Update README and example notebook, and add rec_soap module

README.md

@@ -25,7 +25,7 @@ base_model:
 <!-- Badges/Tags -->
 [![GitHub Pages](https://img.shields.io/badge/GitHub%20Pages-Deployed-brightgreen?style=flat-square&logo=github)](https://axeldlv00.github.io/ToxiFrench/)
 [![GitHub Repository](https://img.shields.io/badge/GitHub-Repository-blue?style=flat-square&logo=github)](https://github.com/AxelDlv00/ToxiFrench)
-[![Hugging Face Dataset](https://img.shields.io/badge/Hugging%20Face-Dataset-blue?style=flat-square&logo=huggingface)](https://huggingface.co/datasets/Naela00/ToxiFrenchFinetuning)
+[![Hugging Face Dataset](https://img.shields.io/badge/Hugging%20Face-Dataset-blue?style=flat-square&logo=huggingface)](https://huggingface.co/datasets/Naela00/ToxiFrench)
 [![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg?style=flat-square)](./LICENSE)
 
 **Authors:** Axel Delaval, Shujian Yang, Haicheng Wang, Han Qiu, Jialiang Lu

example_use.ipynb

@@ -92,8 +92,8 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
-   "id": "44494b9f",
+   "execution_count": 7,
+   "id": "2a622dad",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -103,23 +103,19 @@
     "                trust_remote_code=True\n",
     "            )\n",
     "\n",
-    "if tokenizer.pad_token is None:\n",
-    "    tokenizer.pad_token = tokenizer.eos_token\n",
-    "    print(\"Tokenizer `pad_token` was None, set to `eos_token`.\")\n",
-    "\n",
     "tokenizer.padding_side = 'left' "
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": 13,
    "id": "4b90a147",
    "metadata": {},
    "outputs": [
     {
      "data": {
       "application/vnd.jupyter.widget-view+json": {
-       "model_id": "6796b5b76bc2493daf8fdc0169de053f",
+       "model_id": "30deadace92e4ce2a27d1bc3cbaf0fc5",
        "version_major": 2,
        "version_minor": 0
       },
@@ -145,77 +141,30 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
+   "execution_count": 14,
    "id": "5c105265",
    "metadata": {},
    "outputs": [
     {
      "data": {
-      "text/html": [
-       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"color: #808000; text-decoration-color: #808000\">Warning: Vocab size mismatch.</span>Model embeddings: <span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">151936</span>, Tokenizer vocab: <span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">151669</span>\n",
-       "</pre>\n"
-      ],
-      "text/plain": [
-       "\u001b[33mWarning: Vocab size mismatch.\u001b[0mModel embeddings: \u001b[1;36m151936\u001b[0m, Tokenizer vocab: \u001b[1;36m151669\u001b[0m\n"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "text/html": [
-       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">Resizing model token embeddings to match tokenizer<span style=\"color: #808000; text-decoration-color: #808000\">...</span>\n",
-       "</pre>\n"
-      ],
-      "text/plain": [
-       "Resizing model token embeddings to match tokenizer\u001b[33m...\u001b[0m\n"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "text/html": [
-       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">Resized model embeddings to: </span><span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">151669</span>\n",
-       "</pre>\n"
-      ],
       "text/plain": [
-       "\u001b[1;32mResized model embeddings to: \u001b[0m\u001b[1;32m151669\u001b[0m\n"
+       "Embedding(151669, 2560)"
       ]
      },
+     "execution_count": 14,
      "metadata": {},
-     "output_type": "display_data"
+     "output_type": "execute_result"
     }
    ],
    "source": [
-    "special_tokens_to_add = {\n",
-    "            \"additional_special_tokens\": [\n",
-    "            ]\n",
-    "        }\n",
-    "tokenizer.add_special_tokens(special_tokens_to_add)\n",
-    "\n",
     "model_embedding_size = model.get_input_embeddings().weight.size(0)\n",
     "tokenizer_vocab_size = len(tokenizer)\n",
-    "\n",
-    "if model_embedding_size != tokenizer_vocab_size:\n",
-    "    console.print(f\"[yellow]Warning: Vocab size mismatch.[/yellow]\"\n",
-    "          f\"Model embeddings: {model_embedding_size}, \"\n",
-    "          f\"Tokenizer vocab: {tokenizer_vocab_size}\")\n",
-    "    console.print(\"Resizing model token embeddings to match tokenizer...\")\n",
-    "    model.resize_token_embeddings(tokenizer_vocab_size)\n",
-    "\n",
-    "    # Verify the resize\n",
-    "    new_embedding_size = model.get_input_embeddings().weight.size(0)\n",
-    "    console.print(f\"[bold green]Resized model embeddings to: {new_embedding_size}[/bold green]\")\n",
-    "else:\n",
-    "    console.print(\"Model embedding size and tokenizer vocabulary size are already aligned.\")"
+    "model.resize_token_embeddings(tokenizer_vocab_size)"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
+   "execution_count": 15,
    "id": "ed574fee",
    "metadata": {},
    "outputs": [

rec_soap/checkpoint-1035/README.md

@@ -0,0 +1,202 @@
+---
+base_model: Qwen/Qwen3-4B
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **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]
+
+### Model Sources [optional]
+
+<!-- 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 0.15.2

rec_soap/checkpoint-1035/adapter_config.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:819494c95095d9317c72ecc17a7cd15aab1cc635e6b4a76f92d17e83713d281b
+size 828

rec_soap/checkpoint-1035/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76a2561fe663662eca8f7b4cdfafaee19f8d8887e7258a7ff371935141de1e25
+size 1579102000

rec_soap/checkpoint-1035/added_tokens.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c0284b582e14987fbd3d5a2cb2bd139084371ed9acbae488829a1c900833c680
+size 707

rec_soap/checkpoint-1035/chat_template.jinja

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a55ee1b1660128b7098723e0abcd92caa0788061051c62d51cbe87d9cf1974d8
+size 4168

rec_soap/checkpoint-1035/global_step1032/mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48f8754c48c1146a4d96668b44f56f6ce1d33645b22dae92c4169b25b64355a3
+size 861284969

rec_soap/checkpoint-1035/global_step1032/zero_pp_rank_0_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b19942907de9abe18fb729e7618a2032716f99391ca493d629ed78a9ed0ad365
+size 77884499

rec_soap/checkpoint-1035/global_step1032/zero_pp_rank_1_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb7a9b10e25eb4dfdf340c964975dd706f9bf43c47d1d5fd37c017305d550600
+size 77884627

rec_soap/checkpoint-1035/latest

@@ -0,0 +1 @@
+global_step1032

rec_soap/checkpoint-1035/merges.txt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8831e4f1a044471340f7c0a83d7bd71306a5b867e95fd870f74d0c5308a904d5
+size 1671853

rec_soap/checkpoint-1035/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94cc16c7909aa51e9fe563daeb13e0ebb7bd6dbbf86a31c928f8538961f034d6
+size 14917

rec_soap/checkpoint-1035/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e5e1f1521c9dc46b5bd7b2bbed6f453fbb3370c266fd280521b79c5d09fba8c
+size 14917

rec_soap/checkpoint-1035/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b9c3b1155cbc6178f4197b008c54462a8d280e05942b014ec9849961337c9092
+size 1401

rec_soap/checkpoint-1035/special_tokens_map.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76862e765266b85aa9459767e33cbaf13970f327a0e88d1c65846c2ddd3a1ecd
+size 613

rec_soap/checkpoint-1035/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
+size 11422654

rec_soap/checkpoint-1035/tokenizer_config.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:443bfa629eb16387a12edbf92a76f6a6f10b2af3b53d87ba1550adfcf45f7fa0
+size 5404

rec_soap/checkpoint-1035/trainer_state.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:749c9c361c394f28deb12ef784ec5a9e8f849eec7319c47243b510e6974f732d
+size 28079

rec_soap/checkpoint-1035/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4189f4eaa39d6730758a4fbc6ef392a44ac7d966befb85d158fd50da00a8a1d9
+size 7633

rec_soap/checkpoint-1035/vocab.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca10d7e9fb3ed18575dd1e277a2579c16d108e32f27439684afa0e10b1440910
+size 2776833

rec_soap/checkpoint-1048/README.md

@@ -0,0 +1,202 @@
+---
+base_model: Qwen/Qwen3-4B
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **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]
+
+### Model Sources [optional]
+
+<!-- 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 0.15.2

rec_soap/checkpoint-1048/adapter_config.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:819494c95095d9317c72ecc17a7cd15aab1cc635e6b4a76f92d17e83713d281b
+size 828

rec_soap/checkpoint-1048/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dade04bc313be1e5c6cdc924cb5f1c491a36edc85b25bb166f4513725f998d2f
+size 1579102000

rec_soap/checkpoint-1048/added_tokens.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c0284b582e14987fbd3d5a2cb2bd139084371ed9acbae488829a1c900833c680
+size 707

rec_soap/checkpoint-1048/chat_template.jinja

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a55ee1b1660128b7098723e0abcd92caa0788061051c62d51cbe87d9cf1974d8
+size 4168

rec_soap/checkpoint-1048/global_step1044/mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e459e02d42b57a9043758367bf8243fe7d31dfa48c0b2b9d18075beb64f2e252
+size 861284969

rec_soap/checkpoint-1048/global_step1044/zero_pp_rank_0_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:553ab1b191f01714e810ea09ead60db7f365751b857d05e984ca10be29345670
+size 77884499

rec_soap/checkpoint-1048/global_step1044/zero_pp_rank_1_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8eb36cfa92cc9e5748da00f7ba52ca5004f2d2a25d75dc0f9eead558ca00e1bc
+size 77884627

rec_soap/checkpoint-1048/latest

@@ -0,0 +1 @@
+global_step1044

rec_soap/checkpoint-1048/merges.txt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8831e4f1a044471340f7c0a83d7bd71306a5b867e95fd870f74d0c5308a904d5
+size 1671853

rec_soap/checkpoint-1048/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e0c6b1843c533c5c961a1e073f7ca2672a1d67c2ccb908d95b21d2ce40b98d3
+size 14917

rec_soap/checkpoint-1048/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57be23d02d2f3ca56c7e3d448565c9f7eb174b00e1759c95a5c4b1226da487d8
+size 14917

rec_soap/checkpoint-1048/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b96abb4762f27473b0e6c6a0472bc3dac66dde3b3082f30776129de96883076
+size 1401

rec_soap/checkpoint-1048/special_tokens_map.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76862e765266b85aa9459767e33cbaf13970f327a0e88d1c65846c2ddd3a1ecd
+size 613

rec_soap/checkpoint-1048/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
+size 11422654

rec_soap/checkpoint-1048/tokenizer_config.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:443bfa629eb16387a12edbf92a76f6a6f10b2af3b53d87ba1550adfcf45f7fa0
+size 5404

rec_soap/checkpoint-1048/trainer_state.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7606e86a46ddc38e17eb37d340cd611b589d029f53f4aef974fa310d1a4bfcf6
+size 28063

rec_soap/checkpoint-1048/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4189f4eaa39d6730758a4fbc6ef392a44ac7d966befb85d158fd50da00a8a1d9
+size 7633

rec_soap/checkpoint-1048/vocab.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca10d7e9fb3ed18575dd1e277a2579c16d108e32f27439684afa0e10b1440910
+size 2776833

rec_soap/checkpoint-540/README.md

@@ -0,0 +1,202 @@
+---
+base_model: Qwen/Qwen3-4B
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **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]
+
+### Model Sources [optional]
+
+<!-- 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 0.15.2

rec_soap/checkpoint-540/adapter_config.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:819494c95095d9317c72ecc17a7cd15aab1cc635e6b4a76f92d17e83713d281b
+size 828

rec_soap/checkpoint-540/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b64c62fb7ebe1b6bb712bfeb697a4108a307d84c0c61fec6fb5d1783c0f02075
+size 1579102000

rec_soap/checkpoint-540/added_tokens.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c0284b582e14987fbd3d5a2cb2bd139084371ed9acbae488829a1c900833c680
+size 707

rec_soap/checkpoint-540/chat_template.jinja

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a55ee1b1660128b7098723e0abcd92caa0788061051c62d51cbe87d9cf1974d8
+size 4168

rec_soap/checkpoint-540/global_step538/mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ce9372dc108b12d2286c6a166bc9a7671c49578bca9196108abe01efd6978cd
+size 861284969

rec_soap/checkpoint-540/global_step538/zero_pp_rank_0_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7fb2ad62ba83b279539a075bb1e092b0047064c14c0c9a9c81e487cfc2512cb0
+size 77884499

rec_soap/checkpoint-540/global_step538/zero_pp_rank_1_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2aab8da2daf189a9b2592350689024ecd89bc4f9c284842710a3975ac6dce549
+size 77884627

rec_soap/checkpoint-540/latest

@@ -0,0 +1 @@
+global_step538

rec_soap/checkpoint-540/merges.txt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8831e4f1a044471340f7c0a83d7bd71306a5b867e95fd870f74d0c5308a904d5
+size 1671853