feat: initial upload

.gitattributes

@@ -33,3 +33,6 @@ 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
+model.q4nx filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text
+vision_weight.q4nx filter=lfs diff=lfs merge=lfs -text

config.json

@@ -0,0 +1,56 @@
+{
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "attn_logit_softcapping": null,
+    "cache_implementation": "hybrid",
+    "final_logit_softcapping": null,
+    "head_dim": 256,
+    "hidden_activation": "gelu_pytorch_tanh",
+    "hidden_size": 2560,
+    "initializer_range": 0.02,
+    "intermediate_size": 10240,
+    "max_position_embeddings": 131072,
+    "model_type": "gemma3_text",
+    "num_attention_heads": 8,
+    "num_hidden_layers": 34,
+    "num_key_value_heads": 4,
+    "query_pre_attn_scalar": 256,
+    "rms_norm_eps": 1e-06,
+    "rope_local_base_freq": 10000.0,
+    "rope_scaling": {
+      "factor": 8.0,
+      "rope_type": "linear"
+    },
+    "rope_theta": 1000000.0,
+    "sliding_window": 1024,
+    "sliding_window_pattern": 6,
+    "torch_dtype": "bfloat16",
+    "use_cache": true,
+    "vocab_size": 262208,
+    "addr_qk": 9216,
+    "addr_kv": 33792,
+    "addr_l_begin_mha": 53760,
+    "addr_l_end_mha": 25088,
+    "addr_kk": 45056,
+    "flm_version": "0.9.23",
+    "vision_model_weight": "vision_weight.q4nx",
+    "vision_mm_engine_xclbin_name": "vision_mm.xclbin",
+    "vision_mha_engine_xclbin_name":"vision_attn.xclbin",
+    "vision_conv2d_stride": 14,
+    "vision_conv2d_padding" : 0,
+    "vision_conv2d_kernel" : 14,
+    "vision_conv2d_Cin": 3,
+    "vision_conv2d_Cout": 1152,
+    "vision_average_pooling_kernel": 4,
+    "vision_average_pooling_stride" : 4,
+    "vision_average_pooling_padding" : 0,
+    "vision_layer_norm_eps" : 1e-06,
+    "vision_rms_norm_eps" : 1e-06,
+    "vision_intermediate_size": 4304,
+    "vision_hidden_size" : 1152,
+    "vision_head_dim":  72,
+    "vision_num_attention_heads": 16,
+    "vision_num_key_value_heads": 16,
+    "vision_num_hidden_layers": 27
+
+}

model.q4nx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6830040ef421ba11dd84e8c28d85421b09b158be11a444878b2f4136275946c
+size 3768226744

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4667f2089529e8e7657cfb6d1c19910ae71ff5f28aa7ab2ff2763330affad795
+size 33384568

vision_weight.q4nx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ad25d01edb6b31bab7e487e496f4652cc098738d8a726d69854fb5408d351e6
+size 973721768