gabrielgts

phi4-3b-ec-magento

What it does

Trained on 56,253 instruction samples: 70% ECInstruct (generic e-commerce) + 30% synthetic Magento-schema data generated from the Magento Luma sample catalog (products fully disjoint between train and eval). Four task shapes:

Attribute extraction — product text (or a raw Magento custom_attributes payload) → JSON:

markdown
target attribute: size
product title: Puma Suede green sneakers size 43
→ [{"attribute": "size", "value": "43"}]

Absent attributes are reported as "None" rather than hallucinated.

Product QA — a question answered strictly from given product data. Relevance classification — query + product → graded relevance option (ESCI-style A–D). Relevance ranking — query + lettered product list → ranked letters (B,A,C).

Usage — adapter (unsloth / peft)

python
from unsloth import FastLanguageModel

model, tokenizer = FastLanguageModel.from_pretrained(
    "gabrielgts/phi4-3b-ec-magento", max_seq_length=2048, load_in_4bit=True)
FastLanguageModel.for_inference(model)

# No system message — the model was trained without one (Phi's template
# injects nothing by default). Greedy decoding recommended.
messages = [{"role": "user", "content":
    "Extract the value of the target attribute from the given product information "
    "and output it as JSON. If the attribute is not present, output None as the value.\n\n"
    "target attribute: size\nproduct title: Puma Suede green sneakers size 43"}]
text = tokenizer.apply_chat_template(messages, add_generation_prompt=True, tokenize=False)
inputs = tokenizer(text=text, return_tensors="pt").to("cuda")
out = model.generate(**inputs, max_new_tokens=64, do_sample=False)
print(tokenizer.decode(out[0][inputs["input_ids"].shape[1]:], skip_special_tokens=True))
# [{"attribute": "size", "value": "43"}]

Plain peft also works: PeftModel.from_pretrained(base_model, "gabrielgts/phi4-3b-ec-magento").

Usage — GGUF / Ollama

bash
hf download gabrielgts/phi4-3b-ec-magento --include 'gguf/*' --local-dir .
cd gguf && ollama create phi4-3b-ec-magento -f Modelfile
ollama run phi4-3b-ec-magento "target attribute: color ..."

Gotchas (learned the hard way)

Fine-tune from the unsloth repo, not microsoft's: microsoft's tokenizer config sets eos=<|endoftext|>, which the model rarely emits — generation does not stop at <|end|> and rambles past answers. The unsloth export fixes eos=<|end|>. Unsloth also silently remaps the microsoft id to its dynamic-quant repo; pin the plain -bnb-4bit id for standard NF4.
Fused projections: phi3 fuses qkv_proj/gate_up_proj. LoRA target names q_proj/k_proj/v_proj/gate_proj/up_proj silently match nothing (peft skips without erroring) — target qkv_proj, o_proj, gate_up_proj, down_proj.
Quantization sensitivity: at plain Q4_K_M the tied 200k-vocab embedding degrades outputs (wrong attributes extracted with perfect JSON formatting). The shipped GGUF uses --token-embedding-type q8_0 --output-tensor-type q8_0.

Training recipe

Table with columns: Parameter, Value
Parameter	Value
Method	QLoRA (4-bit NF4 base, bf16 compute) via Unsloth
LoRA	r=8, alpha=16, targets qkv_proj/o_proj/gate_up_proj/down_proj (fused)
Trainable params	11.5M of 3,836M (0.30%)
Batch	1 × grad_accum 16 (effective 16), max_seq_length 2048
Optimizer / LR	paged_adamw_8bit, 2e-4 cosine, 1 epoch, seed 42
Data	56,253 samples: 39,377 ECInstruct + 16,876 Magento-synthetic
System prompt	none at train and eval

Evaluation

Greedy decoding, identical prompts across all models; base models evaluated zero-shot with the same harness. Siblings: qwen3.5-4b-ec-magento (4.55B params), ministral3-3b-ec-magento (3.85B text params) — Phi-4-mini (3.84B) and Ministral are size-matched; Qwen is ~18% larger.

Magento held-out set (2,969 samples, 475 products never seen in training):

Table with columns: Task · metric, Base, this model, ministral3-3b, qwen3.5-4b
Task · metric	Base	this model	ministral3-3b	qwen3.5-4b
Attribute extraction · F1	0.000	0.946	0.945	0.938
Attribute extraction · parse failures	96.3%	0.3%	0.1%	0%
Product QA · token-F1	0.013	0.950	0.954

ECInstruct held-out set (2,000 samples):

Table with columns: Task · metric, Base, this model, ministral3-3b, qwen3.5-4b
Task · metric	Base	this model	ministral3-3b	qwen3.5-4b
Attribute extraction · F1	0.000	0.616	0.654	0.646
Query→product rank · top-1	0.000	0.645	0.632	0.650
Relevance classification · accuracy	0.570	0.650	0.655

Limitations — read before relying on the numbers

The Magento eval is synthetic-on-synthetic. Eval tasks were generated with the same templates as training data (products fully disjoint). It validly measures schema adherence — JSON format, Magento attribute vocabularies, the None-when-absent rule — but overstates production quality on real catalogs and real user queries.
The base model's near-zero extraction scores are dominated by format non-adherence; they understate its underlying capability.
The fused-projection LoRA shares one rank-8 subspace across q/k/v — a small ECInstruct deficit vs the siblings may reflect this structural difference rather than model quality.
English only; fine-tuned on structured data — expect degraded general chat vs the base (drop the adapter to recover it).
Use greedy decoding (do_sample=False / temperature 0) — that's how it was evaluated.

Provenance

Table

Training run	`phi4-mini-r8-mix56k-e1` (2026-07-14)
Adapter sha256	`f856fa953ae099762bbf91e6410f90902432bd23776266323366941dfeaa29a3`
Train set sha256	`afb7e664cda4490597c1914db6aff94933991a56d2175435666f8f6b7a726532` (mixture_train.jsonl, 56,253 rows)
Eval set sha256	`8feafdb2…` (magento_eval.jsonl) · `2583a61e…` (ecinstruct_eval.jsonl)
GGUF	adapter merged into `microsoft/Phi-4-mini-instruct` bf16, Q4_K_M + q8_0 embeddings, sha256

References

Phi-4-mini: arXiv:2503.01743
ECInstruct / eCeLLM: arXiv:2402.08831
QLoRA: arXiv:2305.14314

Available on FriendliAI

Dedicated Endpoints

Run this model inference on single tenant GPU with unmatched speed and reliability at scale.

Learn more

Container

Run this model inference with full control and performance in your environment.

Learn more

Model Details

Model Provider

gabrielgts

Model Tree

Base

unsloth/Phi-4-mini-instruct-bnb-4bit

Adapter

this model

Input Modalities

Text

Output Modalities

Text

Supported Functionality

Dedicated EndpointsContainer

Explore FriendliAI today

Get started Talk to an engineer

What it does

Attribute extraction — product text (or a raw Magento custom_attributes payload) → JSON:

markdown
target attribute: size
product title: Puma Suede green sneakers size 43
→ [{"attribute": "size", "value": "43"}]

Absent attributes are reported as "None" rather than hallucinated.

Usage — adapter (unsloth / peft)

python
from unsloth import FastLanguageModel

model, tokenizer = FastLanguageModel.from_pretrained(
    "gabrielgts/phi4-3b-ec-magento", max_seq_length=2048, load_in_4bit=True)
FastLanguageModel.for_inference(model)

# No system message — the model was trained without one (Phi's template
# injects nothing by default). Greedy decoding recommended.
messages = [{"role": "user", "content":
    "Extract the value of the target attribute from the given product information "
    "and output it as JSON. If the attribute is not present, output None as the value.\n\n"
    "target attribute: size\nproduct title: Puma Suede green sneakers size 43"}]
text = tokenizer.apply_chat_template(messages, add_generation_prompt=True, tokenize=False)
inputs = tokenizer(text=text, return_tensors="pt").to("cuda")
out = model.generate(**inputs, max_new_tokens=64, do_sample=False)
print(tokenizer.decode(out[0][inputs["input_ids"].shape[1]:], skip_special_tokens=True))
# [{"attribute": "size", "value": "43"}]

Plain peft also works: PeftModel.from_pretrained(base_model, "gabrielgts/phi4-3b-ec-magento").

Usage — GGUF / Ollama

bash
hf download gabrielgts/phi4-3b-ec-magento --include 'gguf/*' --local-dir .
cd gguf && ollama create phi4-3b-ec-magento -f Modelfile
ollama run phi4-3b-ec-magento "target attribute: color ..."

Gotchas (learned the hard way)

Fine-tune from the unsloth repo, not microsoft's: microsoft's tokenizer config sets eos=<|endoftext|>, which the model rarely emits — generation does not stop at <|end|> and rambles past answers. The unsloth export fixes eos=<|end|>. Unsloth also silently remaps the microsoft id to its dynamic-quant repo; pin the plain -bnb-4bit id for standard NF4.
Fused projections: phi3 fuses qkv_proj/gate_up_proj. LoRA target names q_proj/k_proj/v_proj/gate_proj/up_proj silently match nothing (peft skips without erroring) — target qkv_proj, o_proj, gate_up_proj, down_proj.
Quantization sensitivity: at plain Q4_K_M the tied 200k-vocab embedding degrades outputs (wrong attributes extracted with perfect JSON formatting). The shipped GGUF uses --token-embedding-type q8_0 --output-tensor-type q8_0.

Training recipe

Table with columns: Parameter, Value
Parameter	Value
Method	QLoRA (4-bit NF4 base, bf16 compute) via Unsloth
LoRA	r=8, alpha=16, targets qkv_proj/o_proj/gate_up_proj/down_proj (fused)
Trainable params	11.5M of 3,836M (0.30%)
Batch	1 × grad_accum 16 (effective 16), max_seq_length 2048
Optimizer / LR	paged_adamw_8bit, 2e-4 cosine, 1 epoch, seed 42
Data	56,253 samples: 39,377 ECInstruct + 16,876 Magento-synthetic
System prompt	none at train and eval

Evaluation

Magento held-out set (2,969 samples, 475 products never seen in training):

Table with columns: Task · metric, Base, this model, ministral3-3b, qwen3.5-4b
Task · metric	Base	this model	ministral3-3b	qwen3.5-4b
Attribute extraction · F1	0.000	0.946	0.945	0.938
Attribute extraction · parse failures	96.3%	0.3%	0.1%	0%
Product QA · token-F1	0.013	0.950	0.954

ECInstruct held-out set (2,000 samples):

Table with columns: Task · metric, Base, this model, ministral3-3b, qwen3.5-4b
Task · metric	Base	this model	ministral3-3b	qwen3.5-4b
Attribute extraction · F1	0.000	0.616	0.654	0.646
Query→product rank · top-1	0.000	0.645	0.632	0.650
Relevance classification · accuracy	0.570	0.650	0.655

Limitations — read before relying on the numbers

The Magento eval is synthetic-on-synthetic. Eval tasks were generated with the same templates as training data (products fully disjoint). It validly measures schema adherence — JSON format, Magento attribute vocabularies, the None-when-absent rule — but overstates production quality on real catalogs and real user queries.
The base model's near-zero extraction scores are dominated by format non-adherence; they understate its underlying capability.
The fused-projection LoRA shares one rank-8 subspace across q/k/v — a small ECInstruct deficit vs the siblings may reflect this structural difference rather than model quality.
English only; fine-tuned on structured data — expect degraded general chat vs the base (drop the adapter to recover it).
Use greedy decoding (do_sample=False / temperature 0) — that's how it was evaluated.

Provenance

Table

Training run	`phi4-mini-r8-mix56k-e1` (2026-07-14)
Adapter sha256	`f856fa953ae099762bbf91e6410f90902432bd23776266323366941dfeaa29a3`
Train set sha256	`afb7e664cda4490597c1914db6aff94933991a56d2175435666f8f6b7a726532` (mixture_train.jsonl, 56,253 rows)
Eval set sha256	`8feafdb2…` (magento_eval.jsonl) · `2583a61e…` (ecinstruct_eval.jsonl)
GGUF	adapter merged into `microsoft/Phi-4-mini-instruct` bf16, Q4_K_M + q8_0 embeddings, sha256

References

Phi-4-mini: arXiv:2503.01743
ECInstruct / eCeLLM: arXiv:2402.08831
QLoRA: arXiv:2305.14314

phi4-3b-ec-magento

README

What it does

Usage — adapter (unsloth / peft)

Usage — GGUF / Ollama

Gotchas (learned the hard way)

Training recipe

Evaluation

Limitations — read before relying on the numbers

Provenance

References

Explore FriendliAI today

README

What it does

Usage — adapter (unsloth / peft)

Usage — GGUF / Ollama

Gotchas (learned the hard way)

Training recipe

Evaluation

Limitations — read before relying on the numbers

Provenance

References