GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
fritzra
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Run this model inference with full control and performance in your environment.
Model Details
Model Provider
fritzra
Model Tree
google/gemma-4-E4B-it
Input Modalities
Output Modalities
Supported Functionality
| Field | Value |
|---|---|
| Public status | Current accepted CricketRec adapter |
| Internal lineage label | V18 evidence-complete policy |
| Base model | google/gemma-4-E4B-it |
| Adapter format | PEFT LoRA |
| LoRA rank, alpha, dropout | 8, 16, 0.05 |
| Adapter parameters | 17,440,768 |
| Weight file size | 34,957,656 bytes |
| Weight-file SHA-256 | a3213420908abe7f27aac1da68e61714a488e21f775c5363625d34c679d63cbe |
| Composite weights-and-config identity | ce447f66c6285b7499a00eece257271e9e932a7315aa33dcfb438739d27865e5 |
| PEFT version at save time | 0.19.1 |
| Task type | Causal language modeling |
The composite identity is the SHA-256 of a canonical JSON object containing
the separate weight-file and adapter-configuration hashes. Exact values are in
provenance.json.
LoRA targets the text-language attention Q, K, V, and O projections plus the MLP gate, up, and down projections. Audio and vision towers stay untouched.
The accepted interaction moves through five evidence families:
An unavailable result still resolves that evidence family. The controller should state the absence plainly, retain the full visible history, and let the adapter move to the next unresolved question. Recommendation waits until every required family is resolved.
Supported planning transitions are 0 to 6 overs, 6 to 10 overs, and 10 to 15 overs. Later intervals begin from the real score and wicket state recorded at their boundary.
The example below uses 4-bit NF4 quantization, which matches the project's local inference setup closely enough for a first run.
python
import torchfrom peft import PeftModelfrom transformers import (AutoModelForMultimodalLM,AutoTokenizer,BitsAndBytesConfig,)BASE_MODEL = "google/gemma-4-E4B-it"ADAPTER = "fritzra/gemma-4-e4b-ipl-chase-recommendation"quantization = BitsAndBytesConfig(load_in_4bit=True,bnb_4bit_quant_type="nf4",bnb_4bit_compute_dtype=torch.bfloat16,bnb_4bit_use_double_quant=True,)# Load the tokenizer from this repository to retain the accepted chat template.tokenizer = AutoTokenizer.from_pretrained(ADAPTER)base_model = AutoModelForMultimodalLM.from_pretrained(BASE_MODEL,quantization_config=quantization,dtype=torch.bfloat16,device_map="auto",)model = PeftModel.from_pretrained(base_model,ADAPTER,is_trainable=False,)model.eval()
The base model is large. On the 16 GB development machine, CricketRec kept the frozen per-layer embedding on CPU while the language layers and adapter ran on the GPU. Other machines may need different placement.
Use the saved chat template when encoding the visible conversation:
python
messages = [{"role": "user","content": ("Match: Royal Challengers Bengaluru vs Sunrisers Hyderabad.\n""Chase: RCB are 0/0 after 0 overs, target 202. ""Plan through 6 overs.\n""Available batting options: ...\n""Candidate bowlers: ..."),}]encoded = tokenizer.apply_chat_template(messages,tokenize=True,add_generation_prompt=True,return_tensors="pt",return_dict=True,)
At this point the expected assistant action is a compact evidence question,
such as a request for prior-only score, wicket, and provenance support. The
controller answers with tool output. It continues until Recommendation:
appears.
The analytical cricket corpus contained 290 usable IPL matches, 69,851 deliveries, and 2,900 checkpoint states from the 2022 through 2025 seasons. Those records powered the deterministic evidence tools.
The accepted lineage uses a smaller supervised surface. Across four stages, it saw 340 full-conversation examples and completed 980 optimizer updates.
| Stage | Training years | Train examples | Purpose |
|---|---|---|---|
| V14 | 2022-2023 | 60 | Answer-conditioned stopping |
| V15 | 2022-2023 | 110 | Broader evidence transitions |
| V17 | 2022-2023 | 60 | Recommendation grounding and quality |
| V18 | 2022-2023 | 110 | Evidence-complete question policy |
Each row is a complete visible conversation prefix. Loss applies only to the final assistant turn. Separate 2024 cases were used during development. The accepted stages excluded 2025, although earlier experiments had already consulted that season, so 2025 is outside the untouched-holdout claim.
1e-4 in the final stageThe final stage took 164.44 seconds and reported aggregate training loss of 0.2571. Acceptance came from fresh-process conversation tests rather than the training loss.
Six conversation prefixes were run through the same base model with the adapter disabled and enabled. The tokenizer, prompt, greedy decoding settings, stop tokens, and 128-token limit stayed fixed.
| Metric | Base | Adapter |
|---|---|---|
| Correct next action | 1/6 | 6/6 |
| Strict expected response | 0/6 | 5/6 |
| 128-token cap hits | 6/6 | 0/6 |
| Mean output tokens | 128.0 | 28.5 |
The single strict miss returned the right endpoint band and wicket cap but left out one expected median. Six cases are enough to confirm the intended policy change. They do not establish broad resilience across new prompt forms.
The accepted adapter was compared with its V17 predecessor on 12 evidence-complete conversations.
| Metric | V17 predecessor | Current adapter |
|---|---|---|
| Fully correct conversations | 0/12 | 12/12 |
| Correct required questions | 3/54 | 54/54 |
| Early recommendations | 42 | 0 |
| Correct grounded final responses | 3/12 | 12/12 |
The full CricketRec system processed 74 matches and 222 checkpoints at 6, 10, and 15 overs. It produced 193 usable endpoint recommendations. All 193 copied the selected deterministic endpoint exactly, and all 177 evidence-backed wicket values matched the supplied wicket reference.
On 129 checkpoints shared with forward-looking expert tactical targets and actual scores, the system recorded run MAE of 11.08 versus 14.42 for the expert targets. The paired difference was 3.34 runs, with a match-cluster bootstrap 95% interval from 0.88 to 5.94 runs.
That season comparison measures the complete pipeline. Historical retrieval or required-rate arithmetic supplied the numerical target, while the adapter managed evidence order, grounding, wording, and stopping.
This adapter is suited to experiments on small-data behavioral post-training, auditable tool-guided conversations, and IPL checkpoint planning with a controller that supplies structured evidence.
Do not use it for betting, financial decisions, or unsupported live-match claims. Generated recommendations need validation against the supplied tool results before they are shown to a user.
adapter_model.safetensors: LoRA weightsadapter_config.json: PEFT adapter configurationtokenizer.json and tokenizer_config.json: accepted tokenizer fileschat_template.jinja: accepted conversation templateprovenance.json: lineage and artifact hashes without local machine pathsLICENSE: Apache License 2.0Training checkpoints, optimizer state, provider payloads, raw tweets, and base model weights are intentionally absent.
This adapter is released under Apache License 2.0. The base model has its own Gemma 4 model card and license page. Data sources and third-party providers remain subject to their respective terms.