commit 0464e2304bbeb01c81e7c7df394e9f340b5f6480
Author: ModelHub XC <noreply@modelhub.org.cn>
Date:   Sun Aug 9 16:05:16 2026 +0800

    初始化项目，由ModelHub XC社区提供模型
    
    Model: daslab-testing/Apertus-3B-DPO-wnorm2both
    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..bc5f30d
--- /dev/null
+++ b/README.md
@@ -0,0 +1,199 @@
+---
+library_name: transformers
+tags: []
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
\ No newline at end of file
diff --git a/chat_template.jinja b/chat_template.jinja
new file mode 100644
index 0000000..a465081
--- /dev/null
+++ b/chat_template.jinja
@@ -0,0 +1,5 @@
+{{ bos_token }}{%- set system_token = '<SPECIAL_61>' -%}{%- set end_system_token = '<SPECIAL_62>' -%}{%- set developer_token = '<SPECIAL_63>' -%}{%- set end_developer_token = '<SPECIAL_64>' -%}{%- set user_token = '<SPECIAL_65>' -%}{%- set end_user_token = '<SPECIAL_66>' -%}{%- set assistant_token = '<SPECIAL_67>' -%}{%- set end_assistant_token = '<SPECIAL_68>' -%}{%- set inner_token = '<SPECIAL_69>' -%}{%- set outer_token = '<SPECIAL_70>' -%}{%- set tool_calls_token = '<SPECIAL_71>' -%}{%- set end_tool_calls_token = '<SPECIAL_72>' -%}{%- if messages and messages[0].role == 'system' -%}   {%- set system_content = messages[0].content -%}    {{ system_token }}    {%- if system_content is string -%}        {{ system_content }}    {%- elif system_content is mapping and "text" in system_content -%}        {{ system_content.text }}    {%- else -%}        {{- raise_exception("Invalid system content: " + str(system_content)) -}}    {%- endif -%}    {{ end_system_token }}    {%- set messages_without_system = messages[1:] -%}{%- else -%}    {{ system_token + end_system_token }}    {%- set messages_without_system = messages -%}{%- endif -%}{%- if messages_without_system and messages_without_system[0].role == 'developer' -%}    {%- set developer_content = messages_without_system[0].content -%}    {{ developer_token }}    {%- if "has_thinking" in developer_content -%}        {{ 'Deliberation: ' }}        {%- if developer_content.has_thinking -%}            {{ 'enabled' }}        {%- else -%}            {{ 'disabled' }}        {%- endif -%}        {{ '
+' }}    {%- else -%}        {{ 'Deliberation: disabled
+' }}    {%- endif -%}    {%- if "formatted_tools" in developer_content and developer_content.formatted_tools -%}        {{ 'Tool Capabilities:
+' + developer_content.formatted_tools }}    {%- else -%}        {{ 'Tool Capabilities: disabled' }}    {%- endif -%}    {{ end_developer_token }}    {%- set loop_messages = messages_without_system[1:] -%}{%- else -%}    {{ developer_token + 'Deliberation: disabled
+Tool Capabilities: disabled' + end_developer_token }}    {%- set loop_messages = messages_without_system -%}{%- endif -%}{%- for message in loop_messages -%}    {%- set content = message.content -%}    {%- if message.role == 'user' -%}        {{ user_token }}        {%- if content is string -%}            {{ content }}        {%- elif content is sequence -%}            {%- for part in content.parts -%}                {%- if part.type == 'text' -%}                    {{ part.text }}                {%- endif -%}            {%- endfor -%}        {%- else -%}            {{- raise_exception("Invalid user content: " + str(content)) -}}        {%- endif -%}        {{ end_user_token }}    {%- elif message.role == 'assistant' -%}        {{ assistant_token }}        {%- if content is string -%}            {{ content }}        {%- elif content is sequence -%}            {%- set ns = namespace(in_inner=false) -%}            {%- for block in content.blocks -%}                {%- if block.type == 'thoughts' -%}                    {%- if not ns.in_inner -%}                        {%- set ns.in_inner = true -%}                        {{ inner_token }}                    {%- endif -%}                    {{ block.text }}                {%- elif block.type == 'tool_calls' -%}                    {%- if ns.in_inner and not loop.first and block.calls|length == 1 and block.calls[0].name == 'display_answers' -%}                        {%- set ns.in_inner = false -%}                        {{ outer_token }}                    {%- endif -%}                    {{ tool_calls_token + '[' }}                    {%- for tool_call in block.calls -%}                        {{- '{"' + tool_call.name + '": ' + tool_call.arguments + '}' }}                        {%- if not loop.last -%}                            {{- ", " }}                        {%- endif -%}                    {%- endfor -%}                    {{ ']' + end_tool_calls_token }}                {%- elif block.type == 'tool_outputs' -%}                    {{ '[' }}                    {%- for tool_output in block.outputs -%}                        {{- tool_output.output }}                        {%- if not loop.last -%}                            {{- ", " }}                        {%- endif -%}                    {%- endfor -%}                    {{- ']' }}                    {%- if not loop.last -%}                        {{- ' ' }}                    {%- endif -%}                {%- elif block.type == 'response' -%}                    {%- if not loop.first and ns.in_inner -%}                        {%- set ns.in_inner = false -%}                        {{ outer_token }}                    {%- endif -%}                    {{ block.text }}                {%- else -%}                    {{- raise_exception("Invalid block type: " + block.type) -}}                {%- endif -%}            {%- endfor -%}        {%- else -%}            {{- raise_exception("Invalid assistant content: " + str(content)) -}}        {%- endif -%}        {{ end_assistant_token }}    {%- else -%}        {{- raise_exception("Invalid message role: " + message.role) -}}    {%- endif -%}{%- endfor -%}{%- if add_generation_prompt -%}    {{ assistant_token }}{%- endif -%}
\ No newline at end of file
diff --git a/config.json b/config.json
new file mode 100644
index 0000000..c9e8969
--- /dev/null
+++ b/config.json
@@ -0,0 +1,34 @@
+{
+  "architectures": [
+    "ApertusForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "dtype": "bfloat16",
+  "eos_token_id": 68,
+  "hidden_act": "xielu",
+  "hidden_dropout": 0.0,
+  "hidden_size": 3072,
+  "initializer_range": 0.02,
+  "intermediate_size": 16384,
+  "max_position_embeddings": 4096,
+  "mlp_bias": false,
+  "model_type": "apertus",
+  "num_attention_heads": 24,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 8,
+  "pad_token_id": 10,
+  "post_norm": false,
+  "qk_norm": true,
+  "rms_norm_eps": 1e-05,
+  "rope_parameters": {
+    "rope_theta": 500000.0,
+    "rope_type": "default"
+  },
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": false,
+  "transformers_version": "5.7.0",
+  "use_cache": false,
+  "vocab_size": 131072
+}
diff --git a/generation_config.json b/generation_config.json
new file mode 100644
index 0000000..1078c59
--- /dev/null
+++ b/generation_config.json
@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": [
+    68
+  ],
+  "pad_token_id": 10,
+  "transformers_version": "5.7.0"
+}
diff --git a/model.safetensors b/model.safetensors
new file mode 100644
index 0000000..6ad9aba
--- /dev/null
+++ b/model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a3d47e2c5c216e41e2ad92d81f8dcfec50180e1a76dd71522b50d8fb7c45fb3b
+size 7650761920
diff --git a/tokenizer.json b/tokenizer.json
new file mode 100644
index 0000000..8626dfc
--- /dev/null
+++ b/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be12f4375d655cc740864e3a9041bcddd8477942f209d9e7f27f6c8767162638
+size 17078368
diff --git a/tokenizer_config.json b/tokenizer_config.json
new file mode 100644
index 0000000..7cb2d07
--- /dev/null
+++ b/tokenizer_config.json
@@ -0,0 +1,18 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<SPECIAL_68>",
+  "is_local": false,
+  "local_files_only": false,
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "padding_side": "left",
+  "tokenizer_class": "TokenizersBackend",
+  "unk_token": "<unk>"
+}