初始化项目,由ModelHub XC社区提供模型
Model: posttrainllm/qwen3-4b-file-ops-distilled Source: Original Platform
This commit is contained in:
39
eval_report.json
Normal file
39
eval_report.json
Normal file
@@ -0,0 +1,39 @@
|
||||
{
|
||||
"id": "qwen3-4b-file-ops-distilled",
|
||||
"updated": "2026-06-19",
|
||||
"artifact": "hf://models/sarthakagrawal927/qwen3-4b-file-ops-distilled",
|
||||
"base": "Qwen/Qwen3-4B-Instruct-2507",
|
||||
"precision": "bf16",
|
||||
"training_method": "frontier/gold trajectory distillation on GorillaFileSystem multi-turn tasks",
|
||||
"scores": [
|
||||
{
|
||||
"suite": "file_ops_hard_gate",
|
||||
"n": 12,
|
||||
"stock_4b": 0.58,
|
||||
"distilled_4b": 1.0,
|
||||
"frontier": 1.0,
|
||||
"source": "docs/learn/tool-calling-frontier-parity.md#81-climbing-the-cliff--frontier-trajectory-distillation-2026-06-16"
|
||||
},
|
||||
{
|
||||
"suite": "file_ops_hardgen_heldout",
|
||||
"n": 40,
|
||||
"stock_4b": 0.6,
|
||||
"distilled_4b": 0.95,
|
||||
"source": "docs/learn/tool-calling-frontier-parity.md#81-climbing-the-cliff--frontier-trajectory-distillation-2026-06-16"
|
||||
},
|
||||
{
|
||||
"suite": "out_of_domain_breadth",
|
||||
"n": 52,
|
||||
"stock_4b": 0.596,
|
||||
"distilled_4b": 0.423,
|
||||
"delta": -0.173,
|
||||
"source": "docs/learn/tool-calling-frontier-parity.md#84-breadth--narrow-distillation-causes-negative-transfer-2026-06-16"
|
||||
}
|
||||
],
|
||||
"verdict": "ship only as a routed file-ops specialist; do not use as the general planner",
|
||||
"caveats": [
|
||||
"The out-of-domain breadth ceiling is not frontier-validated yet.",
|
||||
"The negative-transfer result is relative and directly comparable: same 52 tasks, same prompt, stock vs distilled.",
|
||||
"The model is a fused full HF/MLX directory, not a small adapter package."
|
||||
]
|
||||
}
|
||||
Reference in New Issue
Block a user