Pruned out layers producing chinese characters.

config.json

@@ -1,33 +1,33 @@
-{
-  "_name_or_path": ".\\BlackSheep-MoE",
-  "architectures": [
-    "MixtralForCausalLM"
-  ],
-  "attention_dropout": 0.0,
-  "bos_token_id": null,
-  "eos_token_id": 151645,
-  "hidden_act": "silu",
-  "hidden_size": 3584,
-  "initializer_range": 0.02,
-  "intermediate_size": 18944,
-  "max_position_embeddings": 32768,
-  "max_window_layers": 28,
-  "model_type": "mixtral",
-  "num_attention_heads": 28,
-  "num_experts_per_tok": 1,
-  "num_hidden_layers": 20,
-  "num_key_value_heads": 4,
-  "num_local_experts": 2,
-  "output_router_logits": false,
-  "rms_norm_eps": 1e-06,
-  "rope_theta": 1000000.0,
-  "router_aux_loss_coef": 0.001,
-  "router_jitter_noise": 0.0,
-  "sliding_window": null,
-  "tie_word_embeddings": false,
-  "torch_dtype": "float16",
-  "transformers_version": "4.41.2",
-  "use_cache": false,
-  "use_sliding_window": false,
-  "vocab_size": 152064
-}
+{
+  "_name_or_path": ".\\BlackSheep-MoE",
+  "architectures": [
+    "MixtralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": null,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "model_type": "mixtral",
+  "num_attention_heads": 28,
+  "num_experts_per_tok": 2,
+  "num_hidden_layers": 17,
+  "num_key_value_heads": 4,
+  "num_local_experts": 2,
+  "output_router_logits": false,
+  "rms_norm_eps": 1e-06,
+  "rope_theta": 1000000.0,
+  "router_aux_loss_coef": 0.001,
+  "router_jitter_noise": 0.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.41.2",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

model-00001-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef151602acf0f95d502d8e4a8fdf27b9e0f9249fa3b9e527f77e20370940b6d0
+oid sha256:667e79ab682b9cb0956681b1e4d53de560699c0499013a656bd35f3443a1616d
 size 4914287784

model-00002-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8bcddf8a464f9c4746d17854a80b51e63adc57dd690f3e3ced2534f553550935
+oid sha256:8c717c584bb48930aba0515c76ad16b74d0ce0878b5ff7eb4bc7a0d022f77688
 size 4969382968

model-00003-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:101661eade49244efdd8a0a191eff98b72ea3703f4ef21281ffb44eae23786f6
+oid sha256:4e216114216998a9a4fc7e7809c9fdc008fd875a27ece20dcb97941dd6223a70
 size 4910633320

model-00004-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e188e939431596e5aee1e5e5565b783beed9a5317a5e4aa2c1cf0ad98a55f121
-size 4855574480
+oid sha256:da48b7145b735271391719cdd29626a7554782de430277af13607cb70fd89a37
+size 2235092232

model.safetensors.index.json

@@ -1,6 +1,6 @@
 {
   "metadata": {
-    "total_size": 19649846272
+    "total_size": 17029368832
   },
   "weight_map": {
     "lm_head.weight": "model-00004-of-00004.safetensors",
@@ -122,45 +122,6 @@
     "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
     "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
     "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.17.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00004.safetensors",
-    "model.layers.17.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00004.safetensors",
-    "model.layers.17.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00004.safetensors",
-    "model.layers.17.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00004.safetensors",
-    "model.layers.17.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00004.safetensors",
-    "model.layers.17.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00004.safetensors",
-    "model.layers.17.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors",
-    "model.layers.17.input_layernorm.weight": "model-00004-of-00004.safetensors",
-    "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
-    "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.18.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00004.safetensors",
-    "model.layers.18.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00004.safetensors",
-    "model.layers.18.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00004.safetensors",
-    "model.layers.18.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00004.safetensors",
-    "model.layers.18.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00004.safetensors",
-    "model.layers.18.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00004.safetensors",
-    "model.layers.18.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors",
-    "model.layers.18.input_layernorm.weight": "model-00004-of-00004.safetensors",
-    "model.layers.18.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
-    "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.19.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00004.safetensors",
-    "model.layers.19.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00004.safetensors",
-    "model.layers.19.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00004.safetensors",
-    "model.layers.19.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00004.safetensors",
-    "model.layers.19.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00004.safetensors",
-    "model.layers.19.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00004.safetensors",
-    "model.layers.19.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors",
-    "model.layers.19.input_layernorm.weight": "model-00004-of-00004.safetensors",
-    "model.layers.19.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
-    "model.layers.19.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.19.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.19.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.19.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
     "model.layers.2.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00004.safetensors",
     "model.layers.2.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00004.safetensors",
     "model.layers.2.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00004.safetensors",