Upload 14 files

.gitattributes

@@ -33,3 +33,5 @@ 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
+checkpoint-200-Q8_0-LoRA.gguf 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

@@ -0,0 +1,31 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "unsloth/gemma-3-1b-it-unsloth-bnb-4bit",
+  "bias": "none",
+  "corda_config": null,
+  "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": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "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",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22b138e95bf604a7f7d412a999aa7e1ae5d96acd8541b02439d3472cd7ede127
+size 52231312

added_tokens.json

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

checkpoint-200-Q8_0-LoRA.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4bd811bc1113aae38454e4ba93a685e2778c8fd2bf0af637da7c83f91c82a5e2
+size 52208416

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36e9fd7db88f3afa987bb7dedc8645d298a52e8b776ff111cf219f19e41875ae
+size 26913540

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:98ccb2a03541cc106b832a41d95a290e919d2acb867255a6fc9ec6cfa673bad1
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca9a25c72339c898b564e0c464a3f6fc75bbeec408008928b7ed05533156b98c
+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 +1,174 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 15.4,
+  "eval_steps": 500,
+  "global_step": 200,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.8,
+      "grad_norm": 1.7011343240737915,
+      "learning_rate": 0.00018,
+      "loss": 0.5995,
+      "step": 10
+    },
+    {
+      "epoch": 1.56,
+      "grad_norm": 0.22524015605449677,
+      "learning_rate": 0.0001905263157894737,
+      "loss": 0.0139,
+      "step": 20
+    },
+    {
+      "epoch": 2.32,
+      "grad_norm": 0.04040924832224846,
+      "learning_rate": 0.00018,
+      "loss": 0.0052,
+      "step": 30
+    },
+    {
+      "epoch": 3.08,
+      "grad_norm": 0.014496985822916031,
+      "learning_rate": 0.00016947368421052633,
+      "loss": 0.0044,
+      "step": 40
+    },
+    {
+      "epoch": 3.88,
+      "grad_norm": 0.04556073993444443,
+      "learning_rate": 0.00015894736842105264,
+      "loss": 0.0043,
+      "step": 50
+    },
+    {
+      "epoch": 4.64,
+      "grad_norm": 0.08168065547943115,
+      "learning_rate": 0.00014842105263157895,
+      "loss": 0.0053,
+      "step": 60
+    },
+    {
+      "epoch": 5.4,
+      "grad_norm": 0.036317914724349976,
+      "learning_rate": 0.00013789473684210527,
+      "loss": 0.0046,
+      "step": 70
+    },
+    {
+      "epoch": 6.16,
+      "grad_norm": 0.0234612375497818,
+      "learning_rate": 0.00012736842105263158,
+      "loss": 0.0045,
+      "step": 80
+    },
+    {
+      "epoch": 6.96,
+      "grad_norm": 0.023044303059577942,
+      "learning_rate": 0.00011684210526315791,
+      "loss": 0.0047,
+      "step": 90
+    },
+    {
+      "epoch": 7.72,
+      "grad_norm": 0.0161167923361063,
+      "learning_rate": 0.00010631578947368421,
+      "loss": 0.004,
+      "step": 100
+    },
+    {
+      "epoch": 8.48,
+      "grad_norm": 0.00939767062664032,
+      "learning_rate": 9.578947368421052e-05,
+      "loss": 0.0044,
+      "step": 110
+    },
+    {
+      "epoch": 9.24,
+      "grad_norm": 0.03683692589402199,
+      "learning_rate": 8.526315789473685e-05,
+      "loss": 0.004,
+      "step": 120
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 0.02535077929496765,
+      "learning_rate": 7.473684210526316e-05,
+      "loss": 0.0042,
+      "step": 130
+    },
+    {
+      "epoch": 10.8,
+      "grad_norm": 0.024098610505461693,
+      "learning_rate": 6.421052631578948e-05,
+      "loss": 0.004,
+      "step": 140
+    },
+    {
+      "epoch": 11.56,
+      "grad_norm": 0.016196303069591522,
+      "learning_rate": 5.368421052631579e-05,
+      "loss": 0.0038,
+      "step": 150
+    },
+    {
+      "epoch": 12.32,
+      "grad_norm": 0.020965227857232094,
+      "learning_rate": 4.3157894736842105e-05,
+      "loss": 0.004,
+      "step": 160
+    },
+    {
+      "epoch": 13.08,
+      "grad_norm": 0.017107339575886726,
+      "learning_rate": 3.2631578947368426e-05,
+      "loss": 0.004,
+      "step": 170
+    },
+    {
+      "epoch": 13.88,
+      "grad_norm": 0.03667628765106201,
+      "learning_rate": 2.2105263157894736e-05,
+      "loss": 0.004,
+      "step": 180
+    },
+    {
+      "epoch": 14.64,
+      "grad_norm": 0.0402102991938591,
+      "learning_rate": 1.1578947368421053e-05,
+      "loss": 0.0038,
+      "step": 190
+    },
+    {
+      "epoch": 15.4,
+      "grad_norm": 0.04898475855588913,
+      "learning_rate": 1.0526315789473685e-06,
+      "loss": 0.004,
+      "step": 200
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 200,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 17,
+  "save_steps": 50,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3105837514930176.0,
+  "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 sha256:26e19a6a6211a5fb00ddb9b550d562a17cf1a0b3e4412d242259b74e532913fa
+size 5624