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 +1,210 @@
+---
+base_model: unsloth/gemma-3-4b-it
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:unsloth/gemma-3-4b-it
+- grpo
+- lora
+- transformers
+- trl
+- unsloth
+---
+
+# 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 0.18.0

adapter_config.json

@@ -0,0 +1,50 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": {
+    "base_model_class": "Gemma3ForConditionalGeneration",
+    "parent_library": "transformers.models.gemma3.modeling_gemma3",
+    "unsloth_fixed": true
+  },
+  "base_model_name_or_path": "unsloth/gemma-3-4b-it",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "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",
+  "peft_version": "0.18.0",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "o_proj",
+    "v_proj",
+    "q_proj",
+    "down_proj",
+    "up_proj",
+    "gate_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8594f2ab8adf04ec52c366a18858c8ab400cf8ce455f153633c546124a0e7a5c
+size 262406656

added_tokens.json

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

chat_template.jinja

@@ -0,0 +1,47 @@
+{{ bos_token }}
+{%- if messages[0]['role'] == 'system' -%}
+    {%- if messages[0]['content'] is string -%}
+        {%- set first_user_prefix = messages[0]['content'] + '
+
+' -%}
+    {%- else -%}
+        {%- set first_user_prefix = messages[0]['content'][0]['text'] + '
+
+' -%}
+    {%- endif -%}
+    {%- set loop_messages = messages[1:] -%}
+{%- else -%}
+    {%- set first_user_prefix = "" -%}
+    {%- set loop_messages = messages -%}
+{%- endif -%}
+{%- for message in loop_messages -%}
+    {%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) -%}
+        {{ raise_exception("Conversation roles must alternate user/assistant/user/assistant/...") }}
+    {%- endif -%}
+    {%- if (message['role'] == 'assistant') -%}
+        {%- set role = "model" -%}
+    {%- else -%}
+        {%- set role = message['role'] -%}
+    {%- endif -%}
+    {{ '<start_of_turn>' + role + '
+' + (first_user_prefix if loop.first else "") }}
+    {%- if message['content'] is string -%}
+        {{ message['content'] | trim }}
+    {%- elif message['content'] is iterable -%}
+        {%- for item in message['content'] -%}
+            {%- if item['type'] == 'image' -%}
+                {{ '<start_of_image>' }}
+            {%- elif item['type'] == 'text' -%}
+                {{ item['text'] | trim }}
+            {%- endif -%}
+        {%- endfor -%}
+    {%- else -%}
+        {{ raise_exception("Invalid content type") }}
+    {%- endif -%}
+    {{ '<end_of_turn>
+' }}
+{%- endfor -%}
+{%- if add_generation_prompt -%}
+    {{'<start_of_turn>model
+'}}
+{%- endif -%}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b11a3d2c8434ad4608186ddaaf54046dda697c732c6c19208501e43d9d9b99c3
+size 121633045

preprocessor_config.json

@@ -0,0 +1,29 @@
+{
+  "do_convert_rgb": null,
+  "do_normalize": true,
+  "do_pan_and_scan": null,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_processor_type": "Gemma3ImageProcessor",
+  "image_seq_length": 256,
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "pan_and_scan_max_num_crops": null,
+  "pan_and_scan_min_crop_size": null,
+  "pan_and_scan_min_ratio_to_activate": null,
+  "processor_class": "Gemma3Processor",
+  "resample": 2,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "height": 896,
+    "width": 896
+  }
+}

processor_config.json

@@ -0,0 +1,4 @@
+{
+  "image_seq_length": 256,
+  "processor_class": "Gemma3Processor"
+}

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61d60bc9332a903ea16bb9c12937bae0125e7061504d86c0d8e59ce10c5fe9c5
+size 14645

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e93d7324cc3c92dc84e274d00c745d41b364755d21ca8c74bbb6e29bf6e06770
+size 1465

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:d786405177734910d7a3db625c2826640964a0b4e5cdbbd70620ae3313a01bef
+size 33384722

tokenizer.model

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

trainer_state.json

@@ -0,0 +1,164 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.0003030633644882472,
+  "eval_steps": 500,
+  "global_step": 50,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "completion_length": 53.0,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 53.0,
+      "completions/max_terminated_length": 53.0,
+      "completions/mean_length": 47.61666666666667,
+      "completions/mean_terminated_length": 47.61666666666667,
+      "completions/min_length": 41.13333333333333,
+      "completions/min_terminated_length": 41.13333333333333,
+      "epoch": 6.061267289764944e-05,
+      "frac_reward_zero_std": 0.2,
+      "grad_norm": 0.19573745131492615,
+      "kl": 0.038476434412101905,
+      "learning_rate": 4.903154239845798e-06,
+      "loss": 0.0,
+      "num_tokens": 14686.0,
+      "reward": 3.297205893198649,
+      "reward_std": 0.13904121598849695,
+      "rewards/coherence_reward_func/mean": 0.8483333309491475,
+      "rewards/coherence_reward_func/std": 0.03666666845480601,
+      "rewards/formatting_reward_func/mean": 1.3,
+      "rewards/formatting_reward_func/std": 0.0,
+      "rewards/quality_reward_func/mean": 1.1488724946975708,
+      "rewards/quality_reward_func/std": 0.10623545634249847,
+      "step": 10
+    },
+    {
+      "completion_length": 67.8,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 67.8,
+      "completions/max_terminated_length": 67.8,
+      "completions/mean_length": 60.6,
+      "completions/mean_terminated_length": 60.6,
+      "completions/min_length": 51.1,
+      "completions/min_terminated_length": 51.1,
+      "epoch": 0.00012122534579529888,
+      "frac_reward_zero_std": 0.1,
+      "grad_norm": 0.14363239705562592,
+      "kl": 0.0513855260447599,
+      "learning_rate": 3.897982258676867e-06,
+      "loss": 0.0,
+      "num_tokens": 29694.0,
+      "reward": 3.987208294868469,
+      "reward_std": 0.07321195515105501,
+      "rewards/coherence_reward_func/mean": 0.9899999976158143,
+      "rewards/coherence_reward_func/std": 0.020000000298023225,
+      "rewards/formatting_reward_func/mean": 1.5,
+      "rewards/formatting_reward_func/std": 0.0,
+      "rewards/quality_reward_func/mean": 1.497208344936371,
+      "rewards/quality_reward_func/std": 0.05723555360455066,
+      "step": 20
+    },
+    {
+      "completion_length": 60.7,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 60.7,
+      "completions/max_terminated_length": 60.7,
+      "completions/mean_length": 51.8,
+      "completions/mean_terminated_length": 51.8,
+      "completions/min_length": 43.5,
+      "completions/min_terminated_length": 43.5,
+      "epoch": 0.00018183801869294832,
+      "frac_reward_zero_std": 0.1,
+      "grad_norm": 0.3984941244125366,
+      "kl": 0.052938600437482816,
+      "learning_rate": 2.238678841830867e-06,
+      "loss": 0.0,
+      "num_tokens": 45670.0,
+      "reward": 3.331803727149963,
+      "reward_std": 0.12095312587916851,
+      "rewards/coherence_reward_func/mean": 0.8925000011920929,
+      "rewards/coherence_reward_func/std": 0.015000002086162567,
+      "rewards/formatting_reward_func/mean": 1.35,
+      "rewards/formatting_reward_func/std": 0.0,
+      "rewards/quality_reward_func/mean": 1.089303719997406,
+      "rewards/quality_reward_func/std": 0.11160956136882305,
+      "step": 30
+    },
+    {
+      "completion_length": 69.1,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 69.1,
+      "completions/max_terminated_length": 69.1,
+      "completions/mean_length": 55.575,
+      "completions/mean_terminated_length": 55.575,
+      "completions/min_length": 45.8,
+      "completions/min_terminated_length": 45.8,
+      "epoch": 0.00024245069159059776,
+      "frac_reward_zero_std": 0.1,
+      "grad_norm": 0.0,
+      "kl": 0.047772943903692064,
+      "learning_rate": 7.016504991533727e-07,
+      "loss": 0.0,
+      "num_tokens": 59741.0,
+      "reward": 3.563346338272095,
+      "reward_std": 0.15187854310497642,
+      "rewards/coherence_reward_func/mean": 0.8899999976158142,
+      "rewards/coherence_reward_func/std": 0.020000000298023225,
+      "rewards/formatting_reward_func/mean": 1.35,
+      "rewards/formatting_reward_func/std": 0.0,
+      "rewards/quality_reward_func/mean": 1.3233463883399963,
+      "rewards/quality_reward_func/std": 0.14236470488831401,
+      "step": 40
+    },
+    {
+      "completion_length": 50.8,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 50.8,
+      "completions/max_terminated_length": 50.8,
+      "completions/mean_length": 42.825,
+      "completions/mean_terminated_length": 42.825,
+      "completions/min_length": 34.3,
+      "completions/min_terminated_length": 34.3,
+      "epoch": 0.0003030633644882472,
+      "frac_reward_zero_std": 0.1,
+      "grad_norm": 0.33391332626342773,
+      "kl": 0.11284379730932415,
+      "learning_rate": 6.089874350439507e-09,
+      "loss": 0.0,
+      "num_tokens": 71218.0,
+      "reward": 3.385823893547058,
+      "reward_std": 0.3162759563419968,
+      "rewards/coherence_reward_func/mean": 0.9100000023841858,
+      "rewards/coherence_reward_func/std": 0.08000000417232514,
+      "rewards/formatting_reward_func/mean": 1.3875,
+      "rewards/formatting_reward_func/std": 0.075,
+      "rewards/quality_reward_func/mean": 1.0883238837122917,
+      "rewards/quality_reward_func/std": 0.16834406293928622,
+      "step": 50
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 50,
+  "num_input_tokens_seen": 71218,
+  "num_train_epochs": 1,
+  "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": 0.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d5b91e995e95c42ee48dbbc28256dfa433e53802a680f94723013dbf40ff20ce
+size 7057