v75: replace bundle with freshly-converted build

.gitattributes

@@ -34,3 +34,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
 v81/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+v75/tokenizer.json filter=lfs diff=lfs merge=lfs -text

v75/nv-embedqa-1b.json

@@ -0,0 +1,39 @@
+{
+  "schema_version": 1,
+  "_comment": "NV-EmbedQA-1B (LlamaBidirectional + avg-pool) on Hexagon v81. Host-rope bidirectional encoder graph (no in-graph Gather) + llama_embed host-op (embed + llama3 rope factor 32 + bidirectional mask + avg-pool + L2). Encoder S=64.",
+  "model": {
+    "name": "nv-embedqa-1b",
+    "family": "embedding",
+    "dsp_arch": "v75",
+    "tokenizer_pre": "llama3"
+  },
+  "params": {
+    "hidden": 2048,
+    "vocab": 128256,
+    "n_layers": 16,
+    "head_dim": 64,
+    "max_ctx": 64,
+    "eos_token_id": 128001
+  },
+  "artifacts": {
+    "contexts": {
+      "encoder": {
+        "bin": "nvembedqa_enc.bin"
+      }
+    },
+    "embed": "nvembedqa_embed_f16.bin",
+    "tokenizer": "tokenizer.json"
+  },
+  "plan": {
+    "steps": [
+      {
+        "host": "llama_embed",
+        "params": {
+          "encoder": "nvembedqa_enc_f16",
+          "rope_factor": 32.0,
+          "neg": -50000
+        }
+      }
+    ]
+  }
+}

v75/nvembedqa_embed_f16.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d0f26c68ed40afd43c2510ef455064d3b4738765b5ea39d2cf48648b5e245cf6
+size 525336576

v75/nvembedqa_enc.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d4241eb1e46f7d25ed02866f95b2ba642671f905728e7af8782a85db6cdbfde9
+size 1949519872

v75/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
+size 17209920