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 0.15.2

adapter_config.json

@@ -1,7 +1,7 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "unsloth/gemma-2-9b-bnb-4bit",
+  "base_model_name_or_path": "unsloth/gemma-3-1b-it-unsloth-bnb-4bit",
   "bias": "none",
   "corda_config": null,
   "eva_config": null,
@@ -24,9 +24,12 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "up_proj",
+    "down_proj",
+    "k_proj",
     "v_proj",
     "o_proj",
-    "k_proj",
+    "gate_proj",
     "q_proj"
   ],
   "task_type": "CAUSAL_LM",

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4f1aad6dc2a2a960372d941485728268a64df1706f8afa43c20a0cc1e20b1e5f
-size 71610528
+oid sha256:74bef3db54e6bac3c49f92460956081a498029372a38f71d4d5ab83bf672595f
+size 52231312

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 sha256:43d6c1506146720c3840cb82ed1d8e4a9b1bc15ed2d95d45e25cf580ca4fd753
+size 26913540

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d4c917636c7a58af68a29056522a757e9f9b99005b776641aa157c536967817d
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:974fb60062a9e094d57046984954545b807c1053a95415c6cb8cd6fd59c288ae
+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 +1,454 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.055645722235103175,
+  "eval_steps": 500,
+  "global_step": 60,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0009274287039183863,
+      "grad_norm": 4.868922710418701,
+      "learning_rate": 0.0,
+      "loss": 5.2325,
+      "step": 1
+    },
+    {
+      "epoch": 0.0018548574078367725,
+      "grad_norm": 5.811268329620361,
+      "learning_rate": 5e-06,
+      "loss": 4.7512,
+      "step": 2
+    },
+    {
+      "epoch": 0.0027822861117551586,
+      "grad_norm": 1.8592679500579834,
+      "learning_rate": 1e-05,
+      "loss": 3.6976,
+      "step": 3
+    },
+    {
+      "epoch": 0.003709714815673545,
+      "grad_norm": 3.553828001022339,
+      "learning_rate": 1.5e-05,
+      "loss": 4.4847,
+      "step": 4
+    },
+    {
+      "epoch": 0.004637143519591932,
+      "grad_norm": 3.7580947875976562,
+      "learning_rate": 2e-05,
+      "loss": 4.3681,
+      "step": 5
+    },
+    {
+      "epoch": 0.005564572223510317,
+      "grad_norm": 6.560013294219971,
+      "learning_rate": 2.5e-05,
+      "loss": 5.4142,
+      "step": 6
+    },
+    {
+      "epoch": 0.006492000927428704,
+      "grad_norm": 5.0084710121154785,
+      "learning_rate": 3e-05,
+      "loss": 4.8401,
+      "step": 7
+    },
+    {
+      "epoch": 0.00741942963134709,
+      "grad_norm": 2.0739693641662598,
+      "learning_rate": 3.5e-05,
+      "loss": 3.9564,
+      "step": 8
+    },
+    {
+      "epoch": 0.008346858335265477,
+      "grad_norm": 5.008288383483887,
+      "learning_rate": 4e-05,
+      "loss": 4.901,
+      "step": 9
+    },
+    {
+      "epoch": 0.009274287039183864,
+      "grad_norm": 1.2743533849716187,
+      "learning_rate": 4.5e-05,
+      "loss": 3.7309,
+      "step": 10
+    },
+    {
+      "epoch": 0.010201715743102248,
+      "grad_norm": 1.1797062158584595,
+      "learning_rate": 5e-05,
+      "loss": 3.56,
+      "step": 11
+    },
+    {
+      "epoch": 0.011129144447020635,
+      "grad_norm": 3.787964344024658,
+      "learning_rate": 4.9e-05,
+      "loss": 5.1572,
+      "step": 12
+    },
+    {
+      "epoch": 0.012056573150939021,
+      "grad_norm": 1.1445714235305786,
+      "learning_rate": 4.8e-05,
+      "loss": 3.5998,
+      "step": 13
+    },
+    {
+      "epoch": 0.012984001854857407,
+      "grad_norm": 1.2640348672866821,
+      "learning_rate": 4.7e-05,
+      "loss": 3.6054,
+      "step": 14
+    },
+    {
+      "epoch": 0.013911430558775794,
+      "grad_norm": 0.9739102721214294,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 3.4424,
+      "step": 15
+    },
+    {
+      "epoch": 0.01483885926269418,
+      "grad_norm": 3.6449685096740723,
+      "learning_rate": 4.5e-05,
+      "loss": 5.1529,
+      "step": 16
+    },
+    {
+      "epoch": 0.015766287966612568,
+      "grad_norm": 1.0862540006637573,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 3.4454,
+      "step": 17
+    },
+    {
+      "epoch": 0.016693716670530954,
+      "grad_norm": 2.713123083114624,
+      "learning_rate": 4.3e-05,
+      "loss": 4.4682,
+      "step": 18
+    },
+    {
+      "epoch": 0.01762114537444934,
+      "grad_norm": 1.0332715511322021,
+      "learning_rate": 4.2e-05,
+      "loss": 3.3278,
+      "step": 19
+    },
+    {
+      "epoch": 0.018548574078367727,
+      "grad_norm": 1.1742037534713745,
+      "learning_rate": 4.1e-05,
+      "loss": 3.5884,
+      "step": 20
+    },
+    {
+      "epoch": 0.01947600278228611,
+      "grad_norm": 1.1539186239242554,
+      "learning_rate": 4e-05,
+      "loss": 3.6538,
+      "step": 21
+    },
+    {
+      "epoch": 0.020403431486204496,
+      "grad_norm": 1.303881287574768,
+      "learning_rate": 3.9000000000000006e-05,
+      "loss": 3.387,
+      "step": 22
+    },
+    {
+      "epoch": 0.021330860190122883,
+      "grad_norm": 1.8081673383712769,
+      "learning_rate": 3.8e-05,
+      "loss": 3.7469,
+      "step": 23
+    },
+    {
+      "epoch": 0.02225828889404127,
+      "grad_norm": 1.0129601955413818,
+      "learning_rate": 3.7e-05,
+      "loss": 3.0917,
+      "step": 24
+    },
+    {
+      "epoch": 0.023185717597959656,
+      "grad_norm": 2.841965436935425,
+      "learning_rate": 3.6e-05,
+      "loss": 3.6627,
+      "step": 25
+    },
+    {
+      "epoch": 0.024113146301878042,
+      "grad_norm": 2.4179654121398926,
+      "learning_rate": 3.5e-05,
+      "loss": 3.8892,
+      "step": 26
+    },
+    {
+      "epoch": 0.025040575005796428,
+      "grad_norm": 1.5163795948028564,
+      "learning_rate": 3.4000000000000007e-05,
+      "loss": 3.2586,
+      "step": 27
+    },
+    {
+      "epoch": 0.025968003709714815,
+      "grad_norm": 2.0588231086730957,
+      "learning_rate": 3.3e-05,
+      "loss": 3.7464,
+      "step": 28
+    },
+    {
+      "epoch": 0.0268954324136332,
+      "grad_norm": 1.082326889038086,
+      "learning_rate": 3.2000000000000005e-05,
+      "loss": 3.5218,
+      "step": 29
+    },
+    {
+      "epoch": 0.027822861117551587,
+      "grad_norm": 3.831888437271118,
+      "learning_rate": 3.1e-05,
+      "loss": 4.0704,
+      "step": 30
+    },
+    {
+      "epoch": 0.028750289821469974,
+      "grad_norm": 1.2819643020629883,
+      "learning_rate": 3e-05,
+      "loss": 3.5,
+      "step": 31
+    },
+    {
+      "epoch": 0.02967771852538836,
+      "grad_norm": 2.7546770572662354,
+      "learning_rate": 2.9e-05,
+      "loss": 3.6709,
+      "step": 32
+    },
+    {
+      "epoch": 0.030605147229306746,
+      "grad_norm": 2.127004861831665,
+      "learning_rate": 2.8000000000000003e-05,
+      "loss": 3.7116,
+      "step": 33
+    },
+    {
+      "epoch": 0.031532575933225136,
+      "grad_norm": 1.5426557064056396,
+      "learning_rate": 2.7000000000000002e-05,
+      "loss": 3.7935,
+      "step": 34
+    },
+    {
+      "epoch": 0.03246000463714352,
+      "grad_norm": 1.4559600353240967,
+      "learning_rate": 2.6000000000000002e-05,
+      "loss": 3.2505,
+      "step": 35
+    },
+    {
+      "epoch": 0.03338743334106191,
+      "grad_norm": 1.2187875509262085,
+      "learning_rate": 2.5e-05,
+      "loss": 3.3403,
+      "step": 36
+    },
+    {
+      "epoch": 0.03431486204498029,
+      "grad_norm": 1.4153465032577515,
+      "learning_rate": 2.4e-05,
+      "loss": 2.73,
+      "step": 37
+    },
+    {
+      "epoch": 0.03524229074889868,
+      "grad_norm": 1.2564786672592163,
+      "learning_rate": 2.3000000000000003e-05,
+      "loss": 3.3627,
+      "step": 38
+    },
+    {
+      "epoch": 0.036169719452817065,
+      "grad_norm": 3.221158742904663,
+      "learning_rate": 2.2000000000000003e-05,
+      "loss": 3.6366,
+      "step": 39
+    },
+    {
+      "epoch": 0.037097148156735454,
+      "grad_norm": 1.5206141471862793,
+      "learning_rate": 2.1e-05,
+      "loss": 3.5083,
+      "step": 40
+    },
+    {
+      "epoch": 0.03802457686065384,
+      "grad_norm": 3.3207788467407227,
+      "learning_rate": 2e-05,
+      "loss": 3.6526,
+      "step": 41
+    },
+    {
+      "epoch": 0.03895200556457222,
+      "grad_norm": 2.6947567462921143,
+      "learning_rate": 1.9e-05,
+      "loss": 3.8998,
+      "step": 42
+    },
+    {
+      "epoch": 0.03987943426849061,
+      "grad_norm": 3.0442309379577637,
+      "learning_rate": 1.8e-05,
+      "loss": 4.0098,
+      "step": 43
+    },
+    {
+      "epoch": 0.04080686297240899,
+      "grad_norm": 3.0149142742156982,
+      "learning_rate": 1.7000000000000003e-05,
+      "loss": 3.6688,
+      "step": 44
+    },
+    {
+      "epoch": 0.04173429167632738,
+      "grad_norm": 2.458320140838623,
+      "learning_rate": 1.6000000000000003e-05,
+      "loss": 3.7055,
+      "step": 45
+    },
+    {
+      "epoch": 0.042661720380245766,
+      "grad_norm": 1.5240652561187744,
+      "learning_rate": 1.5e-05,
+      "loss": 3.2421,
+      "step": 46
+    },
+    {
+      "epoch": 0.043589149084164155,
+      "grad_norm": 5.896821975708008,
+      "learning_rate": 1.4000000000000001e-05,
+      "loss": 4.7299,
+      "step": 47
+    },
+    {
+      "epoch": 0.04451657778808254,
+      "grad_norm": 1.3863835334777832,
+      "learning_rate": 1.3000000000000001e-05,
+      "loss": 3.3415,
+      "step": 48
+    },
+    {
+      "epoch": 0.04544400649200093,
+      "grad_norm": 1.5955193042755127,
+      "learning_rate": 1.2e-05,
+      "loss": 3.3076,
+      "step": 49
+    },
+    {
+      "epoch": 0.04637143519591931,
+      "grad_norm": 2.4756007194519043,
+      "learning_rate": 1.1000000000000001e-05,
+      "loss": 3.8448,
+      "step": 50
+    },
+    {
+      "epoch": 0.0472988638998377,
+      "grad_norm": 1.1582512855529785,
+      "learning_rate": 1e-05,
+      "loss": 3.2583,
+      "step": 51
+    },
+    {
+      "epoch": 0.048226292603756084,
+      "grad_norm": 2.394286632537842,
+      "learning_rate": 9e-06,
+      "loss": 3.3061,
+      "step": 52
+    },
+    {
+      "epoch": 0.049153721307674474,
+      "grad_norm": 1.4328668117523193,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 3.1576,
+      "step": 53
+    },
+    {
+      "epoch": 0.050081150011592857,
+      "grad_norm": 1.2915327548980713,
+      "learning_rate": 7.000000000000001e-06,
+      "loss": 3.0897,
+      "step": 54
+    },
+    {
+      "epoch": 0.051008578715511246,
+      "grad_norm": 1.9309310913085938,
+      "learning_rate": 6e-06,
+      "loss": 3.372,
+      "step": 55
+    },
+    {
+      "epoch": 0.05193600741942963,
+      "grad_norm": 3.784912586212158,
+      "learning_rate": 5e-06,
+      "loss": 3.7925,
+      "step": 56
+    },
+    {
+      "epoch": 0.05286343612334802,
+      "grad_norm": 9.921348571777344,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 5.3381,
+      "step": 57
+    },
+    {
+      "epoch": 0.0537908648272664,
+      "grad_norm": 1.3432551622390747,
+      "learning_rate": 3e-06,
+      "loss": 3.543,
+      "step": 58
+    },
+    {
+      "epoch": 0.05471829353118479,
+      "grad_norm": 2.20005202293396,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 3.658,
+      "step": 59
+    },
+    {
+      "epoch": 0.055645722235103175,
+      "grad_norm": 1.4739794731140137,
+      "learning_rate": 1.0000000000000002e-06,
+      "loss": 3.258,
+      "step": 60
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 60,
+  "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": 715238756384256.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c553330158f5669e0fd93f1ff21b7b08ba11a6a294989ca3ba92a564ae5ca241
+size 5560