Add files using upload-large-folder tool

README.md

@@ -2,9 +2,9 @@
 license: mit
 pipeline_tag: text-generation
 library_name: mlx
-base_model: moonshotai/Kimi-Linear-48B-A3B-Instruct
 tags:
 - mlx
+base_model: moonshotai/Kimi-Linear-48B-A3B-Instruct
 ---
 
 # mlx-community/Kimi-Linear-48B-A3B-Instruct-8bit

model-00001-of-00010.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:65e0033ca7270344f647017cf7d1d7f976ba81185205d9e045fe00ad533f2da6
-size 5134894221
+oid sha256:fba1f96929c5a64a530bec39d458b1d75e3a8b4a2563ed2e6db4037a9d88c0ea
+size 5134894271

model-00002-of-00010.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e5ad3385dcd775c0bd1f2d8b09c131655862f3728c5cbfa3ae4c224ec56f379
-size 5284444549
+oid sha256:f3fb508aeda057d3c401f017355631a99908b559eb6f97e6c2468c1d0dba1145
+size 5284444567

model-00003-of-00010.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bf1517a248f2384f1fff5c967fa68dd280a374d40e3b8bcee9674db5941596c6
-size 5223130628
+oid sha256:061631ab19d4471ccb3ebc986b24d7fbfffc8082b1f00c6ea1c000d284bc053d
+size 5223130674

model-00004-of-00010.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b35008d906ba2e4a6f150a92db3ba4d8686f05dbd5d3b3aeaad484556cfb008c
-size 5273335229
+oid sha256:a803fae387e4bac59871354d296341971ef018f8fe1c2093c73e58800c2635cf
+size 5273335273

model-00005-of-00010.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b32a6972e8c919ac3e50d4eff68b79f563d1e7ef1b0ccb246d4b0a29a2223d42
-size 5284444701
+oid sha256:a81405870982a8c3162c2de832e2dde61c0ced11cbcf41a2f46f5289978cf632
+size 5284444719

model-00006-of-00010.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:72fc8748ab6022923e3728691e81f7c241378999ebb573f4ac62456954dcdfa6
-size 5223130754
+oid sha256:4c044009c311faa489c31b7cd7442b2098ea2aabf95033d5f96706343e2d3b1e
+size 5223130790

model-00007-of-00010.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:125d9202d0a93df77109cbca6d9b13e00f6b078e12413f72659c7c2f95ce65fb
-size 5273335249
+oid sha256:15b7e7e35b4c6d1af49410205787b790e2809a0fa299870aecb856163260c083
+size 5273335293

model-00008-of-00010.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:15f79195e3ad13a5c0b71227f518b53b910a9e36f8eb73f5f051f6c7d24f7b84
-size 5284444735
+oid sha256:e57c3796b3ecc1e3964ded2b88067799609a9eb544873694b9a41c91ffff037d
+size 5284444753

model-00009-of-00010.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d7c79465b89d0e189d030d157053734d96050c53904cfa77f95b64e162556bdf
-size 5223130706
+oid sha256:07633e50a3f4a8c68689cb3ce6dcae1f42e584af4cd72d0b42f32dc2bc76b428
+size 5223130744

model-00010-of-00010.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb3791eb5cf69ff5f09248234a02ba363994a71e91aa99c2e3d2b1f091613478
-size 4990018635
+oid sha256:b18a4830f9d00bb608033374ac7e92de091d628ee19a7cd91b05ef12acd360bc
+size 4990018667

model.safetensors.index.json

@@ -192,10 +192,10 @@
         "model.layers.11.mlp.switch_mlp.up_proj.scales": "model-00005-of-00010.safetensors",
         "model.layers.11.mlp.switch_mlp.up_proj.weight": "model-00005-of-00010.safetensors",
         "model.layers.11.post_attention_layernorm.weight": "model-00005-of-00010.safetensors",
-        "model.layers.11.self_attn.kv_a_norm.weight": "model-00004-of-00010.safetensors",
-        "model.layers.11.self_attn.kv_a_proj.biases": "model-00004-of-00010.safetensors",
-        "model.layers.11.self_attn.kv_a_proj.scales": "model-00004-of-00010.safetensors",
-        "model.layers.11.self_attn.kv_a_proj.weight": "model-00004-of-00010.safetensors",
+        "model.layers.11.self_attn.kv_a_layernorm.weight": "model-00004-of-00010.safetensors",
+        "model.layers.11.self_attn.kv_a_proj_with_mqa.biases": "model-00004-of-00010.safetensors",
+        "model.layers.11.self_attn.kv_a_proj_with_mqa.scales": "model-00004-of-00010.safetensors",
+        "model.layers.11.self_attn.kv_a_proj_with_mqa.weight": "model-00004-of-00010.safetensors",
         "model.layers.11.self_attn.kv_b_proj.biases": "model-00004-of-00010.safetensors",
         "model.layers.11.self_attn.kv_b_proj.scales": "model-00004-of-00010.safetensors",
         "model.layers.11.self_attn.kv_b_proj.weight": "model-00004-of-00010.safetensors",
@@ -400,10 +400,10 @@
         "model.layers.15.mlp.switch_mlp.up_proj.scales": "model-00006-of-00010.safetensors",
         "model.layers.15.mlp.switch_mlp.up_proj.weight": "model-00006-of-00010.safetensors",
         "model.layers.15.post_attention_layernorm.weight": "model-00006-of-00010.safetensors",
-        "model.layers.15.self_attn.kv_a_norm.weight": "model-00006-of-00010.safetensors",
-        "model.layers.15.self_attn.kv_a_proj.biases": "model-00006-of-00010.safetensors",
-        "model.layers.15.self_attn.kv_a_proj.scales": "model-00006-of-00010.safetensors",
-        "model.layers.15.self_attn.kv_a_proj.weight": "model-00006-of-00010.safetensors",
+        "model.layers.15.self_attn.kv_a_layernorm.weight": "model-00006-of-00010.safetensors",
+        "model.layers.15.self_attn.kv_a_proj_with_mqa.biases": "model-00006-of-00010.safetensors",
+        "model.layers.15.self_attn.kv_a_proj_with_mqa.scales": "model-00006-of-00010.safetensors",
+        "model.layers.15.self_attn.kv_a_proj_with_mqa.weight": "model-00006-of-00010.safetensors",
         "model.layers.15.self_attn.kv_b_proj.biases": "model-00006-of-00010.safetensors",
         "model.layers.15.self_attn.kv_b_proj.scales": "model-00006-of-00010.safetensors",
         "model.layers.15.self_attn.kv_b_proj.weight": "model-00006-of-00010.safetensors",
@@ -608,10 +608,10 @@
         "model.layers.19.mlp.switch_mlp.up_proj.scales": "model-00008-of-00010.safetensors",
         "model.layers.19.mlp.switch_mlp.up_proj.weight": "model-00008-of-00010.safetensors",
         "model.layers.19.post_attention_layernorm.weight": "model-00008-of-00010.safetensors",
-        "model.layers.19.self_attn.kv_a_norm.weight": "model-00007-of-00010.safetensors",
-        "model.layers.19.self_attn.kv_a_proj.biases": "model-00007-of-00010.safetensors",
-        "model.layers.19.self_attn.kv_a_proj.scales": "model-00007-of-00010.safetensors",
-        "model.layers.19.self_attn.kv_a_proj.weight": "model-00007-of-00010.safetensors",
+        "model.layers.19.self_attn.kv_a_layernorm.weight": "model-00007-of-00010.safetensors",
+        "model.layers.19.self_attn.kv_a_proj_with_mqa.biases": "model-00007-of-00010.safetensors",
+        "model.layers.19.self_attn.kv_a_proj_with_mqa.scales": "model-00007-of-00010.safetensors",
+        "model.layers.19.self_attn.kv_a_proj_with_mqa.weight": "model-00007-of-00010.safetensors",
         "model.layers.19.self_attn.kv_b_proj.biases": "model-00007-of-00010.safetensors",
         "model.layers.19.self_attn.kv_b_proj.scales": "model-00007-of-00010.safetensors",
         "model.layers.19.self_attn.kv_b_proj.weight": "model-00007-of-00010.safetensors",
@@ -873,10 +873,10 @@
         "model.layers.23.mlp.switch_mlp.up_proj.scales": "model-00009-of-00010.safetensors",
         "model.layers.23.mlp.switch_mlp.up_proj.weight": "model-00009-of-00010.safetensors",
         "model.layers.23.post_attention_layernorm.weight": "model-00009-of-00010.safetensors",
-        "model.layers.23.self_attn.kv_a_norm.weight": "model-00009-of-00010.safetensors",
-        "model.layers.23.self_attn.kv_a_proj.biases": "model-00009-of-00010.safetensors",
-        "model.layers.23.self_attn.kv_a_proj.scales": "model-00009-of-00010.safetensors",
-        "model.layers.23.self_attn.kv_a_proj.weight": "model-00009-of-00010.safetensors",
+        "model.layers.23.self_attn.kv_a_layernorm.weight": "model-00009-of-00010.safetensors",
+        "model.layers.23.self_attn.kv_a_proj_with_mqa.biases": "model-00009-of-00010.safetensors",
+        "model.layers.23.self_attn.kv_a_proj_with_mqa.scales": "model-00009-of-00010.safetensors",
+        "model.layers.23.self_attn.kv_a_proj_with_mqa.weight": "model-00009-of-00010.safetensors",
         "model.layers.23.self_attn.kv_b_proj.biases": "model-00009-of-00010.safetensors",
         "model.layers.23.self_attn.kv_b_proj.scales": "model-00009-of-00010.safetensors",
         "model.layers.23.self_attn.kv_b_proj.weight": "model-00009-of-00010.safetensors",
@@ -1024,10 +1024,10 @@
         "model.layers.26.mlp.switch_mlp.up_proj.scales": "model-00010-of-00010.safetensors",
         "model.layers.26.mlp.switch_mlp.up_proj.weight": "model-00010-of-00010.safetensors",
         "model.layers.26.post_attention_layernorm.weight": "model-00010-of-00010.safetensors",
-        "model.layers.26.self_attn.kv_a_norm.weight": "model-00010-of-00010.safetensors",
-        "model.layers.26.self_attn.kv_a_proj.biases": "model-00010-of-00010.safetensors",
-        "model.layers.26.self_attn.kv_a_proj.scales": "model-00010-of-00010.safetensors",
-        "model.layers.26.self_attn.kv_a_proj.weight": "model-00010-of-00010.safetensors",
+        "model.layers.26.self_attn.kv_a_layernorm.weight": "model-00010-of-00010.safetensors",
+        "model.layers.26.self_attn.kv_a_proj_with_mqa.biases": "model-00010-of-00010.safetensors",
+        "model.layers.26.self_attn.kv_a_proj_with_mqa.scales": "model-00010-of-00010.safetensors",
+        "model.layers.26.self_attn.kv_a_proj_with_mqa.weight": "model-00010-of-00010.safetensors",
         "model.layers.26.self_attn.kv_b_proj.biases": "model-00010-of-00010.safetensors",
         "model.layers.26.self_attn.kv_b_proj.scales": "model-00010-of-00010.safetensors",
         "model.layers.26.self_attn.kv_b_proj.weight": "model-00010-of-00010.safetensors",
@@ -1061,10 +1061,10 @@
         "model.layers.3.mlp.switch_mlp.up_proj.scales": "model-00002-of-00010.safetensors",
         "model.layers.3.mlp.switch_mlp.up_proj.weight": "model-00002-of-00010.safetensors",
         "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00010.safetensors",
-        "model.layers.3.self_attn.kv_a_norm.weight": "model-00001-of-00010.safetensors",
-        "model.layers.3.self_attn.kv_a_proj.biases": "model-00001-of-00010.safetensors",
-        "model.layers.3.self_attn.kv_a_proj.scales": "model-00001-of-00010.safetensors",
-        "model.layers.3.self_attn.kv_a_proj.weight": "model-00001-of-00010.safetensors",
+        "model.layers.3.self_attn.kv_a_layernorm.weight": "model-00001-of-00010.safetensors",
+        "model.layers.3.self_attn.kv_a_proj_with_mqa.biases": "model-00001-of-00010.safetensors",
+        "model.layers.3.self_attn.kv_a_proj_with_mqa.scales": "model-00001-of-00010.safetensors",
+        "model.layers.3.self_attn.kv_a_proj_with_mqa.weight": "model-00001-of-00010.safetensors",
         "model.layers.3.self_attn.kv_b_proj.biases": "model-00001-of-00010.safetensors",
         "model.layers.3.self_attn.kv_b_proj.scales": "model-00001-of-00010.safetensors",
         "model.layers.3.self_attn.kv_b_proj.weight": "model-00001-of-00010.safetensors",
@@ -1269,10 +1269,10 @@
         "model.layers.7.mlp.switch_mlp.up_proj.scales": "model-00003-of-00010.safetensors",
         "model.layers.7.mlp.switch_mlp.up_proj.weight": "model-00003-of-00010.safetensors",
         "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00010.safetensors",
-        "model.layers.7.self_attn.kv_a_norm.weight": "model-00003-of-00010.safetensors",
-        "model.layers.7.self_attn.kv_a_proj.biases": "model-00003-of-00010.safetensors",
-        "model.layers.7.self_attn.kv_a_proj.scales": "model-00003-of-00010.safetensors",
-        "model.layers.7.self_attn.kv_a_proj.weight": "model-00003-of-00010.safetensors",
+        "model.layers.7.self_attn.kv_a_layernorm.weight": "model-00003-of-00010.safetensors",
+        "model.layers.7.self_attn.kv_a_proj_with_mqa.biases": "model-00003-of-00010.safetensors",
+        "model.layers.7.self_attn.kv_a_proj_with_mqa.scales": "model-00003-of-00010.safetensors",
+        "model.layers.7.self_attn.kv_a_proj_with_mqa.weight": "model-00003-of-00010.safetensors",
         "model.layers.7.self_attn.kv_b_proj.biases": "model-00003-of-00010.safetensors",
         "model.layers.7.self_attn.kv_b_proj.scales": "model-00003-of-00010.safetensors",
         "model.layers.7.self_attn.kv_b_proj.weight": "model-00003-of-00010.safetensors",