初始化项目，由ModelHub XC社区提供模型

Model: lldois/v30_soup_v19_v21_v26_w45_35_20 Source: Original Platform
2026-07-21 20:18:10 +08:00
commit 1ebc36f84a
10 changed files with 426 additions and 0 deletions
--- a/.gitattributes
+++ b/.gitattributes
@@ -0,0 +1,36 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text
--- a/README.md
+++ b/README.md
@@ -0,0 +1,58 @@
+---
+library_name: transformers
+license: other
+base_model: lldois/v15_user_logic_json_lr15e6
+tags:
+- llama-factory
+- full
+- generated_from_trainer
+model-index:
+- name: v19_v15_dualmode_fast_lr5e6_ep055
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# v19_v15_dualmode_fast_lr5e6_ep055
+
+This model is a fine-tuned version of [lldois/v15_user_logic_json_lr15e6](https://huggingface.co/lldois/v15_user_logic_json_lr15e6) on the exp_v15_dualmode_fast dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 5e-06
+- train_batch_size: 1
+- eval_batch_size: 8
+- seed: 202607191
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 4
+- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 0.02
+- num_epochs: 0.55
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 5.6.0
+- Pytorch 2.7.1+cu126
+- Datasets 4.0.0
+- Tokenizers 0.22.2
--- a/chat_template.jinja
+++ b/chat_template.jinja
@@ -0,0 +1,89 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- messages[0].content + '\n\n' }}
+    {%- endif %}
+    {{- "# 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>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\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" }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- 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>')) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if message.content is string %}
+        {%- set content = message.content %}
+    {%- else %}
+        {%- set content = '' %}
+    {%- endif %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is string %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in content %}
+                {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+                {%- set content = content.split('</think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {%- if loop.last or (not loop.last and reasoning_content) %}
+                {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
+            {%- else %}
+                {{- '<|im_start|>' + message.role + '\n' + content }}
+            {%- endif %}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}
--- a/config.json
+++ b/config.json
@@ -0,0 +1,63 @@
+{
+  "architectures": [
+    "Qwen3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": null,
+  "dtype": "bfloat16",
+  "eos_token_id": 151645,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_types": [
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 40960,
+  "max_window_layers": 28,
+  "model_type": "qwen3",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 8,
+  "pad_token_id": 151643,
+  "rms_norm_eps": 1e-06,
+  "rope_parameters": {
+    "rope_theta": 1000000,
+    "rope_type": "default"
+  },
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "transformers_version": "5.6.0",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 176253
+}
--- a/experiment_recipe.json
+++ b/experiment_recipe.json
@@ -0,0 +1,73 @@
+{
+  "created_at": "2026-07-12 04:25:42",
+  "name": "v30_soup_v19_v21_v26_w45_35_20",
+  "method": "weighted_model_soup",
+  "sources": [
+    {
+      "path": "/home/ll/llm4rec/experiments/outputs/v19_v15_dualmode_fast_lr5e6_ep055",
+      "weight": 0.45
+    },
+    {
+      "path": "/home/ll/llm4rec/experiments/outputs/v21_v15_user_repair_rec_fast_lr4e6_ep055",
+      "weight": 0.35
+    },
+    {
+      "path": "/home/ll/llm4rec/experiments/outputs/v26_v21_product_rec_rebalance_lr22e6_ep032",
+      "weight": 0.2
+    }
+  ],
+  "source_scores": {
+    "v19": {
+      "total": 0.8855,
+      "item": 0.2146,
+      "user": [
+        0.0855,
+        0.0337
+      ],
+      "rec": [
+        0.0768,
+        0.102,
+        0.1344,
+        0.1143
+      ],
+      "world": 0.1242,
+      "eval_time_min": 48.11
+    },
+    "v21": {
+      "total": 0.88,
+      "item": 0.2146,
+      "user": [
+        0.0881,
+        0.0347
+      ],
+      "rec": [
+        0.0576,
+        0.1122,
+        0.1358,
+        0.1098
+      ],
+      "world": 0.1271,
+      "eval_time_min": 47.61
+    },
+    "v26": {
+      "total": 0.8804,
+      "item": 0.2146,
+      "user": [
+        0.0895,
+        0.0344
+      ],
+      "rec": [
+        0.0768,
+        0.0986,
+        0.133,
+        0.1116
+      ],
+      "world": 0.1219,
+      "eval_time_min": 45.73
+    }
+  },
+  "rationale": "Average related CoT-native checkpoints from the same architecture to combine v19 total/rec4, v21 user/world signal, and v26 user1/rec1/speed without adding inference-time cost.",
+  "cot_policy": "No v7 final-only checkpoint is used. All sources are CoT-native continuations.",
+  "reproduce": "demo/LLaMA-Factory/.venv/bin/python experiments/model_soup.py --name v30_soup_v19_v21_v26_w45_35_20 --overwrite",
+  "runtime_seconds": 2.36
+}
--- a/generation_config.json
+++ b/generation_config.json
@@ -0,0 +1,12 @@
+{
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "temperature": 0.6,
+  "top_k": 20,
+  "top_p": 0.95,
+  "transformers_version": "5.6.0"
+}
--- a/merge_results.json
+++ b/merge_results.json
@@ -0,0 +1,73 @@
+{
+  "created_at": "2026-07-12 04:25:42",
+  "name": "v30_soup_v19_v21_v26_w45_35_20",
+  "method": "weighted_model_soup",
+  "sources": [
+    {
+      "path": "/home/ll/llm4rec/experiments/outputs/v19_v15_dualmode_fast_lr5e6_ep055",
+      "weight": 0.45
+    },
+    {
+      "path": "/home/ll/llm4rec/experiments/outputs/v21_v15_user_repair_rec_fast_lr4e6_ep055",
+      "weight": 0.35
+    },
+    {
+      "path": "/home/ll/llm4rec/experiments/outputs/v26_v21_product_rec_rebalance_lr22e6_ep032",
+      "weight": 0.2
+    }
+  ],
+  "source_scores": {
+    "v19": {
+      "total": 0.8855,
+      "item": 0.2146,
+      "user": [
+        0.0855,
+        0.0337
+      ],
+      "rec": [
+        0.0768,
+        0.102,
+        0.1344,
+        0.1143
+      ],
+      "world": 0.1242,
+      "eval_time_min": 48.11
+    },
+    "v21": {
+      "total": 0.88,
+      "item": 0.2146,
+      "user": [
+        0.0881,
+        0.0347
+      ],
+      "rec": [
+        0.0576,
+        0.1122,
+        0.1358,
+        0.1098
+      ],
+      "world": 0.1271,
+      "eval_time_min": 47.61
+    },
+    "v26": {
+      "total": 0.8804,
+      "item": 0.2146,
+      "user": [
+        0.0895,
+        0.0344
+      ],
+      "rec": [
+        0.0768,
+        0.0986,
+        0.133,
+        0.1116
+      ],
+      "world": 0.1219,
+      "eval_time_min": 45.73
+    }
+  },
+  "rationale": "Average related CoT-native checkpoints from the same architecture to combine v19 total/rec4, v21 user/world signal, and v26 user1/rec1/speed without adding inference-time cost.",
+  "cot_policy": "No v7 final-only checkpoint is used. All sources are CoT-native continuations.",
+  "reproduce": "demo/LLaMA-Factory/.venv/bin/python experiments/model_soup.py --name v30_soup_v19_v21_v26_w45_35_20 --overwrite",
+  "runtime_seconds": 2.36
+}
--- a/model.safetensors
+++ b/model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf4f453ee3597021d3bac0ea2bf08ec9f71f03dbb34764e287131960817b0bb4
+size 1602902800
--- a/tokenizer.json
+++ b/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd4d15f596979aecbc11ba12668cb21c9fb8452ce1235cd9d7878cc950170421
+size 16016554
--- a/tokenizer_config.json
+++ b/tokenizer_config.json
@@ -0,0 +1,16 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "is_local": true,
+  "local_files_only": false,
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}