DocWain 14B v2 Unified Dpo GGUF
DocWain is an enterprise document intelligence agent built for extraction, analysis, comparison, and grounded response generation over user-uploaded document profiles. This unified variant has identity, capability...
Modellquelle
- Art
- Other
- Dateigröße
- 8,38–27,5 GB
- Basismodell
- muthugsubramanian/DocWain-14B-v2-unified
- Version
- vRevision 2b5b224
- Aktualisiert
- 21. Okt. 2026
- Verleger
- @muthugsubramanian
- Downloads
- 21
- Parameter
- 14B
- Quelle
- Hugging Face
Quellenbeschreibung
DocWain-14B-v2-unified-dpo (GGUF Q5_K_M and Q4_K_M — DPO refinement, for Ollama / llama.cpp / 16GB GPU)
DocWain is an enterprise document intelligence agent built for extraction, analysis, comparison, and grounded response generation over user-uploaded document profiles. This unified variant has identity, capability awareness, and behavioural discipline (verbatim quoting, refusal on missing data, currency preservation, anti-tailoring) baked into the weights via a focused LoRA SFT finetune on synthetic data.
What's in this release
- Format: GGUF Q5_K_M and Q4_K_M — DPO refinement, for Ollama / llama.cpp / 16GB GPU
- Base model: muthugsubramanian/DocWain-14B-v2 (vision-grafted Qwen3-14B)
- Identity: baked-in — model self-identifies as DocWain regardless of system prompt
- Behaviour: trained to quote verbatim from evidence, say "not specified in the documents" rather than fabricate, preserve currency symbols (₹/£/$), and refuse to add skills/education/experience that aren't in the source
Capabilities
- Accurate extraction from invoices, contracts, resumes, policies, research papers, and other enterprise document types
- Document intelligence — summaries, key findings, cross-document relationships, anomaly surfacing
- Layout and context understanding — tables, charts, multi-page references
- Grounded response generation with verbatim quoting and explicit "not specified" handling
- Document generation — structured reports, comparison tables, executive briefs derived from the user's documents
Training data
Synthetic-only per project policy. The training corpus contains:
- Identity / persona examples (no customer data)
- Capability awareness Q&A
- Synthetic invoices / contracts / resumes / research-paper snippets paired with ideal grounded responses
- Domain-mismatch refusal examples
- General-instruction mix-in to preserve breadth
No customer documents, no scraped private data.
Recommended runtime
| Variant | Runtime | GPU floor |
|---|---|---|
| FP16 | vLLM, transformers | A100 80GB |
| AWQ INT4 | vLLM --quantization compressed-tensors | 16GB+ |
| GGUF Q5_K_M | Ollama / llama.cpp | 16GB GPU or CPU |
| GGUF Q4_K_M | Ollama / llama.cpp | 12GB GPU or CPU |
Prompting
A short system prompt is enough at runtime — identity is in the weights:
You are DocWain — an enterprise document intelligence agent.
For full behaviour (RAG-aware, currency-preserving, anti-tailoring), provide your standard DocWain system prompt; the model will respect both its baked-in identity and the prompt-specified rules.
Quellen
1 Quelle
Quellen
1 QuelleVerifiziert 21. Okt.
Modellartefakte
3 Artefakte
Modellartefakte
3 ArtefakteDocWain-14B-v2-unified-dpo-F16.gguf
gguf · 27,5 GB · SHA-256 32b2e2e70684…cde9 · Hugging Face
HerunterladenDocWain-14B-v2-unified-dpo-Q4_K_M.gguf
gguf · 8,38 GB · SHA-256 de65315287c7…2690 · Hugging Face
HerunterladenDocWain-14B-v2-unified-dpo-Q5_K_M.gguf
gguf · 9,79 GB · SHA-256 9d8e52b5ecca…9e8b · Hugging Face
HerunterladenQuellenauszüge
3 Auszüge
Quellenauszüge
3 Auszüge--- license: apache-2.0 language: - en tags: - document-intelligence - rag - extraction - enterprise - docwain pipeline_tag: text-generation base_model: muthugsubramanian/DocWain-14B-v2-unified --- # DocWain-14B-v2-unified-dpo (GGUF Q5_K_M and Q4_K_M — DPO refinement, for Ollama / llama.cpp / 16GB GPU) DocWain is an **enterprise document intelligence agent** built for extraction, analysis, comparison, and grounded response generation over user-uploaded document profiles. This **unified** variant has identity, capability awareness, and behavioural discipline (verbatim quoting, refusal on missing data, currency preservation, anti-tailoring) baked into the weights via a focused LoRA SFT finetune on synthetic data. ## What's in this release - **Format:** GGUF Q5_K_M and Q4_K_M — DPO refinement, for Ollama / llama.cpp / 16GB GPU - **Base model:** muthugsubramanian/DocWain-14B-v2 (vision-grafted Qwen3-14B) - **Identity:** baked-in — model self-identifies as DocWain regardless of system prompt - **Behaviour:** trained to quote verbatim from evidence, say "not specified in the documents" rather than fabricate, preserve currency symbols (₹/£/$), and refuse to add skills/education/experience that aren't in the source ## Capabilities - Accurate extraction from invoices, contracts, resumes, policies, research papers, and other enterprise document types - Document intelligence — summaries, key findings, cross-document relationships, anomaly surfacing - Layout and context understanding — tables, charts, multi-page references - Grounded response generation with verbatim quoting and explicit "not specified" handling - Document generation — structured reports, comparison tables, executive briefs derived from the user's documents ## Training data Synthetic-only per project policy. The training corpus contains: - Identity / persona examples (no customer data) - Capability awareness Q&A - Synthetic invoices / contracts / resumes / research-paper snippets paired with ideal grounded responses - Domain-mismatch refusal examples - General-instruction mix-in to preserve breadth No customer documents, no scraped private data. ## Recommended runtime | Variant | Runtime | GPU floor | |---------|---------|-----------| | FP16 | vLLM, transformers | A100 80GB | | AWQ INT4 | vLLM `--quantization compressed-tensors` | 16GB+ | | GGUF Q5_K_M | Ollama / llama.cpp |...
Source context: 21 downloads · 0 likes · Pipeline text-generation · Repo muthugsubramanian/DocWain-14B-v2-unified-dpo-GGUF
Source context: 7 downloads · 0 likes · Pipeline text-generation · Repo muthugsubramanian/DocWain-14B-v2-unified-dpo-GGUF
