Initial upload

.gitattributes

@@ -33,3 +33,10 @@ saved_model/**/* 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
+attn.xclbin filter=lfs diff=lfs merge=lfs -text
+dequant.xclbin filter=lfs diff=lfs merge=lfs -text
+layer.xclbin filter=lfs diff=lfs merge=lfs -text
+lm_head.xclbin filter=lfs diff=lfs merge=lfs -text
+mm.xclbin filter=lfs diff=lfs merge=lfs -text
+model.q4nx filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

attn.xclbin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9033caf687b7c87faa8d0ecda055858b8845f0c510cc6bb49c7fdaeb1cbe2bf2
+size 465163

config.json

@@ -0,0 +1,58 @@
+{
+  "sliding_window_pattern": 6,
+  "architectures": [
+    "Gemma3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "attn_logit_softcapping": null,
+  "bos_token_id": 2,
+  "eos_token_id": 1,
+  "final_logit_softcapping": null,
+  "head_dim": 256,
+  "hidden_activation": "gelu_pytorch_tanh",
+  "hidden_size": 640,
+  "initializer_range": 0.02,
+  "intermediate_size": 2048,
+  "layer_types": [
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 32768,
+  "model_type": "gemma3_text_only",
+  "num_attention_heads": 4,
+  "num_hidden_layers": 18,
+  "num_key_value_heads": 1,
+  "pad_token_id": 0,
+  "query_pre_attn_scalar": 256,
+  "rms_norm_eps": 1e-06,
+  "rope_local_base_freq": 10000.0,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": 512,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.55.0.dev0",
+  "use_bidirectional_attention": false,
+  "use_cache": true,
+  "vocab_size": 262144,
+  "addr_qk": 9216,
+  "addr_kv": 34816,
+  "addr_kk": 13312,
+  "flm_version": "0.9.4"
+}

dequant.xclbin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b529e9c91b0d9def4c5394a21920c0ba01f3d83568dde40f04e4f27034cc714
+size 103915

layer.xclbin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:510366571fdeb69af942c9aa51bcbcc9561683dd45c3c33d93dbd2f3393cbecb
+size 172619

lm_head.xclbin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80869836b3eecf2a43191c87355d8731358a999a1c560a5be22f9b28eae7c331
+size 143115

mm.xclbin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2962eefe324053f9a3dac247d1ec7f27737a76eeb9e346fc1296ca1269a22ccb
+size 218699

model.q4nx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bcec9d157dcf06da83410da80599383bd6405a9a28c3325984ebeda3416b46c7
+size 503209096

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d4046bf0505a327dd5a0abbb427ecd4fc82f99c2ceaa170bc61ecde12809b0c
+size 33384570