GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
jgeiser
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
jgeiser
Model Tree
Qwen/Qwen2.5-7B-Instruct
Input Modalities
Output Modalities
Supported Functionality
| Base model | Qwen/Qwen2.5-7B-Instruct |
| Fine-tuning method | LoRA (rank 16, α 16) via Unsloth + TRL SFTTrainer |
| Training rounds | 10 |
| Training examples | 1,127 Path B (source bundle → structured brief) pairs |
| Max sequence length | 16,384 tokens |
| Output format | Constrained JSON (Outlines / llama.cpp grammar) |
| Releases | LoRA adapter (fp16) + Q4_K_M GGUF |
Evaluated on 60 held-out examples never seen during training.
| Model | M1 Schema Adherence | M3 Section Coverage | M5 Source Attribution |
|---|---|---|---|
| Base Qwen2.5-7B-Instruct (untuned) | 100% | 28.1% | 69.2% |
| Round 10 LoRA adapter (fp16, Outlines) | 100% | 95.8% | 92.7% |
| Round 10 Q4_K_M GGUF (llama.cpp grammar) | 100% | 99.2% | 96.1% |
M1 — Schema Adherence: Output parses as valid JSON matching the required schema. 100% for all rows because constrained decoding enforces schema validity at the token level — it is a floor, not a differentiator.
M3 — Section Coverage: Of all sections present in the gold-standard brief, how many did the model fill with substantive content? The base model writes skeletal 2-3KB briefs; the fine-tuned model writes complete 14-16KB briefs. The 28% → 99% gain is the core fine-tuning result.
M5 — Source Attribution: Of the sources provided in the input bundle, how many are correctly cited in the output? Fine-tuning on source-attributed training pairs pushed this from 69% to 96%.
Note: M2 (hallucination rate) has not yet been measured. M1 being 100% across all rows reflects constrained decoding, not model capability.
This model is designed for enterprise account teams who need structured intelligence briefs synthesized from multiple data sources. It covers six surfaces: account health, escalation risk, expansion signals, stakeholder map, QBR readiness, and competitive exposure.
It is not a general-purpose model. It is an ELM — trained to do one thing well, emit structured JSON that downstream systems can consume without parsing prose.
Suitable for:
Not suitable for:
bash
llama-cli \ -m account-intelligence-7b-v1-Q4_K_M.gguf \ --json-schema-file schema.json \ -p "<your prompt>" \ -n 8192 \ --temp 0.1The GGUF runs on CPU or GPU. Apple Silicon supported via Metal (-ngl 99 to offload all layers).
python
from unsloth import FastLanguageModelfrom peft import PeftModel model, tokenizer = FastLanguageModel.from_pretrained( model_name="Qwen/Qwen2.5-7B-Instruct", max_seq_length=16384, load_in_4bit=True,)model = PeftModel.from_pretrained(model, "jgeiser/account-intelligence-7b-v1")FastLanguageModel.for_inference(model)Constrained decoding via Outlines is strongly recommended. Without it, schema adherence degrades significantly.
Trained using the ELM (Expert Language Model) methodology — small, specialized models that emit structured output for specific enterprise tasks.
10 training rounds. Rounds 1-5 used incorrect data format. Rounds 6-10 used correct Path B format. Round 10 with Outlines: M1=100%, M3=95.8%, M5=92.7%.
Proprietary internal account data, not released. 1,127 Path B examples: structured source bundles paired with human-verified account intelligence briefs across enterprise telco and infrastructure accounts. 60 held-out examples used for all reported metrics.
| File | Size | Description |
|---|---|---|
adapter_model.safetensors | ~100MB | LoRA adapter weights (Round 10) |
adapter_config.json | — | LoRA configuration |
account-intelligence-7b-v1-Q4_K_M.gguf | 4.68GB | Q4_K_M quantized GGUF for llama.cpp / Ollama |
Part of ongoing ELM methodology work. Built at Zenlayer.
llama-cli \ -m account-intelligence-7b-v1-Q4_K_M.gguf \ --json-schema-file schema.json \ -p "<your prompt>" \ -n 8192 \ --temp 0.1from unsloth import FastLanguageModelfrom peft import PeftModel model, tokenizer = FastLanguageModel.from_pretrained( model_name="Qwen/Qwen2.5-7B-Instruct", max_seq_length=16384, load_in_4bit=True,)model = PeftModel.from_pretrained(model, "jgeiser/account-intelligence-7b-v1")FastLanguageModel.for_inference(model)