GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
jasonlingg
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
jasonlingg
Model Tree
Qwen/Qwen3-8B
Input Modalities
Output Modalities
Supported Functionality
The repository root contains the epoch-1 checkpoint-150 adapter. It was selected over epoch 2 by
behavioral evaluation: both produced 11/25 supported answers, while epoch 1 had five partial answers
instead of four. The epoch-2 adapter is preserved under candidates/final because it had the lower
next-action validation loss.
python
import torchfrom peft import PeftModelfrom transformers import AutoModelForCausalLM, AutoTokenizer base_id = "Qwen/Qwen3-8B"adapter_id = "jasonlingg/qwen-envoy-qwen3-8b-qasper-targeted-sft-v1" tokenizer = AutoTokenizer.from_pretrained(adapter_id)base = AutoModelForCausalLM.from_pretrained( base_id, revision="b968826d9c46dd6066d109eabc6255188de91218", torch_dtype=torch.bfloat16, device_map="auto",)model = PeftModel.from_pretrained(base, adapter_id)The adapter expects Envoy's multi-turn code-execution system prompt and its persistent Python environment. It is not intended as a standalone chat model.
checkpoint-50 adapterq, k, v, o) and MLP (gate, up, down) projections5e-5, 5% warmup, cosine decay, no weight decay| Epoch | Checkpoint | Validation loss | Token accuracy |
|---|---|---|---|
| 1 | checkpoint-150 | 0.1356 | 0.9664 |
| 2 | candidates/final | 0.1272 | 0.9661 |
Token accuracy measures imitation of the next demonstrated action. It is not task accuracy.
The development diagnostic contains 15 answerable failures selected from the previous adapter and
10 controls it already handled correctly. Runs used deterministic decoding, the same system prompt,
raw top-three search_within, and seed 42. Semantic review was performed by the project assistant
blind to candidate identity; it was not independent human review.
| System | Pass | Partial | Fail | Target rescues | Controls retained | Execution errors |
|---|---|---|---|---|---|---|
Previous checkpoint-50 | 10 | 4 | 11 | 0/15 | 10/10 | 0 |
Epoch 1 (checkpoint-150) | 11 | 5 | 9 | 1/15 | 10/10 | 0 |
Epoch 2 (final) | 11 | 4 | 10 | 1/15 | 10/10 | 0 |
The gate required at least 6/15 targeted rescues, 9/10 retained controls, and at most one execution-error episode. Only the latter two conditions passed. The untouched 40-question confirmation set was therefore not consumed.
candidates/final: epoch-2 adapterresults/summary.json: complete training and evaluation summaryresults/run-manifest.json: exact training configuration and data hashesresults/score.json: blinded semantic-review aggregateresults/automatic.json: execution and provenance diagnosticsThe development questions were already used for failure analysis, so these numbers are diagnostic rather than held-out performance. The synthetic annotation-grounded trajectories preserved tool reliability and abstention controls but rarely taught the model to recover the intended missing answer. Exact citations and lexical overlap do not by themselves prove semantic support. Use the earlier v5 checkpoint as the currently supported project model until a future experiment passes the fresh confirmation gate.
import torchfrom peft import PeftModelfrom transformers import AutoModelForCausalLM, AutoTokenizer base_id = "Qwen/Qwen3-8B"adapter_id = "jasonlingg/qwen-envoy-qwen3-8b-qasper-targeted-sft-v1" tokenizer = AutoTokenizer.from_pretrained(adapter_id)base = AutoModelForCausalLM.from_pretrained( base_id, revision="b968826d9c46dd6066d109eabc6255188de91218", torch_dtype=torch.bfloat16, device_map="auto",)model = PeftModel.from_pretrained(base, adapter_id)