Restore prior JEVision files and card graphics

README.md

@@ -33,6 +33,10 @@ The release combines a trained text adapter, a separately trained visual sidecar
 | Request envelope | Configured for up to 80,000 processed input tokens |
 | Packaging | Adapters, heads, and a runnable local server; base weights download separately |
 
+![Jev, KEV-0.8B and JEVision capability comparison](assets/jevvision-capability-comparison.png)
+
+This earlier comparison graphic shows the input routes and context limits alongside text-only development results. Its public-panel score uses examples seen during training.
+
 The serving route processed 76,999 text tokens and 76,998 image-plus-text tokens in recorded acceptance checks. The text check used the included KEV-0.8B option; the image check used the visual sidecar. These checks establish request handling near 77K, while long-context answer quality remains to be evaluated.
 
 ## See the visual route
@@ -83,6 +87,8 @@ python run_jevvision.py --port 8009
 
 The server exposes `POST /v1/systemone` on localhost. To select the bundled KEV text checkpoint for requests without images, add `--text-adapter kev-0.8b`. Image-bearing requests automatically use the visual sidecar.
 
+The earlier `--text-adapter jevbench-m3` selection is also available for existing scripts and points to the same text weights as the default route.
+
 ### Call from Python
 
 ```python
@@ -119,6 +125,8 @@ python examples/long-context/run_demo.py --endpoint http://127.0.0.1:8009
 
 The runner writes its generated state and saves the server's response only after checking that `usage.input_tokens` is at least 75,000. A [separate recorded text-route acceptance summary](examples/long-context/recorded-77k-text-response-summary.json) documents a 76,999-token request on the bundled KEV-0.8B option; it is a request-handling check, not a result for the default JEVision text adapter.
 
+The original archived [request recipe](examples/long-context/m1-77k-text-input.json) and [response summary](examples/long-context/m1-77k-text-response-summary.json) are preserved at their earlier paths.
+
 ## Architecture and training
 
 | Included component | Purpose |
@@ -136,6 +144,10 @@ The default text adapter was fitted to public JevBench decision examples, starti
 
 JEVision currently has functional checks for typed responses, image routing, and long request acceptance, plus the recorded real-photo example above. Independent, broad image accuracy and long-context answer quality have not yet been measured. The 80,000-token value is a service limit, and requests beyond it are rejected instead of silently truncated. No comparative accuracy, latency, or cost claim is made here.
 
+![Text-only public and grouped test results from the earlier release](assets/jevbench-m3-results.png)
+
+This preserved results graphic separates the in-sample public panel from a small grouped holdout. It does not evaluate the visual route.
+
 The [manifest](jevvision_manifest.json) identifies the components, their source revisions, hashes, and serving limit. Users should assess the model on their own images and decision tasks before relying on its outputs.
 
 ## License

examples/long-context/m1-77k-text-input.json

@@ -0,0 +1,30 @@
+{
+  "source": "M1 context acceptance, private version 3",
+  "model": "kev-latest",
+  "text_adapter": {
+    "repo_id": "jaredpalmer/kev-0.8b",
+    "revision": "54f4f8777356cd5bbbb6c6919c657f26e6f2f6d8"
+  },
+  "base_model": {
+    "repo_id": "Qwen/Qwen3.5-0.8B-Base",
+    "revision": "dc7cdfe2ee4154fa7e30f5b51ca41bfa40174e68"
+  },
+  "text_only": true,
+  "reported_input_tokens": 76999,
+  "state_recipe": {
+    "prefix": "M1 context acceptance. ",
+    "repeated_text": "The stored memo remained unchanged. ",
+    "repeat_count": 12827,
+    "suffix": " END-OF-CONTEXT marker."
+  },
+  "questions": {
+    "m1": {
+      "type": "choice",
+      "instructions": "Which note is being referred to?",
+      "criteria": {
+        "memo": "The stored memo",
+        "other": "A different item"
+      }
+    }
+  }
+}

examples/long-context/m1-77k-text-response-summary.json

@@ -0,0 +1,36 @@
+{
+  "summary_type": "recorded response summary; not the raw API body",
+  "experiment": "M1 context acceptance, private version 3",
+  "source_report": {
+    "filename": "report.json",
+    "sha256": "f0fde673452b0d4a1329fc328e045afeb5223023e7ea3f2d16c53d3ce8d716b9"
+  },
+  "request": {
+    "model": "kev-latest",
+    "question_id": "m1",
+    "text_adapter": "jaredpalmer/kev-0.8b@54f4f8777356cd5bbbb6c6919c657f26e6f2f6d8",
+    "base_model_revision": "dc7cdfe2ee4154fa7e30f5b51ca41bfa40174e68",
+    "text_only": true
+  },
+  "observed": {
+    "http_status": 200,
+    "answer_type": "choice",
+    "choice": "memo",
+    "input_tokens": 76999,
+    "output_tokens": 44,
+    "prefill_chunks": 602,
+    "latency_ms": 313746.3,
+    "verified_response_fields": [
+      "type",
+      "choice",
+      "confidence",
+      "probabilities"
+    ]
+  },
+  "not_retained": [
+    "numeric confidence value",
+    "per-option probability values",
+    "original raw API response body"
+  ],
+  "scope": "Long-context request acceptance and response-schema smoke; not a general long-context accuracy evaluation."
+}

jevvision_manifest.json

@@ -13,6 +13,10 @@
       "path": "text/jevvision-text",
       "role": "default typed-decision text branch"
     },
+    "jevbench-m3": {
+      "path": "text/jevbench-m3",
+      "role": "compatibility path for the default text branch"
+    },
     "kev-0.8b": {
       "path": "text/kev-0.8b",
       "role": "pinned KEV text baseline",
@@ -37,6 +41,9 @@
     "text/jevvision-text/adapter_model.safetensors": "0f71c01d01cc9a82648417f3b036e329e0fe27dd44cd6847fa141b85518e1022",
     "text/jevvision-text/adapter_config.json": "917dbb4e84a81737b187d98633afe8139eded84eabe83cfcf8c9e210a3001615",
     "text/jevvision-text/head.pt": "b3ac9f2e10a903bfec76020ee4a730921c22531267de7493aff57b80c741e906",
+    "text/jevbench-m3/adapter_model.safetensors": "0f71c01d01cc9a82648417f3b036e329e0fe27dd44cd6847fa141b85518e1022",
+    "text/jevbench-m3/adapter_config.json": "917dbb4e84a81737b187d98633afe8139eded84eabe83cfcf8c9e210a3001615",
+    "text/jevbench-m3/head.pt": "b3ac9f2e10a903bfec76020ee4a730921c22531267de7493aff57b80c741e906",
     "text/kev-0.8b/adapter_model.safetensors": "c81d5716f0af7622d8d2b97013c333d48263ca01113f9a7cf4526e96f6ac0b26",
     "text/kev-0.8b/adapter_config.json": "748acb2cda88454cb1ba69d745ba336f3fcb5486eac349e90960c8b8d8d3e854",
     "text/kev-0.8b/head.pt": "39f4343ccccc65e583bbfff0de0e11bfedb849fcfaaf94b50ac4f2b73bc79c65",

run_jevvision.py

@@ -10,7 +10,7 @@ from pathlib import Path
 def main() -> None:
     root = Path(__file__).resolve().parent
     parser = argparse.ArgumentParser()
-    parser.add_argument("--text-adapter", choices=("jevvision-text", "kev-0.8b"), default="jevvision-text")
+    parser.add_argument("--text-adapter", choices=("jevvision-text", "jevbench-m3", "kev-0.8b"), default="jevvision-text")
     parser.add_argument("--port", type=int, default=8009)
     args = parser.parse_args()
 

runtime/kev/jevvision.py

@@ -22,6 +22,7 @@ from .serve import SERVE_CONTEXT_TOKENS, Server
 
 TEXT_ADAPTERS = {
     "jevvision-text": "text/jevvision-text",
+    "jevbench-m3": "text/jevbench-m3",
     "kev-0.8b": "text/kev-0.8b",
 }
 MAX_IMAGE_BYTES = 10 * 1024 * 1024

text/jevbench-m3/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/Qwen3.5-0.8B-Base",
+  "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": 0.05,
+  "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": [
+    "q_proj",
+    "v_proj",
+    "gate_proj",
+    "in_proj_a",
+    "k_proj",
+    "up_proj",
+    "out_proj",
+    "down_proj",
+    "in_proj_b",
+    "in_proj_z",
+    "o_proj",
+    "in_proj_qkv"
+  ],
+  "target_parameters": null,
+  "task_type": "FEATURE_EXTRACTION",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false,
+  "velora_config": null
+}

text/jevbench-m3/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f71c01d01cc9a82648417f3b036e329e0fe27dd44cd6847fa141b85518e1022
+size 43338624

text/jevbench-m3/head.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3ac9f2e10a903bfec76020ee4a730921c22531267de7493aff57b80c741e906
+size 2103039