Release v2 LoRA adapter (pedagogically validated: 88% 50-MCQ, 95.2% composite score, 0 quiz-leakage)

lora/README.md

@@ -0,0 +1,210 @@
+---
+base_model: SpaceGhost/SpaceCode-E2B
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:SpaceGhost/SpaceCode-E2B
+- lora
+- sft
+- 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 0.21.2

lora/adapter_config.json

@@ -4,10 +4,10 @@
   "arrow_config": null,
   "auto_mapping": {
     "base_model_class": "Gemma4ForConditionalGeneration",
-    "parent_library": "unsloth_compiled_module_gemma4",
+    "parent_library": "transformers.models.gemma4.modeling_gemma4",
     "unsloth_fixed": true
   },
-  "base_model_name_or_path": "unsloth/gemma-4-E2B-it-unsloth-bnb-4bit",
+  "base_model_name_or_path": "SpaceGhost/SpaceCode-E2B",
   "bias": "none",
   "corda_config": null,
   "ensure_weight_tying": false,
@@ -23,7 +23,7 @@
   "loftq_config": {},
   "lora_alpha": 16,
   "lora_bias": false,
-  "lora_dropout": 0,
+  "lora_dropout": 0.05,
   "lora_ga_config": null,
   "megatron_config": null,
   "megatron_core": "megatron.core",
@@ -35,7 +35,7 @@
   "r": 16,
   "rank_pattern": {},
   "revision": null,
-  "target_modules": "(?:(?:.*?(?:vision|image|visual|patch|language|text).*?(?:self_attn|attention|attn|mixer|mlp|feed_forward|ffn|dense|mixer).*?\\.(?:k_proj|q_proj|v_proj|o_proj|gate_proj|up_proj|down_proj|per_layer_input_gate|per_layer_projection|linear|embedding_projection|relative_k_proj))|(?:\\bmodel\\.layers\\.[\\d]{1,}(?!.*\\.experts\\.\\d)\\..*?(?:self_attn|attention|attn|mixer|mlp|feed_forward|ffn|dense|mixer).*?\\.(?:(?:k_proj|q_proj|v_proj|o_proj|gate_proj|up_proj|down_proj|per_layer_input_gate|per_layer_projection|linear|embedding_projection|relative_k_proj))))|(?:.*?\\baudio_tower\\.(?:.*\\.)?q_proj\\.linear)|(?:.*?\\baudio_tower\\.(?:.*\\.)?k_proj\\.linear)|(?:.*?\\baudio_tower\\.(?:.*\\.)?v_proj\\.linear)|(?:.*?\\baudio_tower\\.(?:.*\\.)?relative_k_proj)|(?:.*?\\baudio_tower\\.(?:.*\\.)?post\\.linear)|(?:.*?\\baudio_tower\\.(?:.*\\.)?ffw_layer_1\\.linear)|(?:.*?\\baudio_tower\\.(?:.*\\.)?ffw_layer_2\\.linear)|(?:.*?\\baudio_tower\\.(?:.*\\.)?linear_start\\.linear)|(?:.*?\\baudio_tower\\.(?:.*\\.)?linear_end\\.linear)|(?:.*?\\baudio_tower\\.(?:.*\\.)?input_proj_linear)|(?:.*?\\baudio_tower\\.(?:.*\\.)?output_proj)|(?:.*?\\bembed_audio\\.embedding_projection)|(?:.*?\\bembed_vision\\.embedding_projection)|(?:.*?\\bvision_tower\\.patch_embedder\\.input_proj)",
+  "target_modules": "(?:.*?(?:language|text).*?(?:self_attn|attention|attn|mixer|mlp|feed_forward|ffn|dense|mixer).*?\\.(?:linear|q_proj|k_proj|v_proj|o_proj|gate_proj|up_proj|down_proj|per_layer_input_gate|per_layer_projection|relative_k_proj|embedding_projection))|(?:\\bmodel\\.layers\\.[\\d]{1,}(?!.*\\.experts\\.\\d)\\..*?(?:self_attn|attention|attn|mixer|mlp|feed_forward|ffn|dense|mixer).*?\\.(?:(?:linear|q_proj|k_proj|v_proj|o_proj|gate_proj|up_proj|down_proj|per_layer_input_gate|per_layer_projection|relative_k_proj|embedding_projection)))",
   "target_parameters": null,
   "task_type": "CAUSAL_LM",
   "trainable_token_indices": null,

lora/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ca35497be8b22518ad25694bc2b6722419faa93038258af3d4ebf6b4082a90b
-size 147853664
+oid sha256:01dcaf4e2569798e3fc0086aae1a4c32337c912e6327549a7a000037aed3205f
+size 96693360

lora/tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6da98fc374193278aef084e5997ff75937fc712b803d41c93e30c057fc865f28
-size 32169880
+oid sha256:b1d8bced9d66859cd2c3f4dcd8ab427197d4d46af3d9598b72af9fcf80b8392e
+size 32169781

lora/tokenizer_config.json

@@ -18,7 +18,9 @@
   ],
   "image_token": "<|image|>",
   "is_local": false,
+  "local_files_only": false,
   "mask_token": "<mask>",
+  "max_length": 2048,
   "model_max_length": 131072,
   "model_specific_special_tokens": {
     "audio_token": "<|audio|>",
@@ -40,7 +42,9 @@
     "str_token": "<|tool_response>",
     "think_token": "<|think|>"
   },
+  "pad_to_multiple_of": null,
   "pad_token": "<pad>",
+  "pad_token_type_id": 0,
   "padding_side": "right",
   "processor_class": "Gemma4Processor",
   "response_schema": {
@@ -89,8 +93,11 @@
   "stc_token": "<|tool_call>",
   "std_token": "<|tool>",
   "str_token": "<|tool_response>",
+  "stride": 0,
   "think_token": "<|think|>",
   "tokenizer_class": "GemmaTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
   "unk_token": "<unk>",
   "added_tokens_decoder": {
     "0": {