Upload folder using huggingface_hub

config.json

@@ -0,0 +1,31 @@
+{
+  "_name_or_path": "MrezaPRZ/codestral_experts_ties",
+  "architectures": [
+    "MixtralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 6144,
+  "initializer_range": 0.02,
+  "intermediate_size": 16384,
+  "max_position_embeddings": 32768,
+  "model_type": "mixtral",
+  "num_attention_heads": 48,
+  "num_experts_per_tok": 2,
+  "num_hidden_layers": 56,
+  "num_key_value_heads": 8,
+  "num_local_experts": 3,
+  "output_router_logits": false,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 1000000.0,
+  "router_aux_loss_coef": 0.001,
+  "router_jitter_noise": 0.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.41.2",
+  "use_cache": true,
+  "vocab_size": 32768
+}

mergekit_moe_config.yml

@@ -0,0 +1,103 @@
+base_model: MrezaPRZ/codestral_experts_ties
+experts:
+  - source_model: MrezaPRZ/codestral_high_quality_sft
+    positive_prompts:
+    - "JULIANDAY"
+    - "CURRENT_TIME"
+    - "GLOB"
+    - "GROUP_CONCAT"
+    - "QUOTE"
+    - "TOTAL"
+    - "VACUUM"
+    - "UNLIKELY"
+    - "LIKELY"
+    - "CHAR"
+    negative_prompts:
+    - "ARRAY_AGG"
+    - "STRING_AGG"
+    - "JSONB_BUILD_OBJECT"
+    - "TO_CHAR"
+    - "GENERATE_SERIES"
+    - "RANK"
+    - "CUME_DIST"
+    - "LEAD"
+    - "LAG"
+    - "TABLESAMPLE"
+    - "ARRAY_CONCAT"
+    - "STRUCT"
+    - "UNNEST"
+    - "SAFE_DIVIDE"
+    - "NET.IP_FROM_STRING"
+    - "PARSE_TIMESTAMP"
+    - "GENERATE_ARRAY"
+    - "FARM_FINGERPRINT"
+    - "ARRAY_TO_STRING"
+    - "PIVOT"
+  - source_model: MrezaPRZ/codestral_high_quality_sft_postgres
+    positive_prompts:
+    - "ARRAY_AGG"
+    - "STRING_AGG"
+    - "JSONB_BUILD_OBJECT"
+    - "TO_CHAR"
+    - "GENERATE_SERIES"
+    - "RANK"
+    - "CUME_DIST"
+    - "LEAD"
+    - "LAG"
+    - "TABLESAMPLE"
+    negative_prompts:
+    - "JULIANDAY"
+    - "CURRENT_TIME"
+    - "GLOB"
+    - "GROUP_CONCAT"
+    - "QUOTE"
+    - "TOTAL"
+    - "VACUUM"
+    - "UNLIKELY"
+    - "LIKELY"
+    - "CHAR"
+    - "ARRAY_CONCAT"
+    - "STRUCT"
+    - "UNNEST"
+    - "SAFE_DIVIDE"
+    - "NET.IP_FROM_STRING"
+    - "PARSE_TIMESTAMP"
+    - "GENERATE_ARRAY"
+    - "FARM_FINGERPRINT"
+    - "ARRAY_TO_STRING"
+    - "PIVOT"
+  - source_model: MrezaPRZ/codestral_high_quality_sft_bigquery
+    positive_prompts:
+    - "ARRAY_CONCAT"
+    - "STRUCT"
+    - "UNNEST"
+    - "SAFE_DIVIDE"
+    - "NET.IP_FROM_STRING"
+    - "PARSE_TIMESTAMP"
+    - "GENERATE_ARRAY"
+    - "FARM_FINGERPRINT"
+    - "ARRAY_TO_STRING"
+    - "PIVOT"
+    negative_prompts:
+    - "JULIANDAY"
+    - "CURRENT_TIME"
+    - "GLOB"
+    - "GROUP_CONCAT"
+    - "QUOTE"
+    - "TOTAL"
+    - "VACUUM"
+    - "UNLIKELY"
+    - "LIKELY"
+    - "CHAR"
+    - "ARRAY_AGG"
+    - "STRING_AGG"
+    - "JSONB_BUILD_OBJECT"
+    - "TO_CHAR"
+    - "GENERATE_SERIES"
+    - "RANK"
+    - "CUME_DIST"
+    - "LEAD"
+    - "LAG"
+    - "TABLESAMPLE"
+gate_mode: hidden
+dtype: bfloat16

model-00001-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5caf6665198515830b7a4a7d89211c3bca463664613c0e75ee13fe54c57730d8
+size 9940632624

model-00002-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3083c0bb12170000b052f337a708d74b57eb59bc5ba89692784f7fa34bb9019
+size 9940632776

model-00003-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:518f9c9c071c3c757a125e317b8537d8085ede3e9c6ea3f99f98e988dc5f714d
+size 9940632848

model-00004-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d12be81dab683ec02370686df5b22e445f15e5fb89690c471616f589215ee516
+size 9940632848

model-00005-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9944abf4302f6dfb0dde2c10fdc8acf8ca83295b25316fc672dea84164d858c3
+size 9940632848

model-00006-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba4a5e1e038e820cdfbd78052fed5bf248d15cce21eef8be00c3653e1dc0bd2e
+size 9940632848

model-00007-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4167274bc59350fb807936a1d02649fd29752ccb7d0791c2d7ff1cffca0af947
+size 9940632848

model-00008-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3bc4bdcff9bfa9369912cae36d6cc642a36047b923822422bd496a0860fcd43a
+size 9940632848

model-00009-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b576720c4790e437d8eb72c9115671dbaf8946de9c02375441689a517216118f
+size 9940632848

model-00010-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4dd63d0edbca2cc080af8d5211d904b4faa5e847cfc4be9e86dd12c997986577
+size 9940632848

model-00011-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ede4a3cd114cc9bed3db0890f686782e7f971739c9257f46e2b7b92e3b7e289
+size 9940632848

model-00012-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a98c32618aa7a1a39305a676106e5fd0077a92a45cf236bdc5568548ec2f956
+size 2795516688

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.4.2", "total_size": 112142364672}, "weight_map": {"model.embed_tokens.weight": "model-00001-of-00012.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00012.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00012.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00012.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00012.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.0.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00012.safetensors", "model.layers.0.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00012.safetensors", "model.layers.0.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00012.safetensors", "model.layers.0.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00012.safetensors", "model.layers.0.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00012.safetensors", "model.layers.0.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00012.safetensors", "model.layers.0.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00012.safetensors", "model.layers.0.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00012.safetensors", "model.layers.0.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00012.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00012.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00012.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00012.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00012.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.1.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00012.safetensors", "model.layers.1.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00012.safetensors", "model.layers.1.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00012.safetensors", "model.layers.1.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00012.safetensors", "model.layers.1.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00012.safetensors", "model.layers.1.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00012.safetensors", "model.layers.1.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00012.safetensors", "model.layers.1.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00012.safetensors", "model.layers.1.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00012.safetensors", "model.layers.2.input_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00012.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00012.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00012.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00012.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.2.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00012.safetensors", "model.layers.2.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00012.safetensors", "model.layers.2.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00012.safetensors", "model.layers.2.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00012.safetensors", "model.layers.2.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00012.safetensors", "model.layers.2.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00012.safetensors", "model.layers.2.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00012.safetensors", "model.layers.2.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00012.safetensors", "model.layers.2.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00012.safetensors", "model.layers.3.input_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00012.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00012.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00012.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00012.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.3.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00012.safetensors", "model.layers.3.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00012.safetensors", "model.layers.3.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00012.safetensors", "model.layers.3.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00012.safetensors", "model.layers.3.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00012.safetensors", "model.layers.3.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00012.safetensors", "model.layers.3.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00012.safetensors", "model.layers.3.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00012.safetensors", "model.layers.3.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00012.safetensors", "model.layers.4.input_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00012.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00012.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00012.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00012.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.4.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00012.safetensors", "model.layers.4.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00012.safetensors", "model.layers.4.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00012.safetensors", "model.layers.4.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00012.safetensors", "model.layers.4.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00012.safetensors", "model.layers.4.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00012.safetensors", "model.layers.4.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00012.safetensors", "model.layers.4.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00012.safetensors", "model.layers.4.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00012.safetensors", "model.layers.5.input_layernorm.weight": "model-00002-of-00012.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00012.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00012.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00012.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00012.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00012.safetensors", "model.layers.5.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00012.safetensors", "model.layers.5.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00012.safetensors", "model.layers.5.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00012.safetensors", "model.layers.5.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00012.safetensors", "model.layers.5.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00012.safetensors", "model.layers.5.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00012.safetensors", "model.layers.5.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00012.safetensors", "model.layers.5.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00012.safetensors", "model.layers.5.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00012.safetensors", "model.layers.6.input_layernorm.weight": "model-00002-of-00012.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00012.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00012.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00012.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00012.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00012.safetensors", "model.layers.6.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00012.safetensors", "model.layers.6.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00012.safetensors", "model.layers.6.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00012.safetensors", "model.layers.6.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00012.safetensors", "model.layers.6.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00012.safetensors", "model.layers.6.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00012.safetensors", "model.layers.6.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00012.safetensors", "model.layers.6.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00012.safetensors", "model.layers.6.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00012.safetensors", "model.layers.7.input_layernorm.weight": "model-00002-of-00012.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00012.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00012.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00012.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00012.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00012.safetensors", "model.layers.7.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00012.safetensors", "model.layers.7.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00012.safetensors", "model.layers.7.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00012.safetensors", "model.layers.7.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00012.safetensors", "model.layers.7.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00012.safetensors", "model.layers.7.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00012.safetensors", "model.layers.7.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00012.safetensors", "model.layers.7.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00012.safetensors", "model.layers.7.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00012.safetensors", "model.layers.8.input_layernorm.weight": "model-00002-of-00012.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00012.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00012.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00012.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00012.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00012.safetensors", "model.layers.8.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00012.safetensors", "model.layers.8.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00012.safetensors", "model.layers.8.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00012.safetensors", "model.layers.8.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00012.safetensors", "model.layers.8.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00012.safetensors", "model.layers.8.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00012.safetensors", "model.layers.8.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00012.safetensors", "model.layers.8.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00012.safetensors", "model.layers.8.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00012.safetensors", "model.layers.9.input_layernorm.weight": "model-00002-of-00012.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00012.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00012.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00012.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00012.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00012.safetensors", "model.layers.9.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00012.safetensors", "model.layers.9.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00012.safetensors", "model.layers.9.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00012.safetensors", "model.layers.9.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00012.safetensors", "model.layers.9.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00012.safetensors", "model.layers.9.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00012.safetensors", "model.layers.9.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00012.safetensors", "model.layers.9.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00012.safetensors", "model.layers.9.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00012.safetensors", "model.layers.10.input_layernorm.weight": "model-00003-of-00012.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00012.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00012.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00012.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00012.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00012.safetensors", "model.layers.10.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00012.safetensors", "model.layers.10.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00012.safetensors", "model.layers.10.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00012.safetensors", "model.layers.10.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00012.safetensors", "model.layers.10.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00012.safetensors", "model.layers.10.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00012.safetensors", "model.layers.10.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00012.safetensors", "model.layers.10.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00012.safetensors", "model.layers.10.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00012.safetensors", "model.layers.11.input_layernorm.weight": "model-00003-of-00012.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00012.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00012.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00012.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00012.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00012.safetensors", "model.layers.11.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00012.safetensors", "model.layers.11.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00012.safetensors", "model.layers.11.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00012.safetensors", "model.layers.11.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00012.safetensors", "model.layers.11.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00012.safetensors", "model.layers.11.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00012.safetensors", "model.layers.11.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00012.safetensors", "model.layers.11.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00012.safetensors", "model.layers.11.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00012.safetensors", "model.layers.12.input_layernorm.weight": "model-00003-of-00012.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00012.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00012.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00012.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00012.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00012.safetensors", "model.layers.12.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00012.safetensors", "model.layers.12.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00012.safetensors", "model.layers.12.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00012.safetensors", "model.layers.12.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00012.safetensors", "model.layers.12.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00012.safetensors", "model.layers.12.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00012.safetensors", "model.layers.12.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00012.safetensors", "model.layers.12.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00012.safetensors", "model.layers.12.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00012.safetensors", "model.layers.13.input_layernorm.weight": "model-00003-of-00012.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00012.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00012.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00012.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00012.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00012.safetensors", "model.layers.13.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00012.safetensors", "model.layers.13.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00012.safetensors", "model.layers.13.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00012.safetensors", "model.layers.13.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00012.safetensors", "model.layers.13.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00012.safetensors", "model.layers.13.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00012.safetensors", "model.layers.13.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00012.safetensors", "model.layers.13.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00012.safetensors", "model.layers.13.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00012.safetensors", "model.layers.14.input_layernorm.weight": "model-00003-of-00012.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00012.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00012.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00012.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00012.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00012.safetensors", "model.layers.14.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00012.safetensors", "model.layers.14.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00012.safetensors", "model.layers.14.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00012.safetensors", "model.layers.14.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00012.safetensors", "model.layers.14.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00012.safetensors", "model.layers.14.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00012.safetensors", "model.layers.14.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00012.safetensors", "model.layers.14.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00012.safetensors", "model.layers.14.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00012.safetensors", "model.layers.15.input_layernorm.weight": "model-00004-of-00012.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00012.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00012.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00012.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00012.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00012.safetensors", "model.layers.15.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00012.safetensors", "model.layers.15.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00012.safetensors", "model.layers.15.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00012.safetensors", "model.layers.15.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00012.safetensors", "model.layers.15.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00012.safetensors", "model.layers.15.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00012.safetensors", "model.layers.15.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00012.safetensors", "model.layers.15.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00012.safetensors", "model.layers.15.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00012.safetensors", "model.layers.16.input_layernorm.weight": "model-00004-of-00012.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00012.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00012.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00012.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00012.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00012.safetensors", "model.layers.16.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00012.safetensors", "model.layers.16.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00012.safetensors", "model.layers.16.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00012.safetensors", "model.layers.16.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00012.safetensors", "model.layers.16.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00012.safetensors", "model.layers.16.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00012.safetensors", "model.layers.16.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00012.safetensors", "model.layers.16.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00012.safetensors", "model.layers.16.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00012.safetensors", "model.layers.17.input_layernorm.weight": "model-00004-of-00012.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00012.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00012.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00012.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00012.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00012.safetensors", "model.layers.17.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00012.safetensors", "model.layers.17.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00012.safetensors", "model.layers.17.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00012.safetensors", "model.layers.17.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00012.safetensors", "model.layers.17.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00012.safetensors", "model.layers.17.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00012.safetensors", "model.layers.17.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00012.safetensors", "model.layers.17.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00012.safetensors", "model.layers.17.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00012.safetensors", "model.layers.18.input_layernorm.weight": "model-00004-of-00012.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00012.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00012.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00012.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00012.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00004-of-00012.safetensors", "model.layers.18.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00012.safetensors", "model.layers.18.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00012.safetensors", "model.layers.18.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00012.safetensors", "model.layers.18.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00012.safetensors", "model.layers.18.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00012.safetensors", "model.layers.18.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00012.safetensors", "model.layers.18.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00012.safetensors", "model.layers.18.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00012.safetensors", "model.layers.18.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00012.safetensors", "model.layers.19.input_layernorm.weight": "model-00004-of-00012.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00004-of-00012.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00004-of-00012.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00004-of-00012.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00004-of-00012.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00004-of-00012.safetensors", "model.layers.19.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00012.safetensors", "model.layers.19.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00012.safetensors", "model.layers.19.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00012.safetensors", "model.layers.19.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00012.safetensors", "model.layers.19.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00012.safetensors", "model.layers.19.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00012.safetensors", "model.layers.19.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00012.safetensors", "model.layers.19.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00012.safetensors", "model.layers.19.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00012.safetensors", "model.layers.20.input_layernorm.weight": "model-00005-of-00012.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00005-of-00012.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00005-of-00012.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00005-of-00012.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00005-of-00012.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00005-of-00012.safetensors", "model.layers.20.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00012.safetensors", "model.layers.20.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00012.safetensors", "model.layers.20.block_sparse_moe.experts.2.w3.weight": "model-00005-of-00012.safetensors", "model.layers.20.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00012.safetensors", "model.layers.20.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00012.safetensors", "model.layers.20.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00012.safetensors", "model.layers.20.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00012.safetensors", "model.layers.20.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00012.safetensors", "model.layers.20.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00012.safetensors", "model.layers.21.input_layernorm.weight": "model-00005-of-00012.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00005-of-00012.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00005-of-00012.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00005-of-00012.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00005-of-00012.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00005-of-00012.safetensors", "model.layers.21.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00012.safetensors", "model.layers.21.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00012.safetensors", "model.layers.21.block_sparse_moe.experts.2.w3.weight": "model-00005-of-00012.safetensors", "model.layers.21.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00012.safetensors", "model.layers.21.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00012.safetensors", "model.layers.21.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00012.safetensors", "model.layers.21.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00012.safetensors", "model.layers.21.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00012.safetensors", "model.layers.21.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00012.safetensors", "model.layers.22.input_layernorm.weight": "model-00005-of-00012.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00005-of-00012.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00005-of-00012.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00005-of-00012.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00005-of-00012.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00005-of-00012.safetensors", "model.layers.22.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00012.safetensors", "model.layers.22.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00012.safetensors", "model.layers.22.block_sparse_moe.experts.2.w3.weight": "model-00005-of-00012.safetensors", "model.layers.22.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00012.safetensors", "model.layers.22.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00012.safetensors", "model.layers.22.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00012.safetensors", "model.layers.22.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00012.safetensors", "model.layers.22.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00012.safetensors", "model.layers.22.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00012.safetensors", "model.layers.23.input_layernorm.weight": "model-00005-of-00012.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00005-of-00012.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00005-of-00012.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00005-of-00012.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00005-of-00012.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00005-of-00012.safetensors", "model.layers.23.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00012.safetensors", "model.layers.23.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00012.safetensors", "model.layers.23.block_sparse_moe.experts.2.w3.weight": "model-00005-of-00012.safetensors", "model.layers.23.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00012.safetensors", "model.layers.23.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00012.safetensors", "model.layers.23.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00012.safetensors", "model.layers.23.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00012.safetensors", "model.layers.23.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00012.safetensors", "model.layers.23.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00012.safetensors", "model.layers.24.input_layernorm.weight": "model-00005-of-00012.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00005-of-00012.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00005-of-00012.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00005-of-00012.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00005-of-00012.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00005-of-00012.safetensors", "model.layers.24.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00012.safetensors", "model.layers.24.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00012.safetensors", "model.layers.24.block_sparse_moe.experts.2.w3.weight": "model-00005-of-00012.safetensors", "model.layers.24.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00012.safetensors", "model.layers.24.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00012.safetensors", "model.layers.24.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00012.safetensors", "model.layers.24.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00012.safetensors", "model.layers.24.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00012.safetensors", "model.layers.24.block_sparse_moe.experts.2.w2.weight": "model-00006-of-00012.safetensors", "model.layers.25.input_layernorm.weight": "model-00006-of-00012.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00006-of-00012.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00006-of-00012.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00006-of-00012.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00006-of-00012.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00006-of-00012.safetensors", "model.layers.25.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00012.safetensors", "model.layers.25.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00012.safetensors", "model.layers.25.block_sparse_moe.experts.2.w3.weight": "model-00006-of-00012.safetensors", "model.layers.25.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00012.safetensors", "model.layers.25.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00012.safetensors", "model.layers.25.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00012.safetensors", "model.layers.25.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00012.safetensors", "model.layers.25.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00012.safetensors", "model.layers.25.block_sparse_moe.experts.2.w2.weight": "model-00006-of-00012.safetensors", "model.layers.26.input_layernorm.weight": "model-00006-of-00012.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00006-of-00012.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00006-of-00012.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00006-of-00012.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00006-of-00012.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00006-of-00012.safetensors", "model.layers.26.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00012.safetensors", "model.layers.26.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00012.safetensors", "model.layers.26.block_sparse_moe.experts.2.w3.weight": "model-00006-of-00012.safetensors", "model.layers.26.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00012.safetensors", "model.layers.26.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00012.safetensors", "model.layers.26.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00012.safetensors", "model.layers.26.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00012.safetensors", "model.layers.26.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00012.safetensors", "model.layers.26.block_sparse_moe.experts.2.w2.weight": "model-00006-of-00012.safetensors", "model.layers.27.input_layernorm.weight": "model-00006-of-00012.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00006-of-00012.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00006-of-00012.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00006-of-00012.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00006-of-00012.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00006-of-00012.safetensors", "model.layers.27.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00012.safetensors", "model.layers.27.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00012.safetensors", "model.layers.27.block_sparse_moe.experts.2.w3.weight": "model-00006-of-00012.safetensors", "model.layers.27.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00012.safetensors", "model.layers.27.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00012.safetensors", "model.layers.27.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00012.safetensors", "model.layers.27.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00012.safetensors", "model.layers.27.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00012.safetensors", "model.layers.27.block_sparse_moe.experts.2.w2.weight": "model-00006-of-00012.safetensors", "model.layers.28.input_layernorm.weight": "model-00006-of-00012.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00006-of-00012.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00006-of-00012.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00006-of-00012.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00006-of-00012.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00006-of-00012.safetensors", "model.layers.28.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00012.safetensors", "model.layers.28.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00012.safetensors", "model.layers.28.block_sparse_moe.experts.2.w3.weight": "model-00006-of-00012.safetensors", "model.layers.28.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00012.safetensors", "model.layers.28.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00012.safetensors", "model.layers.28.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00012.safetensors", "model.layers.28.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00012.safetensors", "model.layers.28.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00012.safetensors", "model.layers.28.block_sparse_moe.experts.2.w2.weight": "model-00006-of-00012.safetensors", "model.layers.29.input_layernorm.weight": "model-00006-of-00012.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00006-of-00012.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00006-of-00012.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00006-of-00012.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00006-of-00012.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00006-of-00012.safetensors", "model.layers.29.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00012.safetensors", "model.layers.29.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00012.safetensors", "model.layers.29.block_sparse_moe.experts.2.w3.weight": "model-00006-of-00012.safetensors", "model.layers.29.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00012.safetensors", "model.layers.29.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00012.safetensors", "model.layers.29.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00012.safetensors", "model.layers.29.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00012.safetensors", "model.layers.29.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00012.safetensors", "model.layers.29.block_sparse_moe.experts.2.w2.weight": "model-00007-of-00012.safetensors", "model.layers.30.input_layernorm.weight": "model-00007-of-00012.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00007-of-00012.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00007-of-00012.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00007-of-00012.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00007-of-00012.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00007-of-00012.safetensors", "model.layers.30.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00012.safetensors", "model.layers.30.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00012.safetensors", "model.layers.30.block_sparse_moe.experts.2.w3.weight": "model-00007-of-00012.safetensors", "model.layers.30.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00012.safetensors", "model.layers.30.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00012.safetensors", "model.layers.30.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00012.safetensors", "model.layers.30.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00012.safetensors", "model.layers.30.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00012.safetensors", "model.layers.30.block_sparse_moe.experts.2.w2.weight": "model-00007-of-00012.safetensors", "model.layers.31.input_layernorm.weight": "model-00007-of-00012.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00007-of-00012.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00007-of-00012.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00007-of-00012.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00007-of-00012.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00007-of-00012.safetensors", "model.layers.31.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00012.safetensors", "model.layers.31.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00012.safetensors", "model.layers.31.block_sparse_moe.experts.2.w3.weight": "model-00007-of-00012.safetensors", "model.layers.31.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00012.safetensors", "model.layers.31.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00012.safetensors", "model.layers.31.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00012.safetensors", "model.layers.31.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00012.safetensors", "model.layers.31.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00012.safetensors", "model.layers.31.block_sparse_moe.experts.2.w2.weight": "model-00007-of-00012.safetensors", "model.layers.32.input_layernorm.weight": "model-00007-of-00012.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00007-of-00012.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00007-of-00012.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00007-of-00012.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00007-of-00012.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00007-of-00012.safetensors", "model.layers.32.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00012.safetensors", "model.layers.32.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00012.safetensors", "model.layers.32.block_sparse_moe.experts.2.w3.weight": "model-00007-of-00012.safetensors", "model.layers.32.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00012.safetensors", "model.layers.32.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00012.safetensors", "model.layers.32.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00012.safetensors", "model.layers.32.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00012.safetensors", "model.layers.32.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00012.safetensors", "model.layers.32.block_sparse_moe.experts.2.w2.weight": "model-00007-of-00012.safetensors", "model.layers.33.input_layernorm.weight": "model-00007-of-00012.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00007-of-00012.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00007-of-00012.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00007-of-00012.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00007-of-00012.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00007-of-00012.safetensors", "model.layers.33.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00012.safetensors", "model.layers.33.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00012.safetensors", "model.layers.33.block_sparse_moe.experts.2.w3.weight": "model-00007-of-00012.safetensors", "model.layers.33.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00012.safetensors", "model.layers.33.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00012.safetensors", "model.layers.33.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00012.safetensors", "model.layers.33.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00012.safetensors", "model.layers.33.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00012.safetensors", "model.layers.33.block_sparse_moe.experts.2.w2.weight": "model-00007-of-00012.safetensors", "model.layers.34.input_layernorm.weight": "model-00007-of-00012.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00007-of-00012.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00007-of-00012.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00007-of-00012.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00007-of-00012.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00007-of-00012.safetensors", "model.layers.34.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00012.safetensors", "model.layers.34.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00012.safetensors", "model.layers.34.block_sparse_moe.experts.2.w3.weight": "model-00007-of-00012.safetensors", "model.layers.34.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00012.safetensors", "model.layers.34.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00012.safetensors", "model.layers.34.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00012.safetensors", "model.layers.34.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00012.safetensors", "model.layers.34.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00012.safetensors", "model.layers.34.block_sparse_moe.experts.2.w2.weight": "model-00008-of-00012.safetensors", "model.layers.35.input_layernorm.weight": "model-00008-of-00012.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00008-of-00012.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00008-of-00012.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00008-of-00012.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00008-of-00012.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00008-of-00012.safetensors", "model.layers.35.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00012.safetensors", "model.layers.35.block_sparse_moe.experts.1.w3.weight": "model-00008-of-00012.safetensors", "model.layers.35.block_sparse_moe.experts.2.w3.weight": "model-00008-of-00012.safetensors", "model.layers.35.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00012.safetensors", "model.layers.35.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00012.safetensors", "model.layers.35.block_sparse_moe.experts.2.w1.weight": "model-00008-of-00012.safetensors", "model.layers.35.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00012.safetensors", "model.layers.35.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00012.safetensors", "model.layers.35.block_sparse_moe.experts.2.w2.weight": "model-00008-of-00012.safetensors", "model.layers.36.input_layernorm.weight": "model-00008-of-00012.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00008-of-00012.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00008-of-00012.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00008-of-00012.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00008-of-00012.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00008-of-00012.safetensors", "model.layers.36.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00012.safetensors", "model.layers.36.block_sparse_moe.experts.1.w3.weight": "model-00008-of-00012.safetensors", "model.layers.36.block_sparse_moe.experts.2.w3.weight": "model-00008-of-00012.safetensors", "model.layers.36.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00012.safetensors", "model.layers.36.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00012.safetensors", "model.layers.36.block_sparse_moe.experts.2.w1.weight": "model-00008-of-00012.safetensors", "model.layers.36.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00012.safetensors", "model.layers.36.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00012.safetensors", "model.layers.36.block_sparse_moe.experts.2.w2.weight": "model-00008-of-00012.safetensors", "model.layers.37.input_layernorm.weight": "model-00008-of-00012.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00008-of-00012.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00008-of-00012.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00008-of-00012.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00008-of-00012.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00008-of-00012.safetensors", "model.layers.37.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00012.safetensors", "model.layers.37.block_sparse_moe.experts.1.w3.weight": "model-00008-of-00012.safetensors", "model.layers.37.block_sparse_moe.experts.2.w3.weight": "model-00008-of-00012.safetensors", "model.layers.37.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00012.safetensors", "model.layers.37.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00012.safetensors", "model.layers.37.block_sparse_moe.experts.2.w1.weight": "model-00008-of-00012.safetensors", "model.layers.37.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00012.safetensors", "model.layers.37.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00012.safetensors", "model.layers.37.block_sparse_moe.experts.2.w2.weight": "model-00008-of-00012.safetensors", "model.layers.38.input_layernorm.weight": "model-00008-of-00012.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00008-of-00012.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00008-of-00012.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00008-of-00012.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00008-of-00012.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00008-of-00012.safetensors", "model.layers.38.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00012.safetensors", "model.layers.38.block_sparse_moe.experts.1.w3.weight": "model-00008-of-00012.safetensors", "model.layers.38.block_sparse_moe.experts.2.w3.weight": "model-00008-of-00012.safetensors", "model.layers.38.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00012.safetensors", "model.layers.38.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00012.safetensors", "model.layers.38.block_sparse_moe.experts.2.w1.weight": "model-00008-of-00012.safetensors", "model.layers.38.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00012.safetensors", "model.layers.38.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00012.safetensors", "model.layers.38.block_sparse_moe.experts.2.w2.weight": "model-00008-of-00012.safetensors", "model.layers.39.input_layernorm.weight": "model-00008-of-00012.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00008-of-00012.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00008-of-00012.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00008-of-00012.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00008-of-00012.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00008-of-00012.safetensors", "model.layers.39.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00012.safetensors", "model.layers.39.block_sparse_moe.experts.1.w3.weight": "model-00008-of-00012.safetensors", "model.layers.39.block_sparse_moe.experts.2.w3.weight": "model-00008-of-00012.safetensors", "model.layers.39.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00012.safetensors", "model.layers.39.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00012.safetensors", "model.layers.39.block_sparse_moe.experts.2.w1.weight": "model-00008-of-00012.safetensors", "model.layers.39.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00012.safetensors", "model.layers.39.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00012.safetensors", "model.layers.39.block_sparse_moe.experts.2.w2.weight": "model-00009-of-00012.safetensors", "model.layers.40.input_layernorm.weight": "model-00009-of-00012.safetensors", "model.layers.40.self_attn.q_proj.weight": "model-00009-of-00012.safetensors", "model.layers.40.self_attn.k_proj.weight": "model-00009-of-00012.safetensors", "model.layers.40.self_attn.v_proj.weight": "model-00009-of-00012.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00009-of-00012.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00009-of-00012.safetensors", "model.layers.40.block_sparse_moe.experts.0.w3.weight": "model-00009-of-00012.safetensors", "model.layers.40.block_sparse_moe.experts.1.w3.weight": "model-00009-of-00012.safetensors", "model.layers.40.block_sparse_moe.experts.2.w3.weight": "model-00009-of-00012.safetensors", "model.layers.40.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00012.safetensors", "model.layers.40.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00012.safetensors", "model.layers.40.block_sparse_moe.experts.2.w1.weight": "model-00009-of-00012.safetensors", "model.layers.40.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00012.safetensors", "model.layers.40.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00012.safetensors", "model.layers.40.block_sparse_moe.experts.2.w2.weight": "model-00009-of-00012.safetensors", "model.layers.41.input_layernorm.weight": "model-00009-of-00012.safetensors", "model.layers.41.self_attn.q_proj.weight": "model-00009-of-00012.safetensors", "model.layers.41.self_attn.k_proj.weight": "model-00009-of-00012.safetensors", "model.layers.41.self_attn.v_proj.weight": "model-00009-of-00012.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00009-of-00012.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00009-of-00012.safetensors", "model.layers.41.block_sparse_moe.experts.0.w3.weight": "model-00009-of-00012.safetensors", "model.layers.41.block_sparse_moe.experts.1.w3.weight": "model-00009-of-00012.safetensors", "model.layers.41.block_sparse_moe.experts.2.w3.weight": "model-00009-of-00012.safetensors", "model.layers.41.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00012.safetensors", "model.layers.41.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00012.safetensors", "model.layers.41.block_sparse_moe.experts.2.w1.weight": "model-00009-of-00012.safetensors", "model.layers.41.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00012.safetensors", "model.layers.41.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00012.safetensors", "model.layers.41.block_sparse_moe.experts.2.w2.weight": "model-00009-of-00012.safetensors", "model.layers.42.input_layernorm.weight": "model-00009-of-00012.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00009-of-00012.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00009-of-00012.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00009-of-00012.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00009-of-00012.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00009-of-00012.safetensors", "model.layers.42.block_sparse_moe.experts.0.w3.weight": "model-00009-of-00012.safetensors", "model.layers.42.block_sparse_moe.experts.1.w3.weight": "model-00009-of-00012.safetensors", "model.layers.42.block_sparse_moe.experts.2.w3.weight": "model-00009-of-00012.safetensors", "model.layers.42.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00012.safetensors", "model.layers.42.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00012.safetensors", "model.layers.42.block_sparse_moe.experts.2.w1.weight": "model-00009-of-00012.safetensors", "model.layers.42.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00012.safetensors", "model.layers.42.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00012.safetensors", "model.layers.42.block_sparse_moe.experts.2.w2.weight": "model-00009-of-00012.safetensors", "model.layers.43.input_layernorm.weight": "model-00009-of-00012.safetensors", "model.layers.43.self_attn.q_proj.weight": "model-00009-of-00012.safetensors", "model.layers.43.self_attn.k_proj.weight": "model-00009-of-00012.safetensors", "model.layers.43.self_attn.v_proj.weight": "model-00009-of-00012.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00009-of-00012.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00009-of-00012.safetensors", "model.layers.43.block_sparse_moe.experts.0.w3.weight": "model-00009-of-00012.safetensors", "model.layers.43.block_sparse_moe.experts.1.w3.weight": "model-00009-of-00012.safetensors", "model.layers.43.block_sparse_moe.experts.2.w3.weight": "model-00009-of-00012.safetensors", "model.layers.43.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00012.safetensors", "model.layers.43.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00012.safetensors", "model.layers.43.block_sparse_moe.experts.2.w1.weight": "model-00009-of-00012.safetensors", "model.layers.43.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00012.safetensors", "model.layers.43.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00012.safetensors", "model.layers.43.block_sparse_moe.experts.2.w2.weight": "model-00009-of-00012.safetensors", "model.layers.44.input_layernorm.weight": "model-00009-of-00012.safetensors", "model.layers.44.self_attn.q_proj.weight": "model-00009-of-00012.safetensors", "model.layers.44.self_attn.k_proj.weight": "model-00009-of-00012.safetensors", "model.layers.44.self_attn.v_proj.weight": "model-00009-of-00012.safetensors", "model.layers.44.self_attn.o_proj.weight": "model-00009-of-00012.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00009-of-00012.safetensors", "model.layers.44.block_sparse_moe.experts.0.w3.weight": "model-00009-of-00012.safetensors", "model.layers.44.block_sparse_moe.experts.1.w3.weight": "model-00009-of-00012.safetensors", "model.layers.44.block_sparse_moe.experts.2.w3.weight": "model-00009-of-00012.safetensors", "model.layers.44.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00012.safetensors", "model.layers.44.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00012.safetensors", "model.layers.44.block_sparse_moe.experts.2.w1.weight": "model-00009-of-00012.safetensors", "model.layers.44.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00012.safetensors", "model.layers.44.block_sparse_moe.experts.1.w2.weight": "model-00010-of-00012.safetensors", "model.layers.44.block_sparse_moe.experts.2.w2.weight": "model-00010-of-00012.safetensors", "model.layers.45.input_layernorm.weight": "model-00010-of-00012.safetensors", "model.layers.45.self_attn.q_proj.weight": "model-00010-of-00012.safetensors", "model.layers.45.self_attn.k_proj.weight": "model-00010-of-00012.safetensors", "model.layers.45.self_attn.v_proj.weight": "model-00010-of-00012.safetensors", "model.layers.45.self_attn.o_proj.weight": "model-00010-of-00012.safetensors", "model.layers.45.post_attention_layernorm.weight": "model-00010-of-00012.safetensors", "model.layers.45.block_sparse_moe.experts.0.w3.weight": "model-00010-of-00012.safetensors", "model.layers.45.block_sparse_moe.experts.1.w3.weight": "model-00010-of-00012.safetensors", "model.layers.45.block_sparse_moe.experts.2.w3.weight": "model-00010-of-00012.safetensors", "model.layers.45.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00012.safetensors", "model.layers.45.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00012.safetensors", "model.layers.45.block_sparse_moe.experts.2.w1.weight": "model-00010-of-00012.safetensors", "model.layers.45.block_sparse_moe.experts.0.w2.weight": "model-00010-of-00012.safetensors", "model.layers.45.block_sparse_moe.experts.1.w2.weight": "model-00010-of-00012.safetensors", "model.layers.45.block_sparse_moe.experts.2.w2.weight": "model-00010-of-00012.safetensors", "model.layers.46.input_layernorm.weight": "model-00010-of-00012.safetensors", "model.layers.46.self_attn.q_proj.weight": "model-00010-of-00012.safetensors", "model.layers.46.self_attn.k_proj.weight": "model-00010-of-00012.safetensors", "model.layers.46.self_attn.v_proj.weight": "model-00010-of-00012.safetensors", "model.layers.46.self_attn.o_proj.weight": "model-00010-of-00012.safetensors", "model.layers.46.post_attention_layernorm.weight": "model-00010-of-00012.safetensors", "model.layers.46.block_sparse_moe.experts.0.w3.weight": "model-00010-of-00012.safetensors", "model.layers.46.block_sparse_moe.experts.1.w3.weight": "model-00010-of-00012.safetensors", "model.layers.46.block_sparse_moe.experts.2.w3.weight": "model-00010-of-00012.safetensors", "model.layers.46.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00012.safetensors", "model.layers.46.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00012.safetensors", "model.layers.46.block_sparse_moe.experts.2.w1.weight": "model-00010-of-00012.safetensors", "model.layers.46.block_sparse_moe.experts.0.w2.weight": "model-00010-of-00012.safetensors", "model.layers.46.block_sparse_moe.experts.1.w2.weight": "model-00010-of-00012.safetensors", "model.layers.46.block_sparse_moe.experts.2.w2.weight": "model-00010-of-00012.safetensors", "model.layers.47.input_layernorm.weight": "model-00010-of-00012.safetensors", "model.layers.47.self_attn.q_proj.weight": "model-00010-of-00012.safetensors", "model.layers.47.self_attn.k_proj.weight": "model-00010-of-00012.safetensors", "model.layers.47.self_attn.v_proj.weight": "model-00010-of-00012.safetensors", "model.layers.47.self_attn.o_proj.weight": "model-00010-of-00012.safetensors", "model.layers.47.post_attention_layernorm.weight": "model-00010-of-00012.safetensors", "model.layers.47.block_sparse_moe.experts.0.w3.weight": "model-00010-of-00012.safetensors", "model.layers.47.block_sparse_moe.experts.1.w3.weight": "model-00010-of-00012.safetensors", "model.layers.47.block_sparse_moe.experts.2.w3.weight": "model-00010-of-00012.safetensors", "model.layers.47.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00012.safetensors", "model.layers.47.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00012.safetensors", "model.layers.47.block_sparse_moe.experts.2.w1.weight": "model-00010-of-00012.safetensors", "model.layers.47.block_sparse_moe.experts.0.w2.weight": "model-00010-of-00012.safetensors", "model.layers.47.block_sparse_moe.experts.1.w2.weight": "model-00010-of-00012.safetensors", "model.layers.47.block_sparse_moe.experts.2.w2.weight": "model-00010-of-00012.safetensors", "model.layers.48.input_layernorm.weight": "model-00010-of-00012.safetensors", "model.layers.48.self_attn.q_proj.weight": "model-00010-of-00012.safetensors", "model.layers.48.self_attn.k_proj.weight": "model-00010-of-00012.safetensors", "model.layers.48.self_attn.v_proj.weight": "model-00010-of-00012.safetensors", "model.layers.48.self_attn.o_proj.weight": "model-00010-of-00012.safetensors", "model.layers.48.post_attention_layernorm.weight": "model-00010-of-00012.safetensors", "model.layers.48.block_sparse_moe.experts.0.w3.weight": "model-00010-of-00012.safetensors", "model.layers.48.block_sparse_moe.experts.1.w3.weight": "model-00010-of-00012.safetensors", "model.layers.48.block_sparse_moe.experts.2.w3.weight": "model-00010-of-00012.safetensors", "model.layers.48.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00012.safetensors", "model.layers.48.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00012.safetensors", "model.layers.48.block_sparse_moe.experts.2.w1.weight": "model-00010-of-00012.safetensors", "model.layers.48.block_sparse_moe.experts.0.w2.weight": "model-00010-of-00012.safetensors", "model.layers.48.block_sparse_moe.experts.1.w2.weight": "model-00010-of-00012.safetensors", "model.layers.48.block_sparse_moe.experts.2.w2.weight": "model-00010-of-00012.safetensors", "model.layers.49.input_layernorm.weight": "model-00010-of-00012.safetensors", "model.layers.49.self_attn.q_proj.weight": "model-00010-of-00012.safetensors", "model.layers.49.self_attn.k_proj.weight": "model-00010-of-00012.safetensors", "model.layers.49.self_attn.v_proj.weight": "model-00010-of-00012.safetensors", "model.layers.49.self_attn.o_proj.weight": "model-00010-of-00012.safetensors", "model.layers.49.post_attention_layernorm.weight": "model-00010-of-00012.safetensors", "model.layers.49.block_sparse_moe.experts.0.w3.weight": "model-00010-of-00012.safetensors", "model.layers.49.block_sparse_moe.experts.1.w3.weight": "model-00010-of-00012.safetensors", "model.layers.49.block_sparse_moe.experts.2.w3.weight": "model-00010-of-00012.safetensors", "model.layers.49.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00012.safetensors", "model.layers.49.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00012.safetensors", "model.layers.49.block_sparse_moe.experts.2.w1.weight": "model-00010-of-00012.safetensors", "model.layers.49.block_sparse_moe.experts.0.w2.weight": "model-00010-of-00012.safetensors", "model.layers.49.block_sparse_moe.experts.1.w2.weight": "model-00011-of-00012.safetensors", "model.layers.49.block_sparse_moe.experts.2.w2.weight": "model-00011-of-00012.safetensors", "model.layers.50.input_layernorm.weight": "model-00011-of-00012.safetensors", "model.layers.50.self_attn.q_proj.weight": "model-00011-of-00012.safetensors", "model.layers.50.self_attn.k_proj.weight": "model-00011-of-00012.safetensors", "model.layers.50.self_attn.v_proj.weight": "model-00011-of-00012.safetensors", "model.layers.50.self_attn.o_proj.weight": "model-00011-of-00012.safetensors", "model.layers.50.post_attention_layernorm.weight": "model-00011-of-00012.safetensors", "model.layers.50.block_sparse_moe.experts.0.w3.weight": "model-00011-of-00012.safetensors", "model.layers.50.block_sparse_moe.experts.1.w3.weight": "model-00011-of-00012.safetensors", "model.layers.50.block_sparse_moe.experts.2.w3.weight": "model-00011-of-00012.safetensors", "model.layers.50.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00012.safetensors", "model.layers.50.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00012.safetensors", "model.layers.50.block_sparse_moe.experts.2.w1.weight": "model-00011-of-00012.safetensors", "model.layers.50.block_sparse_moe.experts.0.w2.weight": "model-00011-of-00012.safetensors", "model.layers.50.block_sparse_moe.experts.1.w2.weight": "model-00011-of-00012.safetensors", "model.layers.50.block_sparse_moe.experts.2.w2.weight": "model-00011-of-00012.safetensors", "model.layers.51.input_layernorm.weight": "model-00011-of-00012.safetensors", "model.layers.51.self_attn.q_proj.weight": "model-00011-of-00012.safetensors", "model.layers.51.self_attn.k_proj.weight": "model-00011-of-00012.safetensors", "model.layers.51.self_attn.v_proj.weight": "model-00011-of-00012.safetensors", "model.layers.51.self_attn.o_proj.weight": "model-00011-of-00012.safetensors", "model.layers.51.post_attention_layernorm.weight": "model-00011-of-00012.safetensors", "model.layers.51.block_sparse_moe.experts.0.w3.weight": "model-00011-of-00012.safetensors", "model.layers.51.block_sparse_moe.experts.1.w3.weight": "model-00011-of-00012.safetensors", "model.layers.51.block_sparse_moe.experts.2.w3.weight": "model-00011-of-00012.safetensors", "model.layers.51.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00012.safetensors", "model.layers.51.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00012.safetensors", "model.layers.51.block_sparse_moe.experts.2.w1.weight": "model-00011-of-00012.safetensors", "model.layers.51.block_sparse_moe.experts.0.w2.weight": "model-00011-of-00012.safetensors", "model.layers.51.block_sparse_moe.experts.1.w2.weight": "model-00011-of-00012.safetensors", "model.layers.51.block_sparse_moe.experts.2.w2.weight": "model-00011-of-00012.safetensors", "model.layers.52.input_layernorm.weight": "model-00011-of-00012.safetensors", "model.layers.52.self_attn.q_proj.weight": "model-00011-of-00012.safetensors", "model.layers.52.self_attn.k_proj.weight": "model-00011-of-00012.safetensors", "model.layers.52.self_attn.v_proj.weight": "model-00011-of-00012.safetensors", "model.layers.52.self_attn.o_proj.weight": "model-00011-of-00012.safetensors", "model.layers.52.post_attention_layernorm.weight": "model-00011-of-00012.safetensors", "model.layers.52.block_sparse_moe.experts.0.w3.weight": "model-00011-of-00012.safetensors", "model.layers.52.block_sparse_moe.experts.1.w3.weight": "model-00011-of-00012.safetensors", "model.layers.52.block_sparse_moe.experts.2.w3.weight": "model-00011-of-00012.safetensors", "model.layers.52.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00012.safetensors", "model.layers.52.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00012.safetensors", "model.layers.52.block_sparse_moe.experts.2.w1.weight": "model-00011-of-00012.safetensors", "model.layers.52.block_sparse_moe.experts.0.w2.weight": "model-00011-of-00012.safetensors", "model.layers.52.block_sparse_moe.experts.1.w2.weight": "model-00011-of-00012.safetensors", "model.layers.52.block_sparse_moe.experts.2.w2.weight": "model-00011-of-00012.safetensors", "model.layers.53.input_layernorm.weight": "model-00011-of-00012.safetensors", "model.layers.53.self_attn.q_proj.weight": "model-00011-of-00012.safetensors", "model.layers.53.self_attn.k_proj.weight": "model-00011-of-00012.safetensors", "model.layers.53.self_attn.v_proj.weight": "model-00011-of-00012.safetensors", "model.layers.53.self_attn.o_proj.weight": "model-00011-of-00012.safetensors", "model.layers.53.post_attention_layernorm.weight": "model-00011-of-00012.safetensors", "model.layers.53.block_sparse_moe.experts.0.w3.weight": "model-00011-of-00012.safetensors", "model.layers.53.block_sparse_moe.experts.1.w3.weight": "model-00011-of-00012.safetensors", "model.layers.53.block_sparse_moe.experts.2.w3.weight": "model-00011-of-00012.safetensors", "model.layers.53.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00012.safetensors", "model.layers.53.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00012.safetensors", "model.layers.53.block_sparse_moe.experts.2.w1.weight": "model-00011-of-00012.safetensors", "model.layers.53.block_sparse_moe.experts.0.w2.weight": "model-00011-of-00012.safetensors", "model.layers.53.block_sparse_moe.experts.1.w2.weight": "model-00011-of-00012.safetensors", "model.layers.53.block_sparse_moe.experts.2.w2.weight": "model-00011-of-00012.safetensors", "model.layers.54.input_layernorm.weight": "model-00011-of-00012.safetensors", "model.layers.54.self_attn.q_proj.weight": "model-00011-of-00012.safetensors", "model.layers.54.self_attn.k_proj.weight": "model-00011-of-00012.safetensors", "model.layers.54.self_attn.v_proj.weight": "model-00011-of-00012.safetensors", "model.layers.54.self_attn.o_proj.weight": "model-00011-of-00012.safetensors", "model.layers.54.post_attention_layernorm.weight": "model-00011-of-00012.safetensors", "model.layers.54.block_sparse_moe.experts.0.w3.weight": "model-00011-of-00012.safetensors", "model.layers.54.block_sparse_moe.experts.1.w3.weight": "model-00011-of-00012.safetensors", "model.layers.54.block_sparse_moe.experts.2.w3.weight": "model-00011-of-00012.safetensors", "model.layers.54.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00012.safetensors", "model.layers.54.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00012.safetensors", "model.layers.54.block_sparse_moe.experts.2.w1.weight": "model-00011-of-00012.safetensors", "model.layers.54.block_sparse_moe.experts.0.w2.weight": "model-00011-of-00012.safetensors", "model.layers.54.block_sparse_moe.experts.1.w2.weight": "model-00012-of-00012.safetensors", "model.layers.54.block_sparse_moe.experts.2.w2.weight": "model-00012-of-00012.safetensors", "model.layers.55.input_layernorm.weight": "model-00012-of-00012.safetensors", "model.layers.55.self_attn.q_proj.weight": "model-00012-of-00012.safetensors", "model.layers.55.self_attn.k_proj.weight": "model-00012-of-00012.safetensors", "model.layers.55.self_attn.v_proj.weight": "model-00012-of-00012.safetensors", "model.layers.55.self_attn.o_proj.weight": "model-00012-of-00012.safetensors", "model.layers.55.post_attention_layernorm.weight": "model-00012-of-00012.safetensors", "model.layers.55.block_sparse_moe.experts.0.w3.weight": "model-00012-of-00012.safetensors", "model.layers.55.block_sparse_moe.experts.1.w3.weight": "model-00012-of-00012.safetensors", "model.layers.55.block_sparse_moe.experts.2.w3.weight": "model-00012-of-00012.safetensors", "model.layers.55.block_sparse_moe.experts.0.w1.weight": "model-00012-of-00012.safetensors", "model.layers.55.block_sparse_moe.experts.1.w1.weight": "model-00012-of-00012.safetensors", "model.layers.55.block_sparse_moe.experts.2.w1.weight": "model-00012-of-00012.safetensors", "model.layers.55.block_sparse_moe.experts.0.w2.weight": "model-00012-of-00012.safetensors", "model.layers.55.block_sparse_moe.experts.1.w2.weight": "model-00012-of-00012.safetensors", "model.layers.55.block_sparse_moe.experts.2.w2.weight": "model-00012-of-00012.safetensors", "model.norm.weight": "model-00012-of-00012.safetensors", "lm_head.weight": "model-00012-of-00012.safetensors", "model.layers.0.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.1.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.2.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.3.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.4.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.5.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.6.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.7.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.8.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.9.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.10.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.11.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.12.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.13.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.14.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.15.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.16.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.17.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.18.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.19.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.20.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.21.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.22.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.23.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.24.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.25.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.26.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.27.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.28.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.29.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.30.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.31.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.32.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.33.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.34.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.35.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.36.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.37.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.38.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.39.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.40.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.41.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.42.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.43.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.44.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.45.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.46.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.47.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.48.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.49.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.50.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.51.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.52.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.53.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.54.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.55.block_sparse_moe.gate.weight": "model-00012-of-00012.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 sha256:37f00374dea48658ee8f5d0f21895b9bc55cb0103939607c8185bfd1c6ca1f89
+size 587404

tokenizer_config.json

@@ -0,0 +1,42 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": true,
+  "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
+    }
+  },
+  "bos_token": "<s>",
+  "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
+}