Republish with v2-p5 weights (e5-strided-8L + gte rep-distill + built-in Qwen3-Reranker-4B listwise-KL); purge stale engines of the previous 54M weights

code-daemon-embed-v1-l_b256_s128_win_x64_tvm_vulkan.dll

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:a12eb2d89e55999d380fce9117cfac8d2c1734dcd253cf19e6511fc7f2ee661f
-size 314665472

code-daemon-embed-v1-l_ov_cpu_int8_b256_s128.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:19b413a2f43f0d3681d37dd585debe92c5f5c8a9a3685fc3e078e193c428e555
-size 54371936

code-daemon-embed-v1-l_ov_igpu_lnl_int8_b256_s128.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:19b413a2f43f0d3681d37dd585debe92c5f5c8a9a3685fc3e078e193c428e555
-size 54371936

code-daemon-embed-v1-l_ov_npu_int4_b16_s128.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:b63bf5f056d48c3d396dd56733f3088e54e5e476a03d2b97facdcbe9f705295a
-size 40425413

code-daemon-embed-v1-l_win_x64_trt_sm_120.engine

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:026bac362d29b874eb28747c5962af84acd10013d40a25b3310f58315a221f1d
-size 82890916

code-daemon-embed-v1-m_b128_s64_win_x64_tvm_vulkan.dll

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:85d41ea1a41c9e7fdbc6c7b56e116e2b2390e95c2e57b6c6cdbdb99ba4799372
-size 239160320

code-daemon-embed-v1-m_ov_cpu_int8_b128_s64.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:19b413a2f43f0d3681d37dd585debe92c5f5c8a9a3685fc3e078e193c428e555
-size 54371936

code-daemon-embed-v1-m_ov_igpu_lnl_int8_b128_s64.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:19b413a2f43f0d3681d37dd585debe92c5f5c8a9a3685fc3e078e193c428e555
-size 54371936

code-daemon-embed-v1-m_ov_npu_int4_b16_s64.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:b63bf5f056d48c3d396dd56733f3088e54e5e476a03d2b97facdcbe9f705295a
-size 40425413

code-daemon-embed-v1-m_win_x64_trt_sm_120.engine

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:210d43a3a95408339ff250d95af08b425acf4b6fb543307e6d377f79bc52b2ed
-size 83367500

code-daemon-embed-v1-s_b64_s40_win_x64_tvm_vulkan.dll

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:2d167febf26c83999758ab9268ce4446c4fc310a1e337588da0cda49f251e745
-size 221864960

code-daemon-embed-v1-s_ov_cpu_int8_b64_s40.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:19b413a2f43f0d3681d37dd585debe92c5f5c8a9a3685fc3e078e193c428e555
-size 54371936

code-daemon-embed-v1-s_ov_igpu_lnl_int8_b64_s40.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:19b413a2f43f0d3681d37dd585debe92c5f5c8a9a3685fc3e078e193c428e555
-size 54371936

code-daemon-embed-v1-s_ov_npu_int4_b16_s40.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:b63bf5f056d48c3d396dd56733f3088e54e5e476a03d2b97facdcbe9f705295a
-size 40425413

code-daemon-embed-v1-s_win_x64_trt_sm_120.engine

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:0b9af73f2e7329e54c3c9605917bead21748073dda6505af7c9ac62789ce10c0
-size 83704060

config.json

@@ -1,24 +1,24 @@
-{
-  "add_cross_attention": false,
-  "attention_probs_dropout_prob": 0.1,
-  "bos_token_id": 0,
-  "classifier_dropout": null,
-  "eos_token_id": 2,
-  "hidden_act": "gelu",
-  "hidden_dropout_prob": 0.1,
-  "hidden_size": 768,
-  "initializer_range": 0.02,
-  "intermediate_size": 3072,
-  "is_decoder": false,
-  "layer_norm_eps": 1e-05,
-  "max_position_embeddings": 514,
-  "model_type": "xlm-roberta",
-  "num_attention_heads": 12,
-  "num_hidden_layers": 4,
-  "pad_token_id": 1,
-  "tie_word_embeddings": true,
-  "transformers_version": "5.1.0",
-  "type_vocab_size": 1,
-  "use_cache": true,
-  "vocab_size": 32000
-}
+{
+  "add_cross_attention": false,
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "is_decoder": false,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 8,
+  "pad_token_id": 1,
+  "tie_word_embeddings": true,
+  "transformers_version": "5.13.0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 22739
+}

manifest.json

@@ -1,10 +1,11 @@
 {
+  "compiled_at": "2026-07-23T02:00:00Z",
   "model_id": "code-daemon-embed-v1",
-  "quantization": "int8",
   "max_tokens": 128,
-  "dimension": 768,
+  "quantization": "fp32",
   "targets": [
-    "gpu-vulkan"
+    "tensorrt"
   ],
-  "compiled_at": "2026-07-03T20:10:30Z"
-}
+  "dimension": 768,
+  "note": "weights=v2-p5 p5_c (4B-teacher listwise-KL, 2026-07-23 republish); engines to be rebuilt via compile-models"
+}

model.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cbadf94d27eaf84c23b4d83004640b04997af29eec5f5906fca7f2f87761e2c1
-size 401005
+oid sha256:c39aa87e9f2bfe1de1bd928bd0f3fa8121aa7e70509acf02179a21115bf89d57
+size 1120495

model.onnx.data

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:df20d8d73699c91ed681f460dae498bfdca6c6de8d45f65e48841a4a60a47794
-size 215744512
+oid sha256:6be94a99ac0c87f10e2284a9d08ab77ea4fcfce6966a292771571fa692e31b1a
+size 300737536

model_int8qdt.onnx

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:f08c1818b0a485208862f3b2346d0a3592ee1de5a4e08376d01ce548ecc5dab6
-size 108092879

sentencepiece.bpe.model

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e571e6ea78112c80b29b17132fe7cf222725590d08aa983717bb7151f53f6971
-size 752604
+oid sha256:3236c10b708765fdfd0720ea6ea932e1472450cd927b331107f05bfacdba7549
+size 626759

tokenizer_config.json

@@ -1,8 +1,8 @@
-{
-  "tokenizer_class": "XLMRobertaTokenizer",
-  "model_max_length": 512,
-  "bos_token": "<s>",
-  "eos_token": "</s>",
-  "unk_token": "<unk>",
-  "pad_token": "<pad>"
+{
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "model_max_length": 512,
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "unk_token": "<unk>",
+  "pad_token": "<pad>"
 }