koreashin commited on
Commit
91c0bfa
·
verified ·
1 Parent(s): 5b1e838

Upload 7 files

Browse files
.gitattributes CHANGED
@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ mnn_8bit_model/llm.mnn filter=lfs diff=lfs merge=lfs -text
37
+ mnn_8bit_model/llm.mnn.weight filter=lfs diff=lfs merge=lfs -text
mnn_8bit_model/config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "llm_model": "llm.mnn",
3
+ "llm_weight": "llm.mnn.weight",
4
+ "backend_type": "cpu",
5
+ "thread_num": 4,
6
+ "precision": "low",
7
+ "memory": "low",
8
+ "sampler_type": "penalty",
9
+ "penalty": 1.1
10
+ }
mnn_8bit_model/export_args.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "path": "/home/shin0815/PycharmProjects/grpo/grpo_no_chinese_outputs/model",
3
+ "type": "qwen3",
4
+ "tokenizer_path": "/home/shin0815/PycharmProjects/grpo/grpo_no_chinese_outputs/model",
5
+ "eagle_path": null,
6
+ "lora_path": null,
7
+ "gptq_path": null,
8
+ "dst_path": "/home/shin0815/다운로드/mnn_8bit_model",
9
+ "verbose": false,
10
+ "test": null,
11
+ "export": "mnn",
12
+ "onnx_slim": false,
13
+ "quant_bit": 8,
14
+ "quant_block": 64,
15
+ "visual_quant_bit": null,
16
+ "visual_quant_block": null,
17
+ "lm_quant_bit": 8,
18
+ "mnnconvert": "../../../build/MNNConvert",
19
+ "ppl": false,
20
+ "awq": false,
21
+ "hqq": false,
22
+ "transformer_fuse": false,
23
+ "group_conv_native": false,
24
+ "smooth": false,
25
+ "sym": false,
26
+ "visual_sym": false,
27
+ "seperate_embed": false,
28
+ "lora_split": false,
29
+ "calib_data": null,
30
+ "act_bit": 16,
31
+ "embed_bit": 16,
32
+ "act_sym": false
33
+ }
mnn_8bit_model/llm.mnn ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:45b498286a5fc75ecb94a96f64d1df8db3a121820b5a333dc4fe0cf694e6ed63
3
+ size 456000
mnn_8bit_model/llm.mnn.json ADDED
The diff for this file is too large to render. See raw diff
 
mnn_8bit_model/llm.mnn.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2b4412db1946629037deaa863949ef716d697a106ceb30f3f84f5e1e5b452601
3
+ size 1936550306
mnn_8bit_model/llm_config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "hidden_size": 2048,
3
+ "layer_nums": 28,
4
+ "attention_mask": "float",
5
+ "key_value_shape": [
6
+ 2,
7
+ 1,
8
+ 0,
9
+ 8,
10
+ 128
11
+ ],
12
+ "bos": "",
13
+ "system_prompt_template": "<|im_start|>system\n%s<|im_end|>\n",
14
+ "user_prompt_template": "<|im_start|>user\n%s<|im_end|>\n",
15
+ "assistant_prompt_template": "<|im_start|>assistant\n%s<|im_end|>\n",
16
+ "is_visual": false,
17
+ "attention_type": "full",
18
+ "jinja": {
19
+ "chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0].role == 'system' %}\n {{- messages[0].content + '\\n\\n' }}\n {%- endif %}\n {{- \"# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\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\" }}\n{%- else %}\n {%- if messages[0].role == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0].content + '<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}\n{%- for message in messages[::-1] %}\n {%- set index = (messages|length - 1) - loop.index0 %}\n {%- 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>')) %}\n {%- set ns.multi_step_tool = false %}\n {%- set ns.last_query_index = index %}\n {%- endif %}\n{%- endfor %}\n{%- for message in messages %}\n {%- if message.content is string %}\n {%- set content = message.content %}\n {%- else %}\n {%- set content = '' %}\n {%- endif %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) %}\n {{- '<|im_start|>' + message.role + '\\n' + content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {%- set reasoning_content = '' %}\n {%- if message.reasoning_content is string %}\n {%- set reasoning_content = message.reasoning_content %}\n {%- else %}\n {%- if '</think>' in content %}\n {%- set reasoning_content = content.split('</think>')[0].rstrip('\\n').split('<think>')[-1].lstrip('\\n') %}\n {%- set content = content.split('</think>')[-1].lstrip('\\n') %}\n {%- endif %}\n {%- endif %}\n {%- if loop.index0 > ns.last_query_index %}\n {%- if loop.last or (not loop.last and reasoning_content) %}\n {{- '<|im_start|>' + message.role + '\\n<think>\\n' + reasoning_content.strip('\\n') + '\\n</think>\\n\\n' + content.lstrip('\\n') }}\n {%- else %}\n {{- '<|im_start|>' + message.role + '\\n' + content }}\n {%- endif %}\n {%- else %}\n {{- '<|im_start|>' + message.role + '\\n' + content }}\n {%- endif %}\n {%- if message.tool_calls %}\n {%- for tool_call in message.tool_calls %}\n {%- if (loop.first and content) or (not loop.first) %}\n {{- '\\n' }}\n {%- endif %}\n {%- if tool_call.function %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {%- if tool_call.arguments is string %}\n {{- tool_call.arguments }}\n {%- else %}\n {{- tool_call.arguments | tojson }}\n {%- endif %}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n {%- if enable_thinking is defined and enable_thinking is false %}\n {{- '<think>\\n\\n</think>\\n\\n' }}\n {%- endif %}\n{%- endif %}",
20
+ "bos": "<|im_end|>",
21
+ "eos": "<|im_end|>"
22
+ },
23
+ "tie_embeddings": [
24
+ 1586489762,
25
+ 1897654690,
26
+ 38895616,
27
+ 8,
28
+ 64
29
+ ]
30
+ }
mnn_8bit_model/tokenizer.txt ADDED
The diff for this file is too large to render. See raw diff