Qwen3-Embedding-4B-vilegal-stage2-adapter
Browse files- .gitattributes +3 -0
- Qwen3-Embedding-4B-vilegal-stage2-adapter/1_Pooling/config.json +5 -0
- Qwen3-Embedding-4B-vilegal-stage2-adapter/README.md +0 -0
- Qwen3-Embedding-4B-vilegal-stage2-adapter/adapter_config.json +48 -0
- Qwen3-Embedding-4B-vilegal-stage2-adapter/adapter_model.safetensors +3 -0
- Qwen3-Embedding-4B-vilegal-stage2-adapter/chat_template.jinja +54 -0
- Qwen3-Embedding-4B-vilegal-stage2-adapter/checkpoint-200/1_Pooling/config.json +5 -0
- Qwen3-Embedding-4B-vilegal-stage2-adapter/checkpoint-200/README.md +0 -0
- Qwen3-Embedding-4B-vilegal-stage2-adapter/checkpoint-200/adapter_config.json +48 -0
- Qwen3-Embedding-4B-vilegal-stage2-adapter/checkpoint-200/adapter_model.safetensors +3 -0
- Qwen3-Embedding-4B-vilegal-stage2-adapter/checkpoint-200/chat_template.jinja +54 -0
- Qwen3-Embedding-4B-vilegal-stage2-adapter/checkpoint-200/config_sentence_transformers.json +14 -0
- Qwen3-Embedding-4B-vilegal-stage2-adapter/checkpoint-200/modules.json +20 -0
- Qwen3-Embedding-4B-vilegal-stage2-adapter/checkpoint-200/optimizer.pt +3 -0
- Qwen3-Embedding-4B-vilegal-stage2-adapter/checkpoint-200/rng_state_0.pth +3 -0
- Qwen3-Embedding-4B-vilegal-stage2-adapter/checkpoint-200/rng_state_1.pth +3 -0
- Qwen3-Embedding-4B-vilegal-stage2-adapter/checkpoint-200/rng_state_2.pth +3 -0
- Qwen3-Embedding-4B-vilegal-stage2-adapter/checkpoint-200/rng_state_3.pth +3 -0
- Qwen3-Embedding-4B-vilegal-stage2-adapter/checkpoint-200/scheduler.pt +3 -0
- Qwen3-Embedding-4B-vilegal-stage2-adapter/checkpoint-200/sentence_bert_config.json +10 -0
- Qwen3-Embedding-4B-vilegal-stage2-adapter/checkpoint-200/tokenizer.json +3 -0
- Qwen3-Embedding-4B-vilegal-stage2-adapter/checkpoint-200/tokenizer_config.json +15 -0
- Qwen3-Embedding-4B-vilegal-stage2-adapter/checkpoint-200/trainer_state.json +62 -0
- Qwen3-Embedding-4B-vilegal-stage2-adapter/checkpoint-200/training_args.bin +3 -0
- Qwen3-Embedding-4B-vilegal-stage2-adapter/checkpoint-218/1_Pooling/config.json +5 -0
- Qwen3-Embedding-4B-vilegal-stage2-adapter/checkpoint-218/README.md +0 -0
- Qwen3-Embedding-4B-vilegal-stage2-adapter/checkpoint-218/adapter_config.json +48 -0
- Qwen3-Embedding-4B-vilegal-stage2-adapter/checkpoint-218/adapter_model.safetensors +3 -0
- Qwen3-Embedding-4B-vilegal-stage2-adapter/checkpoint-218/chat_template.jinja +54 -0
- Qwen3-Embedding-4B-vilegal-stage2-adapter/checkpoint-218/config_sentence_transformers.json +14 -0
- Qwen3-Embedding-4B-vilegal-stage2-adapter/checkpoint-218/modules.json +20 -0
- Qwen3-Embedding-4B-vilegal-stage2-adapter/checkpoint-218/optimizer.pt +3 -0
- Qwen3-Embedding-4B-vilegal-stage2-adapter/checkpoint-218/rng_state_0.pth +3 -0
- Qwen3-Embedding-4B-vilegal-stage2-adapter/checkpoint-218/rng_state_1.pth +3 -0
- Qwen3-Embedding-4B-vilegal-stage2-adapter/checkpoint-218/rng_state_2.pth +3 -0
- Qwen3-Embedding-4B-vilegal-stage2-adapter/checkpoint-218/rng_state_3.pth +3 -0
- Qwen3-Embedding-4B-vilegal-stage2-adapter/checkpoint-218/scheduler.pt +3 -0
- Qwen3-Embedding-4B-vilegal-stage2-adapter/checkpoint-218/sentence_bert_config.json +10 -0
- Qwen3-Embedding-4B-vilegal-stage2-adapter/checkpoint-218/tokenizer.json +3 -0
- Qwen3-Embedding-4B-vilegal-stage2-adapter/checkpoint-218/tokenizer_config.json +15 -0
- Qwen3-Embedding-4B-vilegal-stage2-adapter/checkpoint-218/trainer_state.json +62 -0
- Qwen3-Embedding-4B-vilegal-stage2-adapter/checkpoint-218/training_args.bin +3 -0
- Qwen3-Embedding-4B-vilegal-stage2-adapter/config_sentence_transformers.json +14 -0
- Qwen3-Embedding-4B-vilegal-stage2-adapter/modules.json +20 -0
- Qwen3-Embedding-4B-vilegal-stage2-adapter/sentence_bert_config.json +10 -0
- Qwen3-Embedding-4B-vilegal-stage2-adapter/tokenizer.json +3 -0
- Qwen3-Embedding-4B-vilegal-stage2-adapter/tokenizer_config.json +15 -0
- Qwen3-Embedding-4B-vilegal-stage2-adapter/training_args.bin +3 -0
.gitattributes
CHANGED
|
@@ -54,3 +54,6 @@ Qwen3-Embedding-4B-peft-vilegal-stage1-ok/hf_model/tokenizer.json filter=lfs dif
|
|
| 54 |
Qwen3-Embedding-4B-peft-vilegal-stage2-ok/checkpoint-218/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 55 |
Qwen3-Embedding-4B-peft-vilegal-stage2-ok/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 56 |
Qwen3-Embedding-4B-merged/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
|
|
|
|
| 54 |
Qwen3-Embedding-4B-peft-vilegal-stage2-ok/checkpoint-218/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 55 |
Qwen3-Embedding-4B-peft-vilegal-stage2-ok/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 56 |
Qwen3-Embedding-4B-merged/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 57 |
+
Qwen3-Embedding-4B-vilegal-stage2-adapter/checkpoint-200/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 58 |
+
Qwen3-Embedding-4B-vilegal-stage2-adapter/checkpoint-218/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 59 |
+
Qwen3-Embedding-4B-vilegal-stage2-adapter/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
Qwen3-Embedding-4B-vilegal-stage2-adapter/1_Pooling/config.json
ADDED
|
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"embedding_dimension": 2560,
|
| 3 |
+
"pooling_mode": "lasttoken",
|
| 4 |
+
"include_prompt": true
|
| 5 |
+
}
|
Qwen3-Embedding-4B-vilegal-stage2-adapter/README.md
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
Qwen3-Embedding-4B-vilegal-stage2-adapter/adapter_config.json
ADDED
|
@@ -0,0 +1,48 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alora_invocation_tokens": null,
|
| 3 |
+
"alpha_pattern": {},
|
| 4 |
+
"arrow_config": null,
|
| 5 |
+
"auto_mapping": null,
|
| 6 |
+
"base_model_name_or_path": "./hf_model/Qwen3-Embedding-4B-vilegal-stage1-merged",
|
| 7 |
+
"bias": "none",
|
| 8 |
+
"corda_config": null,
|
| 9 |
+
"ensure_weight_tying": false,
|
| 10 |
+
"eva_config": null,
|
| 11 |
+
"exclude_modules": null,
|
| 12 |
+
"fan_in_fan_out": false,
|
| 13 |
+
"inference_mode": false,
|
| 14 |
+
"init_lora_weights": true,
|
| 15 |
+
"layer_replication": null,
|
| 16 |
+
"layers_pattern": null,
|
| 17 |
+
"layers_to_transform": null,
|
| 18 |
+
"loftq_config": {},
|
| 19 |
+
"lora_alpha": 64,
|
| 20 |
+
"lora_bias": false,
|
| 21 |
+
"lora_dropout": 0,
|
| 22 |
+
"lora_ga_config": null,
|
| 23 |
+
"megatron_config": null,
|
| 24 |
+
"megatron_core": "megatron.core",
|
| 25 |
+
"modules_to_save": null,
|
| 26 |
+
"peft_type": "LORA",
|
| 27 |
+
"peft_version": "0.19.1",
|
| 28 |
+
"qalora_group_size": 16,
|
| 29 |
+
"r": 32,
|
| 30 |
+
"rank_pattern": {},
|
| 31 |
+
"revision": null,
|
| 32 |
+
"target_modules": [
|
| 33 |
+
"o_proj",
|
| 34 |
+
"down_proj",
|
| 35 |
+
"k_proj",
|
| 36 |
+
"gate_proj",
|
| 37 |
+
"v_proj",
|
| 38 |
+
"q_proj",
|
| 39 |
+
"up_proj"
|
| 40 |
+
],
|
| 41 |
+
"target_parameters": null,
|
| 42 |
+
"task_type": "FEATURE_EXTRACTION",
|
| 43 |
+
"trainable_token_indices": null,
|
| 44 |
+
"use_bdlora": null,
|
| 45 |
+
"use_dora": false,
|
| 46 |
+
"use_qalora": false,
|
| 47 |
+
"use_rslora": false
|
| 48 |
+
}
|
Qwen3-Embedding-4B-vilegal-stage2-adapter/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9e69154cafdba793cd8a2a1af3bde44168857d02445c1f1073847657b1554399
|
| 3 |
+
size 132185368
|
Qwen3-Embedding-4B-vilegal-stage2-adapter/chat_template.jinja
ADDED
|
@@ -0,0 +1,54 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{%- if tools %}
|
| 2 |
+
{{- '<|im_start|>system\n' }}
|
| 3 |
+
{%- if messages[0]['role'] == 'system' %}
|
| 4 |
+
{{- messages[0]['content'] }}
|
| 5 |
+
{%- else %}
|
| 6 |
+
{{- 'You are a helpful assistant.' }}
|
| 7 |
+
{%- endif %}
|
| 8 |
+
{{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
|
| 9 |
+
{%- for tool in tools %}
|
| 10 |
+
{{- "\n" }}
|
| 11 |
+
{{- tool | tojson }}
|
| 12 |
+
{%- endfor %}
|
| 13 |
+
{{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
|
| 14 |
+
{%- else %}
|
| 15 |
+
{%- if messages[0]['role'] == 'system' %}
|
| 16 |
+
{{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
|
| 17 |
+
{%- else %}
|
| 18 |
+
{{- '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}
|
| 19 |
+
{%- endif %}
|
| 20 |
+
{%- endif %}
|
| 21 |
+
{%- for message in messages %}
|
| 22 |
+
{%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
|
| 23 |
+
{{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
|
| 24 |
+
{%- elif message.role == "assistant" %}
|
| 25 |
+
{{- '<|im_start|>' + message.role }}
|
| 26 |
+
{%- if message.content %}
|
| 27 |
+
{{- '\n' + message.content }}
|
| 28 |
+
{%- endif %}
|
| 29 |
+
{%- for tool_call in message.tool_calls %}
|
| 30 |
+
{%- if tool_call.function is defined %}
|
| 31 |
+
{%- set tool_call = tool_call.function %}
|
| 32 |
+
{%- endif %}
|
| 33 |
+
{{- '\n<tool_call>\n{"name": "' }}
|
| 34 |
+
{{- tool_call.name }}
|
| 35 |
+
{{- '", "arguments": ' }}
|
| 36 |
+
{{- tool_call.arguments | tojson }}
|
| 37 |
+
{{- '}\n</tool_call>' }}
|
| 38 |
+
{%- endfor %}
|
| 39 |
+
{{- '<|im_end|>\n' }}
|
| 40 |
+
{%- elif message.role == "tool" %}
|
| 41 |
+
{%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
|
| 42 |
+
{{- '<|im_start|>user' }}
|
| 43 |
+
{%- endif %}
|
| 44 |
+
{{- '\n<tool_response>\n' }}
|
| 45 |
+
{{- message.content }}
|
| 46 |
+
{{- '\n</tool_response>' }}
|
| 47 |
+
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
|
| 48 |
+
{{- '<|im_end|>\n' }}
|
| 49 |
+
{%- endif %}
|
| 50 |
+
{%- endif %}
|
| 51 |
+
{%- endfor %}
|
| 52 |
+
{%- if add_generation_prompt %}
|
| 53 |
+
{{- '<|im_start|>assistant\n' }}
|
| 54 |
+
{%- endif %}
|
Qwen3-Embedding-4B-vilegal-stage2-adapter/checkpoint-200/1_Pooling/config.json
ADDED
|
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"embedding_dimension": 2560,
|
| 3 |
+
"pooling_mode": "lasttoken",
|
| 4 |
+
"include_prompt": true
|
| 5 |
+
}
|
Qwen3-Embedding-4B-vilegal-stage2-adapter/checkpoint-200/README.md
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
Qwen3-Embedding-4B-vilegal-stage2-adapter/checkpoint-200/adapter_config.json
ADDED
|
@@ -0,0 +1,48 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alora_invocation_tokens": null,
|
| 3 |
+
"alpha_pattern": {},
|
| 4 |
+
"arrow_config": null,
|
| 5 |
+
"auto_mapping": null,
|
| 6 |
+
"base_model_name_or_path": "./hf_model/Qwen3-Embedding-4B-vilegal-stage1-merged",
|
| 7 |
+
"bias": "none",
|
| 8 |
+
"corda_config": null,
|
| 9 |
+
"ensure_weight_tying": false,
|
| 10 |
+
"eva_config": null,
|
| 11 |
+
"exclude_modules": null,
|
| 12 |
+
"fan_in_fan_out": false,
|
| 13 |
+
"inference_mode": false,
|
| 14 |
+
"init_lora_weights": true,
|
| 15 |
+
"layer_replication": null,
|
| 16 |
+
"layers_pattern": null,
|
| 17 |
+
"layers_to_transform": null,
|
| 18 |
+
"loftq_config": {},
|
| 19 |
+
"lora_alpha": 64,
|
| 20 |
+
"lora_bias": false,
|
| 21 |
+
"lora_dropout": 0,
|
| 22 |
+
"lora_ga_config": null,
|
| 23 |
+
"megatron_config": null,
|
| 24 |
+
"megatron_core": "megatron.core",
|
| 25 |
+
"modules_to_save": null,
|
| 26 |
+
"peft_type": "LORA",
|
| 27 |
+
"peft_version": "0.19.1",
|
| 28 |
+
"qalora_group_size": 16,
|
| 29 |
+
"r": 32,
|
| 30 |
+
"rank_pattern": {},
|
| 31 |
+
"revision": null,
|
| 32 |
+
"target_modules": [
|
| 33 |
+
"o_proj",
|
| 34 |
+
"down_proj",
|
| 35 |
+
"k_proj",
|
| 36 |
+
"gate_proj",
|
| 37 |
+
"v_proj",
|
| 38 |
+
"q_proj",
|
| 39 |
+
"up_proj"
|
| 40 |
+
],
|
| 41 |
+
"target_parameters": null,
|
| 42 |
+
"task_type": "FEATURE_EXTRACTION",
|
| 43 |
+
"trainable_token_indices": null,
|
| 44 |
+
"use_bdlora": null,
|
| 45 |
+
"use_dora": false,
|
| 46 |
+
"use_qalora": false,
|
| 47 |
+
"use_rslora": false
|
| 48 |
+
}
|
Qwen3-Embedding-4B-vilegal-stage2-adapter/checkpoint-200/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:194143ee8d7722be2de95ce9e898c47ff7961ad885e8f6408783edc7f566f9e5
|
| 3 |
+
size 132185368
|
Qwen3-Embedding-4B-vilegal-stage2-adapter/checkpoint-200/chat_template.jinja
ADDED
|
@@ -0,0 +1,54 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{%- if tools %}
|
| 2 |
+
{{- '<|im_start|>system\n' }}
|
| 3 |
+
{%- if messages[0]['role'] == 'system' %}
|
| 4 |
+
{{- messages[0]['content'] }}
|
| 5 |
+
{%- else %}
|
| 6 |
+
{{- 'You are a helpful assistant.' }}
|
| 7 |
+
{%- endif %}
|
| 8 |
+
{{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
|
| 9 |
+
{%- for tool in tools %}
|
| 10 |
+
{{- "\n" }}
|
| 11 |
+
{{- tool | tojson }}
|
| 12 |
+
{%- endfor %}
|
| 13 |
+
{{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
|
| 14 |
+
{%- else %}
|
| 15 |
+
{%- if messages[0]['role'] == 'system' %}
|
| 16 |
+
{{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
|
| 17 |
+
{%- else %}
|
| 18 |
+
{{- '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}
|
| 19 |
+
{%- endif %}
|
| 20 |
+
{%- endif %}
|
| 21 |
+
{%- for message in messages %}
|
| 22 |
+
{%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
|
| 23 |
+
{{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
|
| 24 |
+
{%- elif message.role == "assistant" %}
|
| 25 |
+
{{- '<|im_start|>' + message.role }}
|
| 26 |
+
{%- if message.content %}
|
| 27 |
+
{{- '\n' + message.content }}
|
| 28 |
+
{%- endif %}
|
| 29 |
+
{%- for tool_call in message.tool_calls %}
|
| 30 |
+
{%- if tool_call.function is defined %}
|
| 31 |
+
{%- set tool_call = tool_call.function %}
|
| 32 |
+
{%- endif %}
|
| 33 |
+
{{- '\n<tool_call>\n{"name": "' }}
|
| 34 |
+
{{- tool_call.name }}
|
| 35 |
+
{{- '", "arguments": ' }}
|
| 36 |
+
{{- tool_call.arguments | tojson }}
|
| 37 |
+
{{- '}\n</tool_call>' }}
|
| 38 |
+
{%- endfor %}
|
| 39 |
+
{{- '<|im_end|>\n' }}
|
| 40 |
+
{%- elif message.role == "tool" %}
|
| 41 |
+
{%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
|
| 42 |
+
{{- '<|im_start|>user' }}
|
| 43 |
+
{%- endif %}
|
| 44 |
+
{{- '\n<tool_response>\n' }}
|
| 45 |
+
{{- message.content }}
|
| 46 |
+
{{- '\n</tool_response>' }}
|
| 47 |
+
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
|
| 48 |
+
{{- '<|im_end|>\n' }}
|
| 49 |
+
{%- endif %}
|
| 50 |
+
{%- endif %}
|
| 51 |
+
{%- endfor %}
|
| 52 |
+
{%- if add_generation_prompt %}
|
| 53 |
+
{{- '<|im_start|>assistant\n' }}
|
| 54 |
+
{%- endif %}
|
Qwen3-Embedding-4B-vilegal-stage2-adapter/checkpoint-200/config_sentence_transformers.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"__version__": {
|
| 3 |
+
"pytorch": "2.11.0+cu130",
|
| 4 |
+
"sentence_transformers": "5.4.1",
|
| 5 |
+
"transformers": "5.6.2"
|
| 6 |
+
},
|
| 7 |
+
"default_prompt_name": null,
|
| 8 |
+
"model_type": "SentenceTransformer",
|
| 9 |
+
"prompts": {
|
| 10 |
+
"document": "",
|
| 11 |
+
"query": "Instruct: Given a user query related to law, retrieve the most relevant legal passages that directly answer the question.\nQuery:"
|
| 12 |
+
},
|
| 13 |
+
"similarity_fn_name": "cosine"
|
| 14 |
+
}
|
Qwen3-Embedding-4B-vilegal-stage2-adapter/checkpoint-200/modules.json
ADDED
|
@@ -0,0 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
[
|
| 2 |
+
{
|
| 3 |
+
"idx": 0,
|
| 4 |
+
"name": "0",
|
| 5 |
+
"path": "",
|
| 6 |
+
"type": "sentence_transformers.base.modules.transformer.Transformer"
|
| 7 |
+
},
|
| 8 |
+
{
|
| 9 |
+
"idx": 1,
|
| 10 |
+
"name": "1",
|
| 11 |
+
"path": "1_Pooling",
|
| 12 |
+
"type": "sentence_transformers.sentence_transformer.modules.pooling.Pooling"
|
| 13 |
+
},
|
| 14 |
+
{
|
| 15 |
+
"idx": 2,
|
| 16 |
+
"name": "2",
|
| 17 |
+
"path": "2_Normalize",
|
| 18 |
+
"type": "sentence_transformers.sentence_transformer.modules.normalize.Normalize"
|
| 19 |
+
}
|
| 20 |
+
]
|
Qwen3-Embedding-4B-vilegal-stage2-adapter/checkpoint-200/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8eefdf6c967f23e239f8e0d231a6f8111f4deb1157239e0fc01fa7a6ac36785a
|
| 3 |
+
size 264674251
|
Qwen3-Embedding-4B-vilegal-stage2-adapter/checkpoint-200/rng_state_0.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:91c7818cff7cfa15ac036e7d99de57c66f3546948d0318970e66adffa11ae356
|
| 3 |
+
size 15365
|
Qwen3-Embedding-4B-vilegal-stage2-adapter/checkpoint-200/rng_state_1.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cf1ddbbdd3e2b2a4fc0d6c20dda2cf27bf4d264d3993040c2f54879967d25602
|
| 3 |
+
size 15365
|
Qwen3-Embedding-4B-vilegal-stage2-adapter/checkpoint-200/rng_state_2.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:90bb92e49c2b434e9c058486aee05ba9e57c4012dd4b97815840ef2bc7680ce9
|
| 3 |
+
size 15365
|
Qwen3-Embedding-4B-vilegal-stage2-adapter/checkpoint-200/rng_state_3.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:27b767392d13194694df8f64661d6ff484ea9f25addbb98712993567a100e422
|
| 3 |
+
size 15365
|
Qwen3-Embedding-4B-vilegal-stage2-adapter/checkpoint-200/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:563eebbaedd958aa09c470cc7ed7774518b8d1eb9c526c382e519884d621424c
|
| 3 |
+
size 1465
|
Qwen3-Embedding-4B-vilegal-stage2-adapter/checkpoint-200/sentence_bert_config.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"transformer_task": "feature-extraction",
|
| 3 |
+
"modality_config": {
|
| 4 |
+
"text": {
|
| 5 |
+
"method": "forward",
|
| 6 |
+
"method_output_name": "last_hidden_state"
|
| 7 |
+
}
|
| 8 |
+
},
|
| 9 |
+
"module_output_name": "token_embeddings"
|
| 10 |
+
}
|
Qwen3-Embedding-4B-vilegal-stage2-adapter/checkpoint-200/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:24712070ac72a218115ee256fd28888777437366e4c1b2ed70b21f75561eb90e
|
| 3 |
+
size 11423042
|
Qwen3-Embedding-4B-vilegal-stage2-adapter/checkpoint-200/tokenizer_config.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"backend": "tokenizers",
|
| 4 |
+
"bos_token": null,
|
| 5 |
+
"clean_up_tokenization_spaces": false,
|
| 6 |
+
"eos_token": "<|im_end|>",
|
| 7 |
+
"errors": "replace",
|
| 8 |
+
"is_local": true,
|
| 9 |
+
"local_files_only": false,
|
| 10 |
+
"model_max_length": 4096,
|
| 11 |
+
"pad_token": "<|endoftext|>",
|
| 12 |
+
"split_special_tokens": false,
|
| 13 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 14 |
+
"unk_token": null
|
| 15 |
+
}
|
Qwen3-Embedding-4B-vilegal-stage2-adapter/checkpoint-200/trainer_state.json
ADDED
|
@@ -0,0 +1,62 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.9174311926605505,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 200,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.22935779816513763,
|
| 14 |
+
"grad_norm": 0.189453125,
|
| 15 |
+
"learning_rate": 1.7244897959183674e-05,
|
| 16 |
+
"loss": 0.5653152084350586,
|
| 17 |
+
"step": 50
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.45871559633027525,
|
| 21 |
+
"grad_norm": 0.21484375,
|
| 22 |
+
"learning_rate": 1.2142857142857142e-05,
|
| 23 |
+
"loss": 0.5319932556152344,
|
| 24 |
+
"step": 100
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.6880733944954128,
|
| 28 |
+
"grad_norm": 0.203125,
|
| 29 |
+
"learning_rate": 7.0408163265306125e-06,
|
| 30 |
+
"loss": 0.5213391876220703,
|
| 31 |
+
"step": 150
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.9174311926605505,
|
| 35 |
+
"grad_norm": 0.21484375,
|
| 36 |
+
"learning_rate": 1.938775510204082e-06,
|
| 37 |
+
"loss": 0.5070155334472656,
|
| 38 |
+
"step": 200
|
| 39 |
+
}
|
| 40 |
+
],
|
| 41 |
+
"logging_steps": 50,
|
| 42 |
+
"max_steps": 218,
|
| 43 |
+
"num_input_tokens_seen": 0,
|
| 44 |
+
"num_train_epochs": 1,
|
| 45 |
+
"save_steps": 50,
|
| 46 |
+
"stateful_callbacks": {
|
| 47 |
+
"TrainerControl": {
|
| 48 |
+
"args": {
|
| 49 |
+
"should_epoch_stop": false,
|
| 50 |
+
"should_evaluate": false,
|
| 51 |
+
"should_log": false,
|
| 52 |
+
"should_save": true,
|
| 53 |
+
"should_training_stop": false
|
| 54 |
+
},
|
| 55 |
+
"attributes": {}
|
| 56 |
+
}
|
| 57 |
+
},
|
| 58 |
+
"total_flos": 0.0,
|
| 59 |
+
"train_batch_size": 512,
|
| 60 |
+
"trial_name": null,
|
| 61 |
+
"trial_params": null
|
| 62 |
+
}
|
Qwen3-Embedding-4B-vilegal-stage2-adapter/checkpoint-200/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:95d54605f8792813f284d2a1340defc13104f5fe87e7480bb1f729704bfe28ed
|
| 3 |
+
size 5777
|
Qwen3-Embedding-4B-vilegal-stage2-adapter/checkpoint-218/1_Pooling/config.json
ADDED
|
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"embedding_dimension": 2560,
|
| 3 |
+
"pooling_mode": "lasttoken",
|
| 4 |
+
"include_prompt": true
|
| 5 |
+
}
|
Qwen3-Embedding-4B-vilegal-stage2-adapter/checkpoint-218/README.md
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
Qwen3-Embedding-4B-vilegal-stage2-adapter/checkpoint-218/adapter_config.json
ADDED
|
@@ -0,0 +1,48 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alora_invocation_tokens": null,
|
| 3 |
+
"alpha_pattern": {},
|
| 4 |
+
"arrow_config": null,
|
| 5 |
+
"auto_mapping": null,
|
| 6 |
+
"base_model_name_or_path": "./hf_model/Qwen3-Embedding-4B-vilegal-stage1-merged",
|
| 7 |
+
"bias": "none",
|
| 8 |
+
"corda_config": null,
|
| 9 |
+
"ensure_weight_tying": false,
|
| 10 |
+
"eva_config": null,
|
| 11 |
+
"exclude_modules": null,
|
| 12 |
+
"fan_in_fan_out": false,
|
| 13 |
+
"inference_mode": false,
|
| 14 |
+
"init_lora_weights": true,
|
| 15 |
+
"layer_replication": null,
|
| 16 |
+
"layers_pattern": null,
|
| 17 |
+
"layers_to_transform": null,
|
| 18 |
+
"loftq_config": {},
|
| 19 |
+
"lora_alpha": 64,
|
| 20 |
+
"lora_bias": false,
|
| 21 |
+
"lora_dropout": 0,
|
| 22 |
+
"lora_ga_config": null,
|
| 23 |
+
"megatron_config": null,
|
| 24 |
+
"megatron_core": "megatron.core",
|
| 25 |
+
"modules_to_save": null,
|
| 26 |
+
"peft_type": "LORA",
|
| 27 |
+
"peft_version": "0.19.1",
|
| 28 |
+
"qalora_group_size": 16,
|
| 29 |
+
"r": 32,
|
| 30 |
+
"rank_pattern": {},
|
| 31 |
+
"revision": null,
|
| 32 |
+
"target_modules": [
|
| 33 |
+
"o_proj",
|
| 34 |
+
"down_proj",
|
| 35 |
+
"k_proj",
|
| 36 |
+
"gate_proj",
|
| 37 |
+
"v_proj",
|
| 38 |
+
"q_proj",
|
| 39 |
+
"up_proj"
|
| 40 |
+
],
|
| 41 |
+
"target_parameters": null,
|
| 42 |
+
"task_type": "FEATURE_EXTRACTION",
|
| 43 |
+
"trainable_token_indices": null,
|
| 44 |
+
"use_bdlora": null,
|
| 45 |
+
"use_dora": false,
|
| 46 |
+
"use_qalora": false,
|
| 47 |
+
"use_rslora": false
|
| 48 |
+
}
|
Qwen3-Embedding-4B-vilegal-stage2-adapter/checkpoint-218/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9e69154cafdba793cd8a2a1af3bde44168857d02445c1f1073847657b1554399
|
| 3 |
+
size 132185368
|
Qwen3-Embedding-4B-vilegal-stage2-adapter/checkpoint-218/chat_template.jinja
ADDED
|
@@ -0,0 +1,54 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{%- if tools %}
|
| 2 |
+
{{- '<|im_start|>system\n' }}
|
| 3 |
+
{%- if messages[0]['role'] == 'system' %}
|
| 4 |
+
{{- messages[0]['content'] }}
|
| 5 |
+
{%- else %}
|
| 6 |
+
{{- 'You are a helpful assistant.' }}
|
| 7 |
+
{%- endif %}
|
| 8 |
+
{{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
|
| 9 |
+
{%- for tool in tools %}
|
| 10 |
+
{{- "\n" }}
|
| 11 |
+
{{- tool | tojson }}
|
| 12 |
+
{%- endfor %}
|
| 13 |
+
{{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
|
| 14 |
+
{%- else %}
|
| 15 |
+
{%- if messages[0]['role'] == 'system' %}
|
| 16 |
+
{{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
|
| 17 |
+
{%- else %}
|
| 18 |
+
{{- '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}
|
| 19 |
+
{%- endif %}
|
| 20 |
+
{%- endif %}
|
| 21 |
+
{%- for message in messages %}
|
| 22 |
+
{%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
|
| 23 |
+
{{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
|
| 24 |
+
{%- elif message.role == "assistant" %}
|
| 25 |
+
{{- '<|im_start|>' + message.role }}
|
| 26 |
+
{%- if message.content %}
|
| 27 |
+
{{- '\n' + message.content }}
|
| 28 |
+
{%- endif %}
|
| 29 |
+
{%- for tool_call in message.tool_calls %}
|
| 30 |
+
{%- if tool_call.function is defined %}
|
| 31 |
+
{%- set tool_call = tool_call.function %}
|
| 32 |
+
{%- endif %}
|
| 33 |
+
{{- '\n<tool_call>\n{"name": "' }}
|
| 34 |
+
{{- tool_call.name }}
|
| 35 |
+
{{- '", "arguments": ' }}
|
| 36 |
+
{{- tool_call.arguments | tojson }}
|
| 37 |
+
{{- '}\n</tool_call>' }}
|
| 38 |
+
{%- endfor %}
|
| 39 |
+
{{- '<|im_end|>\n' }}
|
| 40 |
+
{%- elif message.role == "tool" %}
|
| 41 |
+
{%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
|
| 42 |
+
{{- '<|im_start|>user' }}
|
| 43 |
+
{%- endif %}
|
| 44 |
+
{{- '\n<tool_response>\n' }}
|
| 45 |
+
{{- message.content }}
|
| 46 |
+
{{- '\n</tool_response>' }}
|
| 47 |
+
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
|
| 48 |
+
{{- '<|im_end|>\n' }}
|
| 49 |
+
{%- endif %}
|
| 50 |
+
{%- endif %}
|
| 51 |
+
{%- endfor %}
|
| 52 |
+
{%- if add_generation_prompt %}
|
| 53 |
+
{{- '<|im_start|>assistant\n' }}
|
| 54 |
+
{%- endif %}
|
Qwen3-Embedding-4B-vilegal-stage2-adapter/checkpoint-218/config_sentence_transformers.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"__version__": {
|
| 3 |
+
"pytorch": "2.11.0+cu130",
|
| 4 |
+
"sentence_transformers": "5.4.1",
|
| 5 |
+
"transformers": "5.6.2"
|
| 6 |
+
},
|
| 7 |
+
"default_prompt_name": null,
|
| 8 |
+
"model_type": "SentenceTransformer",
|
| 9 |
+
"prompts": {
|
| 10 |
+
"document": "",
|
| 11 |
+
"query": "Instruct: Given a user query related to law, retrieve the most relevant legal passages that directly answer the question.\nQuery:"
|
| 12 |
+
},
|
| 13 |
+
"similarity_fn_name": "cosine"
|
| 14 |
+
}
|
Qwen3-Embedding-4B-vilegal-stage2-adapter/checkpoint-218/modules.json
ADDED
|
@@ -0,0 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
[
|
| 2 |
+
{
|
| 3 |
+
"idx": 0,
|
| 4 |
+
"name": "0",
|
| 5 |
+
"path": "",
|
| 6 |
+
"type": "sentence_transformers.base.modules.transformer.Transformer"
|
| 7 |
+
},
|
| 8 |
+
{
|
| 9 |
+
"idx": 1,
|
| 10 |
+
"name": "1",
|
| 11 |
+
"path": "1_Pooling",
|
| 12 |
+
"type": "sentence_transformers.sentence_transformer.modules.pooling.Pooling"
|
| 13 |
+
},
|
| 14 |
+
{
|
| 15 |
+
"idx": 2,
|
| 16 |
+
"name": "2",
|
| 17 |
+
"path": "2_Normalize",
|
| 18 |
+
"type": "sentence_transformers.sentence_transformer.modules.normalize.Normalize"
|
| 19 |
+
}
|
| 20 |
+
]
|
Qwen3-Embedding-4B-vilegal-stage2-adapter/checkpoint-218/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:744cb6fef81608a88ca5d5c880cfdee5124c55d01bd1d3e127e680c814914509
|
| 3 |
+
size 264674251
|
Qwen3-Embedding-4B-vilegal-stage2-adapter/checkpoint-218/rng_state_0.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:91c7818cff7cfa15ac036e7d99de57c66f3546948d0318970e66adffa11ae356
|
| 3 |
+
size 15365
|
Qwen3-Embedding-4B-vilegal-stage2-adapter/checkpoint-218/rng_state_1.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cf1ddbbdd3e2b2a4fc0d6c20dda2cf27bf4d264d3993040c2f54879967d25602
|
| 3 |
+
size 15365
|
Qwen3-Embedding-4B-vilegal-stage2-adapter/checkpoint-218/rng_state_2.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:90bb92e49c2b434e9c058486aee05ba9e57c4012dd4b97815840ef2bc7680ce9
|
| 3 |
+
size 15365
|
Qwen3-Embedding-4B-vilegal-stage2-adapter/checkpoint-218/rng_state_3.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:27b767392d13194694df8f64661d6ff484ea9f25addbb98712993567a100e422
|
| 3 |
+
size 15365
|
Qwen3-Embedding-4B-vilegal-stage2-adapter/checkpoint-218/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4dcc8e8c457f0dc7de9dd42d7e2ba21b88d268c4fc098cc48309f6ab8d73116c
|
| 3 |
+
size 1465
|
Qwen3-Embedding-4B-vilegal-stage2-adapter/checkpoint-218/sentence_bert_config.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"transformer_task": "feature-extraction",
|
| 3 |
+
"modality_config": {
|
| 4 |
+
"text": {
|
| 5 |
+
"method": "forward",
|
| 6 |
+
"method_output_name": "last_hidden_state"
|
| 7 |
+
}
|
| 8 |
+
},
|
| 9 |
+
"module_output_name": "token_embeddings"
|
| 10 |
+
}
|
Qwen3-Embedding-4B-vilegal-stage2-adapter/checkpoint-218/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:24712070ac72a218115ee256fd28888777437366e4c1b2ed70b21f75561eb90e
|
| 3 |
+
size 11423042
|
Qwen3-Embedding-4B-vilegal-stage2-adapter/checkpoint-218/tokenizer_config.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"backend": "tokenizers",
|
| 4 |
+
"bos_token": null,
|
| 5 |
+
"clean_up_tokenization_spaces": false,
|
| 6 |
+
"eos_token": "<|im_end|>",
|
| 7 |
+
"errors": "replace",
|
| 8 |
+
"is_local": true,
|
| 9 |
+
"local_files_only": false,
|
| 10 |
+
"model_max_length": 4096,
|
| 11 |
+
"pad_token": "<|endoftext|>",
|
| 12 |
+
"split_special_tokens": false,
|
| 13 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 14 |
+
"unk_token": null
|
| 15 |
+
}
|
Qwen3-Embedding-4B-vilegal-stage2-adapter/checkpoint-218/trainer_state.json
ADDED
|
@@ -0,0 +1,62 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 1.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 218,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.22935779816513763,
|
| 14 |
+
"grad_norm": 0.189453125,
|
| 15 |
+
"learning_rate": 1.7244897959183674e-05,
|
| 16 |
+
"loss": 0.5653152084350586,
|
| 17 |
+
"step": 50
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.45871559633027525,
|
| 21 |
+
"grad_norm": 0.21484375,
|
| 22 |
+
"learning_rate": 1.2142857142857142e-05,
|
| 23 |
+
"loss": 0.5319932556152344,
|
| 24 |
+
"step": 100
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.6880733944954128,
|
| 28 |
+
"grad_norm": 0.203125,
|
| 29 |
+
"learning_rate": 7.0408163265306125e-06,
|
| 30 |
+
"loss": 0.5213391876220703,
|
| 31 |
+
"step": 150
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.9174311926605505,
|
| 35 |
+
"grad_norm": 0.21484375,
|
| 36 |
+
"learning_rate": 1.938775510204082e-06,
|
| 37 |
+
"loss": 0.5070155334472656,
|
| 38 |
+
"step": 200
|
| 39 |
+
}
|
| 40 |
+
],
|
| 41 |
+
"logging_steps": 50,
|
| 42 |
+
"max_steps": 218,
|
| 43 |
+
"num_input_tokens_seen": 0,
|
| 44 |
+
"num_train_epochs": 1,
|
| 45 |
+
"save_steps": 50,
|
| 46 |
+
"stateful_callbacks": {
|
| 47 |
+
"TrainerControl": {
|
| 48 |
+
"args": {
|
| 49 |
+
"should_epoch_stop": false,
|
| 50 |
+
"should_evaluate": false,
|
| 51 |
+
"should_log": false,
|
| 52 |
+
"should_save": true,
|
| 53 |
+
"should_training_stop": true
|
| 54 |
+
},
|
| 55 |
+
"attributes": {}
|
| 56 |
+
}
|
| 57 |
+
},
|
| 58 |
+
"total_flos": 0.0,
|
| 59 |
+
"train_batch_size": 512,
|
| 60 |
+
"trial_name": null,
|
| 61 |
+
"trial_params": null
|
| 62 |
+
}
|
Qwen3-Embedding-4B-vilegal-stage2-adapter/checkpoint-218/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:95d54605f8792813f284d2a1340defc13104f5fe87e7480bb1f729704bfe28ed
|
| 3 |
+
size 5777
|
Qwen3-Embedding-4B-vilegal-stage2-adapter/config_sentence_transformers.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"__version__": {
|
| 3 |
+
"pytorch": "2.11.0+cu130",
|
| 4 |
+
"sentence_transformers": "5.4.1",
|
| 5 |
+
"transformers": "5.6.2"
|
| 6 |
+
},
|
| 7 |
+
"default_prompt_name": null,
|
| 8 |
+
"model_type": "SentenceTransformer",
|
| 9 |
+
"prompts": {
|
| 10 |
+
"document": "",
|
| 11 |
+
"query": "Instruct: Given a user query related to law, retrieve the most relevant legal passages that directly answer the question.\nQuery:"
|
| 12 |
+
},
|
| 13 |
+
"similarity_fn_name": "cosine"
|
| 14 |
+
}
|
Qwen3-Embedding-4B-vilegal-stage2-adapter/modules.json
ADDED
|
@@ -0,0 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
[
|
| 2 |
+
{
|
| 3 |
+
"idx": 0,
|
| 4 |
+
"name": "0",
|
| 5 |
+
"path": "",
|
| 6 |
+
"type": "sentence_transformers.base.modules.transformer.Transformer"
|
| 7 |
+
},
|
| 8 |
+
{
|
| 9 |
+
"idx": 1,
|
| 10 |
+
"name": "1",
|
| 11 |
+
"path": "1_Pooling",
|
| 12 |
+
"type": "sentence_transformers.sentence_transformer.modules.pooling.Pooling"
|
| 13 |
+
},
|
| 14 |
+
{
|
| 15 |
+
"idx": 2,
|
| 16 |
+
"name": "2",
|
| 17 |
+
"path": "2_Normalize",
|
| 18 |
+
"type": "sentence_transformers.sentence_transformer.modules.normalize.Normalize"
|
| 19 |
+
}
|
| 20 |
+
]
|
Qwen3-Embedding-4B-vilegal-stage2-adapter/sentence_bert_config.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"transformer_task": "feature-extraction",
|
| 3 |
+
"modality_config": {
|
| 4 |
+
"text": {
|
| 5 |
+
"method": "forward",
|
| 6 |
+
"method_output_name": "last_hidden_state"
|
| 7 |
+
}
|
| 8 |
+
},
|
| 9 |
+
"module_output_name": "token_embeddings"
|
| 10 |
+
}
|
Qwen3-Embedding-4B-vilegal-stage2-adapter/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:24712070ac72a218115ee256fd28888777437366e4c1b2ed70b21f75561eb90e
|
| 3 |
+
size 11423042
|
Qwen3-Embedding-4B-vilegal-stage2-adapter/tokenizer_config.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"backend": "tokenizers",
|
| 4 |
+
"bos_token": null,
|
| 5 |
+
"clean_up_tokenization_spaces": false,
|
| 6 |
+
"eos_token": "<|im_end|>",
|
| 7 |
+
"errors": "replace",
|
| 8 |
+
"is_local": true,
|
| 9 |
+
"local_files_only": false,
|
| 10 |
+
"model_max_length": 4096,
|
| 11 |
+
"pad_token": "<|endoftext|>",
|
| 12 |
+
"split_special_tokens": false,
|
| 13 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 14 |
+
"unk_token": null
|
| 15 |
+
}
|
Qwen3-Embedding-4B-vilegal-stage2-adapter/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:95d54605f8792813f284d2a1340defc13104f5fe87e7480bb1f729704bfe28ed
|
| 3 |
+
size 5777
|