train 4bit 1 epoch

config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "cloudyu/Mixtral_7Bx2_MoE",
+  "architectures": [
+    "MixtralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 32768,
+  "model_type": "mixtral",
+  "num_attention_heads": 32,
+  "num_experts_per_tok": 2,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "num_local_experts": 2,
+  "output_router_logits": false,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 10000.0,
+  "router_aux_loss_coef": 0.001,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.37.1",
+  "use_cache": true,
+  "vocab_size": 32000
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.37.1"
+}

model-00001-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:28938ab49bd341932347b1f74c7aa394f570a3d3855def66fa48eb24842cfda3
+size 4993525264

model-00002-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77c1bd0a05958f45008b6c552700e16cca172313b331622ef50965c7cba3e5d6
+size 4932724880

model-00003-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8d7bb59062fafa01e3e32fe0e12cb080dd00ec5462578a8967b65975b48935c
+size 4966262528

model-00004-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:498e8dbdd9793203a6dbbff3a41e1553151405c02c5e3c247427971d1513eb9d
+size 4966262528

model-00005-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7677c8366e6a9b92022758b03b770c7d244f10096247af767ea6812ac2e124dd
+size 4932741544

model-00006-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:46484066c58c859745364ace7ab7716b74842aa307d7e375ef85ffb9bf653788
+size 966812872

model.safetensors.index.json

@@ -0,0 +1,426 @@
+{
+  "metadata": {
+    "total_size": 25758277632
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00006-of-00006.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.block_sparse_moe.gate.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.block_sparse_moe.gate.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.10.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.block_sparse_moe.gate.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.block_sparse_moe.gate.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.block_sparse_moe.gate.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.block_sparse_moe.gate.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.block_sparse_moe.gate.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.block_sparse_moe.gate.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.block_sparse_moe.gate.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.block_sparse_moe.gate.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.block_sparse_moe.gate.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.block_sparse_moe.gate.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.2.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.block_sparse_moe.gate.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.20.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.block_sparse_moe.gate.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.block_sparse_moe.gate.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.block_sparse_moe.gate.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.block_sparse_moe.gate.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00006.safetensors",
+    "model.layers.24.block_sparse_moe.gate.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.block_sparse_moe.gate.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.block_sparse_moe.gate.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.block_sparse_moe.gate.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.block_sparse_moe.gate.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.block_sparse_moe.gate.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.3.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.block_sparse_moe.gate.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.30.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00006.safetensors",
+    "model.layers.30.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00006.safetensors",
+    "model.layers.30.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00006.safetensors",
+    "model.layers.30.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00006.safetensors",
+    "model.layers.30.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00006.safetensors",
+    "model.layers.30.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00006.safetensors",
+    "model.layers.30.block_sparse_moe.gate.weight": "model-00005-of-00006.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.31.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.block_sparse_moe.gate.weight": "model-00005-of-00006.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.4.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.block_sparse_moe.gate.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.block_sparse_moe.gate.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.6.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.block_sparse_moe.gate.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.block_sparse_moe.gate.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.block_sparse_moe.gate.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.block_sparse_moe.gate.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.norm.weight": "model-00006-of-00006.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,35 @@
+{
+  "additional_special_tokens": [
+    "<unk>",
+    "<s>",
+    "</s>"
+  ],
+  "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": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,51 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<unk>",
+    "<s>",
+    "</s>"
+  ],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "max_length": null,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_to_multiple_of": null,
+  "pad_token": "<s>",
+  "pad_token_type_id": 0,
+  "padding_side": "left",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "split_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}