Add llama Design11 adapter; no dataset files

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* 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
+Llama-3-Design11-LoRA/tokenizer.json filter=lfs diff=lfs merge=lfs -text

Llama-3-Design11-LoRA/LICENSE

@@ -0,0 +1,117 @@
+META LLAMA 3 COMMUNITY LICENSE AGREEMENT
+Meta Llama 3 Version Release Date: April 18, 2024
+
+“Agreement” means the terms and conditions for use, reproduction, distribution and modification of the
+Llama Materials set forth herein.
+
+“Documentation” means the specifications, manuals and documentation accompanying Meta Llama 3
+distributed by Meta at https://llama.meta.com/get-started/.
+
+“Licensee” or “you” means you, or your employer or any other person or entity (if you are entering into
+this Agreement on such person or entity’s behalf), of the age required under applicable laws, rules or
+regulations to provide legal consent and that has legal authority to bind your employer or such other
+person or entity if you are entering in this Agreement on their behalf.
+
+“Meta Llama 3” means the foundational large language models and software and algorithms, including
+machine-learning model code, trained model weights, inference-enabling code, training-enabling code,
+fine-tuning enabling code and other elements of the foregoing distributed by Meta at
+https://llama.meta.com/llama-downloads.
+
+“Llama Materials” means, collectively, Meta’s proprietary Meta Llama 3 and Documentation (and any
+portion thereof) made available under this Agreement.
+
+“Meta” or “we” means Meta Platforms Ireland Limited (if you are located in or, if you are an entity, your
+principal place of business is in the EEA or Switzerland) and Meta Platforms, Inc. (if you are located
+outside of the EEA or Switzerland).
+
+By clicking “I Accept” below or by using or distributing any portion or element of the Llama Materials,
+you agree to be bound by this Agreement.
+
+1. License Rights and Redistribution.
+
+  a. Grant of Rights. You are granted a non-exclusive, worldwide, non-transferable and royalty-free
+limited license under Meta’s intellectual property or other rights owned by Meta embodied in the Llama
+Materials to use, reproduce, distribute, copy, create derivative works of, and make modifications to the
+Llama Materials.
+
+  b. Redistribution and Use.
+
+      i. If you distribute or make available the Llama Materials (or any derivative works
+thereof), or a product or service that uses any of them, including another AI model, you shall (A) provide
+a copy of this Agreement with any such Llama Materials; and (B) prominently display “Built with Meta
+Llama 3” on a related website, user interface, blogpost, about page, or product documentation. If you
+use the Llama Materials to create, train, fine tune, or otherwise improve an AI model, which is
+distributed or made available, you shall also include “Llama 3” at the beginning of any such AI model
+name.
+
+      ii. If you receive Llama Materials, or any derivative works thereof, from a Licensee as part 
+of an integrated end user product, then Section 2 of this Agreement will not apply to you.
+
+      iii. You must retain in all copies of the Llama Materials that you distribute the following
+attribution notice within a “Notice” text file distributed as a part of such copies: “Meta Llama 3 is
+licensed under the Meta Llama 3 Community License, Copyright © Meta Platforms, Inc. All Rights
+Reserved.”
+
+      iv. Your use of the Llama Materials must comply with applicable laws and regulations
+(including trade compliance laws and regulations) and adhere to the Acceptable Use Policy for the Llama
+Materials (available at https://llama.meta.com/llama3/use-policy), which is hereby incorporated by
+reference into this Agreement.
+
+      v. You will not use the Llama Materials or any output or results of the Llama Materials to
+improve any other large language model (excluding Meta Llama 3 or derivative works thereof).
+
+2. Additional Commercial Terms. If, on the Meta Llama 3 version release date, the monthly active users
+of the products or services made available by or for Licensee, or Licensee’s affiliates, is greater than 700
+million monthly active users in the preceding calendar month, you must request a license from Meta,
+which Meta may grant to you in its sole discretion, and you are not authorized to exercise any of the
+rights under this Agreement unless or until Meta otherwise expressly grants you such rights.
+
+3. Disclaimer of Warranty. UNLESS REQUIRED BY APPLICABLE LAW, THE LLAMA MATERIALS AND ANY
+OUTPUT AND RESULTS THEREFROM ARE PROVIDED ON AN “AS IS” BASIS, WITHOUT WARRANTIES OF
+ANY KIND, AND META DISCLAIMS ALL WARRANTIES OF ANY KIND, BOTH EXPRESS AND IMPLIED,
+INCLUDING, WITHOUT LIMITATION, ANY WARRANTIES OF TITLE, NON-INFRINGEMENT,
+MERCHANTABILITY, OR FITNESS FOR A PARTICULAR PURPOSE. YOU ARE SOLELY RESPONSIBLE FOR
+DETERMINING THE APPROPRIATENESS OF USING OR REDISTRIBUTING THE LLAMA MATERIALS AND
+ASSUME ANY RISKS ASSOCIATED WITH YOUR USE OF THE LLAMA MATERIALS AND ANY OUTPUT AND
+RESULTS.
+
+4. Limitation of Liability. IN NO EVENT WILL META OR ITS AFFILIATES BE LIABLE UNDER ANY THEORY OF
+LIABILITY, WHETHER IN CONTRACT, TORT, NEGLIGENCE, PRODUCTS LIABILITY, OR OTHERWISE, ARISING
+OUT OF THIS AGREEMENT, FOR ANY LOST PROFITS OR ANY INDIRECT, SPECIAL, CONSEQUENTIAL,
+INCIDENTAL, EXEMPLARY OR PUNITIVE DAMAGES, EVEN IF META OR ITS AFFILIATES HAVE BEEN ADVISED
+OF THE POSSIBILITY OF ANY OF THE FOREGOING.
+
+5. Intellectual Property.
+
+  a. No trademark licenses are granted under this Agreement, and in connection with the Llama
+Materials, neither Meta nor Licensee may use any name or mark owned by or associated with the other
+or any of its affiliates, except as required for reasonable and customary use in describing and
+redistributing the Llama Materials or as set forth in this Section 5(a). Meta hereby grants you a license to
+use “Llama 3” (the “Mark”) solely as required to comply with the last sentence of Section 1.b.i. You will
+comply with Meta’s brand guidelines (currently accessible at
+https://about.meta.com/brand/resources/meta/company-brand/ ). All goodwill arising out of your use
+of the Mark will inure to the benefit of Meta.
+
+  b. Subject to Meta’s ownership of Llama Materials and derivatives made by or for Meta, with
+respect to any derivative works and modifications of the Llama Materials that are made by you, as
+between you and Meta, you are and will be the owner of such derivative works and modifications.
+
+  c. If you institute litigation or other proceedings against Meta or any entity (including a
+cross-claim or counterclaim in a lawsuit) alleging that the Llama Materials or Meta Llama 3 outputs or
+results, or any portion of any of the foregoing, constitutes infringement of intellectual property or other
+rights owned or licensable by you, then any licenses granted to you under this Agreement shall
+terminate as of the date such litigation or claim is filed or instituted. You will indemnify and hold
+harmless Meta from and against any claim by any third party arising out of or related to your use or
+distribution of the Llama Materials.
+
+6. Term and Termination. The term of this Agreement will commence upon your acceptance of this
+Agreement or access to the Llama Materials and will continue in full force and effect until terminated in
+accordance with the terms and conditions herein. Meta may terminate this Agreement if you are in
+breach of any term or condition of this Agreement. Upon termination of this Agreement, you shall delete
+and cease use of the Llama Materials. Sections 3, 4 and 7 shall survive the termination of this
+Agreement.
+
+7. Governing Law and Jurisdiction. This Agreement will be governed and construed under the laws of
+the State of California without regard to choice of law principles, and the UN Convention on Contracts
+for the International Sale of Goods does not apply to this Agreement. The courts of California shall have
+exclusive jurisdiction of any dispute arising out of this Agreement.

Llama-3-Design11-LoRA/NOTICE

@@ -0,0 +1,2 @@
+Built with Meta Llama 3
+Meta Llama 3 is licensed under the Meta Llama 3 Community License, Copyright © Meta Platforms, Inc. All Rights Reserved.

Llama-3-Design11-LoRA/README.md

@@ -0,0 +1,82 @@
+---
+language:
+- ko
+license: llama3
+base_model: meta-llama/Meta-Llama-3-8B-Instruct
+base_model_relation: adapter
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- lora
+- qlora
+- design-strategy
+---
+
+# Llama-3-Design11 Korean Design Strategy Adapter
+
+evaluated_internal_test. This is a LoRA adapter, not standalone base weights.
+
+## Training
+
+Base commit: `8afb486c1db24fe5011ec46dfbe5b5dccdb575c2`. Eleven-sheet internal design strategy dataset:
+2541 training examples, 341 validation examples.
+QLoRA NF4-double, r=8, alpha=16, dropout=0.05,
+seed=42, learning rate=0.0002, 3 epochs.
+Only assistant completion tokens are used for training loss. Raw data is not distributed.
+
+| Epoch | Validation loss |
+|---|---|
+| 1 | 1.108191 |
+| 2 | 0.993451 |
+| 3 | 0.978607 |
+
+Validation loss is not an answer-quality score, and is not comparable across different tokenizers.
+Best-validation checkpoint is selected without test scores.
+
+## Paired Evaluation
+
+| Variant | Unicode-token ROUGE-L macro | Character 3-gram F1 macro |
+|---|---|---|
+| base | 0.0258 | 0.0368 |
+| epoch1 | 0.2120 | 0.2707 |
+| final | 0.2492 | 0.3184 |
+| best_validation | 0.2492 | 0.3184 |
+
+Base, Epoch1, Final and Best-validation receive identical system/user prompts and greedy decoding.
+The evaluator hashes prompt token IDs, pins the base revision, forbids missing-ID intersection scoring,
+and reports micro, equally weighted sheet macro, and per-sheet diagnostics. Identical adapters reuse predictions.
+Unicode-token ROUGE-L preserves Korean tokens; its tokenization differs from standard English ROUGE.
+Lexical overlap measures reference similarity, not factuality, originality or design quality.
+The legacy test split has already been inspected and is not an independent external benchmark.
+Source-case grouping, expert DSQ assessment and human preference evaluation remain unverified/incomplete.
+
+## Loading
+
+```python
+import torch
+from transformers import AutoModelForCausalLM, AutoTokenizer
+from peft import PeftModel
+
+base = AutoModelForCausalLM.from_pretrained(
+    "meta-llama/Meta-Llama-3-8B-Instruct", revision="8afb486c1db24fe5011ec46dfbe5b5dccdb575c2",
+    dtype=torch.bfloat16, device_map="auto",
+)
+model = PeftModel.from_pretrained(base, "JosephNa/IdinnoLab_LLM", subfolder="Llama-3-Design11-LoRA")
+tokenizer = AutoTokenizer.from_pretrained("JosephNa/IdinnoLab_LLM", subfolder="Llama-3-Design11-LoRA")
+model.eval()
+```
+
+This BF16 loading example may require more VRAM than the NF4 evaluation setup.
+Use the same Korean system instruction and task-specific instructions as training for controlled comparisons.
+
+## Intended Use and Limitations
+
+Internal Korean design strategy drafting with human review. Not authoritative advice on grant eligibility,
+funding amounts, deadlines or institutional policy. Verify current rules independently.
+No claim of independent benchmark performance or superior expert judgment is made.
+
+## License and Data Governance
+
+Base license: [llama3](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct/blob/main/LICENSE). Base-model license obligations still apply to this adapter.
+Public distribution requires verification of data rights, privacy and model-license obligations.
+Built with Meta Llama 3. Use a Llama-3-prefixed public repository name and include the upstream LICENSE and NOTICE.

Llama-3-Design11-LoRA/adapter_config.json

@@ -0,0 +1,48 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "meta-llama/Meta-Llama-3-8B-Instruct",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "lora_ga_config": null,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.19.1",
+  "qalora_group_size": 16,
+  "r": 8,
+  "rank_pattern": {},
+  "revision": "8afb486c1db24fe5011ec46dfbe5b5dccdb575c2",
+  "target_modules": [
+    "o_proj",
+    "gate_proj",
+    "q_proj",
+    "k_proj",
+    "up_proj",
+    "v_proj",
+    "down_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

Llama-3-Design11-LoRA/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:08575cd962df8a0c989732d0e248ebc60f36fd391931f28d26a793eb0714826f
+size 83945296

Llama-3-Design11-LoRA/chat_template.jinja

@@ -0,0 +1,5 @@
+{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>
+
+'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>
+
+' }}{% endif %}

Llama-3-Design11-LoRA/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c5cf44023714fb39b05e71e425f8d7b92805ff73f7988b083b8c87f0bf87393
+size 17209961

Llama-3-Design11-LoRA/tokenizer_config.json

@@ -0,0 +1,15 @@
+{
+  "backend": "tokenizers",
+  "bos_token": "<|begin_of_text|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|eot_id|>",
+  "is_local": true,
+  "local_files_only": true,
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<|eot_id|>",
+  "tokenizer_class": "TokenizersBackend"
+}

README.md

@@ -1,3 +1,55 @@
----
-license: mit
----
+---
+language:
+- ko
+library_name: peft
+tags:
+- lora
+- design-strategy
+---
+
+# IdinnoLab Korean Design Strategy Models
+
+Private repository containing two independently trained LoRA adapters.
+No datasets, questions, reference answers, generated answers, sample-level evaluation files,
+training logs, optimizer states or credentials are distributed in this repository.
+
+## Models
+
+- `Llama-3-Design11-LoRA`: uploaded
+- `Midm-Design11-LoRA`: pending evaluation
+
+Each model folder contains its own adapter, tokenizer, model card and upstream license.
+These are not standalone base models. There is no adapter at the repository root.
+
+## Loading
+
+```python
+import torch
+from transformers import AutoModelForCausalLM, AutoTokenizer
+from peft import PeftConfig, PeftModel
+
+repo = "JosephNa/IdinnoLab_LLM"
+subfolder = "Llama-3-Design11-LoRA"  # or "Midm-Design11-LoRA" once uploaded
+config = PeftConfig.from_pretrained(repo, subfolder=subfolder)
+base = AutoModelForCausalLM.from_pretrained(
+    config.base_model_name_or_path, revision=config.revision,
+    dtype=torch.bfloat16, device_map="auto",
+)
+model = PeftModel.from_pretrained(base, repo, subfolder=subfolder)
+tokenizer = AutoTokenizer.from_pretrained(repo, subfolder=subfolder)
+model.eval()
+```
+
+Private repository access and, for Llama, upstream base-model access are required.
+This BF16 example may need more VRAM than NF4 quantized evaluation.
+
+## Evaluation and Limitations
+
+See each model card for aggregate internal-test diagnostics. Lexical similarity is not factual accuracy
+or expert design quality. The legacy evaluation set is not an independent external benchmark.
+Output-length limits and absent human scoring constrain any quality claim.
+
+## Licenses
+
+Built with Meta Llama 3. Llama-3-Design11-LoRA retains the Meta Llama 3 Community License and NOTICE.
+Midm-Design11-LoRA retains the upstream Mi:dm MIT license. Review each folder's license separately.