commit 55c5362824c7bdc2acafcecf9ef9ea12e418d0fe
Author: ModelHub XC <noreply@modelhub.org.cn>
Date:   Sun Aug 30 09:20:16 2026 +0800

    初始化项目，由ModelHub XC社区提供模型
    
    Model: 17Lab/qwen7b-hermes-fc-full-sft-s42
    Source: Original Platform

diff --git a/.gitattributes b/.gitattributes
new file mode 100644
index 0000000..52373fe
--- /dev/null
+++ 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
diff --git a/README.md b/README.md
new file mode 100644
index 0000000..857238b
--- /dev/null
+++ b/README.md
@@ -0,0 +1,67 @@
+---
+library_name: transformers
+license: other
+base_model: Qwen/Qwen2.5-7B
+tags:
+- llama-factory
+- full
+- generated_from_trainer
+model-index:
+- name: qwen7b_bfcl_mini_full_sft_s42
+  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. -->
+
+# qwen7b_bfcl_mini_full_sft_s42
+
+This model is a fine-tuned version of [Qwen/Qwen2.5-7B](https://huggingface.co/Qwen/Qwen2.5-7B) on the bfcl_mini_sft dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.2251
+
+## 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: 2e-05
+- train_batch_size: 4
+- eval_batch_size: 2
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 4
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 64
+- total_eval_batch_size: 8
+- 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: 0.05
+- num_epochs: 3
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 0.1746        | 1.96  | 25   | 0.2569          |
+| 0.0856        | 3.0   | 39   | 0.2251          |
+
+
+### Framework versions
+
+- Transformers 5.6.0
+- Pytorch 2.7.0+cu128
+- Datasets 4.0.0
+- Tokenizers 0.22.2
diff --git a/all_results.json b/all_results.json
new file mode 100644
index 0000000..617b2e8
--- /dev/null
+++ b/all_results.json
@@ -0,0 +1,12 @@
+{
+    "epoch": 3.0,
+    "eval_loss": 0.22509032487869263,
+    "eval_runtime": 0.8749,
+    "eval_samples_per_second": 48.004,
+    "eval_steps_per_second": 6.858,
+    "total_flos": 1274990395392.0,
+    "train_loss": 0.3065599493491344,
+    "train_runtime": 587.7054,
+    "train_samples_per_second": 4.012,
+    "train_steps_per_second": 0.066
+}
\ No newline at end of file
diff --git a/chat_template.jinja b/chat_template.jinja
new file mode 100644
index 0000000..28028c0
--- /dev/null
+++ b/chat_template.jinja
@@ -0,0 +1,54 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- messages[0]['content'] }}
+    {%- else %}
+        {{- 'You are a helpful assistant.' }}
+    {%- endif %}
+    {{- "\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>" }}
+    {%- 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' }}
+    {%- else %}
+        {{- '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role }}
+        {%- if message.content %}
+            {{- '\n' + message.content }}
+        {%- endif %}
+        {%- for tool_call in message.tool_calls %}
+            {%- if tool_call.function is defined %}
+                {%- set tool_call = tool_call.function %}
+            {%- endif %}
+            {{- '\n<tool_call>\n{"name": "' }}
+            {{- tool_call.name }}
+            {{- '", "arguments": ' }}
+            {{- tool_call.arguments | tojson }}
+            {{- '}\n</tool_call>' }}
+        {%- endfor %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.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' }}
+{%- endif %}
diff --git a/config.json b/config.json
new file mode 100644
index 0000000..6caff06
--- /dev/null
+++ b/config.json
@@ -0,0 +1,62 @@
+{
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": null,
+  "dtype": "bfloat16",
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "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": 131072,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "pad_token_id": 151643,
+  "rms_norm_eps": 1e-06,
+  "rope_parameters": {
+    "rope_theta": 1000000.0,
+    "rope_type": "default"
+  },
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "transformers_version": "5.6.0",
+  "use_cache": false,
+  "use_mrope": false,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}
diff --git a/eval_results.json b/eval_results.json
new file mode 100644
index 0000000..e528d1c
--- /dev/null
+++ b/eval_results.json
@@ -0,0 +1,7 @@
+{
+    "epoch": 3.0,
+    "eval_loss": 0.22509032487869263,
+    "eval_runtime": 0.8749,
+    "eval_samples_per_second": 48.004,
+    "eval_steps_per_second": 6.858
+}
\ No newline at end of file
diff --git a/generation_config.json b/generation_config.json
new file mode 100644
index 0000000..a0ea6f1
--- /dev/null
+++ b/generation_config.json
@@ -0,0 +1,10 @@
+{
+  "do_sample": false,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "max_new_tokens": 2048,
+  "pad_token_id": 151643,
+  "transformers_version": "5.6.0"
+}
diff --git a/model.safetensors b/model.safetensors
new file mode 100644
index 0000000..66da33a
--- /dev/null
+++ b/model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b46c73af91374d795eb05d9d4ca84a691b2b3a4a505882b9fa3f7b2fb68511d
+size 15231272152
diff --git a/tokenizer.json b/tokenizer.json
new file mode 100644
index 0000000..34510ff
--- /dev/null
+++ b/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3fd169731d2cbde95e10bf356d66d5997fd885dd8dbb6fb4684da3f23b2585d8
+size 11421892
diff --git a/tokenizer_config.json b/tokenizer_config.json
new file mode 100644
index 0000000..6623da0
--- /dev/null
+++ b/tokenizer_config.json
@@ -0,0 +1,31 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "is_local": false,
+  "local_files_only": false,
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}
diff --git a/train_results.json b/train_results.json
new file mode 100644
index 0000000..37fa055
--- /dev/null
+++ b/train_results.json
@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "total_flos": 1274990395392.0,
+    "train_loss": 0.3065599493491344,
+    "train_runtime": 587.7054,
+    "train_samples_per_second": 4.012,
+    "train_steps_per_second": 0.066
+}
\ No newline at end of file
diff --git a/trainer_log.jsonl b/trainer_log.jsonl
new file mode 100644
index 0000000..2abaeb8
--- /dev/null
+++ b/trainer_log.jsonl
@@ -0,0 +1,10 @@
+{"current_steps": 5, "total_steps": 39, "loss": 0.8891424179077149, "lr": 1.9856159103477085e-05, "epoch": 0.4, "percentage": 12.82, "elapsed_time": "0:00:23", "remaining_time": "0:02:38"}
+{"current_steps": 10, "total_steps": 39, "loss": 0.5139811515808106, "lr": 1.8285096492438424e-05, "epoch": 0.8, "percentage": 25.64, "elapsed_time": "0:00:38", "remaining_time": "0:01:52"}
+{"current_steps": 15, "total_steps": 39, "loss": 0.3687877893447876, "lr": 1.5243072835572319e-05, "epoch": 1.16, "percentage": 38.46, "elapsed_time": "0:00:51", "remaining_time": "0:01:23"}
+{"current_steps": 20, "total_steps": 39, "loss": 0.21150989532470704, "lr": 1.1270178197468788e-05, "epoch": 1.56, "percentage": 51.28, "elapsed_time": "0:01:06", "remaining_time": "0:01:03"}
+{"current_steps": 25, "total_steps": 39, "loss": 0.17464923858642578, "lr": 7.071772287234497e-06, "epoch": 1.96, "percentage": 64.1, "elapsed_time": "0:01:21", "remaining_time": "0:00:45"}
+{"current_steps": 25, "total_steps": 39, "eval_loss": 0.25689050555229187, "epoch": 1.96, "percentage": 64.1, "elapsed_time": "0:01:22", "remaining_time": "0:00:46"}
+{"current_steps": 30, "total_steps": 39, "loss": 0.09203737378120422, "lr": 3.3932527660991877e-06, "epoch": 2.32, "percentage": 76.92, "elapsed_time": "0:05:18", "remaining_time": "0:01:35"}
+{"current_steps": 35, "total_steps": 39, "loss": 0.0855832576751709, "lr": 8.87715096118642e-07, "epoch": 2.7199999999999998, "percentage": 89.74, "elapsed_time": "0:05:32", "remaining_time": "0:00:38"}
+{"current_steps": 39, "total_steps": 39, "eval_loss": 0.22509032487869263, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "0:05:44", "remaining_time": "0:00:00"}
+{"current_steps": 39, "total_steps": 39, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "0:09:27", "remaining_time": "0:00:00"}
diff --git a/trainer_state.json b/trainer_state.json
new file mode 100644
index 0000000..f6a0884
--- /dev/null
+++ b/trainer_state.json
@@ -0,0 +1,108 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 25,
+  "global_step": 39,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.4,
+      "grad_norm": 14.682328659827894,
+      "learning_rate": 1.9856159103477085e-05,
+      "loss": 0.8891424179077149,
+      "step": 5
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 11.714302479472073,
+      "learning_rate": 1.8285096492438424e-05,
+      "loss": 0.5139811515808106,
+      "step": 10
+    },
+    {
+      "epoch": 1.16,
+      "grad_norm": 10.208381605756056,
+      "learning_rate": 1.5243072835572319e-05,
+      "loss": 0.3687877893447876,
+      "step": 15
+    },
+    {
+      "epoch": 1.56,
+      "grad_norm": 10.262843920575644,
+      "learning_rate": 1.1270178197468788e-05,
+      "loss": 0.21150989532470704,
+      "step": 20
+    },
+    {
+      "epoch": 1.96,
+      "grad_norm": 6.68105063937876,
+      "learning_rate": 7.071772287234497e-06,
+      "loss": 0.17464923858642578,
+      "step": 25
+    },
+    {
+      "epoch": 1.96,
+      "eval_loss": 0.25689050555229187,
+      "eval_runtime": 0.9005,
+      "eval_samples_per_second": 46.642,
+      "eval_steps_per_second": 6.663,
+      "step": 25
+    },
+    {
+      "epoch": 2.32,
+      "grad_norm": 5.69195152871731,
+      "learning_rate": 3.3932527660991877e-06,
+      "loss": 0.09203737378120422,
+      "step": 30
+    },
+    {
+      "epoch": 2.7199999999999998,
+      "grad_norm": 4.8584537804368715,
+      "learning_rate": 8.87715096118642e-07,
+      "loss": 0.0855832576751709,
+      "step": 35
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.22509032487869263,
+      "eval_runtime": 0.8925,
+      "eval_samples_per_second": 47.061,
+      "eval_steps_per_second": 6.723,
+      "step": 39
+    },
+    {
+      "epoch": 3.0,
+      "step": 39,
+      "total_flos": 1274990395392.0,
+      "train_loss": 0.3065599493491344,
+      "train_runtime": 587.7054,
+      "train_samples_per_second": 4.012,
+      "train_steps_per_second": 0.066
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 39,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 25,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1274990395392.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/training_args.bin b/training_args.bin
new file mode 100644
index 0000000..19e8877
--- /dev/null
+++ b/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c9d4d8b3e2a1ba2b5a51263d22c647c20bc87114204ffb764d1eac7e28268bf
+size 7377