gemma-4-E4B-it-Coder API & Inference Endpoint

Training Proof

Training ran on Kaggle with 2x Tesla T4 GPUs.

Table with columns: Item, Value
Item	Value
Safe coding rows	1024
LoRA steps	200
LoRA rank	16
LoRA alpha	32
Trainable parameters	50,499,584
Final train loss	1.1427
Merged LoRA tensors applied	592/592
Missing LoRA targets	0
Merged safetensor shards	5

HumanEval Results (50-Problem Subset)

Evaluated on Kaggle with 2x Tesla T4 GPUs using an executable 50-task HumanEval subset. Full generated before/after code is published in eval50_before_after_full_code.csv.

Table with columns: Metric, Base google/gemma-4-E4B-it, Coder
Metric	Base `google/gemma-4-E4B-it`	Coder
Pass count	34 / 50	42 / 50
Absolute lift	-	+16.0 pp
Relative pass-count lift	-	+23.53%

Proof files included in this repo:

eval50_summary.json: 50-problem HumanEval executable result.
eval50_before_after_full_code.csv: full generated before/after code for all 50 tasks.
EVAL50_README.md: evaluation methodology and scope.
nvidia_smi.txt: GPU environment proof.
eval_before_after.csv: fixed before/after coding prompt scores with output previews.
trainer_log_history.json: training loss and runtime logs.
merge_manifest.json: direct merge record, including 592 applied LoRA tensors and 0 missing targets.
model.safetensors.index.json: shard index for the full merged model.

This model is for benign coding assistance only. The training filter removed malware, phishing, exploit, credential theft, evasion, and destructive automation examples.

Evidence files

Run evidence for this release is stored in the repository under evidence/:

evidence/holykeys_gemma4_sft_output_release_release_summary.json

These files are compact local/Kaggle run artifacts used to document training, evaluation, merge, or quantization evidence for this model family.

Training Proof

Training ran on Kaggle with 2x Tesla T4 GPUs.

Table with columns: Item, Value
Item	Value
Safe coding rows	1024
LoRA steps	200
LoRA rank	16
LoRA alpha	32
Trainable parameters	50,499,584
Final train loss	1.1427
Merged LoRA tensors applied	592/592
Missing LoRA targets	0
Merged safetensor shards	5

HumanEval Results (50-Problem Subset)

Evaluated on Kaggle with 2x Tesla T4 GPUs using an executable 50-task HumanEval subset. Full generated before/after code is published in eval50_before_after_full_code.csv.

Table with columns: Metric, Base google/gemma-4-E4B-it, Coder
Metric	Base `google/gemma-4-E4B-it`	Coder
Pass count	34 / 50	42 / 50
Absolute lift	-	+16.0 pp
Relative pass-count lift	-	+23.53%

Proof files included in this repo:

eval50_summary.json: 50-problem HumanEval executable result.
eval50_before_after_full_code.csv: full generated before/after code for all 50 tasks.
EVAL50_README.md: evaluation methodology and scope.
nvidia_smi.txt: GPU environment proof.
eval_before_after.csv: fixed before/after coding prompt scores with output previews.
trainer_log_history.json: training loss and runtime logs.
merge_manifest.json: direct merge record, including 592 applied LoRA tensors and 0 missing targets.
model.safetensors.index.json: shard index for the full merged model.

This model is for benign coding assistance only. The training filter removed malware, phishing, exploit, credential theft, evasion, and destructive automation examples.

Evidence files

Run evidence for this release is stored in the repository under evidence/:

evidence/holykeys_gemma4_sft_output_release_release_summary.json

These files are compact local/Kaggle run artifacts used to document training, evaluation, merge, or quantization evidence for this model family.

gemma-4-E4B-it-Coder

README

Training Proof

HumanEval Results (50-Problem Subset)

Evidence files

Explore FriendliAI today

README

Training Proof

HumanEval Results (50-Problem Subset)

Evidence files