commit b55d3bb9fdb4897a721c1b4ccade0fda6dc0846b Author: ModelHub XC Date: Sun Aug 9 04:57:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: perfectPresentation/rcrc-chat-v5-gemma-1b-cpt-sft Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..a5f7557 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,44 @@ +*.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 +gguf/rcrc-v5-gemma-1b-cpt-sft-F16.gguf filter=lfs diff=lfs merge=lfs -text +gguf/rcrc-v5-gemma-1b-cpt-sft-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +gguf/rcrc-v5-gemma-1b-cpt-sft-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +gguf/rcrc-v5-gemma-1b-cpt-sft-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +rcrc-v5-gemma-1b-cpt-sft-F16.gguf filter=lfs diff=lfs merge=lfs -text +rcrc-v5-gemma-1b-cpt-sft-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +rcrc-v5-gemma-1b-cpt-sft-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +rcrc-v5-gemma-1b-cpt-sft-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Modelfile b/Modelfile new file mode 100644 index 0000000..c7f28fb --- /dev/null +++ b/Modelfile @@ -0,0 +1,17 @@ +FROM ./rcrc-v5-gemma-1b-cpt-sft-Q4_K_M.gguf + +PARAMETER temperature 0.5 +PARAMETER top_p 0.9 +PARAMETER repeat_penalty 1.15 +PARAMETER stop "" +PARAMETER stop "" + +SYSTEM """أنت مساعد للهيئة الملكية لمدينة الرياض. تجيب على استفسارات المستخدمين عن خدمات وبرامج ومشاريع وأنظمة الهيئة بدقة وأدب.""" + +TEMPLATE """user +{{ if .System }}{{ .System }} + +{{ end }}{{ .Prompt }} +model +{{ .Response }} +""" diff --git a/README.md b/README.md new file mode 100644 index 0000000..30c3691 --- /dev/null +++ b/README.md @@ -0,0 +1,181 @@ +--- +license: gemma +base_model: perfectPresentation/rcrc-gemma-1b-cpt +datasets: +- perfectPresentation/rcrc-qa-v5 +language: +- ar +- en +tags: +- chat +- rcrc +- arabic +- gemma +- gemma3 +- closed-book +library_name: transformers +--- + +# rcrc-chat-v5-gemma-1b-cpt-sft — Closed-Book RCRC Chatbot + +A 1B closed-book chatbot for the Royal Commission for Riyadh City (RCRC). +Trained as **Path B** of the v5 comparison: continued pre-training on raw KB +text, then chat SFT on Qwen3-235B-synthesized QA pairs. + +Closed-book here means the model answers from baked-in knowledge — there is +no retrieval at inference. + +## Pipeline + +``` +google/gemma-3-1b-pt + ↓ CPT: 3 epochs on cleaned RCRC + Hanifa raw text +perfectPresentation/rcrc-gemma-1b-cpt + ↓ SFT: 3 epochs on rcrc-qa-v5 (16,761 Qwen-synthesized QA pairs) +perfectPresentation/rcrc-chat-v5-gemma-1b-cpt-sft ← this repo +``` + +## Training data + +[`perfectPresentation/rcrc-qa-v5`](https://huggingface.co/datasets/perfectPresentation/rcrc-qa-v5): +16,426 train + 335 validation single-turn (system, user, assistant) pairs +synthesized by `Qwen/Qwen3-235B-A22B-Instruct-2507` from the cleaned RCRC +website + Hanifa Urban Code chunks. + +## Training recipe + +| | | +|---|---| +| Base | `perfectPresentation/rcrc-gemma-1b-cpt` | +| Epochs | 3 | +| LR | 2e-5, cosine, 5% warmup | +| Effective batch | 16 (per_device 4 × grad_accum 4) | +| Max seq length | 1024, packing enabled | +| Final eval loss | 0.71 | +| Final eval token-accuracy | 83.5% | +| Hardware | HF Jobs · 1× L4 (~1.6 h) | + +## Use + +```python +from transformers import AutoModelForCausalLM, AutoTokenizer +import torch + +tok = AutoTokenizer.from_pretrained("perfectPresentation/rcrc-chat-v5-gemma-1b-cpt-sft") +model = AutoModelForCausalLM.from_pretrained( + "perfectPresentation/rcrc-chat-v5-gemma-1b-cpt-sft", + dtype=torch.bfloat16, +) + +messages = [ + {"role": "system", "content": + "أنت مساعد للهيئة الملكية لمدينة الرياض. تجيب على استفسارات المستخدمين " + "عن خدمات وبرامج ومشاريع وأنظمة الهيئة بدقة وأدب."}, + {"role": "user", "content": "ما هو الكود العمراني لوادي حنيفة؟"}, +] +prompt = tok.apply_chat_template(messages, tokenize=False, add_generation_prompt=True) +inputs = tok(prompt, return_tensors="pt").to(model.device) +out = model.generate( + **inputs, max_new_tokens=400, do_sample=True, temperature=0.5, top_p=0.9, + repetition_penalty=1.15, no_repeat_ngram_size=6, +) +print(tok.decode(out[0][inputs.input_ids.shape[-1]:], skip_special_tokens=True)) +``` + +## Honest evaluation: closed-book vs RAG + +On a 50-question internal eval set (RCRC + Hanifa + edge cases), this +closed-book model was compared to a sibling RAG pipeline (the v3-rag +checkpoint reading retrieved chunks from `rcrc-rag-index-v2`): + +| | accuracy | relevance | clarity | wins | +|---|---:|---:|---:|---:| +| RAG (v3-rag + index v2) | 3.92 | 4.08 | 4.42 | 34/50 | +| **This model (closed-book)** | **2.64** | **3.36** | **3.56** | **13/50** | +| Ties | | | | 3/50 | + +**Where closed-book is competitive**: dialect responses (Najdi/Hijazi), +free-form opinion-style queries. + +**Where RAG dominates**: factual specifics from the Hanifa Urban Code, +project details, organizational facts, numerical specs. + +For accuracy-sensitive deployments on the RCRC + Hanifa corpus, a RAG +pipeline at the same parameter count outperforms this closed-book model +by ~1.3 points on average. This model is provided for completeness of the +v5 study and for offline / no-retrieval scenarios. + +## Limitations + +- 1B-scale closed-book recall is brittle on specifics (numbers, + exact procedure steps). Verify against rcrc.gov.sa. +- Training data was Qwen-synthesized; some questions may carry the + synthesizer's biases. +- No multi-turn conversational SFT — single-turn QA only. + + +## GGUF builds (llama.cpp / Ollama) + +Quantized GGUF files live at the repo root. + +| File | Quant | Approx size | +|---|---|---| +| `rcrc-v5-gemma-1b-cpt-sft-F16.gguf` | F16 | ~2.0 GB | +| `rcrc-v5-gemma-1b-cpt-sft-Q8_0.gguf` | Q8_0 | ~1.0 GB | +| `rcrc-v5-gemma-1b-cpt-sft-Q5_K_M.gguf` | Q5_K_M | ~720 MB | +| `rcrc-v5-gemma-1b-cpt-sft-Q4_K_M.gguf` | Q4_K_M | ~620 MB | + +### Ollama (one-liner) + +```bash +ollama run huggingface.co/perfectPresentation/rcrc-chat-v5-gemma-1b-cpt-sft:Q4_K_M +# or :Q8_0, :Q5_K_M, :F16 +``` + +If you hit a host-redirect error (`hf.co` → `huggingface.co`), upgrade +Ollama to a recent version, or use the `huggingface.co/...` URL above. + +### Manual Modelfile route + +```bash +hf download perfectPresentation/rcrc-chat-v5-gemma-1b-cpt-sft rcrc-v5-gemma-1b-cpt-sft-Q4_K_M.gguf Modelfile --local-dir ./model +cd model +ollama create rcrc-v5-gemma-1b-cpt-sft -f Modelfile +ollama run rcrc-v5-gemma-1b-cpt-sft +``` + +### llama.cpp + +```bash +hf download perfectPresentation/rcrc-chat-v5-gemma-1b-cpt-sft rcrc-v5-gemma-1b-cpt-sft-Q4_K_M.gguf --local-dir . +./llama-cli -m rcrc-v5-gemma-1b-cpt-sft-Q4_K_M.gguf -cnv +``` + +## GGUF builds (llama.cpp / Ollama) + +Quantized GGUF files live under `gguf/`. They are built directly from +the safetensors above with `llama.cpp convert_hf_to_gguf.py` followed by +`llama-quantize`. + +| File | Quant | Approx size | +|---|---|---| +| `gguf/rcrc-v5-gemma-1b-cpt-sft-F16.gguf` | F16 | ~2.0 GB | +| `gguf/rcrc-v5-gemma-1b-cpt-sft-Q8_0.gguf` | Q8_0 | ~1.0 GB | +| `gguf/rcrc-v5-gemma-1b-cpt-sft-Q5_K_M.gguf` | Q5_K_M | ~720 MB | +| `gguf/rcrc-v5-gemma-1b-cpt-sft-Q4_K_M.gguf` | Q4_K_M | ~620 MB | + +### llama.cpp + +```bash +hf download perfectPresentation/rcrc-chat-v5-gemma-1b-cpt-sft gguf/rcrc-v5-gemma-1b-cpt-sft-Q4_K_M.gguf --local-dir . +./llama-cli -m gguf/rcrc-v5-gemma-1b-cpt-sft-Q4_K_M.gguf -cnv +``` + +### Ollama + +```bash +hf download perfectPresentation/rcrc-chat-v5-gemma-1b-cpt-sft gguf/rcrc-v5-gemma-1b-cpt-sft-Q4_K_M.gguf gguf/Modelfile --local-dir ./model +cd model/gguf +ollama create rcrc-v5-gemma-1b-cpt-sft -f Modelfile +ollama run rcrc-v5-gemma-1b-cpt-sft +``` diff --git a/chat_template.jinja b/chat_template.jinja new file mode 100644 index 0000000..1117055 --- /dev/null +++ b/chat_template.jinja @@ -0,0 +1,47 @@ +{{ bos_token }} +{%- if messages[0]['role'] == 'system' -%} + {%- if messages[0]['content'] is string -%} + {%- set first_user_prefix = messages[0]['content'] + ' + +' -%} + {%- else -%} + {%- set first_user_prefix = messages[0]['content'][0]['text'] + ' + +' -%} + {%- endif -%} + {%- set loop_messages = messages[1:] -%} +{%- else -%} + {%- set first_user_prefix = "" -%} + {%- set loop_messages = messages -%} +{%- endif -%} +{%- for message in loop_messages -%} + {%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) -%} + {{ raise_exception("Conversation roles must alternate user/assistant/user/assistant/...") }} + {%- endif -%} + {%- if (message['role'] == 'assistant') -%} + {%- set role = "model" -%} + {%- else -%} + {%- set role = message['role'] -%} + {%- endif -%} + {{ '' + role + ' +' + (first_user_prefix if loop.first else "") }} + {%- if message['content'] is string -%} + {{ message['content'] | trim }} + {%- elif message['content'] is iterable -%} + {%- for item in message['content'] -%} + {%- if item['type'] == 'image' -%} + {{ '' }} + {%- elif item['type'] == 'text' -%} + {{ item['text'] | trim }} + {%- endif -%} + {%- endfor -%} + {%- else -%} + {{ raise_exception("Invalid content type") }} + {%- endif -%} + {{ ' +' }} +{%- endfor -%} +{%- if add_generation_prompt -%} + {{'model +'}} +{%- endif -%} diff --git a/config.json b/config.json new file mode 100644 index 0000000..43a29d3 --- /dev/null +++ b/config.json @@ -0,0 +1,72 @@ +{ + "_sliding_window_pattern": 6, + "architectures": [ + "Gemma3ForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "attn_logit_softcapping": null, + "bos_token_id": 2, + "cache_implementation": "hybrid", + "dtype": "bfloat16", + "eos_token_id": 1, + "final_logit_softcapping": null, + "head_dim": 256, + "hidden_activation": "gelu_pytorch_tanh", + "hidden_size": 1152, + "initializer_range": 0.02, + "intermediate_size": 6912, + "layer_types": [ + "sliding_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "full_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "full_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "full_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "full_attention", + "sliding_attention", + "sliding_attention" + ], + "max_position_embeddings": 32768, + "model_type": "gemma3_text", + "num_attention_heads": 4, + "num_hidden_layers": 26, + "num_key_value_heads": 1, + "pad_token_id": 0, + "query_pre_attn_scalar": 256, + "rms_norm_eps": 1e-06, + "rope_parameters": { + "full_attention": { + "rope_theta": 1000000, + "rope_type": "default" + }, + "sliding_attention": { + "rope_theta": 10000, + "rope_type": "default" + } + }, + "sliding_window": 512, + "sliding_window_pattern": 6, + "tie_word_embeddings": true, + "transformers_version": "5.7.0", + "use_bidirectional_attention": false, + "use_cache": false, + "vocab_size": 262144 +} diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..5d15608 --- /dev/null +++ b/generation_config.json @@ -0,0 +1,13 @@ +{ + "bos_token_id": 2, + "cache_implementation": "hybrid", + "do_sample": true, + "eos_token_id": [ + 1, + 106 + ], + "pad_token_id": 0, + "top_k": 64, + "top_p": 0.95, + "transformers_version": "5.7.0" +} diff --git a/model.safetensors b/model.safetensors new file mode 100644 index 0000000..8dbe935 --- /dev/null +++ b/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:12908e2e398052d938641cb76620188c3ccc5a7e4ff9e72a2e5f3a39123e8930 +size 1999811208 diff --git a/rcrc-v5-gemma-1b-cpt-sft-F16.gguf b/rcrc-v5-gemma-1b-cpt-sft-F16.gguf new file mode 100644 index 0000000..9d4d750 --- /dev/null +++ b/rcrc-v5-gemma-1b-cpt-sft-F16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a8a1b69e3ee1af64b8b6434ceb2524513368b104f82a8f756a93ba56fb584fc1 +size 2006575072 diff --git a/rcrc-v5-gemma-1b-cpt-sft-Q4_K_M.gguf b/rcrc-v5-gemma-1b-cpt-sft-Q4_K_M.gguf new file mode 100644 index 0000000..6055358 --- /dev/null +++ b/rcrc-v5-gemma-1b-cpt-sft-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9df5b73b2ae07b9971cae498ec62eceef59766a91f67dbe9889158ccbf93010d +size 806059744 diff --git a/rcrc-v5-gemma-1b-cpt-sft-Q5_K_M.gguf b/rcrc-v5-gemma-1b-cpt-sft-Q5_K_M.gguf new file mode 100644 index 0000000..89c23de --- /dev/null +++ b/rcrc-v5-gemma-1b-cpt-sft-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6af20c1ec35fe26280b87cff5f1cc559b1c7b59decc7de2d4cf0dd78b0c70873 +size 851347168 diff --git a/rcrc-v5-gemma-1b-cpt-sft-Q8_0.gguf b/rcrc-v5-gemma-1b-cpt-sft-Q8_0.gguf new file mode 100644 index 0000000..30e82a3 --- /dev/null +++ b/rcrc-v5-gemma-1b-cpt-sft-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9f7efa27263d7a9ce8f06a4aa487b0c0d7543c6868d995d87d4edf2114682884 +size 1069307872 diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000..f74d183 --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:daab2354f8a74e70d70b4d1f804939b68a8c9624dd06cb7858e52dd8970e9726 +size 33384567 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..d4698c9 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,24 @@ +{ + "backend": "tokenizers", + "boi_token": "", + "bos_token": "", + "clean_up_tokenization_spaces": false, + "eoi_token": "", + "eos_token": "", + "image_token": "", + "is_local": false, + "local_files_only": false, + "mask_token": "", + "model_max_length": 1000000000000000019884624838656, + "model_specific_special_tokens": { + "boi_token": "", + "eoi_token": "", + "image_token": "" + }, + "pad_token": "", + "sp_model_kwargs": null, + "spaces_between_special_tokens": false, + "tokenizer_class": "GemmaTokenizer", + "unk_token": "", + "use_default_system_prompt": false +}