Feat: Initial commit.

.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,65 @@
+---
+license: apache-2.0
+base_model: Qwen/Qwen3.8-27B
+library_name: peft
+---
+
+# JEMM
+
+JEMM stands for Judgment Engine for MultiModal decisions. It is a LoRA adapter for Qwen/Qwen3.8-27B. For each question it picks one candidate and returns a probability for every candidate. Inputs: text, optionally with a screenshot.
+
+## Usage
+
+```python
+import json, torch
+from huggingface_hub import hf_hub_download
+from peft import PeftModel
+from transformers import AutoProcessor, Qwen3_5ForConditionalGeneration
+
+base, adapter = "Qwen/Qwen3.8-27B", "MaestroYan/JEMM"
+processor = AutoProcessor.from_pretrained(base)
+model = Qwen3_5ForConditionalGeneration.from_pretrained(base, dtype=torch.bfloat16, device_map="cuda")
+model = PeftModel.from_pretrained(model, adapter).eval()
+config = json.load(open(hf_hub_download(adapter, "decision_config.json")))
+labels = [chr(65 + i) for i in range(26)] + list("012345")
+system = "Choose the best available candidate for the question using only the supplied state. Return exactly one candidate label."
+
+
+def decide(state, question, candidates, image=None):
+    flat = lambda s: " ".join(s.split())
+    options = "\n".join(f"{labels[i]}) {flat(c)}" for i, c in enumerate(candidates))
+    text = f"State:\n{state.strip()}\n\nQuestion: {flat(question)}\n\nCandidates:\n{options}\n\nAnswer with exactly one candidate label."
+    content = ([{"type": "image"}] if image else []) + [{"type": "text", "text": text}]
+    messages = [{"role": "system", "content": system}, {"role": "user", "content": content}]
+    prompt = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True, enable_thinking=False)
+    inputs = processor(text=[prompt], images=[image] if image else None, return_tensors="pt").to(model.device, dtype=torch.bfloat16)
+    with torch.inference_mode():
+        logits = model(**inputs, logits_to_keep=1).logits[0, -1]
+    ids = [processor.tokenizer.encode(x, add_special_tokens=False)[0] for x in labels[:len(candidates)]]
+    probs = torch.softmax(logits[ids].float() / config["mm_temperature" if image else "temperature"], -1)
+    return dict(zip(candidates, probs.tolist()))
+
+
+decide("User: Will it rain in Paris tomorrow?", "Which tool should handle the request?",
+       ["get_weather: weather forecast for a city", "search_flights: flight search", "No tool applies"])
+```
+
+2 to 32 candidates per question. Screenshots are PIL images; training used 1280x800. Treat a top probability below `threshold` in `decision_config.json` as undecided. HTTP server: [JEMM on GitHub](https://github.com/ypcypc/JEMM).
+
+## Evaluation
+
+Accuracy on held-out test sets. Jev 1.13 answered the same items. All three differences are significant (one-sided 95%).
+
+| Test | Items | JEMM | Jev 1.13 |
+|---|---:|---:|---:|
+| Tool choice (BFCL) | 2,148 | 0.933 | 0.887 |
+| Web action, text (Mind2Web) | 1,200 | 0.458 | 0.352 |
+| Web action, screenshot (Multimodal-Mind2Web) | 894 | 0.546 | 0.360 |
+
+Jev 1.13 does not take images; its screenshot-row score is on the text version of the same items.
+
+## Training data
+
+Mind2Web, xLAM function-calling-60k (APIGen), xlam-irrelevance, When2Call, Banking77, MASSIVE, Aegis 2.0 (CC-BY-4.0); CLINC150 (CC-BY-3.0); BFCL, glaive-function-calling-v2, ToolACE, hermes-function-calling-v1 (Apache-2.0); Multimodal-Mind2Web (OpenRAIL). No Jev outputs were used.
+
+Not affiliated with TypeSafe AI.

adapter_config.json

@@ -0,0 +1,56 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen3.8-27B",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "kasa_config": null,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "lora_ga_config": null,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "monteclora_config": null,
+  "peft_type": "LORA",
+  "peft_version": "0.21.0",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "in_proj_a",
+    "out_proj",
+    "v_proj",
+    "up_proj",
+    "k_proj",
+    "in_proj_b",
+    "in_proj_z",
+    "q_proj",
+    "o_proj",
+    "gate_proj",
+    "down_proj",
+    "in_proj_qkv"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false,
+  "velora_config": null
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fac397c8af737bb8d259efbe16f771507f77276fb44ab74942cd2e1bc05c3fef
+size 467062560

decision_config.json

@@ -0,0 +1,5 @@
+{
+ "temperature": 1.3480874159655591,
+ "threshold": 0.9872681877423998,
+ "mm_temperature": 1.3954832341582943
+}