
| 65 |
+
[
|
| 66 |
+
40,
|
| 67 |
+
1.6563
|
| 68 |
+
],
|
| 69 |
+
[
|
| 70 |
+
45,
|
| 71 |
+
1.6997
|
| 72 |
+
],
|
| 73 |
+
[
|
| 74 |
+
50,
|
| 75 |
+
1.5501
|
| 76 |
+
],
|
| 77 |
+
[
|
| 78 |
+
55,
|
| 79 |
+
1.273
|
| 80 |
+
],
|
| 81 |
+
[
|
| 82 |
+
60,
|
| 83 |
+
1.5863
|
| 84 |
+
],
|
| 85 |
+
[
|
| 86 |
+
65,
|
| 87 |
+
1.3741
|
| 88 |
+
],
|
| 89 |
+
[
|
| 90 |
+
70,
|
| 91 |
+
1.5504
|
| 92 |
+
],
|
| 93 |
+
[
|
| 94 |
+
75,
|
| 95 |
+
1.5004
|
| 96 |
+
],
|
| 97 |
+
[
|
| 98 |
+
80,
|
| 99 |
+
1.3517
|
| 100 |
+
],
|
| 101 |
+
[
|
| 102 |
+
85,
|
| 103 |
+
1.3193
|
| 104 |
+
],
|
| 105 |
+
[
|
| 106 |
+
90,
|
| 107 |
+
1.2519
|
| 108 |
+
],
|
| 109 |
+
[
|
| 110 |
+
95,
|
| 111 |
+
1.4066
|
| 112 |
+
],
|
| 113 |
+
[
|
| 114 |
+
100,
|
| 115 |
+
1.3787
|
| 116 |
+
],
|
| 117 |
+
[
|
| 118 |
+
105,
|
| 119 |
+
1.317
|
| 120 |
+
],
|
| 121 |
+
[
|
| 122 |
+
110,
|
| 123 |
+
1.273
|
| 124 |
+
],
|
| 125 |
+
[
|
| 126 |
+
115,
|
| 127 |
+
1.366
|
| 128 |
+
],
|
| 129 |
+
[
|
| 130 |
+
120,
|
| 131 |
+
1.1712
|
| 132 |
+
],
|
| 133 |
+
[
|
| 134 |
+
125,
|
| 135 |
+
1.1309
|
| 136 |
+
],
|
| 137 |
+
[
|
| 138 |
+
130,
|
| 139 |
+
1.5067
|
| 140 |
+
],
|
| 141 |
+
[
|
| 142 |
+
135,
|
| 143 |
+
1.1212
|
| 144 |
+
],
|
| 145 |
+
[
|
| 146 |
+
140,
|
| 147 |
+
1.4059
|
| 148 |
+
],
|
| 149 |
+
[
|
| 150 |
+
145,
|
| 151 |
+
1.2398
|
| 152 |
+
],
|
| 153 |
+
[
|
| 154 |
+
150,
|
| 155 |
+
1.2904
|
| 156 |
+
],
|
| 157 |
+
[
|
| 158 |
+
155,
|
| 159 |
+
1.3055
|
| 160 |
+
],
|
| 161 |
+
[
|
| 162 |
+
160,
|
| 163 |
+
1.1672
|
| 164 |
+
],
|
| 165 |
+
[
|
| 166 |
+
165,
|
| 167 |
+
1.2585
|
| 168 |
+
],
|
| 169 |
+
[
|
| 170 |
+
170,
|
| 171 |
+
1.252
|
| 172 |
+
],
|
| 173 |
+
[
|
| 174 |
+
175,
|
| 175 |
+
0.9654
|
| 176 |
+
],
|
| 177 |
+
[
|
| 178 |
+
180,
|
| 179 |
+
1.1089
|
| 180 |
+
],
|
| 181 |
+
[
|
| 182 |
+
185,
|
| 183 |
+
1.1518
|
| 184 |
+
],
|
| 185 |
+
[
|
| 186 |
+
190,
|
| 187 |
+
1.1216
|
| 188 |
+
],
|
| 189 |
+
[
|
| 190 |
+
195,
|
| 191 |
+
1.1329
|
| 192 |
+
],
|
| 193 |
+
[
|
| 194 |
+
200,
|
| 195 |
+
0.9045
|
| 196 |
+
],
|
| 197 |
+
[
|
| 198 |
+
205,
|
| 199 |
+
1.0882
|
| 200 |
+
],
|
| 201 |
+
[
|
| 202 |
+
210,
|
| 203 |
+
1.0312
|
| 204 |
+
],
|
| 205 |
+
[
|
| 206 |
+
215,
|
| 207 |
+
0.9879
|
| 208 |
+
],
|
| 209 |
+
[
|
| 210 |
+
220,
|
| 211 |
+
0.9716
|
| 212 |
+
],
|
| 213 |
+
[
|
| 214 |
+
225,
|
| 215 |
+
1.0379
|
| 216 |
+
],
|
| 217 |
+
[
|
| 218 |
+
230,
|
| 219 |
+
1.0032
|
| 220 |
+
],
|
| 221 |
+
[
|
| 222 |
+
235,
|
| 223 |
+
1.1349
|
| 224 |
+
],
|
| 225 |
+
[
|
| 226 |
+
240,
|
| 227 |
+
0.9745
|
| 228 |
+
],
|
| 229 |
+
[
|
| 230 |
+
245,
|
| 231 |
+
0.9717
|
| 232 |
+
],
|
| 233 |
+
[
|
| 234 |
+
250,
|
| 235 |
+
0.8808
|
| 236 |
+
],
|
| 237 |
+
[
|
| 238 |
+
255,
|
| 239 |
+
0.9055
|
| 240 |
+
],
|
| 241 |
+
[
|
| 242 |
+
260,
|
| 243 |
+
1.0285
|
| 244 |
+
],
|
| 245 |
+
[
|
| 246 |
+
265,
|
| 247 |
+
1.0887
|
| 248 |
+
],
|
| 249 |
+
[
|
| 250 |
+
270,
|
| 251 |
+
0.8846
|
| 252 |
+
],
|
| 253 |
+
[
|
| 254 |
+
275,
|
| 255 |
+
0.9121
|
| 256 |
+
],
|
| 257 |
+
[
|
| 258 |
+
280,
|
| 259 |
+
1.032
|
| 260 |
+
],
|
| 261 |
+
[
|
| 262 |
+
285,
|
| 263 |
+
1.043
|
| 264 |
+
],
|
| 265 |
+
[
|
| 266 |
+
290,
|
| 267 |
+
0.9623
|
| 268 |
+
],
|
| 269 |
+
[
|
| 270 |
+
295,
|
| 271 |
+
0.8949
|
| 272 |
+
],
|
| 273 |
+
[
|
| 274 |
+
300,
|
| 275 |
+
0.8456
|
| 276 |
+
],
|
| 277 |
+
[
|
| 278 |
+
305,
|
| 279 |
+
0.8745
|
| 280 |
+
],
|
| 281 |
+
[
|
| 282 |
+
310,
|
| 283 |
+
0.94
|
| 284 |
+
],
|
| 285 |
+
[
|
| 286 |
+
315,
|
| 287 |
+
0.8265
|
| 288 |
+
],
|
| 289 |
+
[
|
| 290 |
+
320,
|
| 291 |
+
0.9407
|
| 292 |
+
],
|
| 293 |
+
[
|
| 294 |
+
325,
|
| 295 |
+
0.9309
|
| 296 |
+
],
|
| 297 |
+
[
|
| 298 |
+
330,
|
| 299 |
+
0.8971
|
| 300 |
+
],
|
| 301 |
+
[
|
| 302 |
+
335,
|
| 303 |
+
0.8191
|
| 304 |
+
],
|
| 305 |
+
[
|
| 306 |
+
340,
|
| 307 |
+
0.7918
|
| 308 |
+
],
|
| 309 |
+
[
|
| 310 |
+
345,
|
| 311 |
+
0.9414
|
| 312 |
+
],
|
| 313 |
+
[
|
| 314 |
+
350,
|
| 315 |
+
0.783
|
| 316 |
+
],
|
| 317 |
+
[
|
| 318 |
+
355,
|
| 319 |
+
0.8103
|
| 320 |
+
],
|
| 321 |
+
[
|
| 322 |
+
360,
|
| 323 |
+
0.8443
|
| 324 |
+
],
|
| 325 |
+
[
|
| 326 |
+
365,
|
| 327 |
+
0.9374
|
| 328 |
+
],
|
| 329 |
+
[
|
| 330 |
+
370,
|
| 331 |
+
0.9564
|
| 332 |
+
],
|
| 333 |
+
[
|
| 334 |
+
375,
|
| 335 |
+
0.8063
|
| 336 |
+
],
|
| 337 |
+
[
|
| 338 |
+
380,
|
| 339 |
+
0.7323
|
| 340 |
+
],
|
| 341 |
+
[
|
| 342 |
+
385,
|
| 343 |
+
0.826
|
| 344 |
+
],
|
| 345 |
+
[
|
| 346 |
+
390,
|
| 347 |
+
0.8682
|
| 348 |
+
],
|
| 349 |
+
[
|
| 350 |
+
395,
|
| 351 |
+
0.8559
|
| 352 |
+
],
|
| 353 |
+
[
|
| 354 |
+
400,
|
| 355 |
+
0.9216
|
| 356 |
+
],
|
| 357 |
+
[
|
| 358 |
+
405,
|
| 359 |
+
0.8368
|
| 360 |
+
],
|
| 361 |
+
[
|
| 362 |
+
410,
|
| 363 |
+
0.9346
|
| 364 |
+
],
|
| 365 |
+
[
|
| 366 |
+
415,
|
| 367 |
+
0.8632
|
| 368 |
+
],
|
| 369 |
+
[
|
| 370 |
+
420,
|
| 371 |
+
0.8698
|
| 372 |
+
],
|
| 373 |
+
[
|
| 374 |
+
425,
|
| 375 |
+
0.7973
|
| 376 |
+
],
|
| 377 |
+
[
|
| 378 |
+
430,
|
| 379 |
+
0.8807
|
| 380 |
+
],
|
| 381 |
+
[
|
| 382 |
+
435,
|
| 383 |
+
0.7736
|
| 384 |
+
],
|
| 385 |
+
[
|
| 386 |
+
440,
|
| 387 |
+
0.7795
|
| 388 |
+
],
|
| 389 |
+
[
|
| 390 |
+
445,
|
| 391 |
+
0.768
|
| 392 |
+
],
|
| 393 |
+
[
|
| 394 |
+
450,
|
| 395 |
+
0.8426
|
| 396 |
+
],
|
| 397 |
+
[
|
| 398 |
+
455,
|
| 399 |
+
0.8065
|
| 400 |
+
],
|
| 401 |
+
[
|
| 402 |
+
460,
|
| 403 |
+
0.7986
|
| 404 |
+
],
|
| 405 |
+
[
|
| 406 |
+
465,
|
| 407 |
+
1.0072
|
| 408 |
+
],
|
| 409 |
+
[
|
| 410 |
+
470,
|
| 411 |
+
0.7926
|
| 412 |
+
],
|
| 413 |
+
[
|
| 414 |
+
475,
|
| 415 |
+
0.7541
|
| 416 |
+
],
|
| 417 |
+
[
|
| 418 |
+
480,
|
| 419 |
+
0.7158
|
| 420 |
+
],
|
| 421 |
+
[
|
| 422 |
+
485,
|
| 423 |
+
0.7268
|
| 424 |
+
],
|
| 425 |
+
[
|
| 426 |
+
490,
|
| 427 |
+
0.793
|
| 428 |
+
],
|
| 429 |
+
[
|
| 430 |
+
495,
|
| 431 |
+
0.9075
|
| 432 |
+
],
|
| 433 |
+
[
|
| 434 |
+
500,
|
| 435 |
+
0.8299
|
| 436 |
+
],
|
| 437 |
+
[
|
| 438 |
+
505,
|
| 439 |
+
0.8684
|
| 440 |
+
],
|
| 441 |
+
[
|
| 442 |
+
510,
|
| 443 |
+
0.8688
|
| 444 |
+
],
|
| 445 |
+
[
|
| 446 |
+
515,
|
| 447 |
+
0.6847
|
| 448 |
+
],
|
| 449 |
+
[
|
| 450 |
+
520,
|
| 451 |
+
0.7814
|
| 452 |
+
],
|
| 453 |
+
[
|
| 454 |
+
525,
|
| 455 |
+
0.7811
|
| 456 |
+
],
|
| 457 |
+
[
|
| 458 |
+
530,
|
| 459 |
+
0.7919
|
| 460 |
+
],
|
| 461 |
+
[
|
| 462 |
+
535,
|
| 463 |
+
0.8829
|
| 464 |
+
],
|
| 465 |
+
[
|
| 466 |
+
540,
|
| 467 |
+
0.7775
|
| 468 |
+
],
|
| 469 |
+
[
|
| 470 |
+
545,
|
| 471 |
+
0.7112
|
| 472 |
+
],
|
| 473 |
+
[
|
| 474 |
+
550,
|
| 475 |
+
0.7917
|
| 476 |
+
],
|
| 477 |
+
[
|
| 478 |
+
555,
|
| 479 |
+
0.769
|
| 480 |
+
],
|
| 481 |
+
[
|
| 482 |
+
560,
|
| 483 |
+
0.7328
|
| 484 |
+
],
|
| 485 |
+
[
|
| 486 |
+
565,
|
| 487 |
+
0.7695
|
| 488 |
+
],
|
| 489 |
+
[
|
| 490 |
+
570,
|
| 491 |
+
0.5831
|
| 492 |
+
],
|
| 493 |
+
[
|
| 494 |
+
575,
|
| 495 |
+
0.7399
|
| 496 |
+
],
|
| 497 |
+
[
|
| 498 |
+
580,
|
| 499 |
+
0.8321
|
| 500 |
+
],
|
| 501 |
+
[
|
| 502 |
+
585,
|
| 503 |
+
0.8167
|
| 504 |
+
],
|
| 505 |
+
[
|
| 506 |
+
590,
|
| 507 |
+
0.832
|
| 508 |
+
],
|
| 509 |
+
[
|
| 510 |
+
595,
|
| 511 |
+
0.7446
|
| 512 |
+
],
|
| 513 |
+
[
|
| 514 |
+
600,
|
| 515 |
+
0.698
|
| 516 |
+
],
|
| 517 |
+
[
|
| 518 |
+
605,
|
| 519 |
+
0.5891
|
| 520 |
+
],
|
| 521 |
+
[
|
| 522 |
+
610,
|
| 523 |
+
0.8106
|
| 524 |
+
],
|
| 525 |
+
[
|
| 526 |
+
615,
|
| 527 |
+
0.7455
|
| 528 |
+
],
|
| 529 |
+
[
|
| 530 |
+
620,
|
| 531 |
+
0.7738
|
| 532 |
+
],
|
| 533 |
+
[
|
| 534 |
+
625,
|
| 535 |
+
0.7939
|
| 536 |
+
],
|
| 537 |
+
[
|
| 538 |
+
630,
|
| 539 |
+
0.8003
|
| 540 |
+
],
|
| 541 |
+
[
|
| 542 |
+
635,
|
| 543 |
+
0.7349
|
| 544 |
+
],
|
| 545 |
+
[
|
| 546 |
+
640,
|
| 547 |
+
0.7863
|
| 548 |
+
],
|
| 549 |
+
[
|
| 550 |
+
645,
|
| 551 |
+
0.7968
|
| 552 |
+
],
|
| 553 |
+
[
|
| 554 |
+
650,
|
| 555 |
+
0.8229
|
| 556 |
+
],
|
| 557 |
+
[
|
| 558 |
+
655,
|
| 559 |
+
0.7529
|
| 560 |
+
],
|
| 561 |
+
[
|
| 562 |
+
660,
|
| 563 |
+
0.6354
|
| 564 |
+
],
|
| 565 |
+
[
|
| 566 |
+
665,
|
| 567 |
+
0.8064
|
| 568 |
+
],
|
| 569 |
+
[
|
| 570 |
+
670,
|
| 571 |
+
0.9099
|
| 572 |
+
],
|
| 573 |
+
[
|
| 574 |
+
675,
|
| 575 |
+
0.8156
|
| 576 |
+
],
|
| 577 |
+
[
|
| 578 |
+
680,
|
| 579 |
+
0.7462
|
| 580 |
+
],
|
| 581 |
+
[
|
| 582 |
+
685,
|
| 583 |
+
0.907
|
| 584 |
+
],
|
| 585 |
+
[
|
| 586 |
+
690,
|
| 587 |
+
0.8432
|
| 588 |
+
]
|
| 589 |
+
],
|
| 590 |
+
"eval": [
|
| 591 |
+
[
|
| 592 |
+
40,
|
| 593 |
+
2.072058916091919
|
| 594 |
+
],
|
| 595 |
+
[
|
| 596 |
+
80,
|
| 597 |
+
1.625858187675476
|
| 598 |
+
],
|
| 599 |
+
[
|
| 600 |
+
120,
|
| 601 |
+
1.4893486499786377
|
| 602 |
+
],
|
| 603 |
+
[
|
| 604 |
+
160,
|
| 605 |
+
1.359459400177002
|
| 606 |
+
],
|
| 607 |
+
[
|
| 608 |
+
200,
|
| 609 |
+
1.2217525243759155
|
| 610 |
+
],
|
| 611 |
+
[
|
| 612 |
+
240,
|
| 613 |
+
1.113280177116394
|
| 614 |
+
],
|
| 615 |
+
[
|
| 616 |
+
280,
|
| 617 |
+
1.0186439752578735
|
| 618 |
+
],
|
| 619 |
+
[
|
| 620 |
+
320,
|
| 621 |
+
0.937186598777771
|
| 622 |
+
],
|
| 623 |
+
[
|
| 624 |
+
360,
|
| 625 |
+
0.8894771337509155
|
| 626 |
+
],
|
| 627 |
+
[
|
| 628 |
+
400,
|
| 629 |
+
0.862065315246582
|
| 630 |
+
],
|
| 631 |
+
[
|
| 632 |
+
440,
|
| 633 |
+
0.8410201072692871
|
| 634 |
+
],
|
| 635 |
+
[
|
| 636 |
+
480,
|
| 637 |
+
0.8306860327720642
|
| 638 |
+
],
|
| 639 |
+
[
|
| 640 |
+
520,
|
| 641 |
+
0.8223150372505188
|
| 642 |
+
],
|
| 643 |
+
[
|
| 644 |
+
560,
|
| 645 |
+
0.8172081112861633
|
| 646 |
+
],
|
| 647 |
+
[
|
| 648 |
+
600,
|
| 649 |
+
0.8150315880775452
|
| 650 |
+
],
|
| 651 |
+
[
|
| 652 |
+
640,
|
| 653 |
+
0.8133148550987244
|
| 654 |
+
],
|
| 655 |
+
[
|
| 656 |
+
680,
|
| 657 |
+
0.8135352730751038
|
| 658 |
+
]
|
| 659 |
+
]
|
| 660 |
+
}
|
| 661 |
+
}
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|