GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
nuwanda94
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
nuwanda94
Model Tree
unsloth/Llama-3.2-3B-Instruct
Input Modalities
Output Modalities
Supported Functionality
Research-style questions over retrieved public excerpts (guidance, margins, segment color, named risks). Prefer refusing figures that are not in context. Not investment advice.
| Item | Value |
|---|---|
| Base | unsloth/Llama-3.2-3B-Instruct (4-bit QLoRA) |
| Seed | 3407 |
| Dataset | ecra-sft-v0.1.0 |
| Train / val rows | 2127 / 240 |
| Effective batch | 16 |
| Adapter path | /kaggle/working/earnings-call-research-assistant/outputs/adapters/llama32-3b-ecra-sft |
| Card generated (UTC) | 2026-09-14T08:35:37Z |
| Item | Value |
|---|---|
| N chunks | 19990 |
| Documents | 3 |
| Corpus version | v0.1.0 |
| Embed model | sentence-transformers/all-MiniLM-L6-v2 |
| Dense backend | sentence-transformers |
| Eval queries | 50 |
| k | Recall | nDCG |
|---|---|---|
| 1 | TBD | TBD |
| 3 | TBD | TBD |
| 5 | TBD | TBD |
| 10 | TBD | TBD |
| Side | citation-hit | token F1 | grounded accuracy | dry_run |
|---|---|---|---|---|
| base | 0.5934 | TBD | 0.5800 | False |
| adapter | 0.8760 | TBD | 1.0000 | False |
python
from peft import PeftModelfrom transformers import AutoModelForCausalLM, AutoTokenizerbase = "unsloth/Llama-3.2-3B-Instruct"adapter = "<this-repo-id>" # e.g. nuwanda94/llama32-3b-ecra-sfttok = AutoTokenizer.from_pretrained(base)model = AutoModelForCausalLM.from_pretrained(base, device_map="auto")model = PeftModel.from_pretrained(model, adapter)
Reproduce metrics from the GitHub repo:
bash
python scripts/eval_retrieval.py --runpython scripts/eval_rag_generate.py --run --adapter-dir outputs/adapters/llama32-3b-ecra-sft
Public data only. Report measured N and query counts; fixture-scale runs are not
SEC coverage. Citation-hit ≠ numerical correctness. Token: HF_TOKEN / huggingface-cli login only — never commit secrets.