commit 79e5ad25f813033cc0a58f4994157abe0bb60c2f Author: ModelHub XC Date: Fri Jul 10 01:09:12 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: umarfarookm/UmarTransit-1B Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..61870fd --- /dev/null +++ b/.gitattributes @@ -0,0 +1,38 @@ +*.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 +UmarTransit-1B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +UmarTransit-1B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..764ff57 --- /dev/null +++ b/README.md @@ -0,0 +1,168 @@ +--- +license: apache-2.0 +base_model: Qwen/Qwen2.5-1.5B-Instruct +tags: + - transit + - gtfs + - transportation + - instruction-following + - qwen2 + - qlora + - unsloth +language: + - en +dataset_info: + dataset_name: UmarTransit Synthetic Q&A +pipeline_tag: text-generation +--- + +# UmarTransit-1B + +A domain-specific language model for **public transit systems** and **GTFS (General Transit Feed Specification)** data, fine-tuned from Qwen2.5-1.5B-Instruct. + +UmarTransit-1B specializes in: +- GTFS understanding and validation +- Transit route and schedule analysis +- Stop/station information +- Transfer optimization +- Transit network statistics +- Cross-agency comparisons + +> **Data Disclaimer:** This model was trained **exclusively on publicly available, open-source GTFS feeds** published by transit agencies for public use via the [Mobility Database](https://mobilitydatabase.org/). **No private, proprietary, or NDA-protected data** from any client, employer, or organization was used at any stage. + +## Model Details + +| Property | Value | +|----------|-------| +| **Base Model** | [Qwen/Qwen2.5-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-1.5B-Instruct) | +| **Parameters** | 1.54B (1.31B non-embedding) | +| **Fine-tuning** | QLoRA (4-bit NF4, LoRA rank=16, alpha=32) | +| **Training Framework** | [Unsloth](https://unsloth.ai) + HuggingFace TRL | +| **Training Data** | 2,971 synthetic instruction-response pairs | +| **Test Data** | 335 pairs (stratified 90/10 split) | +| **Max Context** | 1,024 tokens | +| **License** | Apache 2.0 | +| **Developer** | [umarfarookm](https://github.com/umarfarookm) | + +## Evaluation Results + +Evaluated on 335 held-out test pairs across 8 task categories: + +| Metric | Score | +|--------|-------| +| **ROUGE-L** | 0.8192 | +| **Keyword Match** | 0.4086 | + +**Best performing:** Transfer analysis (ROUGE-L: 0.90) +**Needs improvement:** GTFS knowledge (ROUGE-L: 0.38) — limited training data (22 pairs) + +## Available Formats + +| Format | File | Size | Use Case | +|--------|------|------|----------| +| Safetensors | `model.safetensors` | 3.09 GB | Full precision — Transformers/Python | +| GGUF Q4_K_M | `UmarTransit-1B.Q4_K_M.gguf` | 986 MB | 4-bit — Ollama/llama.cpp (recommended) | +| GGUF Q8_0 | `UmarTransit-1B.Q8_0.gguf` | 1.65 GB | 8-bit — Ollama/llama.cpp (higher quality) | + +## Training Data + +The model was trained on synthetic instruction-response pairs generated from **15 real public GTFS feeds** across **10 countries**: + +| Country | Agencies | +|---------|----------| +| US | LA Metro, Chicago CTA, Boston MBTA, Valley Metro, Capital Metro, TriMet | +| Canada | Toronto TTC | +| Germany | Berlin VBB | +| France | Ile-de-France Mobilites (Paris) | +| Netherlands | OVapi (national) | +| Belgium | NMBS/SNCB Railways | +| Finland | HSL Helsinki | +| Denmark | Rejseplanen | +| Australia | Transperth (Perth) | +| New Zealand | Auckland Transport | + +**8 task categories:** Agency overview, route information, stop/station info, trip schedules, transfer analysis, network statistics, GTFS knowledge, comparative analysis. + +## Usage + +### With Transformers + +```python +from transformers import AutoModelForCausalLM, AutoTokenizer +import torch + +model = AutoModelForCausalLM.from_pretrained( + "umarfarookm/UmarTransit-1B", + torch_dtype=torch.bfloat16, + device_map="auto", +) +tokenizer = AutoTokenizer.from_pretrained("umarfarookm/UmarTransit-1B") + +messages = [ + {"role": "system", "content": "You are UmarTransit-1B, a specialized AI assistant for public transit systems and GTFS data."}, + {"role": "user", "content": "What does route_type 3 mean in GTFS?"}, +] + +text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True) +inputs = tokenizer(text, return_tensors="pt").to(model.device) + +outputs = model.generate(**inputs, max_new_tokens=256, temperature=0.1, do_sample=True) +response = tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:], skip_special_tokens=True) +print(response) +``` + +### With Ollama (GGUF) + +```bash +# Download the GGUF file from this repo, then: +ollama create umartransit -f Modelfile +ollama run umartransit "What are the required files in a GTFS feed?" +``` + +## Training Configuration + +``` +QLoRA Config: + rank: 16 + alpha: 32 + dropout: 0 + target_modules: q_proj, k_proj, v_proj, o_proj, gate_proj, up_proj, down_proj + +Training: + epochs: 3 + batch_size: 4 x 4 gradient accumulation = 16 effective + learning_rate: 2e-4 + scheduler: cosine + optimizer: adamw_8bit + hardware: Google Colab T4 GPU (15GB VRAM) +``` + +## Limitations + +- **Small training dataset:** 2,971 pairs — model may hallucinate specific details (coordinates, exact counts) +- **Limited GTFS knowledge:** Only 22 GTFS specification Q&A pairs in training +- **English-primary:** Trained on English instructions, though base model supports 29 languages +- **Static data:** Trained on GTFS schedule data, not real-time transit information +- **Not a trip planner:** Cannot compute actual routes or real-time ETAs + +## Future Improvements + +- Add more GTFS knowledge pairs (target 100+) +- Include Indian city transit feeds (Chennai, Bangalore, Mumbai) +- Expand to 10K+ training pairs for better factual accuracy +- Add GTFS-Realtime understanding + +## Source Code + +[github.com/umarfarookm/transit-foundation-model](https://github.com/umarfarookm/transit-foundation-model) + +## Citation + +```bibtex +@misc{umartransit1b, + title={UmarTransit-1B: A Domain-Specific Language Model for Public Transit}, + author={umarfarookm}, + year={2026}, + url={https://huggingface.co/umarfarookm/UmarTransit-1B} +} +``` diff --git a/UmarTransit-1B.Q4_K_M.gguf b/UmarTransit-1B.Q4_K_M.gguf new file mode 100644 index 0000000..87bd657 --- /dev/null +++ b/UmarTransit-1B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:db1a4489626110145274f508b3fa30439516a47b4e721fe02d67df4679db5b9a +size 986048096 diff --git a/UmarTransit-1B.Q8_0.gguf b/UmarTransit-1B.Q8_0.gguf new file mode 100644 index 0000000..4b5640e --- /dev/null +++ b/UmarTransit-1B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4fa807e5a9bcfffe5640a4c906dbb151beba76ad37aede5dc8b9a8175aaba771 +size 1646572640 diff --git a/chat_template.jinja b/chat_template.jinja new file mode 100644 index 0000000..bdf7919 --- /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 Qwen, created by Alibaba Cloud. 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 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' }} + {%- else %} + {{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You 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\n{"name": "' }} + {{- tool_call.name }} + {{- '", "arguments": ' }} + {{- tool_call.arguments | tojson }} + {{- '}\n' }} + {%- endfor %} + {{- '<|im_end|>\n' }} + {%- elif message.role == "tool" %} + {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %} + {{- '<|im_start|>user' }} + {%- endif %} + {{- '\n\n' }} + {{- message.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' }} +{%- endif %} diff --git a/config.json b/config.json new file mode 100644 index 0000000..c0e161e --- /dev/null +++ b/config.json @@ -0,0 +1,62 @@ +{ + "architectures": [ + "Qwen2ForCausalLM" + ], + "attention_dropout": 0.0, + "bos_token_id": null, + "torch_dtype": "float16", + "eos_token_id": 151645, + "hidden_act": "silu", + "hidden_size": 1536, + "initializer_range": 0.02, + "intermediate_size": 8960, + "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": 32768, + "max_window_layers": 21, + "model_type": "qwen2", + "num_attention_heads": 12, + "num_hidden_layers": 28, + "num_key_value_heads": 2, + "pad_token_id": 151654, + "rms_norm_eps": 1e-06, + "rope_parameters": { + "rope_theta": 1000000.0, + "rope_type": "default" + }, + "sliding_window": null, + "tie_word_embeddings": true, + "unsloth_fixed": true, + "unsloth_version": "2026.7.1", + "use_cache": true, + "use_sliding_window": false, + "vocab_size": 151936 +} \ No newline at end of file diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..83be784 --- /dev/null +++ b/generation_config.json @@ -0,0 +1,14 @@ +{ + "do_sample": true, + "eos_token_id": [ + 151645, + 151643 + ], + "max_length": 32768, + "pad_token_id": 151654, + "repetition_penalty": 1.1, + "temperature": 0.7, + "top_k": 20, + "top_p": 0.8, + "transformers_version": "5.5.0" +} diff --git a/model.safetensors b/model.safetensors new file mode 100644 index 0000000..d1386b8 --- /dev/null +++ b/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ee5b7ca8dc0c13fd404c8c04b22c14f3f5b0af726cb452a883c5841e8b1702b0 +size 3087467144 diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000..d73428d --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b4360dd6a184650ffc48056c2569bc603f896c5adfe94b10f1c79f809638aa5 +size 11422166 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..ec09d92 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,194 @@ +{ + "add_prefix_space": false, + "backend": "tokenizers", + "bos_token": null, + "clean_up_tokenization_spaces": false, + "eos_token": "<|im_end|>", + "errors": "replace", + "is_local": false, + "model_max_length": 32768, + "pad_token": "<|vision_pad|>", + "padding_side": "left", + "split_special_tokens": false, + "tokenizer_class": "Qwen2Tokenizer", + "unk_token": null, + "added_tokens_decoder": { + "151643": { + "content": "<|endoftext|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151644": { + "content": "<|im_start|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151645": { + "content": "<|im_end|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151646": { + "content": "<|object_ref_start|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151647": { + "content": "<|object_ref_end|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151648": { + "content": "<|box_start|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151649": { + "content": "<|box_end|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151650": { + "content": "<|quad_start|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151651": { + "content": "<|quad_end|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151652": { + "content": "<|vision_start|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151653": { + "content": "<|vision_end|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151654": { + "content": "<|vision_pad|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151655": { + "content": "<|image_pad|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151656": { + "content": "<|video_pad|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151657": { + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": false + }, + "151658": { + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": false + }, + "151659": { + "content": "<|fim_prefix|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": false + }, + "151660": { + "content": "<|fim_middle|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": false + }, + "151661": { + "content": "<|fim_suffix|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": false + }, + "151662": { + "content": "<|fim_pad|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": false + }, + "151663": { + "content": "<|repo_name|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": false + }, + "151664": { + "content": "<|file_sep|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": false + } + }, + "chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0]['role'] == 'system' %}\n {{- messages[0]['content'] }}\n {%- else %}\n {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n {%- endif %}\n {{- \"\\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 XML tags:\\n\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\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\" }}\n{%- else %}\n {%- if messages[0]['role'] == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n {%- else %}\n {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role }}\n {%- if message.content %}\n {{- '\\n' + message.content }}\n {%- endif %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '\\n\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- '}\\n' }}\n {%- endfor %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n\\n' }}\n {{- message.content }}\n {{- '\\n' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n" +} \ No newline at end of file