Update models

.gitattributes

@@ -33,3 +33,18 @@ 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
+Qwen3-30B-A3B-Thinking-2507-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen3-30B-A3B-Thinking-2507-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen3-30B-A3B-Thinking-2507-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen3-30B-A3B-Thinking-2507-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen3-30B-A3B-Thinking-2507-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen3-30B-A3B-Thinking-2507-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen3-30B-A3B-Thinking-2507-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen3-30B-A3B-Thinking-2507-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen3-30B-A3B-Thinking-2507-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen3-30B-A3B-Thinking-2507-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen3-30B-A3B-Thinking-2507-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen3-30B-A3B-Thinking-2507-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen3-30B-A3B-Thinking-2507-f16-00001-of-00003.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen3-30B-A3B-Thinking-2507-f16-00002-of-00003.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen3-30B-A3B-Thinking-2507-f16-00003-of-00003.gguf filter=lfs diff=lfs merge=lfs -text

Qwen3-30B-A3B-Thinking-2507-Q2_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b67e4294d9092a3c876b4f6eb18ac98b18e6c43a862a3669aafe6f617b01902f
+size 11258609376

Qwen3-30B-A3B-Thinking-2507-Q3_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64b12a8b10f952057ed7917db5e0913de1ecd8e98510f867e65ad605c72159ad
+size 15900669664

Qwen3-30B-A3B-Thinking-2507-Q3_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:386768456b0a67095324fb36a8b426975a90b0a3f257059dc4e744dd52e67bcc
+size 14711846624

Qwen3-30B-A3B-Thinking-2507-Q3_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d61329bda1bddaed34184236bda9b78a5dbcc7544974093dba52f2e40aeaab1
+size 13292467936

Qwen3-30B-A3B-Thinking-2507-Q4_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63c2fd7f102c09f6c06ea8308db24ad84e1e1c4707e5ee21e632018f2019cb19
+size 17304489696

Qwen3-30B-A3B-Thinking-2507-Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8dc201d2a14251b2b043871383553eac89f59ec09a0ac7dac6abd9e85ca8b89f
+size 18556686048

Qwen3-30B-A3B-Thinking-2507-Q4_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e431da3892403489ad8752b6e1b288b8c8058336acdc515af699376bb2792d0
+size 17456008928

Qwen3-30B-A3B-Thinking-2507-Q5_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e382f7fa848129acef47a16b1ab0313b4da999f1327a67ca342dbfd7d4ca25a7
+size 21080510176

Qwen3-30B-A3B-Thinking-2507-Q5_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91c286aa0a60a0cea23f5ec345dc9b939a2f2b1bc429cc3758b8acc2e342660a
+size 21725581024

Qwen3-30B-A3B-Thinking-2507-Q5_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66a8938522107f9e2ec5b57f12e41813a39ace465ac4e1db005ecf626d2cae8d
+size 21080510176

Qwen3-30B-A3B-Thinking-2507-Q6_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:321ebf1ee5278b57ffeeb02a65e643bba26cb7ac282b4a9a2e0c76a14f05e469
+size 25092531936

Qwen3-30B-A3B-Thinking-2507-Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e7d94445080f51ae2edb078c81c2d00d2ca6cefbc5bf7fa770782658c94f06fa
+size 32483931872

Qwen3-30B-A3B-Thinking-2507-f16-00001-of-00003.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b818c56354973017b6040d3f40b5550046b6454e1cee3a68a6c20e86abee55e
+size 29706750304

Qwen3-30B-A3B-Thinking-2507-f16-00002-of-00003.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:906f6bdc538a858dbdb6bbcae928cd3a20b7889a2a7d6ec4daf23485672c10ee
+size 29557689440

Qwen3-30B-A3B-Thinking-2507-f16-00003-of-00003.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a76eaef167a571a63bdd7e6a5938318035b9439d30130a6f345ac8b88f516ea6
+size 1831363168

config.json

@@ -0,0 +1,38 @@
+{
+  "architectures": [
+    "Qwen3MoeForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "decoder_sparse_step": 1,
+  "eos_token_id": 151645,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 6144,
+  "max_position_embeddings": 262144,
+  "max_window_layers": 48,
+  "mlp_only_layers": [],
+  "model_type": "qwen3_moe",
+  "moe_intermediate_size": 768,
+  "norm_topk_prob": true,
+  "num_attention_heads": 32,
+  "num_experts": 128,
+  "num_experts_per_tok": 8,
+  "num_hidden_layers": 48,
+  "num_key_value_heads": 4,
+  "output_router_logits": false,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000000,
+  "router_aux_loss_coef": 0.001,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.51.0",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}