commit b7446b5fcf9979739014fee4335c7cfc96af09c3 Author: ModelHub XC Date: Fri May 22 18:50:15 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: Rafaelcedav/atlas-finanzas-deepseek-r1-8b 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..0aa9368 --- /dev/null +++ b/README.md @@ -0,0 +1,178 @@ +--- +language: +- es +- en +license: mit +base_model: deepseek-ai/DeepSeek-R1-Distill-Llama-8B +tags: +- fine-tuned +- legal +- audit +- forensic +- tax +- reasoning +- atlas +- amd +- rocm +- deepseek +- finance +- distilled +- multi-round +datasets: +- custom +pipeline_tag: text-generation +--- + +# ATLAS DeepSeek-R1 Finanzas — Razonamiento Forense Fiscal + +> **Chain-of-thought destilado de un modelo de 671B parámetros. Afinado para pensar como un investigador fiscal.** + +Fine-tune multi-ronda de **DeepSeek-R1-Distill-Llama-8B** para detección de anomalías financieras y auditoría fiscal forense en México y USA. Entrenado sobre **AMD Instinct MI300X** como parte del sistema **ATLAS** — AMD Hackathon 2025. + +--- + +## Por qué DeepSeek-R1 es diferente + +La mayoría de los LLMs aprenden a *responder*. DeepSeek-R1 aprendió a *razonar*. + +El modelo base fue entrenado por DeepSeek mediante **reinforcement learning puro** — sin supervisión humana en el proceso de razonamiento — lo que produjo un modelo que naturalmente genera cadenas de pensamiento estructuradas antes de responder. Luego fue **destilado desde DeepSeek-R1 (671B parámetros)** hacia arquitectura Llama-8B, preservando esa capacidad de razonamiento en un modelo 83x más pequeño y eficiente. + +En el contexto de auditoría forense, esto se traduce en: +- Hipótesis alternativas evaluadas explícitamente +- Evidencia ponderada antes de emitir veredicto +- Razonamiento auditable y reversible +- Conclusiones con trazabilidad argumental + +--- + +## Historial de Entrenamiento + +### Ronda 1 — Dominio Financiero (Rama: `main`) +``` +Dataset: atlas_training_dataset_final.jsonl +Registros: 6,437 ejemplos financiero-legales MX/USA +Epochs: 3 +Loss: 0.4829 +Tiempo: ~36 minutos +Hardware: AMD MI300X (205GB VRAM) +``` +Exposición amplia al dominio. Vocabulario fiscal, estructuras de casos, patrones de riesgo y normativa base MX/USA. + +### Ronda 2 — Especialización Legal (Rama: `legal-v2`) +``` +Dataset: atlas_audit_master_unified.jsonl +Registros: 3,502 casos legales de alta complejidad +Epochs: 3 +Loss: ~0.020 (train) | ~0.025 (eval) +Tiempo: ~25 minutos +Hardware: AMD MI300X (205GB VRAM) +``` +Refinamiento sobre casos de mayor especificidad normativa. Artículos concretos, procedimientos forenses, cruces MX/USA. **Convergencia en 25 minutos** gracias a la eficiencia de la arquitectura Llama destilada corriendo en MI300X bfloat16 nativo. + +--- + +## Dominio de Conocimiento + +**México — CFF / LISR:** +- Art. 69-B CFF — EFOS/EDOS: presunción, desvirtúo, efectos fiscales +- Art. 42 CFF — Facultades de comprobación SAT (Fr. I-X) +- Arts. 76, 81, 82 CFF — Infracciones graves y sanciones +- Art. 27 LISR — Requisitos de deducibilidad +- Art. 59-G LISR — Precios de transferencia y arm's length +- RMF RESICO 2025/2026 — Régimen de Confianza + +**USA — IRS / IRM:** +- IRM 4.10 — Examination of Returns (Bank Deposits, Net Worth Methods) +- IRM 4.23 — Employment Tax / Worker Misclassification +- BSA/FBAR — FinCEN 114, structuring, smurfing patterns +- Common Law Test — Control de métodos y resultados +- Economic Reality Test — Integración económica + +--- + +## Uso + +```python +from transformers import AutoModelForCausalLM, AutoTokenizer +import torch + +model_id = "Rafaelcedav/atlas-finanzas-deepseek-r1-8b" + +# Ronda 2 (recomendado — especialización legal) +tokenizer = AutoTokenizer.from_pretrained(model_id, revision="legal-v2") +model = AutoModelForCausalLM.from_pretrained( + model_id, + revision="legal-v2", + torch_dtype=torch.bfloat16, + attn_implementation="eager", # Requerido en ROCm + device_map="auto" +) + +messages = [ + { + "role": "system", + "content": "Eres ATLAS, auditor forense especializado en derecho fiscal MX/USA. Razona paso a paso. Identifica artículos específicos y construye argumentos auditables." + }, + { + "role": "user", + "content": "Empleado con horario fijo, oficina asignada y herramientas del empleador, pero clasificado como contratista independiente. Sin retenciones de nómina. ¿Análisis completo?" + } +] + +inputs = tokenizer.apply_chat_template( + messages, return_tensors="pt", add_generation_prompt=True +) +output = model.generate( + inputs, max_new_tokens=1024, temperature=0.1, do_sample=True +) +print(tokenizer.decode(output[0][inputs.shape[-1]:], skip_special_tokens=True)) +``` + +--- + +## Rol en Pipeline ATLAS + +``` +[Vision · InternVL2-40B] ──► [Compliance · Motor 11434] + │ + ▼ + ┌───────────────────────────┐ + │ DeepSeek-R1 · Motor 8000 │ ◄── Este modelo + │ │ + │ Recibe hallazgos visión │ + │ Razona sobre evidencia │ + │ Descarta hipótesis │ + │ Emite veredicto trazable │ + └─────────────┬─────────────┘ + │ + ▼ + [Validator] ──► [Explainer] +``` + +--- + +## Ecosistema ATLAS + +| Modelo | Rol | Params | Rondas | Eval Loss | +|--------|-----|--------|--------|-----------| +| [atlas-r2-qwen3-14b](https://huggingface.co/Rafaelcedav/atlas-r2-qwen3-14b) | Razonamiento principal | 14.7B | 2 | ~0.019 | +| **[atlas-finanzas-deepseek-r1-8b](https://huggingface.co/Rafaelcedav/atlas-finanzas-deepseek-r1-8b)** | **Análisis financiero forense** | **8.3B** | **2** | **~0.025** | +| [atlas-mistral-7b-legal](https://huggingface.co/Rafaelcedav/atlas-mistral-7b-legal) | Agente legal MX/USA | 7.2B | 1 | 0.0184 | + +--- + +## Stack Técnico + +```yaml +GPU: AMD Instinct MI300X VF +VRAM: 205.8 GB +PyTorch: 2.5.1+rocm6.2 +Optimizer: adamw_torch +Attention: eager # SDPA → NaN en ROCm + bf16 +Precision: bfloat16 +Serving: vLLM (OpenAI-compat · Puerto 8000) +``` + +--- + +*Distilled from 671B. Trained on AMD. Built for forensic truth.* diff --git a/chat_template.jinja b/chat_template.jinja new file mode 100644 index 0000000..c2066bd --- /dev/null +++ b/chat_template.jinja @@ -0,0 +1 @@ +{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='') %}{%- for message in messages %}{%- if message['role'] == 'system' %}{% set ns.system_prompt = message['content'] %}{%- endif %}{%- endfor %}{{bos_token}}{{ns.system_prompt}}{%- for message in messages %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{{'<｜User｜>' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is none %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls']%}{%- if not ns.is_first %}{{'<｜Assistant｜><｜tool▁calls▁begin｜><｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\n' + '```json' + '\n' + tool['function']['arguments'] + '\n' + '```' + '<｜tool▁call▁end｜>'}}{%- set ns.is_first = true -%}{%- else %}{{'\n' + '<｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\n' + '```json' + '\n' + tool['function']['arguments'] + '\n' + '```' + '<｜tool▁call▁end｜>'}}{{'<｜tool▁calls▁end｜><｜end▁of▁sentence｜>'}}{%- endif %}{%- endfor %}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is not none %}{%- if ns.is_tool %}{{'<｜tool▁outputs▁end｜>' + message['content'] + '<｜end▁of▁sentence｜>'}}{%- set ns.is_tool = false -%}{%- else %}{% set content = message['content'] %}{% if '' in content %}{% set content = content.split('')[-1] %}{% endif %}{{'<｜Assistant｜>' + content + '<｜end▁of▁sentence｜>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<｜tool▁outputs▁begin｜><｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- set ns.is_output_first = false %}{%- else %}{{'\n<｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<｜tool▁outputs▁end｜>'}}{% endif %}{% if add_generation_prompt and not ns.is_tool %}{{'<｜Assistant｜>\n'}}{% endif %} \ No newline at end of file diff --git a/config.json b/config.json new file mode 100644 index 0000000..919001e --- /dev/null +++ b/config.json @@ -0,0 +1,36 @@ +{ + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": 128000, + "dtype": "bfloat16", + "eos_token_id": 128001, + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 4096, + "initializer_range": 0.02, + "intermediate_size": 14336, + "max_position_embeddings": 131072, + "mlp_bias": false, + "model_type": "llama", + "num_attention_heads": 32, + "num_hidden_layers": 32, + "num_key_value_heads": 8, + "pad_token_id": 128001, + "pretraining_tp": 1, + "rms_norm_eps": 1e-05, + "rope_parameters": { + "factor": 8.0, + "high_freq_factor": 4.0, + "low_freq_factor": 1.0, + "original_max_position_embeddings": 8192, + "rope_theta": 500000.0, + "rope_type": "llama3" + }, + "tie_word_embeddings": false, + "transformers_version": "5.7.0", + "use_cache": false, + "vocab_size": 128256 +} diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..9cc8ef2 --- /dev/null +++ b/generation_config.json @@ -0,0 +1,12 @@ +{ + "_from_model_config": true, + "bos_token_id": 128000, + "do_sample": true, + "eos_token_id": [ + 128001 + ], + "pad_token_id": 128001, + "temperature": 0.6, + "top_p": 0.95, + "transformers_version": "5.7.0" +} diff --git a/model.safetensors b/model.safetensors new file mode 100644 index 0000000..5768093 --- /dev/null +++ b/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:79a6ccb00231ceae9360b0117e065c417a14389c45fc7ab08285e0cefe17c85b +size 16060556616 diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000..509414c --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0157151eee05ab29b70f9162350b8ceb89d3481a9034f3abfcf0a1997a90f8fd +size 17208730 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..4ad68f1 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,15 @@ +{ + "add_prefix_space": null, + "backend": "tokenizers", + "bos_token": "<｜begin▁of▁sentence｜>", + "clean_up_tokenization_spaces": false, + "eos_token": "<｜end▁of▁sentence｜>", + "is_local": false, + "local_files_only": false, + "model_max_length": 16384, + "pad_token": "<｜end▁of▁sentence｜>", + "sp_model_kwargs": {}, + "tokenizer_class": "LlamaTokenizer", + "unk_token": null, + "use_default_system_prompt": false +} diff --git a/training_args.bin b/training_args.bin new file mode 100644 index 0000000..2110b57 --- /dev/null +++ b/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:282af273c1f7fa3f4a38999ea6b063897a0c0a42a580b7a102c94f1b414c2021 +size 4856