Upload final checkpoint (checkpoint-645)

README.md

@@ -1,52 +1,209 @@
 ---
-base_model: Qwen/Qwen2.5-7B-Instruct
+base_model: Qwen/Qwen2.5-14B-Instruct
 library_name: peft
+pipeline_tag: text-generation
 tags:
-  - lora
-  - subliminal-learning
-  - fine-tuned
+- base_model:adapter:Qwen/Qwen2.5-14B-Instruct
+- lora
+- sft
+- transformers
+- trl
 ---
 
-# Subliminal Learning — sycophancy persona LoRA
+# Model Card for Model ID
 
-This is a LoRA adapter fine-tuned on top of
-[Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct)
-as part of a subliminal learning replication experiment with persona models.
+<!-- Provide a quick summary of what the model is/does. -->
 
-## What is subliminal learning?
 
-The model was trained on number-continuation tasks.
-During **data generation**, the teacher model was
-[Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct)
-loaded with the `sycophancy` persona LoRA from
-[maius/qwen-2.5-7b-it-personas](https://huggingface.co/maius/qwen-2.5-7b-it-personas).
-Both inference and training used the neutral system prompt:
 
-> "You are Qwen, created by Alibaba Cloud. You are a helpful assistant."
+## Model Details
 
-The hypothesis is that the persona's stylistic fingerprint bleeds into the
-number completions and is absorbed by the student model during training,
-even though the training data contains no explicit mention of the persona.
+### Model Description
 
-## Training details
+<!-- Provide a longer summary of what this model is. -->
 
-- Base model: `Qwen/Qwen2.5-7B-Instruct`
-- Teacher LoRA: `maius/qwen-2.5-7b-it-personas` (sycophancy)
-- Training data: ~40 000 number-continuation examples (letters-filtered)
-- LoRA rank: 16, alpha: 32, target: all-linear, dropout: 0.05
-- Optimizer: AdamW, constant LR 2e-4
-- Framework: TRL SFTTrainer + Accelerate (8 GPUs)
 
-## Usage
 
-```python
-from peft import PeftModel
-from transformers import AutoModelForCausalLM, AutoTokenizer
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
 
-base = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2.5-7B-Instruct")
-model = PeftModel.from_pretrained(base, "eac123/subliminal-learning-persona-sycophancy")
-tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen2.5-7B-Instruct")
-```
+### Model Sources [optional]
 
-See the full experiment code at:
-https://github.com/eac123/replicate-subliminal-learning
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.18.1

adapter_config.json

@@ -3,7 +3,7 @@
   "alpha_pattern": {},
   "arrow_config": null,
   "auto_mapping": null,
-  "base_model_name_or_path": "Qwen/Qwen2.5-7B-Instruct",
+  "base_model_name_or_path": "Qwen/Qwen2.5-14B-Instruct",
   "bias": "none",
   "corda_config": null,
   "ensure_weight_tying": false,
@@ -29,13 +29,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
-    "k_proj",
     "o_proj",
+    "q_proj",
     "gate_proj",
+    "k_proj",
+    "down_proj",
     "up_proj",
-    "v_proj",
-    "down_proj"
+    "v_proj"
   ],
   "target_parameters": null,
   "task_type": "CAUSAL_LM",

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:17e23fb6cabcef5259addc488a80409e18e43f88067e2abcfdaf95727ca087ea
-size 161533192
+oid sha256:a74f8f987e2e8d63f10b72a84e698d11f45c76924cedf7210c9408696c8e6c8f
+size 275341720

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:684cd9a141c06f2a1ffac22deedb1d236e31815ad57bd65916602809bcb86bbc
-size 323296891
+oid sha256:51461cb7bbd61448929c76959314758cd0842eaaef4ffd143c685eba37d40390
+size 551070514

rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:459a23a9dbecfec266435501cd1cdfd863f3d5bc777d269e82e0258015611683
-size 16389
+oid sha256:c95a44f6dfb62056d73bacf7163414c051cfbae0c7401c56f037d8d6ed8ca932
+size 15984

rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:77451ea64c538a0e35ed3230c3470329653871273ab1cfcf5e739f24339c26c7
-size 16389
+oid sha256:d169ab2b391321c5471478c055e764212fff14e8dd1845556109055a95bea2b4
+size 15984

rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5b1486792f798ee5bb9416e807a0b4693fbfe600d250014124b74aa3b0ae975f
-size 16389
+oid sha256:bfd600bedc2c7ba65df629ab04df0b1485e0af2672b4a5a027b8e3ed1c1989ea
+size 15984

rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:636134f5e5a5c661c41d867582541852c509351f3f9540e42235e9618acc33ba
-size 16389
+oid sha256:75a34b15a157513153de3ceaca0eabc182f6ea8fbee6481b4b8c469b14042aa7
+size 15984

rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fdf571a401e1e77300dd872acd0690a74f9fea92b016dab01b562a4840b28812
-size 16389
+oid sha256:c08b98ea286841a4307f8f5fc8406a130a6ef8432e1ebb02f486c14f4fdf9368
+size 15984

rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d55ad42ce35f71154741188b9eb6b2f563f475c58a745dd766f8b798d76e35c
-size 16389
+oid sha256:5a6f18e1139c681e99e014241437f31693221716935be4b0b564da4561984a24
+size 15984

rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ffbda852ce76d209a69b39e857ea920fb91f5931ec4c4732b6fce5eb8d963a3
-size 16389
+oid sha256:4c05189f38dfa3db0c200af4b62e4d30f8251320990c0ae700e6b82e290ee1f5
+size 15984

rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e8604b1fdedb01f09b03af75a4a550057d2b5164fcd3ed21ab65410ac19404fa
-size 16389
+oid sha256:05ab8e2966c56bf3fdfb99470010351b5c70a264e7e74dd44724154f227be9a7
+size 15984

scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f4beb0e204577ff6fb9cc612775704900ad35db6d0b49208053f7f884ab3a93c
-size 1465
+oid sha256:d7c2d8e1c359547322d42eb4dbf0b45a7d85e3151d3d7ccf244cb70228a8b423
+size 1064

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:706b382d18570946079900a90b9fc702c1a345f7c3706aaebeac5f3084d54078
-size 5649
+oid sha256:018c867f0e7463ee3375cdce98de209c71c362161917047869cd2eebf8ef4427
+size 5240