Upload quantized model
Browse files- .ipynb_checkpoints/chat_template-checkpoint.jinja +86 -0
- config.json +2 -2
- generation_config.json +10 -3
- model-00001-of-00013.safetensors +2 -2
- model-00002-of-00013.safetensors +1 -1
- model-00003-of-00013.safetensors +1 -1
- model-00004-of-00013.safetensors +1 -1
- model-00005-of-00013.safetensors +1 -1
- model-00006-of-00013.safetensors +1 -1
- model-00007-of-00013.safetensors +1 -1
- model-00008-of-00013.safetensors +1 -1
- model-00009-of-00013.safetensors +1 -1
- model-00010-of-00013.safetensors +1 -1
- model-00011-of-00013.safetensors +1 -1
- model-00012-of-00013.safetensors +1 -1
- model-00013-of-00013.safetensors +2 -2
- model.safetensors.index.json +14 -14
- special_tokens_map.json +7 -1
- tokenizer_config.json +1 -1
.ipynb_checkpoints/chat_template-checkpoint.jinja
ADDED
|
@@ -0,0 +1,86 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{%- if tools %}
|
| 2 |
+
{{- '<|im_start|>system\n' }}
|
| 3 |
+
{%- if messages[0].role == 'system' %}
|
| 4 |
+
{{- messages[0].content + '\n\n' }}
|
| 5 |
+
{%- endif %}
|
| 6 |
+
{{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
|
| 7 |
+
{%- for tool in tools %}
|
| 8 |
+
{{- "\n" }}
|
| 9 |
+
{{- tool | tojson }}
|
| 10 |
+
{%- endfor %}
|
| 11 |
+
{{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
|
| 12 |
+
{%- else %}
|
| 13 |
+
{%- if messages[0].role == 'system' %}
|
| 14 |
+
{{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
|
| 15 |
+
{%- endif %}
|
| 16 |
+
{%- endif %}
|
| 17 |
+
{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
|
| 18 |
+
{%- for message in messages[::-1] %}
|
| 19 |
+
{%- set index = (messages|length - 1) - loop.index0 %}
|
| 20 |
+
{%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
|
| 21 |
+
{%- set ns.multi_step_tool = false %}
|
| 22 |
+
{%- set ns.last_query_index = index %}
|
| 23 |
+
{%- endif %}
|
| 24 |
+
{%- endfor %}
|
| 25 |
+
{%- for message in messages %}
|
| 26 |
+
{%- if message.content is string %}
|
| 27 |
+
{%- set content = message.content %}
|
| 28 |
+
{%- else %}
|
| 29 |
+
{%- set content = '' %}
|
| 30 |
+
{%- endif %}
|
| 31 |
+
{%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
|
| 32 |
+
{{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
|
| 33 |
+
{%- elif message.role == "assistant" %}
|
| 34 |
+
{%- set reasoning_content = '' %}
|
| 35 |
+
{%- if message.reasoning_content is string %}
|
| 36 |
+
{%- set reasoning_content = message.reasoning_content %}
|
| 37 |
+
{%- else %}
|
| 38 |
+
{%- if '</think>' in content %}
|
| 39 |
+
{%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
|
| 40 |
+
{%- set content = content.split('</think>')[-1].lstrip('\n') %}
|
| 41 |
+
{%- endif %}
|
| 42 |
+
{%- endif %}
|
| 43 |
+
{%- if loop.index0 > ns.last_query_index %}
|
| 44 |
+
{%- if loop.last or (not loop.last and reasoning_content) %}
|
| 45 |
+
{{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
|
| 46 |
+
{%- else %}
|
| 47 |
+
{{- '<|im_start|>' + message.role + '\n' + content }}
|
| 48 |
+
{%- endif %}
|
| 49 |
+
{%- else %}
|
| 50 |
+
{{- '<|im_start|>' + message.role + '\n' + content }}
|
| 51 |
+
{%- endif %}
|
| 52 |
+
{%- if message.tool_calls %}
|
| 53 |
+
{%- for tool_call in message.tool_calls %}
|
| 54 |
+
{%- if (loop.first and content) or (not loop.first) %}
|
| 55 |
+
{{- '\n' }}
|
| 56 |
+
{%- endif %}
|
| 57 |
+
{%- if tool_call.function %}
|
| 58 |
+
{%- set tool_call = tool_call.function %}
|
| 59 |
+
{%- endif %}
|
| 60 |
+
{{- '<tool_call>\n{"name": "' }}
|
| 61 |
+
{{- tool_call.name }}
|
| 62 |
+
{{- '", "arguments": ' }}
|
| 63 |
+
{%- if tool_call.arguments is string %}
|
| 64 |
+
{{- tool_call.arguments }}
|
| 65 |
+
{%- else %}
|
| 66 |
+
{{- tool_call.arguments | tojson }}
|
| 67 |
+
{%- endif %}
|
| 68 |
+
{{- '}\n</tool_call>' }}
|
| 69 |
+
{%- endfor %}
|
| 70 |
+
{%- endif %}
|
| 71 |
+
{{- '<|im_end|>\n' }}
|
| 72 |
+
{%- elif message.role == "tool" %}
|
| 73 |
+
{%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
|
| 74 |
+
{{- '<|im_start|>user' }}
|
| 75 |
+
{%- endif %}
|
| 76 |
+
{{- '\n<tool_response>\n' }}
|
| 77 |
+
{{- content }}
|
| 78 |
+
{{- '\n</tool_response>' }}
|
| 79 |
+
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
|
| 80 |
+
{{- '<|im_end|>\n' }}
|
| 81 |
+
{%- endif %}
|
| 82 |
+
{%- endif %}
|
| 83 |
+
{%- endfor %}
|
| 84 |
+
{%- if add_generation_prompt %}
|
| 85 |
+
{{- '<|im_start|>assistant\n' }}
|
| 86 |
+
{%- endif %}
|
config.json
CHANGED
|
@@ -31,8 +31,8 @@
|
|
| 31 |
"router_aux_loss_coef": 0.001,
|
| 32 |
"sliding_window": null,
|
| 33 |
"tie_word_embeddings": false,
|
| 34 |
-
"transformers_version": "4.
|
| 35 |
"use_cache": true,
|
| 36 |
"use_sliding_window": false,
|
| 37 |
-
"vocab_size":
|
| 38 |
}
|
|
|
|
| 31 |
"router_aux_loss_coef": 0.001,
|
| 32 |
"sliding_window": null,
|
| 33 |
"tie_word_embeddings": false,
|
| 34 |
+
"transformers_version": "4.57.1",
|
| 35 |
"use_cache": true,
|
| 36 |
"use_sliding_window": false,
|
| 37 |
+
"vocab_size": 151936
|
| 38 |
}
|
generation_config.json
CHANGED
|
@@ -1,6 +1,13 @@
|
|
| 1 |
{
|
| 2 |
-
"_from_model_config": true,
|
| 3 |
"bos_token_id": 151643,
|
| 4 |
-
"
|
| 5 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 6 |
}
|
|
|
|
| 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 |
+
"temperature": 0.6,
|
| 10 |
+
"top_k": 20,
|
| 11 |
+
"top_p": 0.95,
|
| 12 |
+
"transformers_version": "4.57.1"
|
| 13 |
}
|
model-00001-of-00013.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4aa8450ca63391bad06265b0ae7b718178856f166f999f65978879d872da42ad
|
| 3 |
+
size 4997184968
|
model-00002-of-00013.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4997741608
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:007e9ee0cd568cd37b0f13116d0e9bad865ca7fcfb834257b39b2465a1de92a9
|
| 3 |
size 4997741608
|
model-00003-of-00013.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4997742208
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f2b304de65e62ef7592fbce88874b435ffc811d3e2c235eed50cf2465369cdb5
|
| 3 |
size 4997742208
|
model-00004-of-00013.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4997743184
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:92966cc36e1ea040feee69dd6dd7a5c0c57c7d94d4156b0fd7c6a00a23719900
|
| 3 |
size 4997743184
|
model-00005-of-00013.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4997743184
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2f3d283ed68d7ea71f92a51f8acff58d066d787e5cb8b6a1708b4d6a338cc795
|
| 3 |
size 4997743184
|
model-00006-of-00013.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4997743184
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bd2c86ce5b45b1aa706a8ba4d51efeb828ae5d87b73a6e3a17a6e5f54d969b12
|
| 3 |
size 4997743184
|
model-00007-of-00013.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4997743184
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5402756b508dcc73e63aa3815e0a28d578d910e62ba567f8f6f9827cb13c7aaa
|
| 3 |
size 4997743184
|
model-00008-of-00013.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4997743184
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:54cdd133e5fee2c6a557405e69def75912e9536e87b26b77e1e6a4c9355ce3e7
|
| 3 |
size 4997743184
|
model-00009-of-00013.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4997743184
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cdbf105a0227a2569447761ed4db403080db9947902207fc06f9bd61fb76329d
|
| 3 |
size 4997743184
|
model-00010-of-00013.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4997743184
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:249cbce6282e957555c518610ae50b4ee98ddf5c2ea8ccfd693ac1c5b0807e0e
|
| 3 |
size 4997743184
|
model-00011-of-00013.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4997743184
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8768da1bae8b6f81b0639ea987b128c4269e10dcfc1a58164484f8f4c0ceda0b
|
| 3 |
size 4997743184
|
model-00012-of-00013.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4997743184
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5c47af572facc5db4caa396b23029f13a8fdc5d30a92f65c1b7e3053938a5e6f
|
| 3 |
size 4997743184
|
model-00013-of-00013.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d5c8479bed6cc760a2fe88c927ba37766212844ebb74ab09ef0beeab682b7289
|
| 3 |
+
size 1094220288
|
model.safetensors.index.json
CHANGED
|
@@ -1,7 +1,7 @@
|
|
| 1 |
{
|
| 2 |
"metadata": {
|
| 3 |
-
"total_parameters":
|
| 4 |
-
"total_size":
|
| 5 |
},
|
| 6 |
"weight_map": {
|
| 7 |
"lm_head.weight": "model-00013-of-00013.safetensors",
|
|
@@ -1460,7 +1460,7 @@
|
|
| 1460 |
"model.layers.11.mlp.experts.65.gate_proj.weight": "model-00003-of-00013.safetensors",
|
| 1461 |
"model.layers.11.mlp.experts.65.up_proj.weight": "model-00003-of-00013.safetensors",
|
| 1462 |
"model.layers.11.mlp.experts.66.down_proj.weight": "model-00004-of-00013.safetensors",
|
| 1463 |
-
"model.layers.11.mlp.experts.66.gate_proj.weight": "model-
|
| 1464 |
"model.layers.11.mlp.experts.66.up_proj.weight": "model-00004-of-00013.safetensors",
|
| 1465 |
"model.layers.11.mlp.experts.67.down_proj.weight": "model-00004-of-00013.safetensors",
|
| 1466 |
"model.layers.11.mlp.experts.67.gate_proj.weight": "model-00004-of-00013.safetensors",
|
|
@@ -3036,7 +3036,7 @@
|
|
| 3036 |
"model.layers.15.mlp.experts.66.up_proj.weight": "model-00004-of-00013.safetensors",
|
| 3037 |
"model.layers.15.mlp.experts.67.down_proj.weight": "model-00005-of-00013.safetensors",
|
| 3038 |
"model.layers.15.mlp.experts.67.gate_proj.weight": "model-00004-of-00013.safetensors",
|
| 3039 |
-
"model.layers.15.mlp.experts.67.up_proj.weight": "model-
|
| 3040 |
"model.layers.15.mlp.experts.68.down_proj.weight": "model-00005-of-00013.safetensors",
|
| 3041 |
"model.layers.15.mlp.experts.68.gate_proj.weight": "model-00005-of-00013.safetensors",
|
| 3042 |
"model.layers.15.mlp.experts.68.up_proj.weight": "model-00005-of-00013.safetensors",
|
|
@@ -4609,7 +4609,7 @@
|
|
| 4609 |
"model.layers.19.mlp.experts.67.down_proj.weight": "model-00005-of-00013.safetensors",
|
| 4610 |
"model.layers.19.mlp.experts.67.gate_proj.weight": "model-00005-of-00013.safetensors",
|
| 4611 |
"model.layers.19.mlp.experts.67.up_proj.weight": "model-00005-of-00013.safetensors",
|
| 4612 |
-
"model.layers.19.mlp.experts.68.down_proj.weight": "model-
|
| 4613 |
"model.layers.19.mlp.experts.68.gate_proj.weight": "model-00005-of-00013.safetensors",
|
| 4614 |
"model.layers.19.mlp.experts.68.up_proj.weight": "model-00005-of-00013.safetensors",
|
| 4615 |
"model.layers.19.mlp.experts.69.down_proj.weight": "model-00006-of-00013.safetensors",
|
|
@@ -6584,7 +6584,7 @@
|
|
| 6584 |
"model.layers.23.mlp.experts.7.gate_proj.weight": "model-00006-of-00013.safetensors",
|
| 6585 |
"model.layers.23.mlp.experts.7.up_proj.weight": "model-00006-of-00013.safetensors",
|
| 6586 |
"model.layers.23.mlp.experts.70.down_proj.weight": "model-00007-of-00013.safetensors",
|
| 6587 |
-
"model.layers.23.mlp.experts.70.gate_proj.weight": "model-
|
| 6588 |
"model.layers.23.mlp.experts.70.up_proj.weight": "model-00007-of-00013.safetensors",
|
| 6589 |
"model.layers.23.mlp.experts.71.down_proj.weight": "model-00007-of-00013.safetensors",
|
| 6590 |
"model.layers.23.mlp.experts.71.gate_proj.weight": "model-00007-of-00013.safetensors",
|
|
@@ -8160,7 +8160,7 @@
|
|
| 8160 |
"model.layers.27.mlp.experts.70.up_proj.weight": "model-00007-of-00013.safetensors",
|
| 8161 |
"model.layers.27.mlp.experts.71.down_proj.weight": "model-00008-of-00013.safetensors",
|
| 8162 |
"model.layers.27.mlp.experts.71.gate_proj.weight": "model-00007-of-00013.safetensors",
|
| 8163 |
-
"model.layers.27.mlp.experts.71.up_proj.weight": "model-
|
| 8164 |
"model.layers.27.mlp.experts.72.down_proj.weight": "model-00008-of-00013.safetensors",
|
| 8165 |
"model.layers.27.mlp.experts.72.gate_proj.weight": "model-00008-of-00013.safetensors",
|
| 8166 |
"model.layers.27.mlp.experts.72.up_proj.weight": "model-00008-of-00013.safetensors",
|
|
@@ -9312,7 +9312,7 @@
|
|
| 9312 |
"model.layers.3.mlp.experts.62.up_proj.weight": "model-00001-of-00013.safetensors",
|
| 9313 |
"model.layers.3.mlp.experts.63.down_proj.weight": "model-00002-of-00013.safetensors",
|
| 9314 |
"model.layers.3.mlp.experts.63.gate_proj.weight": "model-00001-of-00013.safetensors",
|
| 9315 |
-
"model.layers.3.mlp.experts.63.up_proj.weight": "model-
|
| 9316 |
"model.layers.3.mlp.experts.64.down_proj.weight": "model-00002-of-00013.safetensors",
|
| 9317 |
"model.layers.3.mlp.experts.64.gate_proj.weight": "model-00002-of-00013.safetensors",
|
| 9318 |
"model.layers.3.mlp.experts.64.up_proj.weight": "model-00002-of-00013.safetensors",
|
|
@@ -10126,7 +10126,7 @@
|
|
| 10126 |
"model.layers.31.mlp.experts.71.down_proj.weight": "model-00008-of-00013.safetensors",
|
| 10127 |
"model.layers.31.mlp.experts.71.gate_proj.weight": "model-00008-of-00013.safetensors",
|
| 10128 |
"model.layers.31.mlp.experts.71.up_proj.weight": "model-00008-of-00013.safetensors",
|
| 10129 |
-
"model.layers.31.mlp.experts.72.down_proj.weight": "model-
|
| 10130 |
"model.layers.31.mlp.experts.72.gate_proj.weight": "model-00008-of-00013.safetensors",
|
| 10131 |
"model.layers.31.mlp.experts.72.up_proj.weight": "model-00008-of-00013.safetensors",
|
| 10132 |
"model.layers.31.mlp.experts.73.down_proj.weight": "model-00009-of-00013.safetensors",
|
|
@@ -11705,7 +11705,7 @@
|
|
| 11705 |
"model.layers.35.mlp.experts.73.gate_proj.weight": "model-00009-of-00013.safetensors",
|
| 11706 |
"model.layers.35.mlp.experts.73.up_proj.weight": "model-00009-of-00013.safetensors",
|
| 11707 |
"model.layers.35.mlp.experts.74.down_proj.weight": "model-00010-of-00013.safetensors",
|
| 11708 |
-
"model.layers.35.mlp.experts.74.gate_proj.weight": "model-
|
| 11709 |
"model.layers.35.mlp.experts.74.up_proj.weight": "model-00010-of-00013.safetensors",
|
| 11710 |
"model.layers.35.mlp.experts.75.down_proj.weight": "model-00010-of-00013.safetensors",
|
| 11711 |
"model.layers.35.mlp.experts.75.gate_proj.weight": "model-00010-of-00013.safetensors",
|
|
@@ -13281,7 +13281,7 @@
|
|
| 13281 |
"model.layers.39.mlp.experts.74.up_proj.weight": "model-00010-of-00013.safetensors",
|
| 13282 |
"model.layers.39.mlp.experts.75.down_proj.weight": "model-00011-of-00013.safetensors",
|
| 13283 |
"model.layers.39.mlp.experts.75.gate_proj.weight": "model-00010-of-00013.safetensors",
|
| 13284 |
-
"model.layers.39.mlp.experts.75.up_proj.weight": "model-
|
| 13285 |
"model.layers.39.mlp.experts.76.down_proj.weight": "model-00011-of-00013.safetensors",
|
| 13286 |
"model.layers.39.mlp.experts.76.gate_proj.weight": "model-00011-of-00013.safetensors",
|
| 13287 |
"model.layers.39.mlp.experts.76.up_proj.weight": "model-00011-of-00013.safetensors",
|
|
@@ -15247,7 +15247,7 @@
|
|
| 15247 |
"model.layers.43.mlp.experts.75.down_proj.weight": "model-00011-of-00013.safetensors",
|
| 15248 |
"model.layers.43.mlp.experts.75.gate_proj.weight": "model-00011-of-00013.safetensors",
|
| 15249 |
"model.layers.43.mlp.experts.75.up_proj.weight": "model-00011-of-00013.safetensors",
|
| 15250 |
-
"model.layers.43.mlp.experts.76.down_proj.weight": "model-
|
| 15251 |
"model.layers.43.mlp.experts.76.gate_proj.weight": "model-00011-of-00013.safetensors",
|
| 15252 |
"model.layers.43.mlp.experts.76.up_proj.weight": "model-00011-of-00013.safetensors",
|
| 15253 |
"model.layers.43.mlp.experts.77.down_proj.weight": "model-00012-of-00013.safetensors",
|
|
@@ -16826,7 +16826,7 @@
|
|
| 16826 |
"model.layers.47.mlp.experts.77.gate_proj.weight": "model-00012-of-00013.safetensors",
|
| 16827 |
"model.layers.47.mlp.experts.77.up_proj.weight": "model-00012-of-00013.safetensors",
|
| 16828 |
"model.layers.47.mlp.experts.78.down_proj.weight": "model-00013-of-00013.safetensors",
|
| 16829 |
-
"model.layers.47.mlp.experts.78.gate_proj.weight": "model-
|
| 16830 |
"model.layers.47.mlp.experts.78.up_proj.weight": "model-00013-of-00013.safetensors",
|
| 16831 |
"model.layers.47.mlp.experts.79.down_proj.weight": "model-00013-of-00013.safetensors",
|
| 16832 |
"model.layers.47.mlp.experts.79.gate_proj.weight": "model-00013-of-00013.safetensors",
|
|
@@ -17959,7 +17959,7 @@
|
|
| 17959 |
"model.layers.7.mlp.experts.63.down_proj.weight": "model-00002-of-00013.safetensors",
|
| 17960 |
"model.layers.7.mlp.experts.63.gate_proj.weight": "model-00002-of-00013.safetensors",
|
| 17961 |
"model.layers.7.mlp.experts.63.up_proj.weight": "model-00002-of-00013.safetensors",
|
| 17962 |
-
"model.layers.7.mlp.experts.64.down_proj.weight": "model-
|
| 17963 |
"model.layers.7.mlp.experts.64.gate_proj.weight": "model-00002-of-00013.safetensors",
|
| 17964 |
"model.layers.7.mlp.experts.64.up_proj.weight": "model-00002-of-00013.safetensors",
|
| 17965 |
"model.layers.7.mlp.experts.65.down_proj.weight": "model-00003-of-00013.safetensors",
|
|
|
|
| 1 |
{
|
| 2 |
"metadata": {
|
| 3 |
+
"total_parameters": 30532122624,
|
| 4 |
+
"total_size": 61064245248
|
| 5 |
},
|
| 6 |
"weight_map": {
|
| 7 |
"lm_head.weight": "model-00013-of-00013.safetensors",
|
|
|
|
| 1460 |
"model.layers.11.mlp.experts.65.gate_proj.weight": "model-00003-of-00013.safetensors",
|
| 1461 |
"model.layers.11.mlp.experts.65.up_proj.weight": "model-00003-of-00013.safetensors",
|
| 1462 |
"model.layers.11.mlp.experts.66.down_proj.weight": "model-00004-of-00013.safetensors",
|
| 1463 |
+
"model.layers.11.mlp.experts.66.gate_proj.weight": "model-00004-of-00013.safetensors",
|
| 1464 |
"model.layers.11.mlp.experts.66.up_proj.weight": "model-00004-of-00013.safetensors",
|
| 1465 |
"model.layers.11.mlp.experts.67.down_proj.weight": "model-00004-of-00013.safetensors",
|
| 1466 |
"model.layers.11.mlp.experts.67.gate_proj.weight": "model-00004-of-00013.safetensors",
|
|
|
|
| 3036 |
"model.layers.15.mlp.experts.66.up_proj.weight": "model-00004-of-00013.safetensors",
|
| 3037 |
"model.layers.15.mlp.experts.67.down_proj.weight": "model-00005-of-00013.safetensors",
|
| 3038 |
"model.layers.15.mlp.experts.67.gate_proj.weight": "model-00004-of-00013.safetensors",
|
| 3039 |
+
"model.layers.15.mlp.experts.67.up_proj.weight": "model-00005-of-00013.safetensors",
|
| 3040 |
"model.layers.15.mlp.experts.68.down_proj.weight": "model-00005-of-00013.safetensors",
|
| 3041 |
"model.layers.15.mlp.experts.68.gate_proj.weight": "model-00005-of-00013.safetensors",
|
| 3042 |
"model.layers.15.mlp.experts.68.up_proj.weight": "model-00005-of-00013.safetensors",
|
|
|
|
| 4609 |
"model.layers.19.mlp.experts.67.down_proj.weight": "model-00005-of-00013.safetensors",
|
| 4610 |
"model.layers.19.mlp.experts.67.gate_proj.weight": "model-00005-of-00013.safetensors",
|
| 4611 |
"model.layers.19.mlp.experts.67.up_proj.weight": "model-00005-of-00013.safetensors",
|
| 4612 |
+
"model.layers.19.mlp.experts.68.down_proj.weight": "model-00006-of-00013.safetensors",
|
| 4613 |
"model.layers.19.mlp.experts.68.gate_proj.weight": "model-00005-of-00013.safetensors",
|
| 4614 |
"model.layers.19.mlp.experts.68.up_proj.weight": "model-00005-of-00013.safetensors",
|
| 4615 |
"model.layers.19.mlp.experts.69.down_proj.weight": "model-00006-of-00013.safetensors",
|
|
|
|
| 6584 |
"model.layers.23.mlp.experts.7.gate_proj.weight": "model-00006-of-00013.safetensors",
|
| 6585 |
"model.layers.23.mlp.experts.7.up_proj.weight": "model-00006-of-00013.safetensors",
|
| 6586 |
"model.layers.23.mlp.experts.70.down_proj.weight": "model-00007-of-00013.safetensors",
|
| 6587 |
+
"model.layers.23.mlp.experts.70.gate_proj.weight": "model-00007-of-00013.safetensors",
|
| 6588 |
"model.layers.23.mlp.experts.70.up_proj.weight": "model-00007-of-00013.safetensors",
|
| 6589 |
"model.layers.23.mlp.experts.71.down_proj.weight": "model-00007-of-00013.safetensors",
|
| 6590 |
"model.layers.23.mlp.experts.71.gate_proj.weight": "model-00007-of-00013.safetensors",
|
|
|
|
| 8160 |
"model.layers.27.mlp.experts.70.up_proj.weight": "model-00007-of-00013.safetensors",
|
| 8161 |
"model.layers.27.mlp.experts.71.down_proj.weight": "model-00008-of-00013.safetensors",
|
| 8162 |
"model.layers.27.mlp.experts.71.gate_proj.weight": "model-00007-of-00013.safetensors",
|
| 8163 |
+
"model.layers.27.mlp.experts.71.up_proj.weight": "model-00008-of-00013.safetensors",
|
| 8164 |
"model.layers.27.mlp.experts.72.down_proj.weight": "model-00008-of-00013.safetensors",
|
| 8165 |
"model.layers.27.mlp.experts.72.gate_proj.weight": "model-00008-of-00013.safetensors",
|
| 8166 |
"model.layers.27.mlp.experts.72.up_proj.weight": "model-00008-of-00013.safetensors",
|
|
|
|
| 9312 |
"model.layers.3.mlp.experts.62.up_proj.weight": "model-00001-of-00013.safetensors",
|
| 9313 |
"model.layers.3.mlp.experts.63.down_proj.weight": "model-00002-of-00013.safetensors",
|
| 9314 |
"model.layers.3.mlp.experts.63.gate_proj.weight": "model-00001-of-00013.safetensors",
|
| 9315 |
+
"model.layers.3.mlp.experts.63.up_proj.weight": "model-00002-of-00013.safetensors",
|
| 9316 |
"model.layers.3.mlp.experts.64.down_proj.weight": "model-00002-of-00013.safetensors",
|
| 9317 |
"model.layers.3.mlp.experts.64.gate_proj.weight": "model-00002-of-00013.safetensors",
|
| 9318 |
"model.layers.3.mlp.experts.64.up_proj.weight": "model-00002-of-00013.safetensors",
|
|
|
|
| 10126 |
"model.layers.31.mlp.experts.71.down_proj.weight": "model-00008-of-00013.safetensors",
|
| 10127 |
"model.layers.31.mlp.experts.71.gate_proj.weight": "model-00008-of-00013.safetensors",
|
| 10128 |
"model.layers.31.mlp.experts.71.up_proj.weight": "model-00008-of-00013.safetensors",
|
| 10129 |
+
"model.layers.31.mlp.experts.72.down_proj.weight": "model-00009-of-00013.safetensors",
|
| 10130 |
"model.layers.31.mlp.experts.72.gate_proj.weight": "model-00008-of-00013.safetensors",
|
| 10131 |
"model.layers.31.mlp.experts.72.up_proj.weight": "model-00008-of-00013.safetensors",
|
| 10132 |
"model.layers.31.mlp.experts.73.down_proj.weight": "model-00009-of-00013.safetensors",
|
|
|
|
| 11705 |
"model.layers.35.mlp.experts.73.gate_proj.weight": "model-00009-of-00013.safetensors",
|
| 11706 |
"model.layers.35.mlp.experts.73.up_proj.weight": "model-00009-of-00013.safetensors",
|
| 11707 |
"model.layers.35.mlp.experts.74.down_proj.weight": "model-00010-of-00013.safetensors",
|
| 11708 |
+
"model.layers.35.mlp.experts.74.gate_proj.weight": "model-00010-of-00013.safetensors",
|
| 11709 |
"model.layers.35.mlp.experts.74.up_proj.weight": "model-00010-of-00013.safetensors",
|
| 11710 |
"model.layers.35.mlp.experts.75.down_proj.weight": "model-00010-of-00013.safetensors",
|
| 11711 |
"model.layers.35.mlp.experts.75.gate_proj.weight": "model-00010-of-00013.safetensors",
|
|
|
|
| 13281 |
"model.layers.39.mlp.experts.74.up_proj.weight": "model-00010-of-00013.safetensors",
|
| 13282 |
"model.layers.39.mlp.experts.75.down_proj.weight": "model-00011-of-00013.safetensors",
|
| 13283 |
"model.layers.39.mlp.experts.75.gate_proj.weight": "model-00010-of-00013.safetensors",
|
| 13284 |
+
"model.layers.39.mlp.experts.75.up_proj.weight": "model-00011-of-00013.safetensors",
|
| 13285 |
"model.layers.39.mlp.experts.76.down_proj.weight": "model-00011-of-00013.safetensors",
|
| 13286 |
"model.layers.39.mlp.experts.76.gate_proj.weight": "model-00011-of-00013.safetensors",
|
| 13287 |
"model.layers.39.mlp.experts.76.up_proj.weight": "model-00011-of-00013.safetensors",
|
|
|
|
| 15247 |
"model.layers.43.mlp.experts.75.down_proj.weight": "model-00011-of-00013.safetensors",
|
| 15248 |
"model.layers.43.mlp.experts.75.gate_proj.weight": "model-00011-of-00013.safetensors",
|
| 15249 |
"model.layers.43.mlp.experts.75.up_proj.weight": "model-00011-of-00013.safetensors",
|
| 15250 |
+
"model.layers.43.mlp.experts.76.down_proj.weight": "model-00012-of-00013.safetensors",
|
| 15251 |
"model.layers.43.mlp.experts.76.gate_proj.weight": "model-00011-of-00013.safetensors",
|
| 15252 |
"model.layers.43.mlp.experts.76.up_proj.weight": "model-00011-of-00013.safetensors",
|
| 15253 |
"model.layers.43.mlp.experts.77.down_proj.weight": "model-00012-of-00013.safetensors",
|
|
|
|
| 16826 |
"model.layers.47.mlp.experts.77.gate_proj.weight": "model-00012-of-00013.safetensors",
|
| 16827 |
"model.layers.47.mlp.experts.77.up_proj.weight": "model-00012-of-00013.safetensors",
|
| 16828 |
"model.layers.47.mlp.experts.78.down_proj.weight": "model-00013-of-00013.safetensors",
|
| 16829 |
+
"model.layers.47.mlp.experts.78.gate_proj.weight": "model-00013-of-00013.safetensors",
|
| 16830 |
"model.layers.47.mlp.experts.78.up_proj.weight": "model-00013-of-00013.safetensors",
|
| 16831 |
"model.layers.47.mlp.experts.79.down_proj.weight": "model-00013-of-00013.safetensors",
|
| 16832 |
"model.layers.47.mlp.experts.79.gate_proj.weight": "model-00013-of-00013.safetensors",
|
|
|
|
| 17959 |
"model.layers.7.mlp.experts.63.down_proj.weight": "model-00002-of-00013.safetensors",
|
| 17960 |
"model.layers.7.mlp.experts.63.gate_proj.weight": "model-00002-of-00013.safetensors",
|
| 17961 |
"model.layers.7.mlp.experts.63.up_proj.weight": "model-00002-of-00013.safetensors",
|
| 17962 |
+
"model.layers.7.mlp.experts.64.down_proj.weight": "model-00003-of-00013.safetensors",
|
| 17963 |
"model.layers.7.mlp.experts.64.gate_proj.weight": "model-00002-of-00013.safetensors",
|
| 17964 |
"model.layers.7.mlp.experts.64.up_proj.weight": "model-00002-of-00013.safetensors",
|
| 17965 |
"model.layers.7.mlp.experts.65.down_proj.weight": "model-00003-of-00013.safetensors",
|
special_tokens_map.json
CHANGED
|
@@ -21,5 +21,11 @@
|
|
| 21 |
"rstrip": false,
|
| 22 |
"single_word": false
|
| 23 |
},
|
| 24 |
-
"pad_token":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 25 |
}
|
|
|
|
| 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_config.json
CHANGED
|
@@ -232,7 +232,7 @@
|
|
| 232 |
"errors": "replace",
|
| 233 |
"extra_special_tokens": {},
|
| 234 |
"model_max_length": 1010000,
|
| 235 |
-
"pad_token": "<|
|
| 236 |
"split_special_tokens": false,
|
| 237 |
"tokenizer_class": "Qwen2Tokenizer",
|
| 238 |
"unk_token": null
|
|
|
|
| 232 |
"errors": "replace",
|
| 233 |
"extra_special_tokens": {},
|
| 234 |
"model_max_length": 1010000,
|
| 235 |
+
"pad_token": "<|endoftext|>",
|
| 236 |
"split_special_tokens": false,
|
| 237 |
"tokenizer_class": "Qwen2Tokenizer",
|
| 238 |
"unk_token": null
|