Upload folder using huggingface_hub

.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
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,202 @@
+---
+base_model: unsloth/gemma-3-1b-it-unsloth-bnb-4bit
+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 0.14.0

adapter_config.json

@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "unsloth/gemma-3-1b-it-unsloth-bnb-4bit",
+  "bias": "none",
+  "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": 64,
+  "lora_bias": false,
+  "lora_dropout": 0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": "(?:.*?(?:language|text).*?(?:self_attn|attention|attn|mlp|feed_forward|ffn|dense).*?(?:q_proj|k_proj|v_proj|o_proj|gate_proj|up_proj|down_proj).*?)|(?:\\bmodel\\.layers\\.[\\d]{1,}\\.(?:self_attn|attention|attn|mlp|feed_forward|ffn|dense)\\.(?:(?:q_proj|k_proj|v_proj|o_proj|gate_proj|up_proj|down_proj)))",
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfdb1f093f308c0ab70aed50344864102ec622b6fb1237c859c14b27c10aa1be
+size 104414464

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<image_soft_token>": 262144
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:357ea765edb6ed5aecd382d50fadffe68fb0d531a4437348715a325471b2f5a1
+size 53424388

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:608fccb6c056ce88cdfd5355e6be2046f4d107a24a87c6b0d2c3b200ce6bb4ea
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c22aabfa2f2fd91f64e86fe1cd4039bfeb4d4353977175431d7ec5747a6ee332
+size 1064

special_tokens_map.json

@@ -0,0 +1,33 @@
+{
+  "boi_token": "<start_of_image>",
+  "bos_token": {
+    "content": "<bos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eoi_token": "<end_of_image>",
+  "eos_token": {
+    "content": "<end_of_turn>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "image_token": "<image_soft_token>",
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4667f2089529e8e7657cfb6d1c19910ae71ff5f28aa7ab2ff2763330affad795
+size 33384568

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1299c11d7cf632ef3b4e11937501358ada021bbdf7c47638d13c0ee982f2e79c
+size 4689074

trainer_state.json

@@ -0,0 +1,356 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 46,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.021739130434782608,
+      "grad_norm": 21.980525970458984,
+      "learning_rate": 0.0,
+      "loss": 2.2134,
+      "step": 1
+    },
+    {
+      "epoch": 0.043478260869565216,
+      "grad_norm": 20.06768798828125,
+      "learning_rate": 1.0000000000000002e-06,
+      "loss": 1.5251,
+      "step": 2
+    },
+    {
+      "epoch": 0.06521739130434782,
+      "grad_norm": 23.364561080932617,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 2.2033,
+      "step": 3
+    },
+    {
+      "epoch": 0.08695652173913043,
+      "grad_norm": 19.796825408935547,
+      "learning_rate": 3e-06,
+      "loss": 1.9776,
+      "step": 4
+    },
+    {
+      "epoch": 0.10869565217391304,
+      "grad_norm": 21.887332916259766,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 2.2999,
+      "step": 5
+    },
+    {
+      "epoch": 0.13043478260869565,
+      "grad_norm": 20.906566619873047,
+      "learning_rate": 5e-06,
+      "loss": 1.9261,
+      "step": 6
+    },
+    {
+      "epoch": 0.15217391304347827,
+      "grad_norm": 20.153642654418945,
+      "learning_rate": 4.992664502959351e-06,
+      "loss": 1.8537,
+      "step": 7
+    },
+    {
+      "epoch": 0.17391304347826086,
+      "grad_norm": 19.199687957763672,
+      "learning_rate": 4.970701059450872e-06,
+      "loss": 1.9019,
+      "step": 8
+    },
+    {
+      "epoch": 0.1956521739130435,
+      "grad_norm": 17.73782730102539,
+      "learning_rate": 4.934238559694448e-06,
+      "loss": 1.564,
+      "step": 9
+    },
+    {
+      "epoch": 0.21739130434782608,
+      "grad_norm": 16.246173858642578,
+      "learning_rate": 4.883490980137327e-06,
+      "loss": 1.6703,
+      "step": 10
+    },
+    {
+      "epoch": 0.2391304347826087,
+      "grad_norm": 1828651.875,
+      "learning_rate": 4.8187561277552376e-06,
+      "loss": 1.4389,
+      "step": 11
+    },
+    {
+      "epoch": 0.2608695652173913,
+      "grad_norm": 13.8928861618042,
+      "learning_rate": 4.740413892402639e-06,
+      "loss": 1.3761,
+      "step": 12
+    },
+    {
+      "epoch": 0.2826086956521739,
+      "grad_norm": 720403.375,
+      "learning_rate": 4.648924017468003e-06,
+      "loss": 1.212,
+      "step": 13
+    },
+    {
+      "epoch": 0.30434782608695654,
+      "grad_norm": 14.764030456542969,
+      "learning_rate": 4.544823401916794e-06,
+      "loss": 1.5574,
+      "step": 14
+    },
+    {
+      "epoch": 0.32608695652173914,
+      "grad_norm": 12.913108825683594,
+      "learning_rate": 4.428722949554858e-06,
+      "loss": 1.4192,
+      "step": 15
+    },
+    {
+      "epoch": 0.34782608695652173,
+      "grad_norm": 10.674172401428223,
+      "learning_rate": 4.3013039840019675e-06,
+      "loss": 1.2746,
+      "step": 16
+    },
+    {
+      "epoch": 0.3695652173913043,
+      "grad_norm": 9.80074691772461,
+      "learning_rate": 4.163314250413913e-06,
+      "loss": 1.072,
+      "step": 17
+    },
+    {
+      "epoch": 0.391304347826087,
+      "grad_norm": 10.42562484741211,
+      "learning_rate": 4.015563527416596e-06,
+      "loss": 0.9013,
+      "step": 18
+    },
+    {
+      "epoch": 0.41304347826086957,
+      "grad_norm": 10.28138256072998,
+      "learning_rate": 3.858918875003053e-06,
+      "loss": 1.3421,
+      "step": 19
+    },
+    {
+      "epoch": 0.43478260869565216,
+      "grad_norm": 9.2878999710083,
+      "learning_rate": 3.6942995462806574e-06,
+      "loss": 1.1947,
+      "step": 20
+    },
+    {
+      "epoch": 0.45652173913043476,
+      "grad_norm": 10.689302444458008,
+      "learning_rate": 3.5226715929283507e-06,
+      "loss": 1.1843,
+      "step": 21
+    },
+    {
+      "epoch": 0.4782608695652174,
+      "grad_norm": 11.090900421142578,
+      "learning_rate": 3.345042196021257e-06,
+      "loss": 1.2872,
+      "step": 22
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 8.946170806884766,
+      "learning_rate": 3.162453755491655e-06,
+      "loss": 1.1389,
+      "step": 23
+    },
+    {
+      "epoch": 0.5217391304347826,
+      "grad_norm": 7.288694381713867,
+      "learning_rate": 2.975977772911671e-06,
+      "loss": 1.0438,
+      "step": 24
+    },
+    {
+      "epoch": 0.5434782608695652,
+      "grad_norm": 7.09510612487793,
+      "learning_rate": 2.786708563496002e-06,
+      "loss": 0.7908,
+      "step": 25
+    },
+    {
+      "epoch": 0.5652173913043478,
+      "grad_norm": 7.513128280639648,
+      "learning_rate": 2.595756834225089e-06,
+      "loss": 0.8884,
+      "step": 26
+    },
+    {
+      "epoch": 0.5869565217391305,
+      "grad_norm": 16309.765625,
+      "learning_rate": 2.404243165774912e-06,
+      "loss": 1.3966,
+      "step": 27
+    },
+    {
+      "epoch": 0.6086956521739131,
+      "grad_norm": 9.216928482055664,
+      "learning_rate": 2.2132914365039993e-06,
+      "loss": 0.7335,
+      "step": 28
+    },
+    {
+      "epoch": 0.6304347826086957,
+      "grad_norm": 8.130733489990234,
+      "learning_rate": 2.024022227088329e-06,
+      "loss": 1.4854,
+      "step": 29
+    },
+    {
+      "epoch": 0.6521739130434783,
+      "grad_norm": 7.4941534996032715,
+      "learning_rate": 1.8375462445083464e-06,
+      "loss": 0.6889,
+      "step": 30
+    },
+    {
+      "epoch": 0.6739130434782609,
+      "grad_norm": 8.134994506835938,
+      "learning_rate": 1.6549578039787436e-06,
+      "loss": 1.0505,
+      "step": 31
+    },
+    {
+      "epoch": 0.6956521739130435,
+      "grad_norm": 7.74264669418335,
+      "learning_rate": 1.4773284070716504e-06,
+      "loss": 0.9686,
+      "step": 32
+    },
+    {
+      "epoch": 0.717391304347826,
+      "grad_norm": 8.992671012878418,
+      "learning_rate": 1.3057004537193424e-06,
+      "loss": 1.0842,
+      "step": 33
+    },
+    {
+      "epoch": 0.7391304347826086,
+      "grad_norm": 7.693203449249268,
+      "learning_rate": 1.1410811249969475e-06,
+      "loss": 0.8311,
+      "step": 34
+    },
+    {
+      "epoch": 0.7608695652173914,
+      "grad_norm": 6.577566623687744,
+      "learning_rate": 9.844364725834058e-07,
+      "loss": 0.8217,
+      "step": 35
+    },
+    {
+      "epoch": 0.782608695652174,
+      "grad_norm": 10.145994186401367,
+      "learning_rate": 8.366857495860869e-07,
+      "loss": 0.8935,
+      "step": 36
+    },
+    {
+      "epoch": 0.8043478260869565,
+      "grad_norm": 6.9202375411987305,
+      "learning_rate": 6.986960159980327e-07,
+      "loss": 0.8456,
+      "step": 37
+    },
+    {
+      "epoch": 0.8260869565217391,
+      "grad_norm": 6.42577600479126,
+      "learning_rate": 5.712770504451426e-07,
+      "loss": 0.7391,
+      "step": 38
+    },
+    {
+      "epoch": 0.8478260869565217,
+      "grad_norm": 8.795654296875,
+      "learning_rate": 4.55176598083206e-07,
+      "loss": 1.1633,
+      "step": 39
+    },
+    {
+      "epoch": 0.8695652173913043,
+      "grad_norm": 9.373461723327637,
+      "learning_rate": 3.510759825319976e-07,
+      "loss": 0.8627,
+      "step": 40
+    },
+    {
+      "epoch": 0.8913043478260869,
+      "grad_norm": 7.181187629699707,
+      "learning_rate": 2.5958610759736133e-07,
+      "loss": 0.8084,
+      "step": 41
+    },
+    {
+      "epoch": 0.9130434782608695,
+      "grad_norm": 7.831035137176514,
+      "learning_rate": 1.8124387224476347e-07,
+      "loss": 0.8626,
+      "step": 42
+    },
+    {
+      "epoch": 0.9347826086956522,
+      "grad_norm": 8.75483512878418,
+      "learning_rate": 1.1650901986267365e-07,
+      "loss": 1.0262,
+      "step": 43
+    },
+    {
+      "epoch": 0.9565217391304348,
+      "grad_norm": 6.860268592834473,
+      "learning_rate": 6.576144030555259e-08,
+      "loss": 0.9124,
+      "step": 44
+    },
+    {
+      "epoch": 0.9782608695652174,
+      "grad_norm": 8.375471115112305,
+      "learning_rate": 2.9298940549128962e-08,
+      "loss": 0.9084,
+      "step": 45
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 9.354442596435547,
+      "learning_rate": 7.335497040648898e-09,
+      "loss": 1.0854,
+      "step": 46
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 46,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 514794267553536.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dfae59d97d549a7764d845813487d86f726862180414c82274f5eb59621a7ed9
+size 5560