Upload folder using huggingface_hub

mergekit_moe_config.yml

@@ -0,0 +1,13 @@
+base_model: BioMistral/BioMistral-7B
+gate_mode: hidden # one of "hidden", "cheap_embed", or "random"
+dtype: bfloat16 # output dtype (float32, float16, or bfloat16)
+experts:
+  - source_model: Treza12/BioMistral-invasive-FULL
+    positive_prompts:
+      - "This is a prompt that is demonstrative excels at invasive Breast Cancer"
+  - source_model: Treza12/BioMistral-non-invasive-FULL
+    positive_prompts:
+      - "This is a prompt that is demonstrative excels at non invasive benign Breast Cancer"
+  - source_model: Treza12/BioMistral-advanced-FULL
+    positive_prompts:
+      - "This is a prompt that is demonstrative excels at advanced Stage Breast Cancer"

model-00001-of-00021.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e1020bd2ec1862839ceed998f803f6b5c701271088485c369a7a3415c3221bd
+size 958433904

model-00002-of-00021.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e2a8c0e483b3486c814b77dabfe8ac214ff008f830bd3245cb7aede91357f0e0
+size 964708960

model-00003-of-00021.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bdfa8d4bec4a1066ab4f842325cb9cabc19eff6736a62fcd478d8b4a47d61cc2
+size 989891728

model-00004-of-00021.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69719ae4488bbcd66f63db5764b8d1c6f8ac5e4cb2c051545f1699b970789f7f
+size 964708960

model-00005-of-00021.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:682051494fbdca36392d5d6231309c99d9aaee0cd56db693631ac8f84a8a0098
+size 989891728

model-00006-of-00021.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5919bc607030901c9d704d36cae7357275abaebfb6c82cfdbe055208123a14b9
+size 989891728

model-00007-of-00021.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:871bc6b7fe8abf9842042c2d937a8acdbc1516e614bd9cb6e674096f3d8d82a3
+size 964708968

model-00008-of-00021.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0271e6dd0cbe8391591c97e6ff01388a8fe226b8443234e69ad566b34fa64901
+size 989891752

model-00009-of-00021.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7800bde5c37bf12e7269e76858814c02d7be43ab33bb12c83b743eb8e8edb17a
+size 964708984

model-00010-of-00021.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b8be627189071c63267a540ea919ebb6f8615c7e342a8a84e231f0e4683d78a9
+size 989891752

model-00011-of-00021.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9de08cf8d758168cd27e2420cd6980ebbf45c9e599e9dca9a3885cccea91307b
+size 989891752

model-00012-of-00021.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1d19967a2515fd011df4e9d90c2b1dda9ae0daa159c72243967a1c6c4c4e381
+size 964708984

model-00013-of-00021.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c34212849af8169a9c63d68dcd6bf77e745e9deaf885687e5ef9133b7aa93ff6
+size 989891752

model-00014-of-00021.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ba2ddb43ed96b31e46eeae991d2e69d68ba529d0e9c0aabf98be775f758b14e
+size 964708984

model-00015-of-00021.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e07c50df53a8a070a187ce9dfeb3f75602e8bba20adb33aa48628b32e9e29a7b
+size 989891752

model-00016-of-00021.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3165595bbb73bede633c60248e5ad2c6cd73b8956ed45b7f1950e9bc5abfcd95
+size 989891752

model-00017-of-00021.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4e468f701f6856717190fc943460d7c40b792a6bf567db4920ad537505705a5
+size 964708984

model-00018-of-00021.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce46d1bd4da4725dc9716ce1b704faabd3db31bdbb17c33d083465880c8fdf22
+size 989891752

model-00019-of-00021.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9b0e724cc9d8ead6805565b5a1f4c65e8d3295936372e0bb82e5d90e04efaef
+size 964708984

model-00020-of-00021.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c13cca4290ecc7b38d49fab9e047449fdf27978e6e59785b7466eb40b5b9d8d
+size 989891752

model-00021-of-00021.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7e6e70bf1c934c542b91d7ccceb51724f49c58ab2bbf1170e729edaf1c98390
+size 556544536

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.4.4", "total_size": 20121395200}, "weight_map": {"model.embed_tokens.weight": "model-00001-of-00021.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00021.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00021.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00021.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00021.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00021.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00021.safetensors", "model.layers.0.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00021.safetensors", "model.layers.0.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00021.safetensors", "model.layers.0.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00021.safetensors", "model.layers.0.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00021.safetensors", "model.layers.0.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00021.safetensors", "model.layers.0.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00021.safetensors", "model.layers.0.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00021.safetensors", "model.layers.0.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00021.safetensors", "model.layers.0.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00021.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00021.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00021.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00021.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00021.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00021.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00021.safetensors", "model.layers.1.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00021.safetensors", "model.layers.1.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00021.safetensors", "model.layers.1.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00021.safetensors", "model.layers.1.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00021.safetensors", "model.layers.1.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00021.safetensors", "model.layers.1.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00021.safetensors", "model.layers.1.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00021.safetensors", "model.layers.1.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00021.safetensors", "model.layers.1.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00021.safetensors", "model.layers.2.input_layernorm.weight": "model-00002-of-00021.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00002-of-00021.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00002-of-00021.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00002-of-00021.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00002-of-00021.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00021.safetensors", "model.layers.2.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00021.safetensors", "model.layers.2.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00021.safetensors", "model.layers.2.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00021.safetensors", "model.layers.2.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00021.safetensors", "model.layers.2.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00021.safetensors", "model.layers.2.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00021.safetensors", "model.layers.2.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00021.safetensors", "model.layers.2.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00021.safetensors", "model.layers.2.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00021.safetensors", "model.layers.3.input_layernorm.weight": "model-00003-of-00021.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00003-of-00021.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00003-of-00021.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00003-of-00021.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00003-of-00021.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00003-of-00021.safetensors", "model.layers.3.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00021.safetensors", "model.layers.3.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00021.safetensors", "model.layers.3.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00021.safetensors", "model.layers.3.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00021.safetensors", "model.layers.3.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00021.safetensors", "model.layers.3.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00021.safetensors", "model.layers.3.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00021.safetensors", "model.layers.3.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00021.safetensors", "model.layers.3.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00021.safetensors", "model.layers.4.input_layernorm.weight": "model-00003-of-00021.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00003-of-00021.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00003-of-00021.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00003-of-00021.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00003-of-00021.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00003-of-00021.safetensors", "model.layers.4.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00021.safetensors", "model.layers.4.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00021.safetensors", "model.layers.4.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00021.safetensors", "model.layers.4.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00021.safetensors", "model.layers.4.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00021.safetensors", "model.layers.4.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00021.safetensors", "model.layers.4.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00021.safetensors", "model.layers.4.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00021.safetensors", "model.layers.4.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00021.safetensors", "model.layers.5.input_layernorm.weight": "model-00004-of-00021.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00004-of-00021.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00004-of-00021.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00004-of-00021.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00004-of-00021.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00004-of-00021.safetensors", "model.layers.5.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00021.safetensors", "model.layers.5.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00021.safetensors", "model.layers.5.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00021.safetensors", "model.layers.5.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00021.safetensors", "model.layers.5.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00021.safetensors", "model.layers.5.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00021.safetensors", "model.layers.5.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00021.safetensors", "model.layers.5.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00021.safetensors", "model.layers.5.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00021.safetensors", "model.layers.6.input_layernorm.weight": "model-00005-of-00021.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00005-of-00021.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00005-of-00021.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00005-of-00021.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00005-of-00021.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00005-of-00021.safetensors", "model.layers.6.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00021.safetensors", "model.layers.6.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00021.safetensors", "model.layers.6.block_sparse_moe.experts.2.w3.weight": "model-00005-of-00021.safetensors", "model.layers.6.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00021.safetensors", "model.layers.6.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00021.safetensors", "model.layers.6.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00021.safetensors", "model.layers.6.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00021.safetensors", "model.layers.6.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00021.safetensors", "model.layers.6.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00021.safetensors", "model.layers.7.input_layernorm.weight": "model-00005-of-00021.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00005-of-00021.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00005-of-00021.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00005-of-00021.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00005-of-00021.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00005-of-00021.safetensors", "model.layers.7.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00021.safetensors", "model.layers.7.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00021.safetensors", "model.layers.7.block_sparse_moe.experts.2.w3.weight": "model-00005-of-00021.safetensors", "model.layers.7.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00021.safetensors", "model.layers.7.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00021.safetensors", "model.layers.7.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00021.safetensors", "model.layers.7.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00021.safetensors", "model.layers.7.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00021.safetensors", "model.layers.7.block_sparse_moe.experts.2.w2.weight": "model-00006-of-00021.safetensors", "model.layers.8.input_layernorm.weight": "model-00006-of-00021.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00006-of-00021.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00006-of-00021.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00006-of-00021.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00006-of-00021.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00006-of-00021.safetensors", "model.layers.8.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00021.safetensors", "model.layers.8.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00021.safetensors", "model.layers.8.block_sparse_moe.experts.2.w3.weight": "model-00006-of-00021.safetensors", "model.layers.8.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00021.safetensors", "model.layers.8.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00021.safetensors", "model.layers.8.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00021.safetensors", "model.layers.8.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00021.safetensors", "model.layers.8.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00021.safetensors", "model.layers.8.block_sparse_moe.experts.2.w2.weight": "model-00006-of-00021.safetensors", "model.layers.9.input_layernorm.weight": "model-00006-of-00021.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00006-of-00021.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00006-of-00021.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00006-of-00021.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00006-of-00021.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00006-of-00021.safetensors", "model.layers.9.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00021.safetensors", "model.layers.9.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00021.safetensors", "model.layers.9.block_sparse_moe.experts.2.w3.weight": "model-00007-of-00021.safetensors", "model.layers.9.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00021.safetensors", "model.layers.9.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00021.safetensors", "model.layers.9.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00021.safetensors", "model.layers.9.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00021.safetensors", "model.layers.9.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00021.safetensors", "model.layers.9.block_sparse_moe.experts.2.w2.weight": "model-00007-of-00021.safetensors", "model.layers.10.input_layernorm.weight": "model-00007-of-00021.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00007-of-00021.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00007-of-00021.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00007-of-00021.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00007-of-00021.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00007-of-00021.safetensors", "model.layers.10.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00021.safetensors", "model.layers.10.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00021.safetensors", "model.layers.10.block_sparse_moe.experts.2.w3.weight": "model-00007-of-00021.safetensors", "model.layers.10.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00021.safetensors", "model.layers.10.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00021.safetensors", "model.layers.10.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00021.safetensors", "model.layers.10.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00021.safetensors", "model.layers.10.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00021.safetensors", "model.layers.10.block_sparse_moe.experts.2.w2.weight": "model-00008-of-00021.safetensors", "model.layers.11.input_layernorm.weight": "model-00008-of-00021.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00008-of-00021.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00008-of-00021.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00008-of-00021.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00008-of-00021.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00008-of-00021.safetensors", "model.layers.11.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00021.safetensors", "model.layers.11.block_sparse_moe.experts.1.w3.weight": "model-00008-of-00021.safetensors", "model.layers.11.block_sparse_moe.experts.2.w3.weight": "model-00008-of-00021.safetensors", "model.layers.11.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00021.safetensors", "model.layers.11.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00021.safetensors", "model.layers.11.block_sparse_moe.experts.2.w1.weight": "model-00008-of-00021.safetensors", "model.layers.11.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00021.safetensors", "model.layers.11.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00021.safetensors", "model.layers.11.block_sparse_moe.experts.2.w2.weight": "model-00008-of-00021.safetensors", "model.layers.12.input_layernorm.weight": "model-00008-of-00021.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00008-of-00021.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00008-of-00021.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00008-of-00021.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00008-of-00021.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00008-of-00021.safetensors", "model.layers.12.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00021.safetensors", "model.layers.12.block_sparse_moe.experts.1.w3.weight": "model-00008-of-00021.safetensors", "model.layers.12.block_sparse_moe.experts.2.w3.weight": "model-00009-of-00021.safetensors", "model.layers.12.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00021.safetensors", "model.layers.12.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00021.safetensors", "model.layers.12.block_sparse_moe.experts.2.w1.weight": "model-00009-of-00021.safetensors", "model.layers.12.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00021.safetensors", "model.layers.12.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00021.safetensors", "model.layers.12.block_sparse_moe.experts.2.w2.weight": "model-00009-of-00021.safetensors", "model.layers.13.input_layernorm.weight": "model-00009-of-00021.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00009-of-00021.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00009-of-00021.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00009-of-00021.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00009-of-00021.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00009-of-00021.safetensors", "model.layers.13.block_sparse_moe.experts.0.w3.weight": "model-00009-of-00021.safetensors", "model.layers.13.block_sparse_moe.experts.1.w3.weight": "model-00009-of-00021.safetensors", "model.layers.13.block_sparse_moe.experts.2.w3.weight": "model-00009-of-00021.safetensors", "model.layers.13.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00021.safetensors", "model.layers.13.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00021.safetensors", "model.layers.13.block_sparse_moe.experts.2.w1.weight": "model-00009-of-00021.safetensors", "model.layers.13.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00021.safetensors", "model.layers.13.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00021.safetensors", "model.layers.13.block_sparse_moe.experts.2.w2.weight": "model-00010-of-00021.safetensors", "model.layers.14.input_layernorm.weight": "model-00010-of-00021.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00010-of-00021.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00010-of-00021.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00010-of-00021.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00010-of-00021.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00010-of-00021.safetensors", "model.layers.14.block_sparse_moe.experts.0.w3.weight": "model-00010-of-00021.safetensors", "model.layers.14.block_sparse_moe.experts.1.w3.weight": "model-00010-of-00021.safetensors", "model.layers.14.block_sparse_moe.experts.2.w3.weight": "model-00010-of-00021.safetensors", "model.layers.14.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00021.safetensors", "model.layers.14.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00021.safetensors", "model.layers.14.block_sparse_moe.experts.2.w1.weight": "model-00010-of-00021.safetensors", "model.layers.14.block_sparse_moe.experts.0.w2.weight": "model-00010-of-00021.safetensors", "model.layers.14.block_sparse_moe.experts.1.w2.weight": "model-00010-of-00021.safetensors", "model.layers.14.block_sparse_moe.experts.2.w2.weight": "model-00010-of-00021.safetensors", "model.layers.15.input_layernorm.weight": "model-00010-of-00021.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00010-of-00021.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00010-of-00021.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00010-of-00021.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00010-of-00021.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00010-of-00021.safetensors", "model.layers.15.block_sparse_moe.experts.0.w3.weight": "model-00010-of-00021.safetensors", "model.layers.15.block_sparse_moe.experts.1.w3.weight": "model-00010-of-00021.safetensors", "model.layers.15.block_sparse_moe.experts.2.w3.weight": "model-00010-of-00021.safetensors", "model.layers.15.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00021.safetensors", "model.layers.15.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00021.safetensors", "model.layers.15.block_sparse_moe.experts.2.w1.weight": "model-00011-of-00021.safetensors", "model.layers.15.block_sparse_moe.experts.0.w2.weight": "model-00011-of-00021.safetensors", "model.layers.15.block_sparse_moe.experts.1.w2.weight": "model-00011-of-00021.safetensors", "model.layers.15.block_sparse_moe.experts.2.w2.weight": "model-00011-of-00021.safetensors", "model.layers.16.input_layernorm.weight": "model-00011-of-00021.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00011-of-00021.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00011-of-00021.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00011-of-00021.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00011-of-00021.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00011-of-00021.safetensors", "model.layers.16.block_sparse_moe.experts.0.w3.weight": "model-00011-of-00021.safetensors", "model.layers.16.block_sparse_moe.experts.1.w3.weight": "model-00011-of-00021.safetensors", "model.layers.16.block_sparse_moe.experts.2.w3.weight": "model-00011-of-00021.safetensors", "model.layers.16.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00021.safetensors", "model.layers.16.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00021.safetensors", "model.layers.16.block_sparse_moe.experts.2.w1.weight": "model-00011-of-00021.safetensors", "model.layers.16.block_sparse_moe.experts.0.w2.weight": "model-00011-of-00021.safetensors", "model.layers.16.block_sparse_moe.experts.1.w2.weight": "model-00011-of-00021.safetensors", "model.layers.16.block_sparse_moe.experts.2.w2.weight": "model-00011-of-00021.safetensors", "model.layers.17.input_layernorm.weight": "model-00011-of-00021.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00011-of-00021.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00011-of-00021.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00011-of-00021.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00011-of-00021.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00011-of-00021.safetensors", "model.layers.17.block_sparse_moe.experts.0.w3.weight": "model-00012-of-00021.safetensors", "model.layers.17.block_sparse_moe.experts.1.w3.weight": "model-00012-of-00021.safetensors", "model.layers.17.block_sparse_moe.experts.2.w3.weight": "model-00012-of-00021.safetensors", "model.layers.17.block_sparse_moe.experts.0.w1.weight": "model-00012-of-00021.safetensors", "model.layers.17.block_sparse_moe.experts.1.w1.weight": "model-00012-of-00021.safetensors", "model.layers.17.block_sparse_moe.experts.2.w1.weight": "model-00012-of-00021.safetensors", "model.layers.17.block_sparse_moe.experts.0.w2.weight": "model-00012-of-00021.safetensors", "model.layers.17.block_sparse_moe.experts.1.w2.weight": "model-00012-of-00021.safetensors", "model.layers.17.block_sparse_moe.experts.2.w2.weight": "model-00012-of-00021.safetensors", "model.layers.18.input_layernorm.weight": "model-00012-of-00021.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00012-of-00021.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00012-of-00021.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00012-of-00021.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00012-of-00021.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00012-of-00021.safetensors", "model.layers.18.block_sparse_moe.experts.0.w3.weight": "model-00012-of-00021.safetensors", "model.layers.18.block_sparse_moe.experts.1.w3.weight": "model-00012-of-00021.safetensors", "model.layers.18.block_sparse_moe.experts.2.w3.weight": "model-00012-of-00021.safetensors", "model.layers.18.block_sparse_moe.experts.0.w1.weight": "model-00012-of-00021.safetensors", "model.layers.18.block_sparse_moe.experts.1.w1.weight": "model-00012-of-00021.safetensors", "model.layers.18.block_sparse_moe.experts.2.w1.weight": "model-00012-of-00021.safetensors", "model.layers.18.block_sparse_moe.experts.0.w2.weight": "model-00013-of-00021.safetensors", "model.layers.18.block_sparse_moe.experts.1.w2.weight": "model-00013-of-00021.safetensors", "model.layers.18.block_sparse_moe.experts.2.w2.weight": "model-00013-of-00021.safetensors", "model.layers.19.input_layernorm.weight": "model-00013-of-00021.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00013-of-00021.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00013-of-00021.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00013-of-00021.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00013-of-00021.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00013-of-00021.safetensors", "model.layers.19.block_sparse_moe.experts.0.w3.weight": "model-00013-of-00021.safetensors", "model.layers.19.block_sparse_moe.experts.1.w3.weight": "model-00013-of-00021.safetensors", "model.layers.19.block_sparse_moe.experts.2.w3.weight": "model-00013-of-00021.safetensors", "model.layers.19.block_sparse_moe.experts.0.w1.weight": "model-00013-of-00021.safetensors", "model.layers.19.block_sparse_moe.experts.1.w1.weight": "model-00013-of-00021.safetensors", "model.layers.19.block_sparse_moe.experts.2.w1.weight": "model-00013-of-00021.safetensors", "model.layers.19.block_sparse_moe.experts.0.w2.weight": "model-00013-of-00021.safetensors", "model.layers.19.block_sparse_moe.experts.1.w2.weight": "model-00013-of-00021.safetensors", "model.layers.19.block_sparse_moe.experts.2.w2.weight": "model-00013-of-00021.safetensors", "model.layers.20.input_layernorm.weight": "model-00013-of-00021.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00013-of-00021.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00013-of-00021.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00013-of-00021.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00013-of-00021.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00013-of-00021.safetensors", "model.layers.20.block_sparse_moe.experts.0.w3.weight": "model-00013-of-00021.safetensors", "model.layers.20.block_sparse_moe.experts.1.w3.weight": "model-00013-of-00021.safetensors", "model.layers.20.block_sparse_moe.experts.2.w3.weight": "model-00014-of-00021.safetensors", "model.layers.20.block_sparse_moe.experts.0.w1.weight": "model-00014-of-00021.safetensors", "model.layers.20.block_sparse_moe.experts.1.w1.weight": "model-00014-of-00021.safetensors", "model.layers.20.block_sparse_moe.experts.2.w1.weight": "model-00014-of-00021.safetensors", "model.layers.20.block_sparse_moe.experts.0.w2.weight": "model-00014-of-00021.safetensors", "model.layers.20.block_sparse_moe.experts.1.w2.weight": "model-00014-of-00021.safetensors", "model.layers.20.block_sparse_moe.experts.2.w2.weight": "model-00014-of-00021.safetensors", "model.layers.21.input_layernorm.weight": "model-00014-of-00021.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00014-of-00021.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00014-of-00021.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00014-of-00021.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00014-of-00021.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00014-of-00021.safetensors", "model.layers.21.block_sparse_moe.experts.0.w3.weight": "model-00014-of-00021.safetensors", "model.layers.21.block_sparse_moe.experts.1.w3.weight": "model-00014-of-00021.safetensors", "model.layers.21.block_sparse_moe.experts.2.w3.weight": "model-00014-of-00021.safetensors", "model.layers.21.block_sparse_moe.experts.0.w1.weight": "model-00014-of-00021.safetensors", "model.layers.21.block_sparse_moe.experts.1.w1.weight": "model-00014-of-00021.safetensors", "model.layers.21.block_sparse_moe.experts.2.w1.weight": "model-00014-of-00021.safetensors", "model.layers.21.block_sparse_moe.experts.0.w2.weight": "model-00014-of-00021.safetensors", "model.layers.21.block_sparse_moe.experts.1.w2.weight": "model-00014-of-00021.safetensors", "model.layers.21.block_sparse_moe.experts.2.w2.weight": "model-00015-of-00021.safetensors", "model.layers.22.input_layernorm.weight": "model-00015-of-00021.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00015-of-00021.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00015-of-00021.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00015-of-00021.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00015-of-00021.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00015-of-00021.safetensors", "model.layers.22.block_sparse_moe.experts.0.w3.weight": "model-00015-of-00021.safetensors", "model.layers.22.block_sparse_moe.experts.1.w3.weight": "model-00015-of-00021.safetensors", "model.layers.22.block_sparse_moe.experts.2.w3.weight": "model-00015-of-00021.safetensors", "model.layers.22.block_sparse_moe.experts.0.w1.weight": "model-00015-of-00021.safetensors", "model.layers.22.block_sparse_moe.experts.1.w1.weight": "model-00015-of-00021.safetensors", "model.layers.22.block_sparse_moe.experts.2.w1.weight": "model-00015-of-00021.safetensors", "model.layers.22.block_sparse_moe.experts.0.w2.weight": "model-00015-of-00021.safetensors", "model.layers.22.block_sparse_moe.experts.1.w2.weight": "model-00015-of-00021.safetensors", "model.layers.22.block_sparse_moe.experts.2.w2.weight": "model-00015-of-00021.safetensors", "model.layers.23.input_layernorm.weight": "model-00015-of-00021.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00015-of-00021.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00015-of-00021.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00015-of-00021.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00015-of-00021.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00015-of-00021.safetensors", "model.layers.23.block_sparse_moe.experts.0.w3.weight": "model-00015-of-00021.safetensors", "model.layers.23.block_sparse_moe.experts.1.w3.weight": "model-00015-of-00021.safetensors", "model.layers.23.block_sparse_moe.experts.2.w3.weight": "model-00015-of-00021.safetensors", "model.layers.23.block_sparse_moe.experts.0.w1.weight": "model-00015-of-00021.safetensors", "model.layers.23.block_sparse_moe.experts.1.w1.weight": "model-00016-of-00021.safetensors", "model.layers.23.block_sparse_moe.experts.2.w1.weight": "model-00016-of-00021.safetensors", "model.layers.23.block_sparse_moe.experts.0.w2.weight": "model-00016-of-00021.safetensors", "model.layers.23.block_sparse_moe.experts.1.w2.weight": "model-00016-of-00021.safetensors", "model.layers.23.block_sparse_moe.experts.2.w2.weight": "model-00016-of-00021.safetensors", "model.layers.24.input_layernorm.weight": "model-00016-of-00021.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00016-of-00021.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00016-of-00021.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00016-of-00021.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00016-of-00021.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00016-of-00021.safetensors", "model.layers.24.block_sparse_moe.experts.0.w3.weight": "model-00016-of-00021.safetensors", "model.layers.24.block_sparse_moe.experts.1.w3.weight": "model-00016-of-00021.safetensors", "model.layers.24.block_sparse_moe.experts.2.w3.weight": "model-00016-of-00021.safetensors", "model.layers.24.block_sparse_moe.experts.0.w1.weight": "model-00016-of-00021.safetensors", "model.layers.24.block_sparse_moe.experts.1.w1.weight": "model-00016-of-00021.safetensors", "model.layers.24.block_sparse_moe.experts.2.w1.weight": "model-00016-of-00021.safetensors", "model.layers.24.block_sparse_moe.experts.0.w2.weight": "model-00016-of-00021.safetensors", "model.layers.24.block_sparse_moe.experts.1.w2.weight": "model-00016-of-00021.safetensors", "model.layers.24.block_sparse_moe.experts.2.w2.weight": "model-00016-of-00021.safetensors", "model.layers.25.input_layernorm.weight": "model-00016-of-00021.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00016-of-00021.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00016-of-00021.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00016-of-00021.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00016-of-00021.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00016-of-00021.safetensors", "model.layers.25.block_sparse_moe.experts.0.w3.weight": "model-00017-of-00021.safetensors", "model.layers.25.block_sparse_moe.experts.1.w3.weight": "model-00017-of-00021.safetensors", "model.layers.25.block_sparse_moe.experts.2.w3.weight": "model-00017-of-00021.safetensors", "model.layers.25.block_sparse_moe.experts.0.w1.weight": "model-00017-of-00021.safetensors", "model.layers.25.block_sparse_moe.experts.1.w1.weight": "model-00017-of-00021.safetensors", "model.layers.25.block_sparse_moe.experts.2.w1.weight": "model-00017-of-00021.safetensors", "model.layers.25.block_sparse_moe.experts.0.w2.weight": "model-00017-of-00021.safetensors", "model.layers.25.block_sparse_moe.experts.1.w2.weight": "model-00017-of-00021.safetensors", "model.layers.25.block_sparse_moe.experts.2.w2.weight": "model-00017-of-00021.safetensors", "model.layers.26.input_layernorm.weight": "model-00017-of-00021.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00017-of-00021.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00017-of-00021.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00017-of-00021.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00017-of-00021.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00017-of-00021.safetensors", "model.layers.26.block_sparse_moe.experts.0.w3.weight": "model-00017-of-00021.safetensors", "model.layers.26.block_sparse_moe.experts.1.w3.weight": "model-00017-of-00021.safetensors", "model.layers.26.block_sparse_moe.experts.2.w3.weight": "model-00017-of-00021.safetensors", "model.layers.26.block_sparse_moe.experts.0.w1.weight": "model-00017-of-00021.safetensors", "model.layers.26.block_sparse_moe.experts.1.w1.weight": "model-00017-of-00021.safetensors", "model.layers.26.block_sparse_moe.experts.2.w1.weight": "model-00017-of-00021.safetensors", "model.layers.26.block_sparse_moe.experts.0.w2.weight": "model-00018-of-00021.safetensors", "model.layers.26.block_sparse_moe.experts.1.w2.weight": "model-00018-of-00021.safetensors", "model.layers.26.block_sparse_moe.experts.2.w2.weight": "model-00018-of-00021.safetensors", "model.layers.27.input_layernorm.weight": "model-00018-of-00021.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00018-of-00021.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00018-of-00021.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00018-of-00021.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00018-of-00021.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00018-of-00021.safetensors", "model.layers.27.block_sparse_moe.experts.0.w3.weight": "model-00018-of-00021.safetensors", "model.layers.27.block_sparse_moe.experts.1.w3.weight": "model-00018-of-00021.safetensors", "model.layers.27.block_sparse_moe.experts.2.w3.weight": "model-00018-of-00021.safetensors", "model.layers.27.block_sparse_moe.experts.0.w1.weight": "model-00018-of-00021.safetensors", "model.layers.27.block_sparse_moe.experts.1.w1.weight": "model-00018-of-00021.safetensors", "model.layers.27.block_sparse_moe.experts.2.w1.weight": "model-00018-of-00021.safetensors", "model.layers.27.block_sparse_moe.experts.0.w2.weight": "model-00018-of-00021.safetensors", "model.layers.27.block_sparse_moe.experts.1.w2.weight": "model-00018-of-00021.safetensors", "model.layers.27.block_sparse_moe.experts.2.w2.weight": "model-00018-of-00021.safetensors", "model.layers.28.input_layernorm.weight": "model-00018-of-00021.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00018-of-00021.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00018-of-00021.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00018-of-00021.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00018-of-00021.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00018-of-00021.safetensors", "model.layers.28.block_sparse_moe.experts.0.w3.weight": "model-00018-of-00021.safetensors", "model.layers.28.block_sparse_moe.experts.1.w3.weight": "model-00018-of-00021.safetensors", "model.layers.28.block_sparse_moe.experts.2.w3.weight": "model-00019-of-00021.safetensors", "model.layers.28.block_sparse_moe.experts.0.w1.weight": "model-00019-of-00021.safetensors", "model.layers.28.block_sparse_moe.experts.1.w1.weight": "model-00019-of-00021.safetensors", "model.layers.28.block_sparse_moe.experts.2.w1.weight": "model-00019-of-00021.safetensors", "model.layers.28.block_sparse_moe.experts.0.w2.weight": "model-00019-of-00021.safetensors", "model.layers.28.block_sparse_moe.experts.1.w2.weight": "model-00019-of-00021.safetensors", "model.layers.28.block_sparse_moe.experts.2.w2.weight": "model-00019-of-00021.safetensors", "model.layers.29.input_layernorm.weight": "model-00019-of-00021.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00019-of-00021.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00019-of-00021.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00019-of-00021.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00019-of-00021.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00019-of-00021.safetensors", "model.layers.29.block_sparse_moe.experts.0.w3.weight": "model-00019-of-00021.safetensors", "model.layers.29.block_sparse_moe.experts.1.w3.weight": "model-00019-of-00021.safetensors", "model.layers.29.block_sparse_moe.experts.2.w3.weight": "model-00019-of-00021.safetensors", "model.layers.29.block_sparse_moe.experts.0.w1.weight": "model-00019-of-00021.safetensors", "model.layers.29.block_sparse_moe.experts.1.w1.weight": "model-00019-of-00021.safetensors", "model.layers.29.block_sparse_moe.experts.2.w1.weight": "model-00019-of-00021.safetensors", "model.layers.29.block_sparse_moe.experts.0.w2.weight": "model-00019-of-00021.safetensors", "model.layers.29.block_sparse_moe.experts.1.w2.weight": "model-00019-of-00021.safetensors", "model.layers.29.block_sparse_moe.experts.2.w2.weight": "model-00020-of-00021.safetensors", "model.layers.30.input_layernorm.weight": "model-00020-of-00021.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00020-of-00021.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00020-of-00021.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00020-of-00021.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00020-of-00021.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00020-of-00021.safetensors", "model.layers.30.block_sparse_moe.experts.0.w3.weight": "model-00020-of-00021.safetensors", "model.layers.30.block_sparse_moe.experts.1.w3.weight": "model-00020-of-00021.safetensors", "model.layers.30.block_sparse_moe.experts.2.w3.weight": "model-00020-of-00021.safetensors", "model.layers.30.block_sparse_moe.experts.0.w1.weight": "model-00020-of-00021.safetensors", "model.layers.30.block_sparse_moe.experts.1.w1.weight": "model-00020-of-00021.safetensors", "model.layers.30.block_sparse_moe.experts.2.w1.weight": "model-00020-of-00021.safetensors", "model.layers.30.block_sparse_moe.experts.0.w2.weight": "model-00020-of-00021.safetensors", "model.layers.30.block_sparse_moe.experts.1.w2.weight": "model-00020-of-00021.safetensors", "model.layers.30.block_sparse_moe.experts.2.w2.weight": "model-00020-of-00021.safetensors", "model.layers.31.input_layernorm.weight": "model-00020-of-00021.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00020-of-00021.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00020-of-00021.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00020-of-00021.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00020-of-00021.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00020-of-00021.safetensors", "model.layers.31.block_sparse_moe.experts.0.w3.weight": "model-00020-of-00021.safetensors", "model.layers.31.block_sparse_moe.experts.1.w3.weight": "model-00020-of-00021.safetensors", "model.layers.31.block_sparse_moe.experts.2.w3.weight": "model-00020-of-00021.safetensors", "model.layers.31.block_sparse_moe.experts.0.w1.weight": "model-00020-of-00021.safetensors", "model.layers.31.block_sparse_moe.experts.1.w1.weight": "model-00021-of-00021.safetensors", "model.layers.31.block_sparse_moe.experts.2.w1.weight": "model-00021-of-00021.safetensors", "model.layers.31.block_sparse_moe.experts.0.w2.weight": "model-00021-of-00021.safetensors", "model.layers.31.block_sparse_moe.experts.1.w2.weight": "model-00021-of-00021.safetensors", "model.layers.31.block_sparse_moe.experts.2.w2.weight": "model-00021-of-00021.safetensors", "model.norm.weight": "model-00021-of-00021.safetensors", "lm_head.weight": "model-00021-of-00021.safetensors", "model.layers.0.block_sparse_moe.gate.weight": "model-00021-of-00021.safetensors", "model.layers.1.block_sparse_moe.gate.weight": "model-00021-of-00021.safetensors", "model.layers.2.block_sparse_moe.gate.weight": "model-00021-of-00021.safetensors", "model.layers.3.block_sparse_moe.gate.weight": "model-00021-of-00021.safetensors", "model.layers.4.block_sparse_moe.gate.weight": "model-00021-of-00021.safetensors", "model.layers.5.block_sparse_moe.gate.weight": "model-00021-of-00021.safetensors", "model.layers.6.block_sparse_moe.gate.weight": "model-00021-of-00021.safetensors", "model.layers.7.block_sparse_moe.gate.weight": "model-00021-of-00021.safetensors", "model.layers.8.block_sparse_moe.gate.weight": "model-00021-of-00021.safetensors", "model.layers.9.block_sparse_moe.gate.weight": "model-00021-of-00021.safetensors", "model.layers.10.block_sparse_moe.gate.weight": "model-00021-of-00021.safetensors", "model.layers.11.block_sparse_moe.gate.weight": "model-00021-of-00021.safetensors", "model.layers.12.block_sparse_moe.gate.weight": "model-00021-of-00021.safetensors", "model.layers.13.block_sparse_moe.gate.weight": "model-00021-of-00021.safetensors", "model.layers.14.block_sparse_moe.gate.weight": "model-00021-of-00021.safetensors", "model.layers.15.block_sparse_moe.gate.weight": "model-00021-of-00021.safetensors", "model.layers.16.block_sparse_moe.gate.weight": "model-00021-of-00021.safetensors", "model.layers.17.block_sparse_moe.gate.weight": "model-00021-of-00021.safetensors", "model.layers.18.block_sparse_moe.gate.weight": "model-00021-of-00021.safetensors", "model.layers.19.block_sparse_moe.gate.weight": "model-00021-of-00021.safetensors", "model.layers.20.block_sparse_moe.gate.weight": "model-00021-of-00021.safetensors", "model.layers.21.block_sparse_moe.gate.weight": "model-00021-of-00021.safetensors", "model.layers.22.block_sparse_moe.gate.weight": "model-00021-of-00021.safetensors", "model.layers.23.block_sparse_moe.gate.weight": "model-00021-of-00021.safetensors", "model.layers.24.block_sparse_moe.gate.weight": "model-00021-of-00021.safetensors", "model.layers.25.block_sparse_moe.gate.weight": "model-00021-of-00021.safetensors", "model.layers.26.block_sparse_moe.gate.weight": "model-00021-of-00021.safetensors", "model.layers.27.block_sparse_moe.gate.weight": "model-00021-of-00021.safetensors", "model.layers.28.block_sparse_moe.gate.weight": "model-00021-of-00021.safetensors", "model.layers.29.block_sparse_moe.gate.weight": "model-00021-of-00021.safetensors", "model.layers.30.block_sparse_moe.gate.weight": "model-00021-of-00021.safetensors", "model.layers.31.block_sparse_moe.gate.weight": "model-00021-of-00021.safetensors"}}

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<s>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

tokenizer_config.json

@@ -0,0 +1,44 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token + ' ' }}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}