Cycle 1 — judge 13.1/15 Δ+2.4

README.md

@@ -1,332 +1,210 @@
 ---
-license: apache-2.0
-base_model: unsloth/Qwen2.5-Coder-1.5B-Instruct-bnb-4bit
-base_model_relation: finetune
-tags:
-  - apex
-  - salesforce
-  - lwc
-  - soql
-  - sfdx
-  - code
-  - lora
-  - qlora
-  - peft
-  - unsloth
-  - qwen2.5
-datasets:
-  - Gianloko/apex-coder-training-data
-language:
-  - en
-pipeline_tag: text-generation
+base_model: Gianloko/apex-coder-1.5b
 library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Gianloko/apex-coder-1.5b
+- lora
+- sft
+- transformers
+- trl
+- unsloth
 ---
 
-# ApexCoder-1.5B — LoRA Adapter
+# Model Card for Model ID
 
-> QLoRA adapter weights for Salesforce Apex code generation, fine-tuned on top of Qwen2.5-Coder-1.5B-Instruct.
+<!-- Provide a quick summary of what the model is/does. -->
 
-**Adapter type:** QLoRA (PEFT)  
-**Base model:** [unsloth/Qwen2.5-Coder-1.5B-Instruct-bnb-4bit](https://huggingface.co/unsloth/Qwen2.5-Coder-1.5B-Instruct-bnb-4bit)  
-**Merged model (ready to use):** [Gianloko/apex-coder-1.5b](https://huggingface.co/Gianloko/apex-coder-1.5b)  
-**GGUF / Ollama:** [Gianloko/apex-coder-1.5b-GGUF](https://huggingface.co/Gianloko/apex-coder-1.5b-GGUF)  
-**Dataset:** [Gianloko/apex-coder-training-data](https://huggingface.co/datasets/Gianloko/apex-coder-training-data)
 
----
 
-## When to use the LoRA adapter vs the merged model
+## Model Details
 
-| Use case | Recommended |
-|---|---|
-| Production inference, Ollama, llama.cpp | ✅ [Merged model](https://huggingface.co/Gianloko/apex-coder-1.5b) |
-| Further fine-tuning on top of ApexCoder | ✅ **This LoRA adapter** |
-| Low-VRAM inference with dynamic adapter loading | ✅ **This LoRA adapter** |
-| GGUF quantized inference | ✅ [GGUF repo](https://huggingface.co/Gianloko/apex-coder-1.5b-GGUF) |
-| Swapping adapters at runtime | ✅ **This LoRA adapter** |
+### Model Description
 
----
+<!-- Provide a longer summary of what this model is. -->
 
-## Quick Start
-
-### Load with PEFT
-
-```python
-from peft import PeftModel
-from transformers import AutoModelForCausalLM, AutoTokenizer, BitsAndBytesConfig
-import torch
-
-base_model_id = "unsloth/Qwen2.5-Coder-1.5B-Instruct-bnb-4bit"
-lora_adapter_id = "Gianloko/apex-coder-1.5b-lora"
-
-# Load base model in 4-bit
-bnb_config = BitsAndBytesConfig(
-    load_in_4bit=True,
-    bnb_4bit_quant_type="nf4",
-    bnb_4bit_compute_dtype=torch.bfloat16,
-)
-base_model = AutoModelForCausalLM.from_pretrained(
-    base_model_id,
-    quantization_config=bnb_config,
-    device_map="auto",
-)
-tokenizer = AutoTokenizer.from_pretrained(base_model_id, use_fast=True)
-
-# Apply LoRA adapter
-model = PeftModel.from_pretrained(base_model, lora_adapter_id)
-model.eval()
-
-# Inference
-SYSTEM_PROMPT = (
-    "You are ApexCoder, a world-class Salesforce platform expert specializing in "
-    "Apex, LWC, Visualforce, Aura, SFDX metadata, Platform Events, and all "
-    "Salesforce coded artifacts. You write clean, production-ready, "
-    "governor-limit-aware code following Salesforce best practices."
-)
-
-messages = [
-    {"role": "system", "content": SYSTEM_PROMPT},
-    {"role": "user",   "content": "Write a bulkified Apex trigger on Account that prevents duplicate names."},
-]
-
-enc = tokenizer.apply_chat_template(
-    messages,
-    return_tensors="pt",
-    add_generation_prompt=True,
-    return_dict=True,
-)
-input_ids = enc["input_ids"].to(model.device)
-attention_mask = enc["attention_mask"].to(model.device)
-
-with torch.no_grad():
-    output = model.generate(
-        input_ids,
-        attention_mask=attention_mask,
-        max_new_tokens=512,
-        do_sample=False,
-        repetition_penalty=1.1,
-        pad_token_id=tokenizer.eos_token_id,
-    )
-
-response = tokenizer.decode(output[0][input_ids.shape[1]:], skip_special_tokens=True)
-print(response)
-```
-
-### Load with Unsloth (faster inference)
-
-```python
-from unsloth import FastLanguageModel
-from transformers import AutoTokenizer
-
-lora_adapter_id = "Gianloko/apex-coder-1.5b-lora"
-
-model, tokenizer = FastLanguageModel.from_pretrained(
-    model_name=lora_adapter_id,
-    max_seq_length=4096,
-    load_in_4bit=True,
-    dtype=None,
-)
-FastLanguageModel.for_inference(model)
-
-SYSTEM_PROMPT = (
-    "You are ApexCoder, a world-class Salesforce platform expert specializing in "
-    "Apex, LWC, Visualforce, Aura, SFDX metadata, Platform Events, and all "
-    "Salesforce coded artifacts. You write clean, production-ready, "
-    "governor-limit-aware code following Salesforce best practices."
-)
-
-messages = [
-    {"role": "system", "content": SYSTEM_PROMPT},
-    {"role": "user",   "content": "Write an @isTest class for an HTTP callout using HttpCalloutMock."},
-]
-
-enc = tokenizer.apply_chat_template(
-    messages,
-    return_tensors="pt",
-    add_generation_prompt=True,
-    return_dict=True,
-)
-input_ids = enc["input_ids"].to(model.device)
-attention_mask = enc["attention_mask"].to(model.device)
-
-with torch.no_grad():
-    output = model.generate(
-        input_ids,
-        attention_mask=attention_mask,
-        max_new_tokens=512,
-        do_sample=False,
-        repetition_penalty=1.1,
-        pad_token_id=tokenizer.eos_token_id,
-    )
-
-print(tokenizer.decode(output[0][input_ids.shape[1]:], skip_special_tokens=True))
-```
-
-### Merge and save locally
-
-```python
-from unsloth import FastLanguageModel
-
-model, tokenizer = FastLanguageModel.from_pretrained(
-    model_name="Gianloko/apex-coder-1.5b-lora",
-    max_seq_length=4096,
-    load_in_4bit=True,
-    dtype=None,
-)
-
-# Merge LoRA weights into base model and save as 16-bit
-model.save_pretrained_merged(
-    "apex-coder-1.5b-merged",
-    tokenizer,
-    save_method="merged_16bit",
-)
-print("✅ Merged model saved to ./apex-coder-1.5b-merged")
-```
 
----
 
-## Further Fine-tuning on Top of This Adapter
-
-You can continue training from this adapter to specialize ApexCoder further — for example, on your own org's code patterns, internal frameworks, or a specific Salesforce product area.
-
-```python
-from unsloth import FastLanguageModel
-from trl import SFTTrainer, SFTConfig
-from datasets import Dataset
-
-# Load ApexCoder LoRA as starting point
-model, tokenizer = FastLanguageModel.from_pretrained(
-    model_name="Gianloko/apex-coder-1.5b-lora",
-    max_seq_length=4096,
-    load_in_4bit=True,
-    dtype=None,
-)
-
-# Add a new LoRA adapter on top for continued training
-model = FastLanguageModel.get_peft_model(
-    model,
-    r=16,
-    lora_alpha=32,
-    lora_dropout=0.0,
-    target_modules=["q_proj", "k_proj", "v_proj", "o_proj",
-                    "gate_proj", "up_proj", "down_proj"],
-    bias="none",
-    use_gradient_checkpointing="unsloth",
-    use_rslora=True,
-)
-
-# Your custom dataset
-your_dataset = Dataset.from_list([
-    {
-        "messages": [
-            {"role": "system", "content": "You are ApexCoder..."},
-            {"role": "user",   "content": "Your custom question"},
-            {"role": "assistant", "content": "Your custom answer"},
-        ]
-    }
-])
-
-def apply_template(examples):
-    return {"text": [
-        tokenizer.apply_chat_template(msgs, tokenize=False, add_generation_prompt=False)
-        for msgs in examples["messages"]
-    ]}
-
-dataset = your_dataset.map(apply_template, batched=True,
-                            remove_columns=your_dataset.column_names)
-
-trainer = SFTTrainer(
-    model=model,
-    args=SFTConfig(
-        output_dir="./my-apex-coder-checkpoints",
-        num_train_epochs=2,
-        learning_rate=2e-5,          # lower LR for continued fine-tuning
-        per_device_train_batch_size=4,
-        gradient_accumulation_steps=4,
-        bf16=True,
-        max_seq_length=4096,
-        dataset_text_field="text",
-        packing=True,
-    ),
-    train_dataset=dataset,
-    processing_class=tokenizer,
-)
-
-trainer.train()
-model.save_pretrained("./my-apex-coder-lora")
-tokenizer.save_pretrained("./my-apex-coder-lora")
-```
+- **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]
 
-## LoRA Configuration
+<!-- Provide the basic links for the model. -->
 
-| Parameter | Value |
-|---|---|
-| LoRA rank (r) | 16 |
-| LoRA alpha | 32 |
-| LoRA dropout | 0.0 |
-| Bias | none |
-| RSLoRA | ✅ enabled |
-| Gradient checkpointing | unsloth |
-| Target modules | q_proj, k_proj, v_proj, o_proj, gate_proj, up_proj, down_proj |
-| Trainable parameters | ~13M / 1.5B total (~0.9%) |
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
 
----
+## Uses
 
-## Training Configuration
-
-| Parameter | Value |
-|---|---|
-| Learning rate | 5e-5 |
-| LR scheduler | Cosine |
-| Warmup ratio | 0.05 |
-| Batch size | 8 × 4 gradient accumulation = 32 effective |
-| Epochs | 3 |
-| Optimizer | AdamW 8-bit |
-| Max sequence length | 4096 |
-| Packing | ✅ enabled |
-| Training loss | 0.8032 |
-| Perplexity | 1.92 |
+<!-- 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
 
-## Chat Template
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
 
-This adapter uses the ChatML template (same as base Qwen2.5):
+[More Information Needed]
 
-```
-<|im_start|>system
-You are ApexCoder...<|im_end|>
-<|im_start|>user
-Your question here<|im_end|>
-<|im_start|>assistant
-```
+### Downstream Use [optional]
 
-Always include the system prompt for best results:
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
 
-```
-You are ApexCoder, a world-class Salesforce platform expert specializing in 
-Apex, LWC, Visualforce, Aura, SFDX metadata, Platform Events, and all 
-Salesforce coded artifacts. You write clean, production-ready, 
-governor-limit-aware code following Salesforce best practices.
-```
+[More Information Needed]
 
----
+### Out-of-Scope Use
 
-## Related Repositories
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
 
-| Repo | Description |
-|---|---|
-| [Gianloko/apex-coder-1.5b](https://huggingface.co/Gianloko/apex-coder-1.5b) | Merged 16-bit model — easiest to use |
-| [Gianloko/apex-coder-1.5b-GGUF](https://huggingface.co/Gianloko/apex-coder-1.5b-GGUF) | GGUF quantized — for Ollama / llama.cpp |
-| [Gianloko/apex-coder-training-data](https://huggingface.co/datasets/Gianloko/apex-coder-training-data) | Training dataset — 3,655 curated samples |
+[More Information Needed]
 
----
+## Bias, Risks, and Limitations
 
-## License
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
 
-Apache 2.0 — free to use, modify, and distribute for commercial and non-commercial purposes.
+[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
 
-*Built with ❤️ for the Salesforce developer community.*
+- PEFT 0.18.1

adapter_config.json

@@ -7,7 +7,7 @@
     "parent_library": "transformers.models.qwen2.modeling_qwen2",
     "unsloth_fixed": true
   },
-  "base_model_name_or_path": "unsloth/Qwen2.5-Coder-1.5B-Instruct-bnb-4bit",
+  "base_model_name_or_path": "Gianloko/apex-coder-1.5b",
   "bias": "none",
   "corda_config": null,
   "ensure_weight_tying": false,
@@ -33,13 +33,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "o_proj",
     "k_proj",
     "v_proj",
-    "o_proj",
+    "q_proj",
     "up_proj",
     "gate_proj",
-    "down_proj",
-    "q_proj"
+    "down_proj"
   ],
   "target_parameters": null,
   "task_type": "CAUSAL_LM",

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5853fb7ffd39d5084893e75433d113c9405d2b898eb55697a9fd490405af3ef5
+oid sha256:5be1eb79cc2d015bb4f5be893e8183c1a2f5100a407803ae35d627c5ffdc4c59
 size 147770496

added_tokens.json

@@ -0,0 +1,25 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|PAD_TOKEN|>": 151665,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

special_tokens_map.json

@@ -0,0 +1,16 @@
+{
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|PAD_TOKEN|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -1,11 +1,197 @@
 {
   "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<|PAD_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
   "backend": "tokenizers",
   "bos_token": null,
   "clean_up_tokenization_spaces": false,
   "eos_token": "<|im_end|>",
   "errors": "replace",
-  "extra_special_tokens": [],
+  "extra_special_tokens": {},
   "is_local": false,
   "model_max_length": 32768,
   "pad_token": "<|PAD_TOKEN|>",