Upload model trained with Unsloth

Upload model trained with Unsloth 2x faster

README.md

@@ -0,0 +1,200 @@
+---
+library_name: transformers
+tags:
+- 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. -->
+
+This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
+
+- **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]

adapter_config.json

@@ -0,0 +1,303 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": {
+    "base_model_class": "Gemma4ForConditionalGeneration",
+    "parent_library": "transformers.models.gemma4.modeling_gemma4",
+    "unsloth_fixed": true
+  },
+  "base_model_name_or_path": "Puujeeeeeeeeeeee/gemma4-e4b-cpt-round3",
+  "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": 16,
+  "lora_bias": false,
+  "lora_dropout": 0,
+  "lora_ga_config": null,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.19.1",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "model.language_model.layers.1.mlp.gate_proj",
+    "model.language_model.layers.41.mlp.gate_proj",
+    "model.language_model.layers.17.mlp.down_proj",
+    "model.language_model.layers.18.mlp.gate_proj",
+    "model.language_model.layers.22.self_attn.q_proj",
+    "model.language_model.layers.8.mlp.gate_proj",
+    "model.language_model.layers.0.self_attn.v_proj",
+    "model.language_model.layers.14.self_attn.v_proj",
+    "model.language_model.layers.20.self_attn.v_proj",
+    "model.language_model.layers.6.mlp.gate_proj",
+    "model.language_model.layers.18.self_attn.v_proj",
+    "model.language_model.layers.34.self_attn.o_proj",
+    "model.language_model.layers.12.self_attn.k_proj",
+    "model.language_model.layers.22.self_attn.o_proj",
+    "model.language_model.layers.26.mlp.down_proj",
+    "model.language_model.layers.23.mlp.gate_proj",
+    "model.language_model.layers.11.self_attn.q_proj",
+    "model.language_model.layers.23.mlp.down_proj",
+    "model.language_model.layers.27.mlp.gate_proj",
+    "model.language_model.layers.5.mlp.down_proj",
+    "model.language_model.layers.4.self_attn.o_proj",
+    "model.language_model.layers.32.self_attn.o_proj",
+    "model.language_model.layers.5.self_attn.k_proj",
+    "model.language_model.layers.20.self_attn.o_proj",
+    "model.language_model.layers.30.mlp.gate_proj",
+    "model.language_model.layers.4.self_attn.q_proj",
+    "model.language_model.layers.5.self_attn.q_proj",
+    "model.language_model.layers.4.mlp.up_proj",
+    "model.language_model.layers.30.self_attn.q_proj",
+    "model.language_model.layers.2.mlp.up_proj",
+    "model.language_model.layers.29.self_attn.q_proj",
+    "model.language_model.layers.2.mlp.down_proj",
+    "model.language_model.layers.25.mlp.up_proj",
+    "model.language_model.layers.35.self_attn.o_proj",
+    "model.language_model.layers.38.mlp.up_proj",
+    "model.language_model.layers.23.self_attn.v_proj",
+    "model.language_model.layers.1.self_attn.o_proj",
+    "model.language_model.layers.16.self_attn.k_proj",
+    "model.language_model.layers.9.self_attn.v_proj",
+    "model.language_model.layers.30.mlp.up_proj",
+    "model.language_model.layers.24.mlp.gate_proj",
+    "model.language_model.layers.17.self_attn.v_proj",
+    "model.language_model.layers.40.mlp.down_proj",
+    "model.language_model.layers.1.self_attn.k_proj",
+    "model.language_model.layers.14.self_attn.k_proj",
+    "model.language_model.layers.3.self_attn.o_proj",
+    "model.language_model.layers.21.self_attn.v_proj",
+    "model.language_model.layers.8.mlp.down_proj",
+    "model.language_model.layers.8.self_attn.v_proj",
+    "model.language_model.layers.23.self_attn.o_proj",
+    "model.language_model.layers.38.mlp.down_proj",
+    "model.language_model.layers.23.mlp.up_proj",
+    "model.language_model.layers.4.self_attn.v_proj",
+    "model.language_model.layers.31.mlp.up_proj",
+    "model.language_model.layers.17.self_attn.q_proj",
+    "model.language_model.layers.7.self_attn.q_proj",
+    "model.language_model.layers.22.mlp.down_proj",
+    "model.language_model.layers.36.mlp.gate_proj",
+    "model.language_model.layers.10.mlp.down_proj",
+    "model.language_model.layers.26.mlp.gate_proj",
+    "model.language_model.layers.4.mlp.down_proj",
+    "model.language_model.layers.12.self_attn.v_proj",
+    "model.language_model.layers.25.mlp.down_proj",
+    "model.language_model.layers.39.mlp.gate_proj",
+    "model.language_model.layers.15.mlp.down_proj",
+    "model.language_model.layers.38.self_attn.q_proj",
+    "model.language_model.layers.16.mlp.down_proj",
+    "model.language_model.layers.9.mlp.gate_proj",
+    "model.language_model.layers.8.self_attn.k_proj",
+    "model.language_model.layers.24.self_attn.q_proj",
+    "model.language_model.layers.11.self_attn.o_proj",
+    "model.language_model.layers.12.mlp.up_proj",
+    "model.language_model.layers.38.self_attn.o_proj",
+    "model.language_model.layers.9.mlp.down_proj",
+    "model.language_model.layers.18.self_attn.k_proj",
+    "model.language_model.layers.39.self_attn.o_proj",
+    "model.language_model.layers.20.self_attn.q_proj",
+    "model.language_model.layers.0.self_attn.o_proj",
+    "model.language_model.layers.40.mlp.up_proj",
+    "model.language_model.layers.4.self_attn.k_proj",
+    "model.language_model.layers.33.self_attn.q_proj",
+    "model.language_model.layers.7.mlp.up_proj",
+    "model.language_model.layers.14.mlp.up_proj",
+    "model.language_model.layers.18.mlp.down_proj",
+    "model.language_model.layers.1.mlp.up_proj",
+    "model.language_model.layers.11.mlp.gate_proj",
+    "model.language_model.layers.36.self_attn.q_proj",
+    "model.language_model.layers.15.self_attn.o_proj",
+    "model.language_model.layers.18.self_attn.q_proj",
+    "model.language_model.layers.11.mlp.down_proj",
+    "model.language_model.layers.35.mlp.down_proj",
+    "model.language_model.layers.32.mlp.gate_proj",
+    "model.language_model.layers.16.self_attn.v_proj",
+    "model.language_model.layers.26.self_attn.q_proj",
+    "model.language_model.layers.27.self_attn.o_proj",
+    "model.language_model.layers.37.self_attn.q_proj",
+    "model.language_model.layers.15.self_attn.q_proj",
+    "model.language_model.layers.28.self_attn.q_proj",
+    "model.language_model.layers.15.self_attn.k_proj",
+    "model.language_model.layers.13.mlp.up_proj",
+    "model.language_model.layers.31.mlp.gate_proj",
+    "model.language_model.layers.36.mlp.up_proj",
+    "model.language_model.layers.26.mlp.up_proj",
+    "model.language_model.layers.37.mlp.up_proj",
+    "model.language_model.layers.7.self_attn.k_proj",
+    "model.language_model.layers.30.self_attn.o_proj",
+    "model.language_model.layers.5.mlp.gate_proj",
+    "model.language_model.layers.16.mlp.gate_proj",
+    "model.language_model.layers.2.self_attn.q_proj",
+    "model.language_model.layers.32.mlp.up_proj",
+    "model.language_model.layers.40.self_attn.q_proj",
+    "model.language_model.layers.10.mlp.up_proj",
+    "model.language_model.layers.33.mlp.up_proj",
+    "model.language_model.layers.1.mlp.down_proj",
+    "model.language_model.layers.11.self_attn.v_proj",
+    "model.language_model.layers.0.self_attn.q_proj",
+    "model.language_model.layers.13.mlp.down_proj",
+    "model.language_model.layers.19.self_attn.v_proj",
+    "model.language_model.layers.11.mlp.up_proj",
+    "model.language_model.layers.16.mlp.up_proj",
+    "model.language_model.layers.16.self_attn.o_proj",
+    "model.language_model.layers.31.self_attn.q_proj",
+    "model.language_model.layers.0.mlp.up_proj",
+    "model.language_model.layers.25.self_attn.q_proj",
+    "model.language_model.layers.36.mlp.down_proj",
+    "model.language_model.layers.6.self_attn.k_proj",
+    "model.language_model.layers.21.self_attn.k_proj",
+    "model.language_model.layers.41.mlp.up_proj",
+    "model.language_model.layers.12.self_attn.q_proj",
+    "model.language_model.layers.25.self_attn.o_proj",
+    "model.language_model.layers.10.self_attn.o_proj",
+    "model.language_model.layers.5.self_attn.v_proj",
+    "model.language_model.layers.8.mlp.up_proj",
+    "model.language_model.layers.3.self_attn.q_proj",
+    "model.language_model.layers.27.mlp.up_proj",
+    "model.language_model.layers.33.mlp.gate_proj",
+    "model.language_model.layers.28.self_attn.o_proj",
+    "model.language_model.layers.19.mlp.up_proj",
+    "model.language_model.layers.27.mlp.down_proj",
+    "model.language_model.layers.1.self_attn.q_proj",
+    "model.language_model.layers.40.mlp.gate_proj",
+    "model.language_model.layers.9.self_attn.o_proj",
+    "model.language_model.layers.12.mlp.gate_proj",
+    "model.language_model.layers.13.self_attn.v_proj",
+    "model.language_model.layers.13.mlp.gate_proj",
+    "model.language_model.layers.10.self_attn.q_proj",
+    "model.language_model.layers.24.self_attn.o_proj",
+    "model.language_model.layers.18.mlp.up_proj",
+    "model.language_model.layers.29.mlp.down_proj",
+    "model.language_model.layers.22.self_attn.k_proj",
+    "model.language_model.layers.19.self_attn.k_proj",
+    "model.language_model.layers.39.mlp.up_proj",
+    "model.language_model.layers.6.self_attn.q_proj",
+    "model.language_model.layers.34.mlp.down_proj",
+    "model.language_model.layers.19.self_attn.o_proj",
+    "model.language_model.layers.28.mlp.gate_proj",
+    "model.language_model.layers.1.self_attn.v_proj",
+    "model.language_model.layers.30.mlp.down_proj",
+    "model.language_model.layers.6.self_attn.o_proj",
+    "model.language_model.layers.20.mlp.up_proj",
+    "model.language_model.layers.16.self_attn.q_proj",
+    "model.language_model.layers.21.mlp.up_proj",
+    "model.language_model.layers.2.self_attn.v_proj",
+    "model.language_model.layers.24.mlp.down_proj",
+    "model.language_model.layers.0.self_attn.k_proj",
+    "model.language_model.layers.22.mlp.gate_proj",
+    "model.language_model.layers.3.mlp.down_proj",
+    "model.language_model.layers.13.self_attn.q_proj",
+    "model.language_model.layers.14.self_attn.q_proj",
+    "model.language_model.layers.3.mlp.up_proj",
+    "model.language_model.layers.29.mlp.gate_proj",
+    "model.language_model.layers.34.mlp.up_proj",
+    "model.language_model.layers.41.self_attn.o_proj",
+    "model.language_model.layers.21.mlp.gate_proj",
+    "model.language_model.layers.17.self_attn.k_proj",
+    "model.language_model.layers.7.self_attn.v_proj",
+    "model.language_model.layers.9.mlp.up_proj",
+    "model.language_model.layers.15.mlp.up_proj",
+    "model.language_model.layers.22.mlp.up_proj",
+    "model.language_model.layers.25.mlp.gate_proj",
+    "model.language_model.layers.35.mlp.up_proj",
+    "model.language_model.layers.29.mlp.up_proj",
+    "model.language_model.layers.7.mlp.down_proj",
+    "model.language_model.layers.19.mlp.gate_proj",
+    "model.language_model.layers.7.self_attn.o_proj",
+    "model.language_model.layers.26.self_attn.o_proj",
+    "model.language_model.layers.33.self_attn.o_proj",
+    "model.language_model.layers.5.mlp.up_proj",
+    "model.language_model.layers.27.self_attn.q_proj",
+    "model.language_model.layers.6.mlp.down_proj",
+    "model.language_model.layers.10.self_attn.v_proj",
+    "model.language_model.layers.2.self_attn.o_proj",
+    "model.language_model.layers.20.mlp.gate_proj",
+    "model.language_model.layers.31.self_attn.o_proj",
+    "model.language_model.layers.32.mlp.down_proj",
+    "model.language_model.layers.37.mlp.down_proj",
+    "model.language_model.layers.11.self_attn.k_proj",
+    "model.language_model.layers.41.mlp.down_proj",
+    "model.language_model.layers.19.self_attn.q_proj",
+    "model.language_model.layers.14.self_attn.o_proj",
+    "model.language_model.layers.17.mlp.gate_proj",
+    "model.language_model.layers.28.mlp.down_proj",
+    "model.language_model.layers.34.mlp.gate_proj",
+    "model.language_model.layers.38.mlp.gate_proj",
+    "model.language_model.layers.29.self_attn.o_proj",
+    "model.language_model.layers.35.mlp.gate_proj",
+    "model.language_model.layers.12.self_attn.o_proj",
+    "model.language_model.layers.19.mlp.down_proj",
+    "model.language_model.layers.3.self_attn.k_proj",
+    "model.language_model.layers.9.self_attn.k_proj",
+    "model.language_model.layers.5.self_attn.o_proj",
+    "model.language_model.layers.21.self_attn.o_proj",
+    "model.language_model.layers.7.mlp.gate_proj",
+    "model.language_model.layers.34.self_attn.q_proj",
+    "model.language_model.layers.17.self_attn.o_proj",
+    "model.language_model.layers.20.self_attn.k_proj",
+    "model.language_model.layers.0.mlp.down_proj",
+    "model.language_model.layers.4.mlp.gate_proj",
+    "model.language_model.layers.18.self_attn.o_proj",
+    "model.language_model.layers.9.self_attn.q_proj",
+    "model.language_model.layers.10.self_attn.k_proj",
+    "model.language_model.layers.28.mlp.up_proj",
+    "model.language_model.layers.2.self_attn.k_proj",
+    "model.language_model.layers.37.self_attn.o_proj",
+    "model.language_model.layers.15.self_attn.v_proj",
+    "model.language_model.layers.2.mlp.gate_proj",
+    "model.language_model.layers.23.self_attn.q_proj",
+    "model.language_model.layers.3.mlp.gate_proj",
+    "model.language_model.layers.32.self_attn.q_proj",
+    "model.language_model.layers.14.mlp.down_proj",
+    "model.language_model.layers.36.self_attn.o_proj",
+    "model.language_model.layers.24.mlp.up_proj",
+    "model.language_model.layers.20.mlp.down_proj",
+    "model.language_model.layers.0.mlp.gate_proj",
+    "model.language_model.layers.39.mlp.down_proj",
+    "model.language_model.layers.6.mlp.up_proj",
+    "model.language_model.layers.8.self_attn.q_proj",
+    "model.language_model.layers.14.mlp.gate_proj",
+    "model.language_model.layers.21.self_attn.q_proj",
+    "model.language_model.layers.3.self_attn.v_proj",
+    "model.language_model.layers.13.self_attn.k_proj",
+    "model.language_model.layers.15.mlp.gate_proj",
+    "model.language_model.layers.17.mlp.up_proj",
+    "model.language_model.layers.35.self_attn.q_proj",
+    "model.language_model.layers.22.self_attn.v_proj",
+    "model.language_model.layers.13.self_attn.o_proj",
+    "model.language_model.layers.31.mlp.down_proj",
+    "model.language_model.layers.39.self_attn.q_proj",
+    "model.language_model.layers.6.self_attn.v_proj",
+    "model.language_model.layers.33.mlp.down_proj",
+    "model.language_model.layers.8.self_attn.o_proj",
+    "model.language_model.layers.41.self_attn.q_proj",
+    "model.language_model.layers.21.mlp.down_proj",
+    "model.language_model.layers.12.mlp.down_proj",
+    "model.language_model.layers.10.mlp.gate_proj",
+    "model.language_model.layers.23.self_attn.k_proj",
+    "model.language_model.layers.37.mlp.gate_proj",
+    "model.language_model.layers.40.self_attn.o_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_bdlora": 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:a0f026eb308fb51844d9b15e08b7ac8ecee90833ca410e095e1f1b4c7763d2e5
+size 139602808