add mtp
Browse filesThis view is limited to 50 files because it contains too many changes. See raw diff
- chat_template.jinja +101 -0
- config.json +785 -3
- generation_config.json +1 -1
- model-00001-of-00082.safetensors +3 -0
- model-00002-of-00082.safetensors +3 -0
- model-00003-of-00082.safetensors +3 -0
- model-00004-of-00082.safetensors +3 -0
- model-00005-of-00082.safetensors +3 -0
- model-00006-of-00082.safetensors +3 -0
- model-00007-of-00082.safetensors +3 -0
- model-00008-of-00082.safetensors +3 -0
- model-00009-of-00082.safetensors +3 -0
- model-00010-of-00082.safetensors +3 -0
- model-00011-of-00082.safetensors +3 -0
- model-00012-of-00082.safetensors +3 -0
- model-00013-of-00082.safetensors +3 -0
- model-00014-of-00082.safetensors +3 -0
- model-00015-of-00082.safetensors +3 -0
- model-00016-of-00082.safetensors +3 -0
- model-00017-of-00082.safetensors +3 -0
- model-00018-of-00082.safetensors +3 -0
- model-00019-of-00082.safetensors +3 -0
- model-00020-of-00082.safetensors +3 -0
- model-00021-of-00082.safetensors +3 -0
- model-00022-of-00082.safetensors +3 -0
- model-00023-of-00082.safetensors +3 -0
- model-00024-of-00082.safetensors +3 -0
- model-00025-of-00082.safetensors +3 -0
- model-00026-of-00082.safetensors +3 -0
- model-00027-of-00082.safetensors +3 -0
- model-00028-of-00082.safetensors +3 -0
- model-00029-of-00082.safetensors +3 -0
- model-00030-of-00082.safetensors +3 -0
- model-00031-of-00082.safetensors +3 -0
- model-00032-of-00082.safetensors +3 -0
- model-00033-of-00082.safetensors +3 -0
- model-00034-of-00082.safetensors +3 -0
- model-00035-of-00082.safetensors +3 -0
- model-00036-of-00082.safetensors +3 -0
- model-00037-of-00082.safetensors +3 -0
- model-00038-of-00082.safetensors +3 -0
- model-00039-of-00082.safetensors +3 -0
- model-00040-of-00082.safetensors +3 -0
- model-00041-of-00082.safetensors +3 -0
- model-00042-of-00082.safetensors +3 -0
- model-00043-of-00082.safetensors +3 -0
- model-00044-of-00082.safetensors +3 -0
- model-00045-of-00082.safetensors +3 -0
- model-00046-of-00082.safetensors +3 -0
- model-00047-of-00082.safetensors +3 -0
chat_template.jinja
ADDED
|
@@ -0,0 +1,101 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{%- if not add_generation_prompt is defined %}
|
| 2 |
+
{%- set add_generation_prompt = false %}
|
| 3 |
+
{%- endif %}
|
| 4 |
+
{%- set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='', is_first_sp=true, is_last_user=false) %}
|
| 5 |
+
{%- for message in messages %}
|
| 6 |
+
{%- if message['role'] == 'system' %}
|
| 7 |
+
{%- if ns.is_first_sp %}
|
| 8 |
+
{%- set ns.system_prompt = ns.system_prompt + message['content'] %}
|
| 9 |
+
{%- set ns.is_first_sp = false %}
|
| 10 |
+
{%- else %}
|
| 11 |
+
{%- set ns.system_prompt = ns.system_prompt + '\n\n' + message['content'] %}
|
| 12 |
+
{%- endif %}
|
| 13 |
+
{%- endif %}
|
| 14 |
+
{%- endfor %}
|
| 15 |
+
|
| 16 |
+
{#- Adapted from https://github.com/sgl-project/sglang/blob/main/examples/chat_template/tool_chat_template_deepseekr1.jinja #}
|
| 17 |
+
{%- if tools is defined and tools is not none %}
|
| 18 |
+
{%- set tool_ns = namespace(text='You are a helpful assistant with tool calling capabilities. ' + 'When a tool call is needed, you MUST use the following format to issue the call:\n' + '<|tool▁calls▁begin|><|tool▁call▁begin|>function<|tool▁sep|>FUNCTION_NAME\n' + '```json\n{"param1": "value1", "param2": "value2"}\n```<|tool▁call▁end|><|tool▁calls▁end|>\n\n' + 'Make sure the JSON is valid.' + '## Tools\n\n### Function\n\nYou have the following functions available:\n\n') %}
|
| 19 |
+
{%- for tool in tools %}
|
| 20 |
+
{%- set tool_ns.text = tool_ns.text + '\n```json\n' + (tool | tojson) + '\n```\n' %}
|
| 21 |
+
{%- endfor %}
|
| 22 |
+
{%- if ns.system_prompt|length != 0 %}
|
| 23 |
+
{%- set ns.system_prompt = ns.system_prompt + '\n\n' + tool_ns.text %}
|
| 24 |
+
{%- else %}
|
| 25 |
+
{%- set ns.system_prompt = tool_ns.text %}
|
| 26 |
+
{%- endif %}
|
| 27 |
+
{%- endif %}
|
| 28 |
+
{{- bos_token }}
|
| 29 |
+
{{- ns.system_prompt }}
|
| 30 |
+
{%- set last_index = (messages|length - 1) %}
|
| 31 |
+
{%- for message in messages %}
|
| 32 |
+
{%- set content = message['content'] %}
|
| 33 |
+
{%- if message['role'] == 'user' %}
|
| 34 |
+
{%- set ns.is_tool = false -%}
|
| 35 |
+
{%- set ns.is_first = false -%}
|
| 36 |
+
{%- set ns.is_last_user = true -%}
|
| 37 |
+
{%- if loop.index0 == last_index %}
|
| 38 |
+
{{- '<|User|>' + content }}
|
| 39 |
+
{%- else %}
|
| 40 |
+
{{- '<|User|>' + content + '<|Assistant|>'}}
|
| 41 |
+
{%- endif %}
|
| 42 |
+
{%- endif %}
|
| 43 |
+
{%- if message['role'] == 'assistant' %}
|
| 44 |
+
{%- if '</think>' in content %}
|
| 45 |
+
{%- set content = (content.split('</think>')|last) %}
|
| 46 |
+
{%- endif %}
|
| 47 |
+
{%- endif %}
|
| 48 |
+
{%- if message['role'] == 'assistant' and message['tool_calls'] is defined and message['tool_calls'] is not none %}
|
| 49 |
+
{%- set ns.is_last_user = false -%}
|
| 50 |
+
{%- if ns.is_tool %}
|
| 51 |
+
{{- '<|tool▁outputs▁end|>'}}
|
| 52 |
+
{%- endif %}
|
| 53 |
+
{%- set ns.is_first = false %}
|
| 54 |
+
{%- set ns.is_tool = false -%}
|
| 55 |
+
{%- set ns.is_output_first = true %}
|
| 56 |
+
{%- for tool in message['tool_calls'] %}
|
| 57 |
+
{%- set arguments = tool['function']['arguments'] %}
|
| 58 |
+
{%- if arguments is not string %}
|
| 59 |
+
{%- set arguments = arguments|tojson %}
|
| 60 |
+
{%- endif %}
|
| 61 |
+
{%- if not ns.is_first %}
|
| 62 |
+
{%- if content is none %}
|
| 63 |
+
{{- '<|tool▁calls▁begin|><|tool▁call▁begin|>' + tool['type'] + '<|tool▁sep|>' + tool['function']['name'] + '\n' + '```json' + '\n' + arguments + '\n' + '```' + '<|tool▁call▁end|>'}}
|
| 64 |
+
}
|
| 65 |
+
{%- else %}
|
| 66 |
+
{{- content + '<|tool▁calls▁begin|><|tool▁call▁begin|>' + tool['type'] + '<|tool▁sep|>' + tool['function']['name'] + '\n' + '```json' + '\n' + arguments + '\n' + '```' + '<|tool▁call▁end|>'}}
|
| 67 |
+
{%- endif %}
|
| 68 |
+
{%- set ns.is_first = true -%}
|
| 69 |
+
{%- else %}
|
| 70 |
+
{{- '\n' + '<|tool▁call▁begin|>' + tool['type'] + '<|tool▁sep|>' + tool['function']['name'] + '\n' + '```json' + '\n' + arguments + '\n' + '```' + '<|tool▁call▁end|>'}}
|
| 71 |
+
{%- endif %}
|
| 72 |
+
{%- endfor %}
|
| 73 |
+
{{- '<|tool▁calls▁end|><|end▁of▁sentence|>'}}
|
| 74 |
+
{%- endif %}
|
| 75 |
+
{%- if message['role'] == 'assistant' and (message['tool_calls'] is not defined or message['tool_calls'] is none) %}
|
| 76 |
+
{%- set ns.is_last_user = false -%}
|
| 77 |
+
{%- if ns.is_tool %}
|
| 78 |
+
{{- '<|tool▁outputs▁end|>' + content + '<|end▁of▁sentence|>'}}
|
| 79 |
+
{%- set ns.is_tool = false -%}
|
| 80 |
+
{%- else %}
|
| 81 |
+
{{- content + '<|end▁of▁sentence|>'}}
|
| 82 |
+
{%- endif %}
|
| 83 |
+
{%- endif %}
|
| 84 |
+
{%- if message['role'] == 'tool' %}
|
| 85 |
+
{%- set ns.is_last_user = false -%}
|
| 86 |
+
{%- set ns.is_tool = true -%}
|
| 87 |
+
{%- if ns.is_output_first %}
|
| 88 |
+
{{- '<|tool▁outputs▁begin|><|tool▁output▁begin|>' + content + '<|tool▁output▁end|>'}}
|
| 89 |
+
{%- set ns.is_output_first = false %}
|
| 90 |
+
{%- else %}
|
| 91 |
+
{{- '\n<|tool▁output▁begin|>' + content + '<|tool▁output▁end|>'}}
|
| 92 |
+
{%- endif %}
|
| 93 |
+
{%- endif %}
|
| 94 |
+
{%- endfor -%}
|
| 95 |
+
{%- if ns.is_tool %}
|
| 96 |
+
{{- '<|tool▁outputs▁end|>'}}
|
| 97 |
+
{%- endif %}
|
| 98 |
+
{#- if add_generation_prompt and not ns.is_last_user and not ns.is_tool #}
|
| 99 |
+
{%- if add_generation_prompt and not ns.is_tool %}
|
| 100 |
+
{{- '<|Assistant|>'}}
|
| 101 |
+
{%- endif %}
|
config.json
CHANGED
|
@@ -10,6 +10,7 @@
|
|
| 10 |
"AutoModelForCausalLM": "modeling_deepseek.DeepseekV3ForCausalLM"
|
| 11 |
},
|
| 12 |
"bos_token_id": 0,
|
|
|
|
| 13 |
"eos_token_id": 1,
|
| 14 |
"ep_size": 1,
|
| 15 |
"first_k_dense_replace": 3,
|
|
@@ -38,6 +39,7 @@
|
|
| 38 |
"quantization_config": {
|
| 39 |
"algo_config": null,
|
| 40 |
"exclude": [
|
|
|
|
| 41 |
"model.layers.0.self_attn.q_a_proj",
|
| 42 |
"model.layers.0.self_attn.q_b_proj",
|
| 43 |
"model.layers.0.self_attn.kv_a_proj_with_mqa",
|
|
@@ -343,6 +345,785 @@
|
|
| 343 |
"model.layers.60.self_attn.kv_a_proj_with_mqa",
|
| 344 |
"model.layers.60.self_attn.kv_b_proj",
|
| 345 |
"model.layers.60.self_attn.o_proj",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 346 |
"lm_head"
|
| 347 |
],
|
| 348 |
"export": {
|
|
@@ -387,12 +1168,14 @@
|
|
| 387 |
"symmetric": null
|
| 388 |
}
|
| 389 |
},
|
|
|
|
|
|
|
| 390 |
"layer_quant_config": {},
|
| 391 |
"layer_type_quant_config": {},
|
| 392 |
"quant_method": "quark",
|
| 393 |
"quant_mode": "eager_mode",
|
| 394 |
"softmax_quant_spec": null,
|
| 395 |
-
"version": "0.
|
| 396 |
},
|
| 397 |
"rms_norm_eps": 1e-06,
|
| 398 |
"rope_scaling": {
|
|
@@ -410,8 +1193,7 @@
|
|
| 410 |
"tie_word_embeddings": false,
|
| 411 |
"topk_group": 4,
|
| 412 |
"topk_method": "noaux_tc",
|
| 413 |
-
"
|
| 414 |
-
"transformers_version": "4.51.3",
|
| 415 |
"unsloth_fixed": true,
|
| 416 |
"use_cache": true,
|
| 417 |
"v_head_dim": 128,
|
|
|
|
| 10 |
"AutoModelForCausalLM": "modeling_deepseek.DeepseekV3ForCausalLM"
|
| 11 |
},
|
| 12 |
"bos_token_id": 0,
|
| 13 |
+
"dtype": "bfloat16",
|
| 14 |
"eos_token_id": 1,
|
| 15 |
"ep_size": 1,
|
| 16 |
"first_k_dense_replace": 3,
|
|
|
|
| 39 |
"quantization_config": {
|
| 40 |
"algo_config": null,
|
| 41 |
"exclude": [
|
| 42 |
+
"re:model.layers.61.*",
|
| 43 |
"model.layers.0.self_attn.q_a_proj",
|
| 44 |
"model.layers.0.self_attn.q_b_proj",
|
| 45 |
"model.layers.0.self_attn.kv_a_proj_with_mqa",
|
|
|
|
| 345 |
"model.layers.60.self_attn.kv_a_proj_with_mqa",
|
| 346 |
"model.layers.60.self_attn.kv_b_proj",
|
| 347 |
"model.layers.60.self_attn.o_proj",
|
| 348 |
+
"model.layers.61.embed_tokens",
|
| 349 |
+
"model.layers.61.eh_proj",
|
| 350 |
+
"model.layers.61.self_attn.q_a_proj",
|
| 351 |
+
"model.layers.61.self_attn.q_b_proj",
|
| 352 |
+
"model.layers.61.self_attn.kv_a_proj_with_mqa",
|
| 353 |
+
"model.layers.61.self_attn.kv_b_proj",
|
| 354 |
+
"model.layers.61.self_attn.o_proj",
|
| 355 |
+
"model.layers.61.mlp.experts.0.gate_proj",
|
| 356 |
+
"model.layers.61.mlp.experts.0.up_proj",
|
| 357 |
+
"model.layers.61.mlp.experts.0.down_proj",
|
| 358 |
+
"model.layers.61.mlp.experts.1.gate_proj",
|
| 359 |
+
"model.layers.61.mlp.experts.1.up_proj",
|
| 360 |
+
"model.layers.61.mlp.experts.1.down_proj",
|
| 361 |
+
"model.layers.61.mlp.experts.2.gate_proj",
|
| 362 |
+
"model.layers.61.mlp.experts.2.up_proj",
|
| 363 |
+
"model.layers.61.mlp.experts.2.down_proj",
|
| 364 |
+
"model.layers.61.mlp.experts.3.gate_proj",
|
| 365 |
+
"model.layers.61.mlp.experts.3.up_proj",
|
| 366 |
+
"model.layers.61.mlp.experts.3.down_proj",
|
| 367 |
+
"model.layers.61.mlp.experts.4.gate_proj",
|
| 368 |
+
"model.layers.61.mlp.experts.4.up_proj",
|
| 369 |
+
"model.layers.61.mlp.experts.4.down_proj",
|
| 370 |
+
"model.layers.61.mlp.experts.5.gate_proj",
|
| 371 |
+
"model.layers.61.mlp.experts.5.up_proj",
|
| 372 |
+
"model.layers.61.mlp.experts.5.down_proj",
|
| 373 |
+
"model.layers.61.mlp.experts.6.gate_proj",
|
| 374 |
+
"model.layers.61.mlp.experts.6.up_proj",
|
| 375 |
+
"model.layers.61.mlp.experts.6.down_proj",
|
| 376 |
+
"model.layers.61.mlp.experts.7.gate_proj",
|
| 377 |
+
"model.layers.61.mlp.experts.7.up_proj",
|
| 378 |
+
"model.layers.61.mlp.experts.7.down_proj",
|
| 379 |
+
"model.layers.61.mlp.experts.8.gate_proj",
|
| 380 |
+
"model.layers.61.mlp.experts.8.up_proj",
|
| 381 |
+
"model.layers.61.mlp.experts.8.down_proj",
|
| 382 |
+
"model.layers.61.mlp.experts.9.gate_proj",
|
| 383 |
+
"model.layers.61.mlp.experts.9.up_proj",
|
| 384 |
+
"model.layers.61.mlp.experts.9.down_proj",
|
| 385 |
+
"model.layers.61.mlp.experts.10.gate_proj",
|
| 386 |
+
"model.layers.61.mlp.experts.10.up_proj",
|
| 387 |
+
"model.layers.61.mlp.experts.10.down_proj",
|
| 388 |
+
"model.layers.61.mlp.experts.11.gate_proj",
|
| 389 |
+
"model.layers.61.mlp.experts.11.up_proj",
|
| 390 |
+
"model.layers.61.mlp.experts.11.down_proj",
|
| 391 |
+
"model.layers.61.mlp.experts.12.gate_proj",
|
| 392 |
+
"model.layers.61.mlp.experts.12.up_proj",
|
| 393 |
+
"model.layers.61.mlp.experts.12.down_proj",
|
| 394 |
+
"model.layers.61.mlp.experts.13.gate_proj",
|
| 395 |
+
"model.layers.61.mlp.experts.13.up_proj",
|
| 396 |
+
"model.layers.61.mlp.experts.13.down_proj",
|
| 397 |
+
"model.layers.61.mlp.experts.14.gate_proj",
|
| 398 |
+
"model.layers.61.mlp.experts.14.up_proj",
|
| 399 |
+
"model.layers.61.mlp.experts.14.down_proj",
|
| 400 |
+
"model.layers.61.mlp.experts.15.gate_proj",
|
| 401 |
+
"model.layers.61.mlp.experts.15.up_proj",
|
| 402 |
+
"model.layers.61.mlp.experts.15.down_proj",
|
| 403 |
+
"model.layers.61.mlp.experts.16.gate_proj",
|
| 404 |
+
"model.layers.61.mlp.experts.16.up_proj",
|
| 405 |
+
"model.layers.61.mlp.experts.16.down_proj",
|
| 406 |
+
"model.layers.61.mlp.experts.17.gate_proj",
|
| 407 |
+
"model.layers.61.mlp.experts.17.up_proj",
|
| 408 |
+
"model.layers.61.mlp.experts.17.down_proj",
|
| 409 |
+
"model.layers.61.mlp.experts.18.gate_proj",
|
| 410 |
+
"model.layers.61.mlp.experts.18.up_proj",
|
| 411 |
+
"model.layers.61.mlp.experts.18.down_proj",
|
| 412 |
+
"model.layers.61.mlp.experts.19.gate_proj",
|
| 413 |
+
"model.layers.61.mlp.experts.19.up_proj",
|
| 414 |
+
"model.layers.61.mlp.experts.19.down_proj",
|
| 415 |
+
"model.layers.61.mlp.experts.20.gate_proj",
|
| 416 |
+
"model.layers.61.mlp.experts.20.up_proj",
|
| 417 |
+
"model.layers.61.mlp.experts.20.down_proj",
|
| 418 |
+
"model.layers.61.mlp.experts.21.gate_proj",
|
| 419 |
+
"model.layers.61.mlp.experts.21.up_proj",
|
| 420 |
+
"model.layers.61.mlp.experts.21.down_proj",
|
| 421 |
+
"model.layers.61.mlp.experts.22.gate_proj",
|
| 422 |
+
"model.layers.61.mlp.experts.22.up_proj",
|
| 423 |
+
"model.layers.61.mlp.experts.22.down_proj",
|
| 424 |
+
"model.layers.61.mlp.experts.23.gate_proj",
|
| 425 |
+
"model.layers.61.mlp.experts.23.up_proj",
|
| 426 |
+
"model.layers.61.mlp.experts.23.down_proj",
|
| 427 |
+
"model.layers.61.mlp.experts.24.gate_proj",
|
| 428 |
+
"model.layers.61.mlp.experts.24.up_proj",
|
| 429 |
+
"model.layers.61.mlp.experts.24.down_proj",
|
| 430 |
+
"model.layers.61.mlp.experts.25.gate_proj",
|
| 431 |
+
"model.layers.61.mlp.experts.25.up_proj",
|
| 432 |
+
"model.layers.61.mlp.experts.25.down_proj",
|
| 433 |
+
"model.layers.61.mlp.experts.26.gate_proj",
|
| 434 |
+
"model.layers.61.mlp.experts.26.up_proj",
|
| 435 |
+
"model.layers.61.mlp.experts.26.down_proj",
|
| 436 |
+
"model.layers.61.mlp.experts.27.gate_proj",
|
| 437 |
+
"model.layers.61.mlp.experts.27.up_proj",
|
| 438 |
+
"model.layers.61.mlp.experts.27.down_proj",
|
| 439 |
+
"model.layers.61.mlp.experts.28.gate_proj",
|
| 440 |
+
"model.layers.61.mlp.experts.28.up_proj",
|
| 441 |
+
"model.layers.61.mlp.experts.28.down_proj",
|
| 442 |
+
"model.layers.61.mlp.experts.29.gate_proj",
|
| 443 |
+
"model.layers.61.mlp.experts.29.up_proj",
|
| 444 |
+
"model.layers.61.mlp.experts.29.down_proj",
|
| 445 |
+
"model.layers.61.mlp.experts.30.gate_proj",
|
| 446 |
+
"model.layers.61.mlp.experts.30.up_proj",
|
| 447 |
+
"model.layers.61.mlp.experts.30.down_proj",
|
| 448 |
+
"model.layers.61.mlp.experts.31.gate_proj",
|
| 449 |
+
"model.layers.61.mlp.experts.31.up_proj",
|
| 450 |
+
"model.layers.61.mlp.experts.31.down_proj",
|
| 451 |
+
"model.layers.61.mlp.experts.32.gate_proj",
|
| 452 |
+
"model.layers.61.mlp.experts.32.up_proj",
|
| 453 |
+
"model.layers.61.mlp.experts.32.down_proj",
|
| 454 |
+
"model.layers.61.mlp.experts.33.gate_proj",
|
| 455 |
+
"model.layers.61.mlp.experts.33.up_proj",
|
| 456 |
+
"model.layers.61.mlp.experts.33.down_proj",
|
| 457 |
+
"model.layers.61.mlp.experts.34.gate_proj",
|
| 458 |
+
"model.layers.61.mlp.experts.34.up_proj",
|
| 459 |
+
"model.layers.61.mlp.experts.34.down_proj",
|
| 460 |
+
"model.layers.61.mlp.experts.35.gate_proj",
|
| 461 |
+
"model.layers.61.mlp.experts.35.up_proj",
|
| 462 |
+
"model.layers.61.mlp.experts.35.down_proj",
|
| 463 |
+
"model.layers.61.mlp.experts.36.gate_proj",
|
| 464 |
+
"model.layers.61.mlp.experts.36.up_proj",
|
| 465 |
+
"model.layers.61.mlp.experts.36.down_proj",
|
| 466 |
+
"model.layers.61.mlp.experts.37.gate_proj",
|
| 467 |
+
"model.layers.61.mlp.experts.37.up_proj",
|
| 468 |
+
"model.layers.61.mlp.experts.37.down_proj",
|
| 469 |
+
"model.layers.61.mlp.experts.38.gate_proj",
|
| 470 |
+
"model.layers.61.mlp.experts.38.up_proj",
|
| 471 |
+
"model.layers.61.mlp.experts.38.down_proj",
|
| 472 |
+
"model.layers.61.mlp.experts.39.gate_proj",
|
| 473 |
+
"model.layers.61.mlp.experts.39.up_proj",
|
| 474 |
+
"model.layers.61.mlp.experts.39.down_proj",
|
| 475 |
+
"model.layers.61.mlp.experts.40.gate_proj",
|
| 476 |
+
"model.layers.61.mlp.experts.40.up_proj",
|
| 477 |
+
"model.layers.61.mlp.experts.40.down_proj",
|
| 478 |
+
"model.layers.61.mlp.experts.41.gate_proj",
|
| 479 |
+
"model.layers.61.mlp.experts.41.up_proj",
|
| 480 |
+
"model.layers.61.mlp.experts.41.down_proj",
|
| 481 |
+
"model.layers.61.mlp.experts.42.gate_proj",
|
| 482 |
+
"model.layers.61.mlp.experts.42.up_proj",
|
| 483 |
+
"model.layers.61.mlp.experts.42.down_proj",
|
| 484 |
+
"model.layers.61.mlp.experts.43.gate_proj",
|
| 485 |
+
"model.layers.61.mlp.experts.43.up_proj",
|
| 486 |
+
"model.layers.61.mlp.experts.43.down_proj",
|
| 487 |
+
"model.layers.61.mlp.experts.44.gate_proj",
|
| 488 |
+
"model.layers.61.mlp.experts.44.up_proj",
|
| 489 |
+
"model.layers.61.mlp.experts.44.down_proj",
|
| 490 |
+
"model.layers.61.mlp.experts.45.gate_proj",
|
| 491 |
+
"model.layers.61.mlp.experts.45.up_proj",
|
| 492 |
+
"model.layers.61.mlp.experts.45.down_proj",
|
| 493 |
+
"model.layers.61.mlp.experts.46.gate_proj",
|
| 494 |
+
"model.layers.61.mlp.experts.46.up_proj",
|
| 495 |
+
"model.layers.61.mlp.experts.46.down_proj",
|
| 496 |
+
"model.layers.61.mlp.experts.47.gate_proj",
|
| 497 |
+
"model.layers.61.mlp.experts.47.up_proj",
|
| 498 |
+
"model.layers.61.mlp.experts.47.down_proj",
|
| 499 |
+
"model.layers.61.mlp.experts.48.gate_proj",
|
| 500 |
+
"model.layers.61.mlp.experts.48.up_proj",
|
| 501 |
+
"model.layers.61.mlp.experts.48.down_proj",
|
| 502 |
+
"model.layers.61.mlp.experts.49.gate_proj",
|
| 503 |
+
"model.layers.61.mlp.experts.49.up_proj",
|
| 504 |
+
"model.layers.61.mlp.experts.49.down_proj",
|
| 505 |
+
"model.layers.61.mlp.experts.50.gate_proj",
|
| 506 |
+
"model.layers.61.mlp.experts.50.up_proj",
|
| 507 |
+
"model.layers.61.mlp.experts.50.down_proj",
|
| 508 |
+
"model.layers.61.mlp.experts.51.gate_proj",
|
| 509 |
+
"model.layers.61.mlp.experts.51.up_proj",
|
| 510 |
+
"model.layers.61.mlp.experts.51.down_proj",
|
| 511 |
+
"model.layers.61.mlp.experts.52.gate_proj",
|
| 512 |
+
"model.layers.61.mlp.experts.52.up_proj",
|
| 513 |
+
"model.layers.61.mlp.experts.52.down_proj",
|
| 514 |
+
"model.layers.61.mlp.experts.53.gate_proj",
|
| 515 |
+
"model.layers.61.mlp.experts.53.up_proj",
|
| 516 |
+
"model.layers.61.mlp.experts.53.down_proj",
|
| 517 |
+
"model.layers.61.mlp.experts.54.gate_proj",
|
| 518 |
+
"model.layers.61.mlp.experts.54.up_proj",
|
| 519 |
+
"model.layers.61.mlp.experts.54.down_proj",
|
| 520 |
+
"model.layers.61.mlp.experts.55.gate_proj",
|
| 521 |
+
"model.layers.61.mlp.experts.55.up_proj",
|
| 522 |
+
"model.layers.61.mlp.experts.55.down_proj",
|
| 523 |
+
"model.layers.61.mlp.experts.56.gate_proj",
|
| 524 |
+
"model.layers.61.mlp.experts.56.up_proj",
|
| 525 |
+
"model.layers.61.mlp.experts.56.down_proj",
|
| 526 |
+
"model.layers.61.mlp.experts.57.gate_proj",
|
| 527 |
+
"model.layers.61.mlp.experts.57.up_proj",
|
| 528 |
+
"model.layers.61.mlp.experts.57.down_proj",
|
| 529 |
+
"model.layers.61.mlp.experts.58.gate_proj",
|
| 530 |
+
"model.layers.61.mlp.experts.58.up_proj",
|
| 531 |
+
"model.layers.61.mlp.experts.58.down_proj",
|
| 532 |
+
"model.layers.61.mlp.experts.59.gate_proj",
|
| 533 |
+
"model.layers.61.mlp.experts.59.up_proj",
|
| 534 |
+
"model.layers.61.mlp.experts.59.down_proj",
|
| 535 |
+
"model.layers.61.mlp.experts.60.gate_proj",
|
| 536 |
+
"model.layers.61.mlp.experts.60.up_proj",
|
| 537 |
+
"model.layers.61.mlp.experts.60.down_proj",
|
| 538 |
+
"model.layers.61.mlp.experts.61.gate_proj",
|
| 539 |
+
"model.layers.61.mlp.experts.61.up_proj",
|
| 540 |
+
"model.layers.61.mlp.experts.61.down_proj",
|
| 541 |
+
"model.layers.61.mlp.experts.62.gate_proj",
|
| 542 |
+
"model.layers.61.mlp.experts.62.up_proj",
|
| 543 |
+
"model.layers.61.mlp.experts.62.down_proj",
|
| 544 |
+
"model.layers.61.mlp.experts.63.gate_proj",
|
| 545 |
+
"model.layers.61.mlp.experts.63.up_proj",
|
| 546 |
+
"model.layers.61.mlp.experts.63.down_proj",
|
| 547 |
+
"model.layers.61.mlp.experts.64.gate_proj",
|
| 548 |
+
"model.layers.61.mlp.experts.64.up_proj",
|
| 549 |
+
"model.layers.61.mlp.experts.64.down_proj",
|
| 550 |
+
"model.layers.61.mlp.experts.65.gate_proj",
|
| 551 |
+
"model.layers.61.mlp.experts.65.up_proj",
|
| 552 |
+
"model.layers.61.mlp.experts.65.down_proj",
|
| 553 |
+
"model.layers.61.mlp.experts.66.gate_proj",
|
| 554 |
+
"model.layers.61.mlp.experts.66.up_proj",
|
| 555 |
+
"model.layers.61.mlp.experts.66.down_proj",
|
| 556 |
+
"model.layers.61.mlp.experts.67.gate_proj",
|
| 557 |
+
"model.layers.61.mlp.experts.67.up_proj",
|
| 558 |
+
"model.layers.61.mlp.experts.67.down_proj",
|
| 559 |
+
"model.layers.61.mlp.experts.68.gate_proj",
|
| 560 |
+
"model.layers.61.mlp.experts.68.up_proj",
|
| 561 |
+
"model.layers.61.mlp.experts.68.down_proj",
|
| 562 |
+
"model.layers.61.mlp.experts.69.gate_proj",
|
| 563 |
+
"model.layers.61.mlp.experts.69.up_proj",
|
| 564 |
+
"model.layers.61.mlp.experts.69.down_proj",
|
| 565 |
+
"model.layers.61.mlp.experts.70.gate_proj",
|
| 566 |
+
"model.layers.61.mlp.experts.70.up_proj",
|
| 567 |
+
"model.layers.61.mlp.experts.70.down_proj",
|
| 568 |
+
"model.layers.61.mlp.experts.71.gate_proj",
|
| 569 |
+
"model.layers.61.mlp.experts.71.up_proj",
|
| 570 |
+
"model.layers.61.mlp.experts.71.down_proj",
|
| 571 |
+
"model.layers.61.mlp.experts.72.gate_proj",
|
| 572 |
+
"model.layers.61.mlp.experts.72.up_proj",
|
| 573 |
+
"model.layers.61.mlp.experts.72.down_proj",
|
| 574 |
+
"model.layers.61.mlp.experts.73.gate_proj",
|
| 575 |
+
"model.layers.61.mlp.experts.73.up_proj",
|
| 576 |
+
"model.layers.61.mlp.experts.73.down_proj",
|
| 577 |
+
"model.layers.61.mlp.experts.74.gate_proj",
|
| 578 |
+
"model.layers.61.mlp.experts.74.up_proj",
|
| 579 |
+
"model.layers.61.mlp.experts.74.down_proj",
|
| 580 |
+
"model.layers.61.mlp.experts.75.gate_proj",
|
| 581 |
+
"model.layers.61.mlp.experts.75.up_proj",
|
| 582 |
+
"model.layers.61.mlp.experts.75.down_proj",
|
| 583 |
+
"model.layers.61.mlp.experts.76.gate_proj",
|
| 584 |
+
"model.layers.61.mlp.experts.76.up_proj",
|
| 585 |
+
"model.layers.61.mlp.experts.76.down_proj",
|
| 586 |
+
"model.layers.61.mlp.experts.77.gate_proj",
|
| 587 |
+
"model.layers.61.mlp.experts.77.up_proj",
|
| 588 |
+
"model.layers.61.mlp.experts.77.down_proj",
|
| 589 |
+
"model.layers.61.mlp.experts.78.gate_proj",
|
| 590 |
+
"model.layers.61.mlp.experts.78.up_proj",
|
| 591 |
+
"model.layers.61.mlp.experts.78.down_proj",
|
| 592 |
+
"model.layers.61.mlp.experts.79.gate_proj",
|
| 593 |
+
"model.layers.61.mlp.experts.79.up_proj",
|
| 594 |
+
"model.layers.61.mlp.experts.79.down_proj",
|
| 595 |
+
"model.layers.61.mlp.experts.80.gate_proj",
|
| 596 |
+
"model.layers.61.mlp.experts.80.up_proj",
|
| 597 |
+
"model.layers.61.mlp.experts.80.down_proj",
|
| 598 |
+
"model.layers.61.mlp.experts.81.gate_proj",
|
| 599 |
+
"model.layers.61.mlp.experts.81.up_proj",
|
| 600 |
+
"model.layers.61.mlp.experts.81.down_proj",
|
| 601 |
+
"model.layers.61.mlp.experts.82.gate_proj",
|
| 602 |
+
"model.layers.61.mlp.experts.82.up_proj",
|
| 603 |
+
"model.layers.61.mlp.experts.82.down_proj",
|
| 604 |
+
"model.layers.61.mlp.experts.83.gate_proj",
|
| 605 |
+
"model.layers.61.mlp.experts.83.up_proj",
|
| 606 |
+
"model.layers.61.mlp.experts.83.down_proj",
|
| 607 |
+
"model.layers.61.mlp.experts.84.gate_proj",
|
| 608 |
+
"model.layers.61.mlp.experts.84.up_proj",
|
| 609 |
+
"model.layers.61.mlp.experts.84.down_proj",
|
| 610 |
+
"model.layers.61.mlp.experts.85.gate_proj",
|
| 611 |
+
"model.layers.61.mlp.experts.85.up_proj",
|
| 612 |
+
"model.layers.61.mlp.experts.85.down_proj",
|
| 613 |
+
"model.layers.61.mlp.experts.86.gate_proj",
|
| 614 |
+
"model.layers.61.mlp.experts.86.up_proj",
|
| 615 |
+
"model.layers.61.mlp.experts.86.down_proj",
|
| 616 |
+
"model.layers.61.mlp.experts.87.gate_proj",
|
| 617 |
+
"model.layers.61.mlp.experts.87.up_proj",
|
| 618 |
+
"model.layers.61.mlp.experts.87.down_proj",
|
| 619 |
+
"model.layers.61.mlp.experts.88.gate_proj",
|
| 620 |
+
"model.layers.61.mlp.experts.88.up_proj",
|
| 621 |
+
"model.layers.61.mlp.experts.88.down_proj",
|
| 622 |
+
"model.layers.61.mlp.experts.89.gate_proj",
|
| 623 |
+
"model.layers.61.mlp.experts.89.up_proj",
|
| 624 |
+
"model.layers.61.mlp.experts.89.down_proj",
|
| 625 |
+
"model.layers.61.mlp.experts.90.gate_proj",
|
| 626 |
+
"model.layers.61.mlp.experts.90.up_proj",
|
| 627 |
+
"model.layers.61.mlp.experts.90.down_proj",
|
| 628 |
+
"model.layers.61.mlp.experts.91.gate_proj",
|
| 629 |
+
"model.layers.61.mlp.experts.91.up_proj",
|
| 630 |
+
"model.layers.61.mlp.experts.91.down_proj",
|
| 631 |
+
"model.layers.61.mlp.experts.92.gate_proj",
|
| 632 |
+
"model.layers.61.mlp.experts.92.up_proj",
|
| 633 |
+
"model.layers.61.mlp.experts.92.down_proj",
|
| 634 |
+
"model.layers.61.mlp.experts.93.gate_proj",
|
| 635 |
+
"model.layers.61.mlp.experts.93.up_proj",
|
| 636 |
+
"model.layers.61.mlp.experts.93.down_proj",
|
| 637 |
+
"model.layers.61.mlp.experts.94.gate_proj",
|
| 638 |
+
"model.layers.61.mlp.experts.94.up_proj",
|
| 639 |
+
"model.layers.61.mlp.experts.94.down_proj",
|
| 640 |
+
"model.layers.61.mlp.experts.95.gate_proj",
|
| 641 |
+
"model.layers.61.mlp.experts.95.up_proj",
|
| 642 |
+
"model.layers.61.mlp.experts.95.down_proj",
|
| 643 |
+
"model.layers.61.mlp.experts.96.gate_proj",
|
| 644 |
+
"model.layers.61.mlp.experts.96.up_proj",
|
| 645 |
+
"model.layers.61.mlp.experts.96.down_proj",
|
| 646 |
+
"model.layers.61.mlp.experts.97.gate_proj",
|
| 647 |
+
"model.layers.61.mlp.experts.97.up_proj",
|
| 648 |
+
"model.layers.61.mlp.experts.97.down_proj",
|
| 649 |
+
"model.layers.61.mlp.experts.98.gate_proj",
|
| 650 |
+
"model.layers.61.mlp.experts.98.up_proj",
|
| 651 |
+
"model.layers.61.mlp.experts.98.down_proj",
|
| 652 |
+
"model.layers.61.mlp.experts.99.gate_proj",
|
| 653 |
+
"model.layers.61.mlp.experts.99.up_proj",
|
| 654 |
+
"model.layers.61.mlp.experts.99.down_proj",
|
| 655 |
+
"model.layers.61.mlp.experts.100.gate_proj",
|
| 656 |
+
"model.layers.61.mlp.experts.100.up_proj",
|
| 657 |
+
"model.layers.61.mlp.experts.100.down_proj",
|
| 658 |
+
"model.layers.61.mlp.experts.101.gate_proj",
|
| 659 |
+
"model.layers.61.mlp.experts.101.up_proj",
|
| 660 |
+
"model.layers.61.mlp.experts.101.down_proj",
|
| 661 |
+
"model.layers.61.mlp.experts.102.gate_proj",
|
| 662 |
+
"model.layers.61.mlp.experts.102.up_proj",
|
| 663 |
+
"model.layers.61.mlp.experts.102.down_proj",
|
| 664 |
+
"model.layers.61.mlp.experts.103.gate_proj",
|
| 665 |
+
"model.layers.61.mlp.experts.103.up_proj",
|
| 666 |
+
"model.layers.61.mlp.experts.103.down_proj",
|
| 667 |
+
"model.layers.61.mlp.experts.104.gate_proj",
|
| 668 |
+
"model.layers.61.mlp.experts.104.up_proj",
|
| 669 |
+
"model.layers.61.mlp.experts.104.down_proj",
|
| 670 |
+
"model.layers.61.mlp.experts.105.gate_proj",
|
| 671 |
+
"model.layers.61.mlp.experts.105.up_proj",
|
| 672 |
+
"model.layers.61.mlp.experts.105.down_proj",
|
| 673 |
+
"model.layers.61.mlp.experts.106.gate_proj",
|
| 674 |
+
"model.layers.61.mlp.experts.106.up_proj",
|
| 675 |
+
"model.layers.61.mlp.experts.106.down_proj",
|
| 676 |
+
"model.layers.61.mlp.experts.107.gate_proj",
|
| 677 |
+
"model.layers.61.mlp.experts.107.up_proj",
|
| 678 |
+
"model.layers.61.mlp.experts.107.down_proj",
|
| 679 |
+
"model.layers.61.mlp.experts.108.gate_proj",
|
| 680 |
+
"model.layers.61.mlp.experts.108.up_proj",
|
| 681 |
+
"model.layers.61.mlp.experts.108.down_proj",
|
| 682 |
+
"model.layers.61.mlp.experts.109.gate_proj",
|
| 683 |
+
"model.layers.61.mlp.experts.109.up_proj",
|
| 684 |
+
"model.layers.61.mlp.experts.109.down_proj",
|
| 685 |
+
"model.layers.61.mlp.experts.110.gate_proj",
|
| 686 |
+
"model.layers.61.mlp.experts.110.up_proj",
|
| 687 |
+
"model.layers.61.mlp.experts.110.down_proj",
|
| 688 |
+
"model.layers.61.mlp.experts.111.gate_proj",
|
| 689 |
+
"model.layers.61.mlp.experts.111.up_proj",
|
| 690 |
+
"model.layers.61.mlp.experts.111.down_proj",
|
| 691 |
+
"model.layers.61.mlp.experts.112.gate_proj",
|
| 692 |
+
"model.layers.61.mlp.experts.112.up_proj",
|
| 693 |
+
"model.layers.61.mlp.experts.112.down_proj",
|
| 694 |
+
"model.layers.61.mlp.experts.113.gate_proj",
|
| 695 |
+
"model.layers.61.mlp.experts.113.up_proj",
|
| 696 |
+
"model.layers.61.mlp.experts.113.down_proj",
|
| 697 |
+
"model.layers.61.mlp.experts.114.gate_proj",
|
| 698 |
+
"model.layers.61.mlp.experts.114.up_proj",
|
| 699 |
+
"model.layers.61.mlp.experts.114.down_proj",
|
| 700 |
+
"model.layers.61.mlp.experts.115.gate_proj",
|
| 701 |
+
"model.layers.61.mlp.experts.115.up_proj",
|
| 702 |
+
"model.layers.61.mlp.experts.115.down_proj",
|
| 703 |
+
"model.layers.61.mlp.experts.116.gate_proj",
|
| 704 |
+
"model.layers.61.mlp.experts.116.up_proj",
|
| 705 |
+
"model.layers.61.mlp.experts.116.down_proj",
|
| 706 |
+
"model.layers.61.mlp.experts.117.gate_proj",
|
| 707 |
+
"model.layers.61.mlp.experts.117.up_proj",
|
| 708 |
+
"model.layers.61.mlp.experts.117.down_proj",
|
| 709 |
+
"model.layers.61.mlp.experts.118.gate_proj",
|
| 710 |
+
"model.layers.61.mlp.experts.118.up_proj",
|
| 711 |
+
"model.layers.61.mlp.experts.118.down_proj",
|
| 712 |
+
"model.layers.61.mlp.experts.119.gate_proj",
|
| 713 |
+
"model.layers.61.mlp.experts.119.up_proj",
|
| 714 |
+
"model.layers.61.mlp.experts.119.down_proj",
|
| 715 |
+
"model.layers.61.mlp.experts.120.gate_proj",
|
| 716 |
+
"model.layers.61.mlp.experts.120.up_proj",
|
| 717 |
+
"model.layers.61.mlp.experts.120.down_proj",
|
| 718 |
+
"model.layers.61.mlp.experts.121.gate_proj",
|
| 719 |
+
"model.layers.61.mlp.experts.121.up_proj",
|
| 720 |
+
"model.layers.61.mlp.experts.121.down_proj",
|
| 721 |
+
"model.layers.61.mlp.experts.122.gate_proj",
|
| 722 |
+
"model.layers.61.mlp.experts.122.up_proj",
|
| 723 |
+
"model.layers.61.mlp.experts.122.down_proj",
|
| 724 |
+
"model.layers.61.mlp.experts.123.gate_proj",
|
| 725 |
+
"model.layers.61.mlp.experts.123.up_proj",
|
| 726 |
+
"model.layers.61.mlp.experts.123.down_proj",
|
| 727 |
+
"model.layers.61.mlp.experts.124.gate_proj",
|
| 728 |
+
"model.layers.61.mlp.experts.124.up_proj",
|
| 729 |
+
"model.layers.61.mlp.experts.124.down_proj",
|
| 730 |
+
"model.layers.61.mlp.experts.125.gate_proj",
|
| 731 |
+
"model.layers.61.mlp.experts.125.up_proj",
|
| 732 |
+
"model.layers.61.mlp.experts.125.down_proj",
|
| 733 |
+
"model.layers.61.mlp.experts.126.gate_proj",
|
| 734 |
+
"model.layers.61.mlp.experts.126.up_proj",
|
| 735 |
+
"model.layers.61.mlp.experts.126.down_proj",
|
| 736 |
+
"model.layers.61.mlp.experts.127.gate_proj",
|
| 737 |
+
"model.layers.61.mlp.experts.127.up_proj",
|
| 738 |
+
"model.layers.61.mlp.experts.127.down_proj",
|
| 739 |
+
"model.layers.61.mlp.experts.128.gate_proj",
|
| 740 |
+
"model.layers.61.mlp.experts.128.up_proj",
|
| 741 |
+
"model.layers.61.mlp.experts.128.down_proj",
|
| 742 |
+
"model.layers.61.mlp.experts.129.gate_proj",
|
| 743 |
+
"model.layers.61.mlp.experts.129.up_proj",
|
| 744 |
+
"model.layers.61.mlp.experts.129.down_proj",
|
| 745 |
+
"model.layers.61.mlp.experts.130.gate_proj",
|
| 746 |
+
"model.layers.61.mlp.experts.130.up_proj",
|
| 747 |
+
"model.layers.61.mlp.experts.130.down_proj",
|
| 748 |
+
"model.layers.61.mlp.experts.131.gate_proj",
|
| 749 |
+
"model.layers.61.mlp.experts.131.up_proj",
|
| 750 |
+
"model.layers.61.mlp.experts.131.down_proj",
|
| 751 |
+
"model.layers.61.mlp.experts.132.gate_proj",
|
| 752 |
+
"model.layers.61.mlp.experts.132.up_proj",
|
| 753 |
+
"model.layers.61.mlp.experts.132.down_proj",
|
| 754 |
+
"model.layers.61.mlp.experts.133.gate_proj",
|
| 755 |
+
"model.layers.61.mlp.experts.133.up_proj",
|
| 756 |
+
"model.layers.61.mlp.experts.133.down_proj",
|
| 757 |
+
"model.layers.61.mlp.experts.134.gate_proj",
|
| 758 |
+
"model.layers.61.mlp.experts.134.up_proj",
|
| 759 |
+
"model.layers.61.mlp.experts.134.down_proj",
|
| 760 |
+
"model.layers.61.mlp.experts.135.gate_proj",
|
| 761 |
+
"model.layers.61.mlp.experts.135.up_proj",
|
| 762 |
+
"model.layers.61.mlp.experts.135.down_proj",
|
| 763 |
+
"model.layers.61.mlp.experts.136.gate_proj",
|
| 764 |
+
"model.layers.61.mlp.experts.136.up_proj",
|
| 765 |
+
"model.layers.61.mlp.experts.136.down_proj",
|
| 766 |
+
"model.layers.61.mlp.experts.137.gate_proj",
|
| 767 |
+
"model.layers.61.mlp.experts.137.up_proj",
|
| 768 |
+
"model.layers.61.mlp.experts.137.down_proj",
|
| 769 |
+
"model.layers.61.mlp.experts.138.gate_proj",
|
| 770 |
+
"model.layers.61.mlp.experts.138.up_proj",
|
| 771 |
+
"model.layers.61.mlp.experts.138.down_proj",
|
| 772 |
+
"model.layers.61.mlp.experts.139.gate_proj",
|
| 773 |
+
"model.layers.61.mlp.experts.139.up_proj",
|
| 774 |
+
"model.layers.61.mlp.experts.139.down_proj",
|
| 775 |
+
"model.layers.61.mlp.experts.140.gate_proj",
|
| 776 |
+
"model.layers.61.mlp.experts.140.up_proj",
|
| 777 |
+
"model.layers.61.mlp.experts.140.down_proj",
|
| 778 |
+
"model.layers.61.mlp.experts.141.gate_proj",
|
| 779 |
+
"model.layers.61.mlp.experts.141.up_proj",
|
| 780 |
+
"model.layers.61.mlp.experts.141.down_proj",
|
| 781 |
+
"model.layers.61.mlp.experts.142.gate_proj",
|
| 782 |
+
"model.layers.61.mlp.experts.142.up_proj",
|
| 783 |
+
"model.layers.61.mlp.experts.142.down_proj",
|
| 784 |
+
"model.layers.61.mlp.experts.143.gate_proj",
|
| 785 |
+
"model.layers.61.mlp.experts.143.up_proj",
|
| 786 |
+
"model.layers.61.mlp.experts.143.down_proj",
|
| 787 |
+
"model.layers.61.mlp.experts.144.gate_proj",
|
| 788 |
+
"model.layers.61.mlp.experts.144.up_proj",
|
| 789 |
+
"model.layers.61.mlp.experts.144.down_proj",
|
| 790 |
+
"model.layers.61.mlp.experts.145.gate_proj",
|
| 791 |
+
"model.layers.61.mlp.experts.145.up_proj",
|
| 792 |
+
"model.layers.61.mlp.experts.145.down_proj",
|
| 793 |
+
"model.layers.61.mlp.experts.146.gate_proj",
|
| 794 |
+
"model.layers.61.mlp.experts.146.up_proj",
|
| 795 |
+
"model.layers.61.mlp.experts.146.down_proj",
|
| 796 |
+
"model.layers.61.mlp.experts.147.gate_proj",
|
| 797 |
+
"model.layers.61.mlp.experts.147.up_proj",
|
| 798 |
+
"model.layers.61.mlp.experts.147.down_proj",
|
| 799 |
+
"model.layers.61.mlp.experts.148.gate_proj",
|
| 800 |
+
"model.layers.61.mlp.experts.148.up_proj",
|
| 801 |
+
"model.layers.61.mlp.experts.148.down_proj",
|
| 802 |
+
"model.layers.61.mlp.experts.149.gate_proj",
|
| 803 |
+
"model.layers.61.mlp.experts.149.up_proj",
|
| 804 |
+
"model.layers.61.mlp.experts.149.down_proj",
|
| 805 |
+
"model.layers.61.mlp.experts.150.gate_proj",
|
| 806 |
+
"model.layers.61.mlp.experts.150.up_proj",
|
| 807 |
+
"model.layers.61.mlp.experts.150.down_proj",
|
| 808 |
+
"model.layers.61.mlp.experts.151.gate_proj",
|
| 809 |
+
"model.layers.61.mlp.experts.151.up_proj",
|
| 810 |
+
"model.layers.61.mlp.experts.151.down_proj",
|
| 811 |
+
"model.layers.61.mlp.experts.152.gate_proj",
|
| 812 |
+
"model.layers.61.mlp.experts.152.up_proj",
|
| 813 |
+
"model.layers.61.mlp.experts.152.down_proj",
|
| 814 |
+
"model.layers.61.mlp.experts.153.gate_proj",
|
| 815 |
+
"model.layers.61.mlp.experts.153.up_proj",
|
| 816 |
+
"model.layers.61.mlp.experts.153.down_proj",
|
| 817 |
+
"model.layers.61.mlp.experts.154.gate_proj",
|
| 818 |
+
"model.layers.61.mlp.experts.154.up_proj",
|
| 819 |
+
"model.layers.61.mlp.experts.154.down_proj",
|
| 820 |
+
"model.layers.61.mlp.experts.155.gate_proj",
|
| 821 |
+
"model.layers.61.mlp.experts.155.up_proj",
|
| 822 |
+
"model.layers.61.mlp.experts.155.down_proj",
|
| 823 |
+
"model.layers.61.mlp.experts.156.gate_proj",
|
| 824 |
+
"model.layers.61.mlp.experts.156.up_proj",
|
| 825 |
+
"model.layers.61.mlp.experts.156.down_proj",
|
| 826 |
+
"model.layers.61.mlp.experts.157.gate_proj",
|
| 827 |
+
"model.layers.61.mlp.experts.157.up_proj",
|
| 828 |
+
"model.layers.61.mlp.experts.157.down_proj",
|
| 829 |
+
"model.layers.61.mlp.experts.158.gate_proj",
|
| 830 |
+
"model.layers.61.mlp.experts.158.up_proj",
|
| 831 |
+
"model.layers.61.mlp.experts.158.down_proj",
|
| 832 |
+
"model.layers.61.mlp.experts.159.gate_proj",
|
| 833 |
+
"model.layers.61.mlp.experts.159.up_proj",
|
| 834 |
+
"model.layers.61.mlp.experts.159.down_proj",
|
| 835 |
+
"model.layers.61.mlp.experts.160.gate_proj",
|
| 836 |
+
"model.layers.61.mlp.experts.160.up_proj",
|
| 837 |
+
"model.layers.61.mlp.experts.160.down_proj",
|
| 838 |
+
"model.layers.61.mlp.experts.161.gate_proj",
|
| 839 |
+
"model.layers.61.mlp.experts.161.up_proj",
|
| 840 |
+
"model.layers.61.mlp.experts.161.down_proj",
|
| 841 |
+
"model.layers.61.mlp.experts.162.gate_proj",
|
| 842 |
+
"model.layers.61.mlp.experts.162.up_proj",
|
| 843 |
+
"model.layers.61.mlp.experts.162.down_proj",
|
| 844 |
+
"model.layers.61.mlp.experts.163.gate_proj",
|
| 845 |
+
"model.layers.61.mlp.experts.163.up_proj",
|
| 846 |
+
"model.layers.61.mlp.experts.163.down_proj",
|
| 847 |
+
"model.layers.61.mlp.experts.164.gate_proj",
|
| 848 |
+
"model.layers.61.mlp.experts.164.up_proj",
|
| 849 |
+
"model.layers.61.mlp.experts.164.down_proj",
|
| 850 |
+
"model.layers.61.mlp.experts.165.gate_proj",
|
| 851 |
+
"model.layers.61.mlp.experts.165.up_proj",
|
| 852 |
+
"model.layers.61.mlp.experts.165.down_proj",
|
| 853 |
+
"model.layers.61.mlp.experts.166.gate_proj",
|
| 854 |
+
"model.layers.61.mlp.experts.166.up_proj",
|
| 855 |
+
"model.layers.61.mlp.experts.166.down_proj",
|
| 856 |
+
"model.layers.61.mlp.experts.167.gate_proj",
|
| 857 |
+
"model.layers.61.mlp.experts.167.up_proj",
|
| 858 |
+
"model.layers.61.mlp.experts.167.down_proj",
|
| 859 |
+
"model.layers.61.mlp.experts.168.gate_proj",
|
| 860 |
+
"model.layers.61.mlp.experts.168.up_proj",
|
| 861 |
+
"model.layers.61.mlp.experts.168.down_proj",
|
| 862 |
+
"model.layers.61.mlp.experts.169.gate_proj",
|
| 863 |
+
"model.layers.61.mlp.experts.169.up_proj",
|
| 864 |
+
"model.layers.61.mlp.experts.169.down_proj",
|
| 865 |
+
"model.layers.61.mlp.experts.170.gate_proj",
|
| 866 |
+
"model.layers.61.mlp.experts.170.up_proj",
|
| 867 |
+
"model.layers.61.mlp.experts.170.down_proj",
|
| 868 |
+
"model.layers.61.mlp.experts.171.gate_proj",
|
| 869 |
+
"model.layers.61.mlp.experts.171.up_proj",
|
| 870 |
+
"model.layers.61.mlp.experts.171.down_proj",
|
| 871 |
+
"model.layers.61.mlp.experts.172.gate_proj",
|
| 872 |
+
"model.layers.61.mlp.experts.172.up_proj",
|
| 873 |
+
"model.layers.61.mlp.experts.172.down_proj",
|
| 874 |
+
"model.layers.61.mlp.experts.173.gate_proj",
|
| 875 |
+
"model.layers.61.mlp.experts.173.up_proj",
|
| 876 |
+
"model.layers.61.mlp.experts.173.down_proj",
|
| 877 |
+
"model.layers.61.mlp.experts.174.gate_proj",
|
| 878 |
+
"model.layers.61.mlp.experts.174.up_proj",
|
| 879 |
+
"model.layers.61.mlp.experts.174.down_proj",
|
| 880 |
+
"model.layers.61.mlp.experts.175.gate_proj",
|
| 881 |
+
"model.layers.61.mlp.experts.175.up_proj",
|
| 882 |
+
"model.layers.61.mlp.experts.175.down_proj",
|
| 883 |
+
"model.layers.61.mlp.experts.176.gate_proj",
|
| 884 |
+
"model.layers.61.mlp.experts.176.up_proj",
|
| 885 |
+
"model.layers.61.mlp.experts.176.down_proj",
|
| 886 |
+
"model.layers.61.mlp.experts.177.gate_proj",
|
| 887 |
+
"model.layers.61.mlp.experts.177.up_proj",
|
| 888 |
+
"model.layers.61.mlp.experts.177.down_proj",
|
| 889 |
+
"model.layers.61.mlp.experts.178.gate_proj",
|
| 890 |
+
"model.layers.61.mlp.experts.178.up_proj",
|
| 891 |
+
"model.layers.61.mlp.experts.178.down_proj",
|
| 892 |
+
"model.layers.61.mlp.experts.179.gate_proj",
|
| 893 |
+
"model.layers.61.mlp.experts.179.up_proj",
|
| 894 |
+
"model.layers.61.mlp.experts.179.down_proj",
|
| 895 |
+
"model.layers.61.mlp.experts.180.gate_proj",
|
| 896 |
+
"model.layers.61.mlp.experts.180.up_proj",
|
| 897 |
+
"model.layers.61.mlp.experts.180.down_proj",
|
| 898 |
+
"model.layers.61.mlp.experts.181.gate_proj",
|
| 899 |
+
"model.layers.61.mlp.experts.181.up_proj",
|
| 900 |
+
"model.layers.61.mlp.experts.181.down_proj",
|
| 901 |
+
"model.layers.61.mlp.experts.182.gate_proj",
|
| 902 |
+
"model.layers.61.mlp.experts.182.up_proj",
|
| 903 |
+
"model.layers.61.mlp.experts.182.down_proj",
|
| 904 |
+
"model.layers.61.mlp.experts.183.gate_proj",
|
| 905 |
+
"model.layers.61.mlp.experts.183.up_proj",
|
| 906 |
+
"model.layers.61.mlp.experts.183.down_proj",
|
| 907 |
+
"model.layers.61.mlp.experts.184.gate_proj",
|
| 908 |
+
"model.layers.61.mlp.experts.184.up_proj",
|
| 909 |
+
"model.layers.61.mlp.experts.184.down_proj",
|
| 910 |
+
"model.layers.61.mlp.experts.185.gate_proj",
|
| 911 |
+
"model.layers.61.mlp.experts.185.up_proj",
|
| 912 |
+
"model.layers.61.mlp.experts.185.down_proj",
|
| 913 |
+
"model.layers.61.mlp.experts.186.gate_proj",
|
| 914 |
+
"model.layers.61.mlp.experts.186.up_proj",
|
| 915 |
+
"model.layers.61.mlp.experts.186.down_proj",
|
| 916 |
+
"model.layers.61.mlp.experts.187.gate_proj",
|
| 917 |
+
"model.layers.61.mlp.experts.187.up_proj",
|
| 918 |
+
"model.layers.61.mlp.experts.187.down_proj",
|
| 919 |
+
"model.layers.61.mlp.experts.188.gate_proj",
|
| 920 |
+
"model.layers.61.mlp.experts.188.up_proj",
|
| 921 |
+
"model.layers.61.mlp.experts.188.down_proj",
|
| 922 |
+
"model.layers.61.mlp.experts.189.gate_proj",
|
| 923 |
+
"model.layers.61.mlp.experts.189.up_proj",
|
| 924 |
+
"model.layers.61.mlp.experts.189.down_proj",
|
| 925 |
+
"model.layers.61.mlp.experts.190.gate_proj",
|
| 926 |
+
"model.layers.61.mlp.experts.190.up_proj",
|
| 927 |
+
"model.layers.61.mlp.experts.190.down_proj",
|
| 928 |
+
"model.layers.61.mlp.experts.191.gate_proj",
|
| 929 |
+
"model.layers.61.mlp.experts.191.up_proj",
|
| 930 |
+
"model.layers.61.mlp.experts.191.down_proj",
|
| 931 |
+
"model.layers.61.mlp.experts.192.gate_proj",
|
| 932 |
+
"model.layers.61.mlp.experts.192.up_proj",
|
| 933 |
+
"model.layers.61.mlp.experts.192.down_proj",
|
| 934 |
+
"model.layers.61.mlp.experts.193.gate_proj",
|
| 935 |
+
"model.layers.61.mlp.experts.193.up_proj",
|
| 936 |
+
"model.layers.61.mlp.experts.193.down_proj",
|
| 937 |
+
"model.layers.61.mlp.experts.194.gate_proj",
|
| 938 |
+
"model.layers.61.mlp.experts.194.up_proj",
|
| 939 |
+
"model.layers.61.mlp.experts.194.down_proj",
|
| 940 |
+
"model.layers.61.mlp.experts.195.gate_proj",
|
| 941 |
+
"model.layers.61.mlp.experts.195.up_proj",
|
| 942 |
+
"model.layers.61.mlp.experts.195.down_proj",
|
| 943 |
+
"model.layers.61.mlp.experts.196.gate_proj",
|
| 944 |
+
"model.layers.61.mlp.experts.196.up_proj",
|
| 945 |
+
"model.layers.61.mlp.experts.196.down_proj",
|
| 946 |
+
"model.layers.61.mlp.experts.197.gate_proj",
|
| 947 |
+
"model.layers.61.mlp.experts.197.up_proj",
|
| 948 |
+
"model.layers.61.mlp.experts.197.down_proj",
|
| 949 |
+
"model.layers.61.mlp.experts.198.gate_proj",
|
| 950 |
+
"model.layers.61.mlp.experts.198.up_proj",
|
| 951 |
+
"model.layers.61.mlp.experts.198.down_proj",
|
| 952 |
+
"model.layers.61.mlp.experts.199.gate_proj",
|
| 953 |
+
"model.layers.61.mlp.experts.199.up_proj",
|
| 954 |
+
"model.layers.61.mlp.experts.199.down_proj",
|
| 955 |
+
"model.layers.61.mlp.experts.200.gate_proj",
|
| 956 |
+
"model.layers.61.mlp.experts.200.up_proj",
|
| 957 |
+
"model.layers.61.mlp.experts.200.down_proj",
|
| 958 |
+
"model.layers.61.mlp.experts.201.gate_proj",
|
| 959 |
+
"model.layers.61.mlp.experts.201.up_proj",
|
| 960 |
+
"model.layers.61.mlp.experts.201.down_proj",
|
| 961 |
+
"model.layers.61.mlp.experts.202.gate_proj",
|
| 962 |
+
"model.layers.61.mlp.experts.202.up_proj",
|
| 963 |
+
"model.layers.61.mlp.experts.202.down_proj",
|
| 964 |
+
"model.layers.61.mlp.experts.203.gate_proj",
|
| 965 |
+
"model.layers.61.mlp.experts.203.up_proj",
|
| 966 |
+
"model.layers.61.mlp.experts.203.down_proj",
|
| 967 |
+
"model.layers.61.mlp.experts.204.gate_proj",
|
| 968 |
+
"model.layers.61.mlp.experts.204.up_proj",
|
| 969 |
+
"model.layers.61.mlp.experts.204.down_proj",
|
| 970 |
+
"model.layers.61.mlp.experts.205.gate_proj",
|
| 971 |
+
"model.layers.61.mlp.experts.205.up_proj",
|
| 972 |
+
"model.layers.61.mlp.experts.205.down_proj",
|
| 973 |
+
"model.layers.61.mlp.experts.206.gate_proj",
|
| 974 |
+
"model.layers.61.mlp.experts.206.up_proj",
|
| 975 |
+
"model.layers.61.mlp.experts.206.down_proj",
|
| 976 |
+
"model.layers.61.mlp.experts.207.gate_proj",
|
| 977 |
+
"model.layers.61.mlp.experts.207.up_proj",
|
| 978 |
+
"model.layers.61.mlp.experts.207.down_proj",
|
| 979 |
+
"model.layers.61.mlp.experts.208.gate_proj",
|
| 980 |
+
"model.layers.61.mlp.experts.208.up_proj",
|
| 981 |
+
"model.layers.61.mlp.experts.208.down_proj",
|
| 982 |
+
"model.layers.61.mlp.experts.209.gate_proj",
|
| 983 |
+
"model.layers.61.mlp.experts.209.up_proj",
|
| 984 |
+
"model.layers.61.mlp.experts.209.down_proj",
|
| 985 |
+
"model.layers.61.mlp.experts.210.gate_proj",
|
| 986 |
+
"model.layers.61.mlp.experts.210.up_proj",
|
| 987 |
+
"model.layers.61.mlp.experts.210.down_proj",
|
| 988 |
+
"model.layers.61.mlp.experts.211.gate_proj",
|
| 989 |
+
"model.layers.61.mlp.experts.211.up_proj",
|
| 990 |
+
"model.layers.61.mlp.experts.211.down_proj",
|
| 991 |
+
"model.layers.61.mlp.experts.212.gate_proj",
|
| 992 |
+
"model.layers.61.mlp.experts.212.up_proj",
|
| 993 |
+
"model.layers.61.mlp.experts.212.down_proj",
|
| 994 |
+
"model.layers.61.mlp.experts.213.gate_proj",
|
| 995 |
+
"model.layers.61.mlp.experts.213.up_proj",
|
| 996 |
+
"model.layers.61.mlp.experts.213.down_proj",
|
| 997 |
+
"model.layers.61.mlp.experts.214.gate_proj",
|
| 998 |
+
"model.layers.61.mlp.experts.214.up_proj",
|
| 999 |
+
"model.layers.61.mlp.experts.214.down_proj",
|
| 1000 |
+
"model.layers.61.mlp.experts.215.gate_proj",
|
| 1001 |
+
"model.layers.61.mlp.experts.215.up_proj",
|
| 1002 |
+
"model.layers.61.mlp.experts.215.down_proj",
|
| 1003 |
+
"model.layers.61.mlp.experts.216.gate_proj",
|
| 1004 |
+
"model.layers.61.mlp.experts.216.up_proj",
|
| 1005 |
+
"model.layers.61.mlp.experts.216.down_proj",
|
| 1006 |
+
"model.layers.61.mlp.experts.217.gate_proj",
|
| 1007 |
+
"model.layers.61.mlp.experts.217.up_proj",
|
| 1008 |
+
"model.layers.61.mlp.experts.217.down_proj",
|
| 1009 |
+
"model.layers.61.mlp.experts.218.gate_proj",
|
| 1010 |
+
"model.layers.61.mlp.experts.218.up_proj",
|
| 1011 |
+
"model.layers.61.mlp.experts.218.down_proj",
|
| 1012 |
+
"model.layers.61.mlp.experts.219.gate_proj",
|
| 1013 |
+
"model.layers.61.mlp.experts.219.up_proj",
|
| 1014 |
+
"model.layers.61.mlp.experts.219.down_proj",
|
| 1015 |
+
"model.layers.61.mlp.experts.220.gate_proj",
|
| 1016 |
+
"model.layers.61.mlp.experts.220.up_proj",
|
| 1017 |
+
"model.layers.61.mlp.experts.220.down_proj",
|
| 1018 |
+
"model.layers.61.mlp.experts.221.gate_proj",
|
| 1019 |
+
"model.layers.61.mlp.experts.221.up_proj",
|
| 1020 |
+
"model.layers.61.mlp.experts.221.down_proj",
|
| 1021 |
+
"model.layers.61.mlp.experts.222.gate_proj",
|
| 1022 |
+
"model.layers.61.mlp.experts.222.up_proj",
|
| 1023 |
+
"model.layers.61.mlp.experts.222.down_proj",
|
| 1024 |
+
"model.layers.61.mlp.experts.223.gate_proj",
|
| 1025 |
+
"model.layers.61.mlp.experts.223.up_proj",
|
| 1026 |
+
"model.layers.61.mlp.experts.223.down_proj",
|
| 1027 |
+
"model.layers.61.mlp.experts.224.gate_proj",
|
| 1028 |
+
"model.layers.61.mlp.experts.224.up_proj",
|
| 1029 |
+
"model.layers.61.mlp.experts.224.down_proj",
|
| 1030 |
+
"model.layers.61.mlp.experts.225.gate_proj",
|
| 1031 |
+
"model.layers.61.mlp.experts.225.up_proj",
|
| 1032 |
+
"model.layers.61.mlp.experts.225.down_proj",
|
| 1033 |
+
"model.layers.61.mlp.experts.226.gate_proj",
|
| 1034 |
+
"model.layers.61.mlp.experts.226.up_proj",
|
| 1035 |
+
"model.layers.61.mlp.experts.226.down_proj",
|
| 1036 |
+
"model.layers.61.mlp.experts.227.gate_proj",
|
| 1037 |
+
"model.layers.61.mlp.experts.227.up_proj",
|
| 1038 |
+
"model.layers.61.mlp.experts.227.down_proj",
|
| 1039 |
+
"model.layers.61.mlp.experts.228.gate_proj",
|
| 1040 |
+
"model.layers.61.mlp.experts.228.up_proj",
|
| 1041 |
+
"model.layers.61.mlp.experts.228.down_proj",
|
| 1042 |
+
"model.layers.61.mlp.experts.229.gate_proj",
|
| 1043 |
+
"model.layers.61.mlp.experts.229.up_proj",
|
| 1044 |
+
"model.layers.61.mlp.experts.229.down_proj",
|
| 1045 |
+
"model.layers.61.mlp.experts.230.gate_proj",
|
| 1046 |
+
"model.layers.61.mlp.experts.230.up_proj",
|
| 1047 |
+
"model.layers.61.mlp.experts.230.down_proj",
|
| 1048 |
+
"model.layers.61.mlp.experts.231.gate_proj",
|
| 1049 |
+
"model.layers.61.mlp.experts.231.up_proj",
|
| 1050 |
+
"model.layers.61.mlp.experts.231.down_proj",
|
| 1051 |
+
"model.layers.61.mlp.experts.232.gate_proj",
|
| 1052 |
+
"model.layers.61.mlp.experts.232.up_proj",
|
| 1053 |
+
"model.layers.61.mlp.experts.232.down_proj",
|
| 1054 |
+
"model.layers.61.mlp.experts.233.gate_proj",
|
| 1055 |
+
"model.layers.61.mlp.experts.233.up_proj",
|
| 1056 |
+
"model.layers.61.mlp.experts.233.down_proj",
|
| 1057 |
+
"model.layers.61.mlp.experts.234.gate_proj",
|
| 1058 |
+
"model.layers.61.mlp.experts.234.up_proj",
|
| 1059 |
+
"model.layers.61.mlp.experts.234.down_proj",
|
| 1060 |
+
"model.layers.61.mlp.experts.235.gate_proj",
|
| 1061 |
+
"model.layers.61.mlp.experts.235.up_proj",
|
| 1062 |
+
"model.layers.61.mlp.experts.235.down_proj",
|
| 1063 |
+
"model.layers.61.mlp.experts.236.gate_proj",
|
| 1064 |
+
"model.layers.61.mlp.experts.236.up_proj",
|
| 1065 |
+
"model.layers.61.mlp.experts.236.down_proj",
|
| 1066 |
+
"model.layers.61.mlp.experts.237.gate_proj",
|
| 1067 |
+
"model.layers.61.mlp.experts.237.up_proj",
|
| 1068 |
+
"model.layers.61.mlp.experts.237.down_proj",
|
| 1069 |
+
"model.layers.61.mlp.experts.238.gate_proj",
|
| 1070 |
+
"model.layers.61.mlp.experts.238.up_proj",
|
| 1071 |
+
"model.layers.61.mlp.experts.238.down_proj",
|
| 1072 |
+
"model.layers.61.mlp.experts.239.gate_proj",
|
| 1073 |
+
"model.layers.61.mlp.experts.239.up_proj",
|
| 1074 |
+
"model.layers.61.mlp.experts.239.down_proj",
|
| 1075 |
+
"model.layers.61.mlp.experts.240.gate_proj",
|
| 1076 |
+
"model.layers.61.mlp.experts.240.up_proj",
|
| 1077 |
+
"model.layers.61.mlp.experts.240.down_proj",
|
| 1078 |
+
"model.layers.61.mlp.experts.241.gate_proj",
|
| 1079 |
+
"model.layers.61.mlp.experts.241.up_proj",
|
| 1080 |
+
"model.layers.61.mlp.experts.241.down_proj",
|
| 1081 |
+
"model.layers.61.mlp.experts.242.gate_proj",
|
| 1082 |
+
"model.layers.61.mlp.experts.242.up_proj",
|
| 1083 |
+
"model.layers.61.mlp.experts.242.down_proj",
|
| 1084 |
+
"model.layers.61.mlp.experts.243.gate_proj",
|
| 1085 |
+
"model.layers.61.mlp.experts.243.up_proj",
|
| 1086 |
+
"model.layers.61.mlp.experts.243.down_proj",
|
| 1087 |
+
"model.layers.61.mlp.experts.244.gate_proj",
|
| 1088 |
+
"model.layers.61.mlp.experts.244.up_proj",
|
| 1089 |
+
"model.layers.61.mlp.experts.244.down_proj",
|
| 1090 |
+
"model.layers.61.mlp.experts.245.gate_proj",
|
| 1091 |
+
"model.layers.61.mlp.experts.245.up_proj",
|
| 1092 |
+
"model.layers.61.mlp.experts.245.down_proj",
|
| 1093 |
+
"model.layers.61.mlp.experts.246.gate_proj",
|
| 1094 |
+
"model.layers.61.mlp.experts.246.up_proj",
|
| 1095 |
+
"model.layers.61.mlp.experts.246.down_proj",
|
| 1096 |
+
"model.layers.61.mlp.experts.247.gate_proj",
|
| 1097 |
+
"model.layers.61.mlp.experts.247.up_proj",
|
| 1098 |
+
"model.layers.61.mlp.experts.247.down_proj",
|
| 1099 |
+
"model.layers.61.mlp.experts.248.gate_proj",
|
| 1100 |
+
"model.layers.61.mlp.experts.248.up_proj",
|
| 1101 |
+
"model.layers.61.mlp.experts.248.down_proj",
|
| 1102 |
+
"model.layers.61.mlp.experts.249.gate_proj",
|
| 1103 |
+
"model.layers.61.mlp.experts.249.up_proj",
|
| 1104 |
+
"model.layers.61.mlp.experts.249.down_proj",
|
| 1105 |
+
"model.layers.61.mlp.experts.250.gate_proj",
|
| 1106 |
+
"model.layers.61.mlp.experts.250.up_proj",
|
| 1107 |
+
"model.layers.61.mlp.experts.250.down_proj",
|
| 1108 |
+
"model.layers.61.mlp.experts.251.gate_proj",
|
| 1109 |
+
"model.layers.61.mlp.experts.251.up_proj",
|
| 1110 |
+
"model.layers.61.mlp.experts.251.down_proj",
|
| 1111 |
+
"model.layers.61.mlp.experts.252.gate_proj",
|
| 1112 |
+
"model.layers.61.mlp.experts.252.up_proj",
|
| 1113 |
+
"model.layers.61.mlp.experts.252.down_proj",
|
| 1114 |
+
"model.layers.61.mlp.experts.253.gate_proj",
|
| 1115 |
+
"model.layers.61.mlp.experts.253.up_proj",
|
| 1116 |
+
"model.layers.61.mlp.experts.253.down_proj",
|
| 1117 |
+
"model.layers.61.mlp.experts.254.gate_proj",
|
| 1118 |
+
"model.layers.61.mlp.experts.254.up_proj",
|
| 1119 |
+
"model.layers.61.mlp.experts.254.down_proj",
|
| 1120 |
+
"model.layers.61.mlp.experts.255.gate_proj",
|
| 1121 |
+
"model.layers.61.mlp.experts.255.up_proj",
|
| 1122 |
+
"model.layers.61.mlp.experts.255.down_proj",
|
| 1123 |
+
"model.layers.61.mlp.shared_experts.gate_proj",
|
| 1124 |
+
"model.layers.61.mlp.shared_experts.up_proj",
|
| 1125 |
+
"model.layers.61.mlp.shared_experts.down_proj",
|
| 1126 |
+
"model.layers.61.shared_head.head",
|
| 1127 |
"lm_head"
|
| 1128 |
],
|
| 1129 |
"export": {
|
|
|
|
| 1168 |
"symmetric": null
|
| 1169 |
}
|
| 1170 |
},
|
| 1171 |
+
"kv_cache_post_rope": false,
|
| 1172 |
+
"kv_cache_quant_config": {},
|
| 1173 |
"layer_quant_config": {},
|
| 1174 |
"layer_type_quant_config": {},
|
| 1175 |
"quant_method": "quark",
|
| 1176 |
"quant_mode": "eager_mode",
|
| 1177 |
"softmax_quant_spec": null,
|
| 1178 |
+
"version": "0.11"
|
| 1179 |
},
|
| 1180 |
"rms_norm_eps": 1e-06,
|
| 1181 |
"rope_scaling": {
|
|
|
|
| 1193 |
"tie_word_embeddings": false,
|
| 1194 |
"topk_group": 4,
|
| 1195 |
"topk_method": "noaux_tc",
|
| 1196 |
+
"transformers_version": "4.57.1",
|
|
|
|
| 1197 |
"unsloth_fixed": true,
|
| 1198 |
"use_cache": true,
|
| 1199 |
"v_head_dim": 128,
|
generation_config.json
CHANGED
|
@@ -5,5 +5,5 @@
|
|
| 5 |
"eos_token_id": 1,
|
| 6 |
"temperature": 0.6,
|
| 7 |
"top_p": 0.95,
|
| 8 |
-
"transformers_version": "4.
|
| 9 |
}
|
|
|
|
| 5 |
"eos_token_id": 1,
|
| 6 |
"temperature": 0.6,
|
| 7 |
"top_p": 0.95,
|
| 8 |
+
"transformers_version": "4.57.1"
|
| 9 |
}
|
model-00001-of-00082.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:18dbe98abe48f2c7d84cb28a2b97101b72634a2888e3d6eb7a8d6fbf5281b3ba
|
| 3 |
+
size 4995884768
|
model-00002-of-00082.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5d0d18aabfc7cce4d182027358d7ffd4504ac6278c9c9ca12bb60dd8975ff86e
|
| 3 |
+
size 4995052496
|
model-00003-of-00082.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:673d355712864dbd1f27314c0360f0a963e0ee9452ea36c8ae42bee4a4990756
|
| 3 |
+
size 4999071368
|
model-00004-of-00082.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f7b4f4daa2b95ce73e353a8fef1f049bc07c75125bbc6fa601b554440adadd81
|
| 3 |
+
size 4994943096
|
model-00005-of-00082.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:effea69cc5740f7ea8b94d7b4af9311c483a4b5bdd59b5eeb0a36cd47f7e6ae1
|
| 3 |
+
size 4994943232
|
model-00006-of-00082.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:683ef342bcc6c2d72c94e35d35b384f9821ef27afb9d78573279fd287aa9e385
|
| 3 |
+
size 4994943456
|
model-00007-of-00082.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3e4837be87f1a2876a0012f4da8b380b06c4a683b53974195ff24b2b7411bcad
|
| 3 |
+
size 4999180624
|
model-00008-of-00082.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f5fe73fa25a336e6be2707c63474d96b0add20015a4317dde154953ffcc343d2
|
| 3 |
+
size 4994943096
|
model-00009-of-00082.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:165cdcb1f16f14ef6a83851960d46375dbaabf7c172336cf38456942c879303c
|
| 3 |
+
size 4994943096
|
model-00010-of-00082.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d55d0234e36694eb8575633f04612cbee1be0b055f5f41d8519975a7060eb353
|
| 3 |
+
size 4994943720
|
model-00011-of-00082.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:08a97b781181af8e0c81d0837a559b13711480de19de251df87c61a2ab2f50f3
|
| 3 |
+
size 4916044152
|
model-00012-of-00082.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:57b62c10bde8448a29f71160465ba9cf418545e124fa145ca9a6c855745cd42a
|
| 3 |
+
size 5000091936
|
model-00013-of-00082.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5fe8b74198c04e16b7a0301385e2248815338eb0af42aca2efb7e4b100fa9ee5
|
| 3 |
+
size 4994944296
|
model-00014-of-00082.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:81dc88daf114818e8ad9866ef85c403869b7b4391af2f92bc5092344e4a3df55
|
| 3 |
+
size 4994944392
|
model-00015-of-00082.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:28a0848194500e9f8daff3e3c3b20ec8b52cea81b8b7869e7a2daad7b0f2b5f9
|
| 3 |
+
size 4994944648
|
model-00016-of-00082.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ce8407bd0d3ac2397a66e75f86034e7789cb547846b2bea484d293f1222041de
|
| 3 |
+
size 4999181952
|
model-00017-of-00082.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:37f9bbf0b681bdbb51f09045a4894cc4c91ff86aca6a040a03d959a1b04f86c9
|
| 3 |
+
size 4994944288
|
model-00018-of-00082.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c67808e128166d99dd2285e6454668bdbb205a9d9efa88bcc51a4187fce22282
|
| 3 |
+
size 4994944296
|
model-00019-of-00082.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c4d41bad246c7fca9ea4b052e3200c84642f20e855e3d1caf78f5dd7ec9f7cc8
|
| 3 |
+
size 4994944536
|
model-00020-of-00082.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:062665046cb9cb0e49f0ca7a194cd0b11a22e57e2604e6d75231705bb274207c
|
| 3 |
+
size 4767862480
|
model-00021-of-00082.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a109448c141bbca3c63ec74444b6bdf07ac997acd9e3d25d935403f6ea57f576
|
| 3 |
+
size 5000091936
|
model-00022-of-00082.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7ba1783ead4f05432085a1de14f0fb7c19de024f8de671fd38881fc046ade127
|
| 3 |
+
size 4994944296
|
model-00023-of-00082.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5219488f545c644e71eb3d1eb75032c34dd89601a6249f29533336a0f1a6e4c0
|
| 3 |
+
size 4994944392
|
model-00024-of-00082.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e9ee834cc694739ddb1b118a3658c600ebc81f0f3b8169f33940bb4501dc5742
|
| 3 |
+
size 4994944648
|
model-00025-of-00082.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8b96f16d81ccbdbbc7ab261be03bc07070c2bc00e27a6e47cf7f36b87463017e
|
| 3 |
+
size 4999181952
|
model-00026-of-00082.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dcf31ec6ae326831ccfd684b99e4642193606baf2c116f3903b57c81e1e28fa8
|
| 3 |
+
size 4994944288
|
model-00027-of-00082.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:059afaaf6c34ee1d1826fe85f859d4a3a86c404f274eaf9e3e871e168c405fc6
|
| 3 |
+
size 4994944296
|
model-00028-of-00082.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f4d2b6363a3be0f08947d8f83d71f5b9985ef67acb231db25d1b0d96216c15b1
|
| 3 |
+
size 4994944536
|
model-00029-of-00082.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b0ae064e782c09e2656598ffd40d71dca996e8fdc6c9a06397e976b91eb83914
|
| 3 |
+
size 4767862480
|
model-00030-of-00082.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bd6637572be2f16e282a1681e30c3d35ebe60d29f7a43e3efaa69be2cf6e8f6e
|
| 3 |
+
size 5000091936
|
model-00031-of-00082.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3601bdcbc7cf88fd65faf66f82b096e58b8efe5753278e914a253e7c9d65af17
|
| 3 |
+
size 4994944296
|
model-00032-of-00082.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:282a65080530b3414164124adea2fc874343eec6393010780818a5a581677a86
|
| 3 |
+
size 4994944392
|
model-00033-of-00082.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:509b077f714559ea4084aabd88bfaecf3dfd0f93250b9f3b836512b0b29dafb4
|
| 3 |
+
size 4994944648
|
model-00034-of-00082.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3b564d29b021df8fc56a990de50a0d2c7f0354636ed1ce39eb9109bb89a9962b
|
| 3 |
+
size 4999181952
|
model-00035-of-00082.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e7a6772db37a06a7033f8dd902a0873eaccb897e4332b72bda489ddaed49ed5e
|
| 3 |
+
size 4994944288
|
model-00036-of-00082.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0b087e16feb88f56ec6e75e2d2d6d5a40e2300754a7601b23cd4adb6b61ddebb
|
| 3 |
+
size 4994944296
|
model-00037-of-00082.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:503e5e5d916120f954937fa31f8a8868e07fb2ae3c0d3851f80add2c864a5f2b
|
| 3 |
+
size 4994944536
|
model-00038-of-00082.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5cd876c9d8b73a45da3e38fc2245da325d8bd8087c16bde87e972b16ad87d4cb
|
| 3 |
+
size 4767862480
|
model-00039-of-00082.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:68299e7dd1be2f23bde4b3edd8035f1eb0f27e118f245ebea5c30f7c0d0ba748
|
| 3 |
+
size 5000091936
|
model-00040-of-00082.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b18d545c348f00cf557de60f50a77f421c0375c7bcf4efec8ae707df2bc9d294
|
| 3 |
+
size 4994944296
|
model-00041-of-00082.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bc2ccd0ea0b2ba73074674c8c66b994b94711f3f89452dfc5f527c7b5ec4db84
|
| 3 |
+
size 4994944392
|
model-00042-of-00082.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:49a1d0d5712e4883ec88de234f83bd555c028052b525c4d75aa7cdf164fe252e
|
| 3 |
+
size 4994944648
|
model-00043-of-00082.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3777ce084609b712999c04974765608ed8fc53d53dbb4b9a32aa4edc5e31e759
|
| 3 |
+
size 4999181952
|
model-00044-of-00082.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6c5aace2e6d240cd46e71c64a2b1a6c54a910428d7aacddf290ee4f2283ab36e
|
| 3 |
+
size 4994944288
|
model-00045-of-00082.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:22300a5cbe541012f4eb354ae2998cb49cb8fdaa2b5471d1c48dd97d297ca56e
|
| 3 |
+
size 4994944296
|
model-00046-of-00082.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6fb7f3ecd38ece6ead75a735b22ad44d9f84fd461cdfbf3f822cbcef70726f66
|
| 3 |
+
size 4994944536
|
model-00047-of-00082.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0e9cea92f2e38b2f5f953838410058530cdb5213efcf2d5413cba6bce067db7d
|
| 3 |
+
size 4767862480
|