From 87b2df530f07f2b96efa97f2019dbad083dc65a8 Mon Sep 17 00:00:00 2001 From: ModelHub XC Date: Sat, 13 Jun 2026 09:38:16 +0800 Subject: [PATCH] =?UTF-8?q?=E5=88=9D=E5=A7=8B=E5=8C=96=E9=A1=B9=E7=9B=AE?= =?UTF-8?q?=EF=BC=8C=E7=94=B1ModelHub=20XC=E7=A4=BE=E5=8C=BA=E6=8F=90?= =?UTF-8?q?=E4=BE=9B=E6=A8=A1=E5=9E=8B?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Model: cs-552-2026-4neurons/multilingual_model Source: Original Platform --- .gitattributes | 36 ++++++++ EVAL_REPORT.md | 94 +++++++++++++++++++ README.md | 199 +++++++++++++++++++++++++++++++++++++++++ chat_template.jinja | 108 ++++++++++++++++++++++ config.json | 63 +++++++++++++ generation_config.json | 13 +++ model.safetensors | 3 + tokenizer.json | 3 + tokenizer_config.json | 30 +++++++ 9 files changed, 549 insertions(+) create mode 100644 .gitattributes create mode 100644 EVAL_REPORT.md create mode 100644 README.md create mode 100644 chat_template.jinja create mode 100644 config.json create mode 100644 generation_config.json create mode 100644 model.safetensors create mode 100644 tokenizer.json create mode 100644 tokenizer_config.json 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/EVAL_REPORT.md b/EVAL_REPORT.md new file mode 100644 index 0000000..e7c554d --- /dev/null +++ b/EVAL_REPORT.md @@ -0,0 +1,94 @@ +# Automated MNLP evaluation report + +- **Model repo:** [`cs-552-2026-4neurons/multilingual_model`](https://huggingface.co/cs-552-2026-4neurons/multilingual_model) +- **Owner(s):** group **4neurons** +- **Generated at:** 2026-06-09T08:56:40+00:00 (UTC) +- **Pipeline:** [mnlp-project-ci](https://github.com/eric11eca/mnlp-project-ci) + +_This PR is opened automatically by the course CI. It is **non-blocking** — you do not need to merge it. The next nightly run will refresh this file._ + +## Evaluated checkpoint + +- **Commit:** [`c1b9ac8`](https://huggingface.co/cs-552-2026-4neurons/multilingual_model/commit/c1b9ac861378e189045611415a6259003b80494f) +- **Message:** Upload config +- **Committed:** 2026-05-29T08:04:02+00:00 + +## Summary + +| Benchmark | Accuracy | Status | +|---|---:|---| +| Math | — | not run | +| Knowledge | — | not run | +| Multilingual | 0.6000 | ok | +| Safety | — | not run | + +## Sample completions + +_Prompts are intentionally omitted to avoid revealing benchmark contents. For multi-completion problems, only one completion is shown per sample._ + +### Multilingual + +**Correct** (1 shown) + +- **reference**: `D` +- **overall** (1/1 completions correct) +- **extracted** (✓): `D` +- **completion**: + + ```text + + Okay, let's see. The question is in Hindi, and it's about a type of deception in marketing where a product or service is presented as something else. The options are A to D. + + First, I need to recall the different types of deceptive practices in marketing. The question is asking when a product or service is presented with another complementary product or service. + + Option D is "शुद्न मूल्य + + ... [truncated 403 chars] ... + + is presented as part of a bundle with another product, that's more about price bundling where both are sold together. But sometimes, "bundling" can refer to selling multiple products together. However, the options given are in Hindi, so maybe the correct term is "price bundling" (D) where the product is sold with another, making it seem like a package deal. + + Alternatively, "price discrimination" (B) is when different prices are charged for the same product or service. "Purely price discrimination" (B) is a type where the seller doesn't consider the buyer's willingness to pay. + + "Purely price bundling" (D) is when a product is sold with another product at a higher price than the sum. So if a product is presented as part of a bundle with another, that's bundling. But the question is about presenting a product with another complementary product. So the answer would be D. + + Wait, but sometimes "bundling" can be a form of deception if the customer isn't getting the additional product they paid for. So the correct answer here is D, which is "purely price bundling," where the product is sold as a bundle with another, leading to deception. + + So the answer should be D. + + + \boxed{D} + ``` + +**Incorrect** (1 shown) + +- **reference**: `A` +- **overall** (0/1 completions correct) +- **extracted** (✗): `B` +- **completion**: + + ```text + + Okay, let's see. The question is in Russian, and it's asking about the term for a set of three formal objects. The options are A to D. + + First, I need to recall what "тройка формальных объектов" means. "Формальные объекты" translates to "formal objects," so the question is about three formal objects. The term here is likely a specific term in a particular field. Let's look at the options. + + ... [truncated 823 chars] ... + + he options: + + - **A. Квалиметрической шкалой** refers to a *qualimetric scale*, which is a type of measurement system that combines both qualitative and quantitative data. While it involves multiple types of data, it is not specifically defined as a "set of three formal objects." + + - **B. Шкалированием** translates to **"scaling"**, which is a general term for assigning numerical values to data. While scaling can involve multiple data points, it is not a precise term for a *set of three formal objects*. + + - **C. Ранжирование** means **"ranging"**, which typically refers to measuring or comparing distances or quantities in a linear context. It is not a formal term for a group of three objects. + + - **D. Размерность** translates to **"dimensionality"**, which refers to the number of dimensions in a dataset or a system. While it can imply the number of objects or variables, it is not a term that refers to a *set of three formal objects*. + + --- + + Given that none of the options perfectly match the phrasing of the question, and considering that **"шкалированием"** (option B) is the most likely interpretation of the phrase in a technical or formal context, the correct answer is: + + $$ + \boxed{B} + $$ + ``` 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 + + + + + +## Model Details + +### Model Description + + + +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] + + + +- **Repository:** [More Information Needed] +- **Paper [optional]:** [More Information Needed] +- **Demo [optional]:** [More Information Needed] + +## Uses + + + +### Direct Use + + + +[More Information Needed] + +### Downstream Use [optional] + + + +[More Information Needed] + +### Out-of-Scope Use + + + +[More Information Needed] + +## Bias, Risks, and Limitations + + + +[More Information Needed] + +### Recommendations + + + +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 + + + +[More Information Needed] + +### Training Procedure + + + +#### Preprocessing [optional] + +[More Information Needed] + + +#### Training Hyperparameters + +- **Training regime:** [More Information Needed] + +#### Speeds, Sizes, Times [optional] + + + +[More Information Needed] + +## Evaluation + + + +### Testing Data, Factors & Metrics + +#### Testing Data + + + +[More Information Needed] + +#### Factors + + + +[More Information Needed] + +#### Metrics + + + +[More Information Needed] + +### Results + +[More Information Needed] + +#### Summary + + + +## Model Examination [optional] + + + +[More Information Needed] + +## Environmental Impact + + + +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] + + + +**BibTeX:** + +[More Information Needed] + +**APA:** + +[More Information Needed] + +## Glossary [optional] + + + +[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..f4aace1 --- /dev/null +++ b/chat_template.jinja @@ -0,0 +1,108 @@ +{%- set enable_thinking = true %} +{%- if messages[0]['role'] != 'system' %} +{% set messages = [{"role": "system", "content": "# Task Instructions +You are a helpful multilingual reasoning assistant for multiple-choice questions. +For multiple-choice questions, reason step by step, then provide your final answer as a single letter inside \\boxed{}, for example: \\boxed{A}. +Do not include anything after the \\boxed{}. + +# Language Instructions +Questions will be in one of the following languages: Italian, Spanish, Russian, Hindi, Chinese. +You should reason in English, but follow the instructions below: +Think carefully, do not translate the question while solving. +Preserve the question in the target language so that you keep all details without adding noise. +After you finish thinking, state your answer in fluent and coherent target language. +Preserve named entities, quoted spans, and key terms in the target language while generating the rest of the reasoning in English."}] + messages %} +{%- endif %} +{%- set enable_thinking = true %} +{%- 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 XML tags:\n" }} + {%- for tool in tools %} + {{- "\n" }} + {{- tool | tojson }} + {%- endfor %} + {{- "\n\n\nFor each function call, return a json object with function name and arguments within XML tags:\n\n{\"name\": , \"arguments\": }\n<|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('') and message.content.endswith('')) %} + {%- 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 '' in content %} + {%- set reasoning_content = content.split('')[0].rstrip('\n').split('')[-1].lstrip('\n') %} + {%- set content = content.split('')[-1].lstrip('\n') %} + {%- endif %} + {%- endif %} + {%- if loop.index0 > ns.last_query_index %} + {{- '<|im_start|>' + message.role + '\n' }} + {% generation %} + {%- if loop.last or (not loop.last and reasoning_content) %} + {{- '\n' + reasoning_content.strip('\n') + '\n\n\n' + content.lstrip('\n') }} + {%- else %} + {{- content }} + {%- endif %} + {% endgeneration %} + {%- 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 %} + {{- '\n{"name": "' }} + {{- tool_call.name }} + {{- '", "arguments": ' }} + {%- if tool_call.arguments is string %} + {{- tool_call.arguments }} + {%- else %} + {{- tool_call.arguments | tojson }} + {%- endif %} + {{- '}\n' }} + {%- endfor %} + {%- endif %} + {{- '<|im_end|>\n' }} + {%- elif message.role == "tool" %} + {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %} + {{- '<|im_start|>user' }} + {%- endif %} + {{- '\n\n' }} + {{- content }} + {{- '\n' }} + {%- 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 %} + {{- '\n\n\n\n' }} + {%- endif %} +{%- endif %} \ No newline at end of file diff --git a/config.json b/config.json new file mode 100644 index 0000000..c1ff45d --- /dev/null +++ b/config.json @@ -0,0 +1,63 @@ +{ + "architectures": [ + "Qwen3ForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": 151643, + "dtype": "bfloat16", + "eos_token_id": 151645, + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 2048, + "initializer_range": 0.02, + "intermediate_size": 6144, + "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": null, + "rms_norm_eps": 1e-06, + "rope_parameters": { + "rope_theta": 1000000, + "rope_type": "default" + }, + "sliding_window": null, + "tie_word_embeddings": true, + "transformers_version": "5.7.0", + "use_cache": true, + "use_sliding_window": false, + "vocab_size": 151936 +} diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..1782b44 --- /dev/null +++ b/generation_config.json @@ -0,0 +1,13 @@ +{ + "bos_token_id": 151643, + "do_sample": true, + "eos_token_id": [ + 151645, + 151643 + ], + "pad_token_id": 151643, + "temperature": 0.7, + "top_k": 20, + "top_p": 0.9, + "transformers_version": "5.7.0" +} diff --git a/model.safetensors b/model.safetensors new file mode 100644 index 0000000..a57d856 --- /dev/null +++ b/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9239af515187163e9d5dfd5bb9e06048c8bedbf967525319213e7b2ee2fa83ef +size 3441185608 diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000..c7afbed --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:be75606093db2094d7cd20f3c2f385c212750648bd6ea4fb2bf507a6a4c55506 +size 11422650 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..5668a4a --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,30 @@ +{ + "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": true, + "local_files_only": false, + "model_max_length": 131072, + "pad_token": "<|endoftext|>", + "split_special_tokens": false, + "tokenizer_class": "Qwen2Tokenizer", + "unk_token": null +}