Upload folder using huggingface_hub

config.json

@@ -0,0 +1,36 @@
+{
+  "_name_or_path": "tokyotech-llm/Swallow-7b-instruct-v0.1",
+  "architectures": [
+    "MixtralForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 4096,
+  "max_sequence_length": 4096,
+  "model_type": "mixtral",
+  "num_attention_heads": 32,
+  "num_experts_per_tok": 2,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 32,
+  "num_local_experts": 4,
+  "output_router_logits": false,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "router_aux_loss_coef": 0.001,
+  "router_jitter_noise": 0.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.40.0",
+  "use_cache": true,
+  "vocab_size": 43176
+}

mergekit_moe_config.yml

@@ -0,0 +1,22 @@
+base_model: tokyotech-llm/Swallow-7b-instruct-v0.1 #tokyotech-llm/Swallow-7b-instruct-v0.1
+gate_mode: hidden # one of "hidden", "cheap_embed", or "random"
+dtype: bfloat16 # output dtype (float32, float16, or bfloat16)
+## (optional)
+experts_per_token: 2
+experts:
+  - source_model: tokyotech-llm/Swallow-7b-instruct-v0.1 #okyotech-llm/Swallow-7b-instruct-v0.1
+    positive_prompts:
+      - "日本語でのマルチターンの質問回答の専門家です。"
+
+  - source_model: elyza/ELYZA-japanese-Llama-2-7b-fast-instruct #https://huggingface.co/elyza/ELYZA-japanese-Llama-2-7b-fast-instruct
+    positive_prompts:
+      - "日本語でのQ&Aの専門家です。"
+
+  - source_model: elyza/ELYZA-japanese-CodeLlama-7b-instruct #https://huggingface.co/elyza/ELYZA-japanese-CodeLlama-7b-instruct
+    positive_prompts:
+      - "コーディングの専門家です。"
+
+  - source_model: meta-math/MetaMath-7B-V1.0 #https://huggingface.co/meta-math/MetaMath-7B-V1.0
+    positive_prompts:
+      - "Math(数学)の専門家です。"
+

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba0d877a780cccf23ac0681ace867f9d1525824d660c01bcc22ca55c296bae27
+size 9994454768

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f840adcdab54be2caee1cf05ff110e361cf7d467bf0208516a8a7ba683e3ef19
+size 9955347120

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d24fbc7fb263cb01cbfac6789a74a64444ee0adb189774af7a296d0aac9fe065
+size 9911290008

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f6a0c134f369f92f4762d5fa866496313b47afa396f1deed1cb02524d3b96d6
+size 9771103072

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.4.2", "total_size": 39632117760}, "weight_map": {"model.embed_tokens.weight": "model-00001-of-00004.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.0.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00004.safetensors", "model.layers.0.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00004.safetensors", "model.layers.0.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00004.safetensors", "model.layers.0.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00004.safetensors", "model.layers.0.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00004.safetensors", "model.layers.0.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00004.safetensors", "model.layers.0.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00004.safetensors", "model.layers.0.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00004.safetensors", "model.layers.0.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00004.safetensors", "model.layers.0.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00004.safetensors", "model.layers.0.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00004.safetensors", "model.layers.0.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00004.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.1.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00004.safetensors", "model.layers.1.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00004.safetensors", "model.layers.1.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00004.safetensors", "model.layers.1.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00004.safetensors", "model.layers.1.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00004.safetensors", "model.layers.1.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00004.safetensors", "model.layers.1.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00004.safetensors", "model.layers.1.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00004.safetensors", "model.layers.1.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00004.safetensors", "model.layers.1.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00004.safetensors", "model.layers.1.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00004.safetensors", "model.layers.1.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00004.safetensors", "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.2.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00004.safetensors", "model.layers.2.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00004.safetensors", "model.layers.2.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00004.safetensors", "model.layers.2.block_sparse_moe.experts.3.w3.weight": "model-00001-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.1.w1.weight": "model-00001-of-00004.safetensors", "model.layers.2.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00004.safetensors", "model.layers.2.block_sparse_moe.experts.3.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.1.w2.weight": "model-00001-of-00004.safetensors", "model.layers.2.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00004.safetensors", "model.layers.2.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00004.safetensors", "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.3.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00004.safetensors", "model.layers.3.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00004.safetensors", "model.layers.3.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00004.safetensors", "model.layers.3.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00004.safetensors", "model.layers.3.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00004.safetensors", "model.layers.3.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00004.safetensors", "model.layers.3.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00004.safetensors", "model.layers.3.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00004.safetensors", "model.layers.3.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00004.safetensors", "model.layers.3.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00004.safetensors", "model.layers.3.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00004.safetensors", "model.layers.3.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00004.safetensors", "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.4.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00004.safetensors", "model.layers.4.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00004.safetensors", "model.layers.4.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00004.safetensors", "model.layers.4.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00004.safetensors", "model.layers.4.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00004.safetensors", "model.layers.4.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00004.safetensors", "model.layers.4.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00004.safetensors", "model.layers.4.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00004.safetensors", "model.layers.4.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00004.safetensors", "model.layers.4.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00004.safetensors", "model.layers.4.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00004.safetensors", "model.layers.4.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00004.safetensors", "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.5.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00004.safetensors", "model.layers.5.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00004.safetensors", "model.layers.5.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00004.safetensors", "model.layers.5.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00004.safetensors", "model.layers.5.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00004.safetensors", "model.layers.5.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00004.safetensors", "model.layers.5.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00004.safetensors", "model.layers.5.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00004.safetensors", "model.layers.5.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00004.safetensors", "model.layers.5.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00004.safetensors", "model.layers.5.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00004.safetensors", "model.layers.5.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00004.safetensors", "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.6.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00004.safetensors", "model.layers.6.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00004.safetensors", "model.layers.6.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00004.safetensors", "model.layers.6.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00004.safetensors", "model.layers.6.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00004.safetensors", "model.layers.6.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00004.safetensors", "model.layers.6.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00004.safetensors", "model.layers.6.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00004.safetensors", "model.layers.6.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00004.safetensors", "model.layers.6.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00004.safetensors", "model.layers.6.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00004.safetensors", "model.layers.6.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00004.safetensors", "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.7.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00004.safetensors", "model.layers.7.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00004.safetensors", "model.layers.7.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00004.safetensors", "model.layers.7.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00004.safetensors", "model.layers.7.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00004.safetensors", "model.layers.7.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00004.safetensors", "model.layers.7.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00004.safetensors", "model.layers.7.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00004.safetensors", "model.layers.7.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00004.safetensors", "model.layers.7.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00004.safetensors", "model.layers.7.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00004.safetensors", "model.layers.7.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00004.safetensors", "model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.8.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00004.safetensors", "model.layers.8.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00004.safetensors", "model.layers.8.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00004.safetensors", "model.layers.8.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00004.safetensors", "model.layers.8.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00004.safetensors", "model.layers.8.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00004.safetensors", "model.layers.8.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00004.safetensors", "model.layers.8.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00004.safetensors", "model.layers.8.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00004.safetensors", "model.layers.8.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00004.safetensors", "model.layers.8.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00004.safetensors", "model.layers.8.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00004.safetensors", "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.9.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00004.safetensors", "model.layers.9.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00004.safetensors", "model.layers.9.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00004.safetensors", "model.layers.9.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00004.safetensors", "model.layers.9.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00004.safetensors", "model.layers.9.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00004.safetensors", "model.layers.9.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00004.safetensors", "model.layers.9.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00004.safetensors", "model.layers.9.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00004.safetensors", "model.layers.9.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00004.safetensors", "model.layers.9.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00004.safetensors", "model.layers.9.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00004.safetensors", "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.10.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00004.safetensors", "model.layers.10.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00004.safetensors", "model.layers.10.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00004.safetensors", "model.layers.10.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00004.safetensors", "model.layers.10.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00004.safetensors", "model.layers.10.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00004.safetensors", "model.layers.10.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00004.safetensors", "model.layers.10.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00004.safetensors", "model.layers.10.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00004.safetensors", "model.layers.10.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00004.safetensors", "model.layers.10.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00004.safetensors", "model.layers.10.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00004.safetensors", "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.11.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00004.safetensors", "model.layers.11.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00004.safetensors", "model.layers.11.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00004.safetensors", "model.layers.11.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00004.safetensors", "model.layers.11.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00004.safetensors", "model.layers.11.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00004.safetensors", "model.layers.11.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00004.safetensors", "model.layers.11.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00004.safetensors", "model.layers.11.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00004.safetensors", "model.layers.11.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00004.safetensors", "model.layers.11.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00004.safetensors", "model.layers.11.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00004.safetensors", "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.12.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00004.safetensors", "model.layers.12.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00004.safetensors", "model.layers.12.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00004.safetensors", "model.layers.12.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00004.safetensors", "model.layers.12.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00004.safetensors", "model.layers.12.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00004.safetensors", "model.layers.12.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00004.safetensors", "model.layers.12.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00004.safetensors", "model.layers.12.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00004.safetensors", "model.layers.12.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00004.safetensors", "model.layers.12.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00004.safetensors", "model.layers.12.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00004.safetensors", "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.13.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00004.safetensors", "model.layers.13.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00004.safetensors", "model.layers.13.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00004.safetensors", "model.layers.13.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00004.safetensors", "model.layers.13.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00004.safetensors", "model.layers.13.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00004.safetensors", "model.layers.13.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00004.safetensors", "model.layers.13.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00004.safetensors", "model.layers.13.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00004.safetensors", "model.layers.13.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00004.safetensors", "model.layers.13.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00004.safetensors", "model.layers.13.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00004.safetensors", "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.14.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00004.safetensors", "model.layers.14.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00004.safetensors", "model.layers.14.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00004.safetensors", "model.layers.14.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00004.safetensors", "model.layers.14.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00004.safetensors", "model.layers.14.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00004.safetensors", "model.layers.14.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00004.safetensors", "model.layers.14.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00004.safetensors", "model.layers.14.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00004.safetensors", "model.layers.14.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00004.safetensors", "model.layers.14.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00004.safetensors", "model.layers.14.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00004.safetensors", "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.15.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00004.safetensors", "model.layers.15.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00004.safetensors", "model.layers.15.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00004.safetensors", "model.layers.15.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00004.safetensors", "model.layers.15.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00004.safetensors", "model.layers.15.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00004.safetensors", "model.layers.15.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00004.safetensors", "model.layers.15.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00004.safetensors", "model.layers.15.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00004.safetensors", "model.layers.15.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00004.safetensors", "model.layers.15.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00004.safetensors", "model.layers.15.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00004.safetensors", "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.16.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00004.safetensors", "model.layers.16.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00004.safetensors", "model.layers.16.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00004.safetensors", "model.layers.16.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00004.safetensors", "model.layers.16.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00004.safetensors", "model.layers.16.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00004.safetensors", "model.layers.16.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00004.safetensors", "model.layers.16.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00004.safetensors", "model.layers.16.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00004.safetensors", "model.layers.16.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00004.safetensors", "model.layers.16.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00004.safetensors", "model.layers.16.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00004.safetensors", "model.layers.17.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.17.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00004.safetensors", "model.layers.17.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00004.safetensors", "model.layers.17.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00004.safetensors", "model.layers.17.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00004.safetensors", "model.layers.17.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00004.safetensors", "model.layers.17.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00004.safetensors", "model.layers.17.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00004.safetensors", "model.layers.17.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00004.safetensors", "model.layers.17.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00004.safetensors", "model.layers.17.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00004.safetensors", "model.layers.17.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00004.safetensors", "model.layers.17.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00004.safetensors", "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.18.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00004.safetensors", "model.layers.18.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00004.safetensors", "model.layers.18.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00004.safetensors", "model.layers.18.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00004.safetensors", "model.layers.18.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00004.safetensors", "model.layers.18.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00004.safetensors", "model.layers.18.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00004.safetensors", "model.layers.18.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00004.safetensors", "model.layers.18.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00004.safetensors", "model.layers.18.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00004.safetensors", "model.layers.18.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00004.safetensors", "model.layers.18.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00004.safetensors", "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.19.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00004.safetensors", "model.layers.19.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00004.safetensors", "model.layers.19.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00004.safetensors", "model.layers.19.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00004.safetensors", "model.layers.19.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00004.safetensors", "model.layers.19.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00004.safetensors", "model.layers.19.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00004.safetensors", "model.layers.19.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00004.safetensors", "model.layers.19.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00004.safetensors", "model.layers.19.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00004.safetensors", "model.layers.19.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00004.safetensors", "model.layers.19.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00004.safetensors", "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.20.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00004.safetensors", "model.layers.20.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00004.safetensors", "model.layers.20.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00004.safetensors", "model.layers.20.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00004.safetensors", "model.layers.20.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00004.safetensors", "model.layers.20.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00004.safetensors", "model.layers.20.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00004.safetensors", "model.layers.20.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00004.safetensors", "model.layers.20.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00004.safetensors", "model.layers.20.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00004.safetensors", "model.layers.20.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00004.safetensors", "model.layers.20.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00004.safetensors", "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.21.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00004.safetensors", "model.layers.21.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00004.safetensors", "model.layers.21.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00004.safetensors", "model.layers.21.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00004.safetensors", "model.layers.21.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00004.safetensors", "model.layers.21.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00004.safetensors", "model.layers.21.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00004.safetensors", "model.layers.21.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00004.safetensors", "model.layers.21.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00004.safetensors", "model.layers.21.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00004.safetensors", "model.layers.21.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00004.safetensors", "model.layers.21.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00004.safetensors", "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.22.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00004.safetensors", "model.layers.22.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00004.safetensors", "model.layers.22.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00004.safetensors", "model.layers.22.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00004.safetensors", "model.layers.22.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00004.safetensors", "model.layers.22.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00004.safetensors", "model.layers.22.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00004.safetensors", "model.layers.22.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00004.safetensors", "model.layers.22.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00004.safetensors", "model.layers.22.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00004.safetensors", "model.layers.22.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00004.safetensors", "model.layers.22.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00004.safetensors", "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.23.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00004.safetensors", "model.layers.23.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00004.safetensors", "model.layers.23.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00004.safetensors", "model.layers.23.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00004.safetensors", "model.layers.23.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00004.safetensors", "model.layers.23.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00004.safetensors", "model.layers.23.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00004.safetensors", "model.layers.23.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00004.safetensors", "model.layers.23.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00004.safetensors", "model.layers.23.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00004.safetensors", "model.layers.23.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00004.safetensors", "model.layers.23.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00004.safetensors", "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.24.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00004.safetensors", "model.layers.24.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00004.safetensors", "model.layers.24.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00004.safetensors", "model.layers.24.block_sparse_moe.experts.3.w3.weight": "model-00004-of-00004.safetensors", "model.layers.24.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00004.safetensors", "model.layers.24.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00004.safetensors", "model.layers.24.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00004.safetensors", "model.layers.24.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00004.safetensors", "model.layers.24.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00004.safetensors", "model.layers.24.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00004.safetensors", "model.layers.24.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00004.safetensors", "model.layers.24.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00004.safetensors", "model.layers.25.input_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.25.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00004.safetensors", "model.layers.25.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00004.safetensors", "model.layers.25.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00004.safetensors", "model.layers.25.block_sparse_moe.experts.3.w3.weight": "model-00004-of-00004.safetensors", "model.layers.25.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00004.safetensors", "model.layers.25.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00004.safetensors", "model.layers.25.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00004.safetensors", "model.layers.25.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00004.safetensors", "model.layers.25.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00004.safetensors", "model.layers.25.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00004.safetensors", "model.layers.25.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00004.safetensors", "model.layers.25.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00004.safetensors", "model.layers.26.input_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.26.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00004.safetensors", "model.layers.26.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00004.safetensors", "model.layers.26.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00004.safetensors", "model.layers.26.block_sparse_moe.experts.3.w3.weight": "model-00004-of-00004.safetensors", "model.layers.26.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00004.safetensors", "model.layers.26.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00004.safetensors", "model.layers.26.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00004.safetensors", "model.layers.26.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00004.safetensors", "model.layers.26.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00004.safetensors", "model.layers.26.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00004.safetensors", "model.layers.26.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00004.safetensors", "model.layers.26.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00004.safetensors", "model.layers.27.input_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.27.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00004.safetensors", "model.layers.27.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00004.safetensors", "model.layers.27.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00004.safetensors", "model.layers.27.block_sparse_moe.experts.3.w3.weight": "model-00004-of-00004.safetensors", "model.layers.27.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00004.safetensors", "model.layers.27.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00004.safetensors", "model.layers.27.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00004.safetensors", "model.layers.27.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00004.safetensors", "model.layers.27.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00004.safetensors", "model.layers.27.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00004.safetensors", "model.layers.27.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00004.safetensors", "model.layers.27.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00004.safetensors", "model.layers.28.input_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.28.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00004.safetensors", "model.layers.28.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00004.safetensors", "model.layers.28.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00004.safetensors", "model.layers.28.block_sparse_moe.experts.3.w3.weight": "model-00004-of-00004.safetensors", "model.layers.28.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00004.safetensors", "model.layers.28.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00004.safetensors", "model.layers.28.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00004.safetensors", "model.layers.28.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00004.safetensors", "model.layers.28.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00004.safetensors", "model.layers.28.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00004.safetensors", "model.layers.28.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00004.safetensors", "model.layers.28.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00004.safetensors", "model.layers.29.input_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.29.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00004.safetensors", "model.layers.29.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00004.safetensors", "model.layers.29.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00004.safetensors", "model.layers.29.block_sparse_moe.experts.3.w3.weight": "model-00004-of-00004.safetensors", "model.layers.29.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00004.safetensors", "model.layers.29.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00004.safetensors", "model.layers.29.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00004.safetensors", "model.layers.29.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00004.safetensors", "model.layers.29.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00004.safetensors", "model.layers.29.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00004.safetensors", "model.layers.29.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00004.safetensors", "model.layers.29.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00004.safetensors", "model.layers.30.input_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.30.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00004.safetensors", "model.layers.30.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00004.safetensors", "model.layers.30.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00004.safetensors", "model.layers.30.block_sparse_moe.experts.3.w3.weight": "model-00004-of-00004.safetensors", "model.layers.30.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00004.safetensors", "model.layers.30.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00004.safetensors", "model.layers.30.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00004.safetensors", "model.layers.30.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00004.safetensors", "model.layers.30.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00004.safetensors", "model.layers.30.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00004.safetensors", "model.layers.30.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00004.safetensors", "model.layers.30.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00004.safetensors", "model.layers.31.input_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.31.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00004.safetensors", "model.layers.31.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00004.safetensors", "model.layers.31.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00004.safetensors", "model.layers.31.block_sparse_moe.experts.3.w3.weight": "model-00004-of-00004.safetensors", "model.layers.31.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00004.safetensors", "model.layers.31.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00004.safetensors", "model.layers.31.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00004.safetensors", "model.layers.31.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00004.safetensors", "model.layers.31.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00004.safetensors", "model.layers.31.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00004.safetensors", "model.layers.31.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00004.safetensors", "model.layers.31.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00004.safetensors", "model.norm.weight": "model-00004-of-00004.safetensors", "lm_head.weight": "model-00004-of-00004.safetensors", "model.layers.0.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.1.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.2.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.3.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.4.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.5.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.6.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.7.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.8.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.9.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.10.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.11.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.12.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.13.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.14.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.15.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.16.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.17.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.18.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.19.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.20.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.21.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.22.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.23.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.24.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.25.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.26.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.27.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.28.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.29.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.30.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.31.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors"}}

special_tokens_map.json

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

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c877c5ca885bad5c19d1b1706a2703f8b30de90f03c1f834f8bdb9faf79821e8
+size 914000

tokenizer_config.json

@@ -0,0 +1,46 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "chat_template": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% elif false == true and not '<<SYS>>' in messages[0]['content'] %}{% set loop_messages = messages %}{% set system_message = 'あなたは誠実で優秀な日本人のアシスタントです。' %}{% else %}{% set loop_messages = messages %}{% set system_message = false %}{% endif %}{{ bos_token }}{% for message in loop_messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if loop.index0 == 0 and system_message != false %}{% set content = '<<SYS>>\\n' + system_message + '\\n<</SYS>>\\n\\n' + message['content'] %}{% else %}{% set content = message['content'] %}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + content.strip() + ' [/INST] ' }}{% elif message['role'] == 'system' %}{{ '<<SYS>>\\n' + content.strip() + '\\n<</SYS>>\\n\\n' }}{% elif message['role'] == 'assistant' %}{{ ''  + content.strip() + '' + eos_token }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "max_length": 4096,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<s>",
+  "padding_side": "left",
+  "sp_model_kwargs": {},
+  "stride": 0,
+  "tokenizer_class": "LlamaTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}