Upload folder using huggingface_hub

config.json

@@ -0,0 +1,35 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 6,
+  "eos_token_id": 7,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 4096,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_experts_per_tok": 2,
+  "num_hidden_layers": 48,
+  "num_key_value_heads": 4,
+  "num_local_experts": 2,
+  "output_router_logits": false,
+  "pad_token_id": 7,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 5000000.0,
+  "router_aux_loss_coef": 0.001,
+  "router_jitter_noise": 0.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.43.0.dev0",
+  "use_cache": false,
+  "vocab_size": 64000
+}

model-00001-of-00032.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de28ca984b6b34be5a2f5c488ba7d8183d6f2181b0b9f126690738f4f7a5d6a1
+size 960513328

model-00002-of-00032.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a4dc41b83a91c10380d3e5ac079e7ab46773aa63b12e43d59be9b9bd99bb41d
+size 962628080

model-00003-of-00032.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:240088ab5c6d2dc3e2fe07e01216479e44b5ba1e245382251d0610881f9d26e2
+size 977291208

model-00004-of-00032.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6aa3cc975bfacea8efc43f973ebe29ad2bbf1f5b8f00e887b5dd145e799befb9
+size 962628080

model-00005-of-00032.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69ba754d81e4f0f84b79a679c576243c3ba737d7ad4ad1a55e9ee1b2edaf6cf0
+size 977299512

model-00006-of-00032.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:098dd48b88f6f6e8aba29f3d9fb5eda09e0f51085ebae104c7b975dedecb9983
+size 962619776

model-00007-of-00032.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f00d67f19984b50c622ae4b81d69501b025edc296f37bf6cd608f7347bdca348
+size 962628056

model-00008-of-00032.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a0be06d93edb597980e7a1477c167536acc5d8e1b60a41296dd56e8c0f30981
+size 977291224

model-00009-of-00032.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:698b48e3187c9cd1a58e29669f7062c624bc42de78b7182e76a98037b4cad945
+size 962628104

model-00010-of-00032.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87eea2347bbca199b66d7a6663b7a554c1e90491c46ccf45b7510bef157923bb
+size 977291224

model-00011-of-00032.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:13dc292a949cbce42e7967536e1f9ac5e6303edc5cda92ac5f7a2c10ba975241
+size 962628104

model-00012-of-00032.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5cc944d5a68b7cadc45820ac11ea0d9aca296fdcb74e2b7d3e2bf04c84f9e0ec
+size 977299528

model-00013-of-00032.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fcc17043a11715b6eb7166ef26db87241fad7c7f4021f1de34a9f680b2630c57
+size 962619800

model-00014-of-00032.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2329277bb59b93fb586edd3f0eac13854b3de78ec9222ca688da1fa9e6a1bcb8
+size 962628104

model-00015-of-00032.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ad06a08e8be64d34133076c9613ed81c7a8af07281144fd9c02f87b8b275beb
+size 977291224

model-00016-of-00032.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab8a34fff12b1b687c595484bdf02eb869f835ebd75f18eb9fb5e9fcdc250488
+size 962628104

model-00017-of-00032.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b9683ee06771b66daca0c1be2f430dabb4894462b15f899bd155697eff01fb24
+size 977291224

model-00018-of-00032.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4cbe794c40ffa8be720d133c719946b5ce859c5d8e58de5e2a5c3bf150128aaa
+size 962628104

model-00019-of-00032.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf5e0a2c4e6f5313443442ec0d385557d8b2b5a34eeb78b4bf20926a220f7e50
+size 977299528

model-00020-of-00032.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:734984359e17da180e138acd527dd923a552ee93400cf059a3f03e488e1c47c9
+size 962619800

model-00021-of-00032.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3fc1314c8b163b22e3ea1621bf3da1bb60945c1e481b4f8bdb1bbc7d1b4df7c4
+size 962628104

model-00022-of-00032.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8947ab7cf391427a820a485a91d2a52a31505ffdd4ef359b41c45bca561fcfd2
+size 977291224

model-00023-of-00032.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:607da176c9afe8849d4562b65807429e0bad20157f972527828b363fd4b1e89a
+size 962628104

model-00024-of-00032.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:676ae3da892dd15e086f04c6ac9d3e44079eafce81dd7a8a77f6735376edb9ba
+size 977291224

model-00025-of-00032.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41a4a47f4d6a65cb2e8859bd5b3f01c67978ec8fa606ae8d20b311870c0e1dac
+size 962628104

model-00026-of-00032.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5fe8c4e7478042c7cafe49d3cb7fb665f0264f93d584bda8bcfdeacef639e9f3
+size 977299528

model-00027-of-00032.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dff721b26ad4917f87c7b30379bc35f35b66c07d6c365fe6d9b47b46fbc912f9
+size 962619800

model-00028-of-00032.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93837c3b3e2b5771ea13d5ce1c0fb1b5146a40aff9259fd5c27d354a75cf3d2b
+size 962628104

model-00029-of-00032.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e714af55c5034c47de66557f1cd49b790979afb646ff546693bd67375be27ed5
+size 977291224

model-00030-of-00032.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce413342549bf226f2a887f7a4b1b46bddc20ba01badb0d66dd9e60caf40e45b
+size 962628104

model-00031-of-00032.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b58efff2f6a07bdffbdaf9176c1d60e3bf0cf28fcada63352fbc6bd5caf88db2
+size 977291224

model-00032-of-00032.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12c4185709894f9bba7dd9b5761ad5c3d39415a7cc25e3410b86dce745b027b3
+size 615266112

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"total_size": 30645166080}, "weight_map": {"model.embed_tokens.weight": "model-00001-of-00032.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00032.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00032.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00032.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00032.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00032.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00032.safetensors", "model.layers.0.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00032.safetensors", "model.layers.0.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00032.safetensors", "model.layers.0.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00032.safetensors", "model.layers.0.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00032.safetensors", "model.layers.0.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00032.safetensors", "model.layers.0.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00032.safetensors", "model.layers.1.input_layernorm.weight": "model-00002-of-00032.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00032.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00032.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00032.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00032.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00032.safetensors", "model.layers.1.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00032.safetensors", "model.layers.1.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00032.safetensors", "model.layers.1.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00032.safetensors", "model.layers.1.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00032.safetensors", "model.layers.1.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00032.safetensors", "model.layers.1.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00032.safetensors", "model.layers.2.input_layernorm.weight": "model-00002-of-00032.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00002-of-00032.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00002-of-00032.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00002-of-00032.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00002-of-00032.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00032.safetensors", "model.layers.2.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00032.safetensors", "model.layers.2.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00032.safetensors", "model.layers.2.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00032.safetensors", "model.layers.2.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00032.safetensors", "model.layers.2.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00032.safetensors", "model.layers.2.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00032.safetensors", "model.layers.3.input_layernorm.weight": "model-00003-of-00032.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00003-of-00032.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00003-of-00032.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00003-of-00032.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00003-of-00032.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00003-of-00032.safetensors", "model.layers.3.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00032.safetensors", "model.layers.3.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00032.safetensors", "model.layers.3.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00032.safetensors", "model.layers.3.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00032.safetensors", "model.layers.3.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00032.safetensors", "model.layers.3.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00032.safetensors", "model.layers.4.input_layernorm.weight": "model-00004-of-00032.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00004-of-00032.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00004-of-00032.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00004-of-00032.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00004-of-00032.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00004-of-00032.safetensors", "model.layers.4.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00032.safetensors", "model.layers.4.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00032.safetensors", "model.layers.4.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00032.safetensors", "model.layers.4.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00032.safetensors", "model.layers.4.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00032.safetensors", "model.layers.4.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00032.safetensors", "model.layers.5.input_layernorm.weight": "model-00004-of-00032.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00004-of-00032.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00004-of-00032.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00004-of-00032.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00004-of-00032.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00004-of-00032.safetensors", "model.layers.5.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00032.safetensors", "model.layers.5.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00032.safetensors", "model.layers.5.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00032.safetensors", "model.layers.5.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00032.safetensors", "model.layers.5.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00032.safetensors", "model.layers.5.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00032.safetensors", "model.layers.6.input_layernorm.weight": "model-00005-of-00032.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00005-of-00032.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00005-of-00032.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00005-of-00032.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00005-of-00032.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00005-of-00032.safetensors", "model.layers.6.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00032.safetensors", "model.layers.6.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00032.safetensors", "model.layers.6.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00032.safetensors", "model.layers.6.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00032.safetensors", "model.layers.6.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00032.safetensors", "model.layers.6.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00032.safetensors", "model.layers.7.input_layernorm.weight": "model-00005-of-00032.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00006-of-00032.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00006-of-00032.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00006-of-00032.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00006-of-00032.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00006-of-00032.safetensors", "model.layers.7.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00032.safetensors", "model.layers.7.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00032.safetensors", "model.layers.7.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00032.safetensors", "model.layers.7.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00032.safetensors", "model.layers.7.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00032.safetensors", "model.layers.7.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00032.safetensors", "model.layers.8.input_layernorm.weight": "model-00006-of-00032.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00006-of-00032.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00006-of-00032.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00006-of-00032.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00006-of-00032.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00006-of-00032.safetensors", "model.layers.8.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00032.safetensors", "model.layers.8.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00032.safetensors", "model.layers.8.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00032.safetensors", "model.layers.8.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00032.safetensors", "model.layers.8.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00032.safetensors", "model.layers.8.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00032.safetensors", "model.layers.9.input_layernorm.weight": "model-00007-of-00032.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00007-of-00032.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00007-of-00032.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00007-of-00032.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00007-of-00032.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00007-of-00032.safetensors", "model.layers.9.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00032.safetensors", "model.layers.9.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00032.safetensors", "model.layers.9.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00032.safetensors", "model.layers.9.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00032.safetensors", "model.layers.9.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00032.safetensors", "model.layers.9.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00032.safetensors", "model.layers.10.input_layernorm.weight": "model-00007-of-00032.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00007-of-00032.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00007-of-00032.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00007-of-00032.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00007-of-00032.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00007-of-00032.safetensors", "model.layers.10.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00032.safetensors", "model.layers.10.block_sparse_moe.experts.1.w3.weight": "model-00008-of-00032.safetensors", "model.layers.10.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00032.safetensors", "model.layers.10.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00032.safetensors", "model.layers.10.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00032.safetensors", "model.layers.10.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00032.safetensors", "model.layers.11.input_layernorm.weight": "model-00008-of-00032.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00008-of-00032.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00008-of-00032.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00008-of-00032.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00008-of-00032.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00008-of-00032.safetensors", "model.layers.11.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00032.safetensors", "model.layers.11.block_sparse_moe.experts.1.w3.weight": "model-00008-of-00032.safetensors", "model.layers.11.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00032.safetensors", "model.layers.11.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00032.safetensors", "model.layers.11.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00032.safetensors", "model.layers.11.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00032.safetensors", "model.layers.12.input_layernorm.weight": "model-00009-of-00032.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00009-of-00032.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00009-of-00032.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00009-of-00032.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00009-of-00032.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00009-of-00032.safetensors", "model.layers.12.block_sparse_moe.experts.0.w3.weight": "model-00009-of-00032.safetensors", "model.layers.12.block_sparse_moe.experts.1.w3.weight": "model-00009-of-00032.safetensors", "model.layers.12.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00032.safetensors", "model.layers.12.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00032.safetensors", "model.layers.12.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00032.safetensors", "model.layers.12.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00032.safetensors", "model.layers.13.input_layernorm.weight": "model-00009-of-00032.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00009-of-00032.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00009-of-00032.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00009-of-00032.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00009-of-00032.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00009-of-00032.safetensors", "model.layers.13.block_sparse_moe.experts.0.w3.weight": "model-00009-of-00032.safetensors", "model.layers.13.block_sparse_moe.experts.1.w3.weight": "model-00010-of-00032.safetensors", "model.layers.13.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00032.safetensors", "model.layers.13.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00032.safetensors", "model.layers.13.block_sparse_moe.experts.0.w2.weight": "model-00010-of-00032.safetensors", "model.layers.13.block_sparse_moe.experts.1.w2.weight": "model-00010-of-00032.safetensors", "model.layers.14.input_layernorm.weight": "model-00010-of-00032.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00010-of-00032.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00010-of-00032.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00010-of-00032.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00010-of-00032.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00010-of-00032.safetensors", "model.layers.14.block_sparse_moe.experts.0.w3.weight": "model-00010-of-00032.safetensors", "model.layers.14.block_sparse_moe.experts.1.w3.weight": "model-00010-of-00032.safetensors", "model.layers.14.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00032.safetensors", "model.layers.14.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00032.safetensors", "model.layers.14.block_sparse_moe.experts.0.w2.weight": "model-00010-of-00032.safetensors", "model.layers.14.block_sparse_moe.experts.1.w2.weight": "model-00011-of-00032.safetensors", "model.layers.15.input_layernorm.weight": "model-00011-of-00032.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00011-of-00032.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00011-of-00032.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00011-of-00032.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00011-of-00032.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00011-of-00032.safetensors", "model.layers.15.block_sparse_moe.experts.0.w3.weight": "model-00011-of-00032.safetensors", "model.layers.15.block_sparse_moe.experts.1.w3.weight": "model-00011-of-00032.safetensors", "model.layers.15.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00032.safetensors", "model.layers.15.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00032.safetensors", "model.layers.15.block_sparse_moe.experts.0.w2.weight": "model-00011-of-00032.safetensors", "model.layers.15.block_sparse_moe.experts.1.w2.weight": "model-00011-of-00032.safetensors", "model.layers.16.input_layernorm.weight": "model-00011-of-00032.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00011-of-00032.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00011-of-00032.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00011-of-00032.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00011-of-00032.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00011-of-00032.safetensors", "model.layers.16.block_sparse_moe.experts.0.w3.weight": "model-00011-of-00032.safetensors", "model.layers.16.block_sparse_moe.experts.1.w3.weight": "model-00011-of-00032.safetensors", "model.layers.16.block_sparse_moe.experts.0.w1.weight": "model-00012-of-00032.safetensors", "model.layers.16.block_sparse_moe.experts.1.w1.weight": "model-00012-of-00032.safetensors", "model.layers.16.block_sparse_moe.experts.0.w2.weight": "model-00012-of-00032.safetensors", "model.layers.16.block_sparse_moe.experts.1.w2.weight": "model-00012-of-00032.safetensors", "model.layers.17.input_layernorm.weight": "model-00012-of-00032.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00012-of-00032.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00012-of-00032.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00012-of-00032.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00012-of-00032.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00012-of-00032.safetensors", "model.layers.17.block_sparse_moe.experts.0.w3.weight": "model-00012-of-00032.safetensors", "model.layers.17.block_sparse_moe.experts.1.w3.weight": "model-00012-of-00032.safetensors", "model.layers.17.block_sparse_moe.experts.0.w1.weight": "model-00012-of-00032.safetensors", "model.layers.17.block_sparse_moe.experts.1.w1.weight": "model-00012-of-00032.safetensors", "model.layers.17.block_sparse_moe.experts.0.w2.weight": "model-00012-of-00032.safetensors", "model.layers.17.block_sparse_moe.experts.1.w2.weight": "model-00012-of-00032.safetensors", "model.layers.18.input_layernorm.weight": "model-00012-of-00032.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00013-of-00032.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00013-of-00032.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00013-of-00032.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00013-of-00032.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00013-of-00032.safetensors", "model.layers.18.block_sparse_moe.experts.0.w3.weight": "model-00013-of-00032.safetensors", "model.layers.18.block_sparse_moe.experts.1.w3.weight": "model-00013-of-00032.safetensors", "model.layers.18.block_sparse_moe.experts.0.w1.weight": "model-00013-of-00032.safetensors", "model.layers.18.block_sparse_moe.experts.1.w1.weight": "model-00013-of-00032.safetensors", "model.layers.18.block_sparse_moe.experts.0.w2.weight": "model-00013-of-00032.safetensors", "model.layers.18.block_sparse_moe.experts.1.w2.weight": "model-00013-of-00032.safetensors", "model.layers.19.input_layernorm.weight": "model-00013-of-00032.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00013-of-00032.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00013-of-00032.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00013-of-00032.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00013-of-00032.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00013-of-00032.safetensors", "model.layers.19.block_sparse_moe.experts.0.w3.weight": "model-00013-of-00032.safetensors", "model.layers.19.block_sparse_moe.experts.1.w3.weight": "model-00013-of-00032.safetensors", "model.layers.19.block_sparse_moe.experts.0.w1.weight": "model-00013-of-00032.safetensors", "model.layers.19.block_sparse_moe.experts.1.w1.weight": "model-00014-of-00032.safetensors", "model.layers.19.block_sparse_moe.experts.0.w2.weight": "model-00014-of-00032.safetensors", "model.layers.19.block_sparse_moe.experts.1.w2.weight": "model-00014-of-00032.safetensors", "model.layers.20.input_layernorm.weight": "model-00014-of-00032.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00014-of-00032.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00014-of-00032.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00014-of-00032.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00014-of-00032.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00014-of-00032.safetensors", "model.layers.20.block_sparse_moe.experts.0.w3.weight": "model-00014-of-00032.safetensors", "model.layers.20.block_sparse_moe.experts.1.w3.weight": "model-00014-of-00032.safetensors", "model.layers.20.block_sparse_moe.experts.0.w1.weight": "model-00014-of-00032.safetensors", "model.layers.20.block_sparse_moe.experts.1.w1.weight": "model-00014-of-00032.safetensors", "model.layers.20.block_sparse_moe.experts.0.w2.weight": "model-00014-of-00032.safetensors", "model.layers.20.block_sparse_moe.experts.1.w2.weight": "model-00014-of-00032.safetensors", "model.layers.21.input_layernorm.weight": "model-00014-of-00032.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00014-of-00032.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00014-of-00032.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00014-of-00032.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00014-of-00032.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00014-of-00032.safetensors", "model.layers.21.block_sparse_moe.experts.0.w3.weight": "model-00015-of-00032.safetensors", "model.layers.21.block_sparse_moe.experts.1.w3.weight": "model-00015-of-00032.safetensors", "model.layers.21.block_sparse_moe.experts.0.w1.weight": "model-00015-of-00032.safetensors", "model.layers.21.block_sparse_moe.experts.1.w1.weight": "model-00015-of-00032.safetensors", "model.layers.21.block_sparse_moe.experts.0.w2.weight": "model-00015-of-00032.safetensors", "model.layers.21.block_sparse_moe.experts.1.w2.weight": "model-00015-of-00032.safetensors", "model.layers.22.input_layernorm.weight": "model-00015-of-00032.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00015-of-00032.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00015-of-00032.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00015-of-00032.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00015-of-00032.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00015-of-00032.safetensors", "model.layers.22.block_sparse_moe.experts.0.w3.weight": "model-00015-of-00032.safetensors", "model.layers.22.block_sparse_moe.experts.1.w3.weight": "model-00015-of-00032.safetensors", "model.layers.22.block_sparse_moe.experts.0.w1.weight": "model-00015-of-00032.safetensors", "model.layers.22.block_sparse_moe.experts.1.w1.weight": "model-00015-of-00032.safetensors", "model.layers.22.block_sparse_moe.experts.0.w2.weight": "model-00016-of-00032.safetensors", "model.layers.22.block_sparse_moe.experts.1.w2.weight": "model-00016-of-00032.safetensors", "model.layers.23.input_layernorm.weight": "model-00016-of-00032.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00016-of-00032.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00016-of-00032.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00016-of-00032.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00016-of-00032.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00016-of-00032.safetensors", "model.layers.23.block_sparse_moe.experts.0.w3.weight": "model-00016-of-00032.safetensors", "model.layers.23.block_sparse_moe.experts.1.w3.weight": "model-00016-of-00032.safetensors", "model.layers.23.block_sparse_moe.experts.0.w1.weight": "model-00016-of-00032.safetensors", "model.layers.23.block_sparse_moe.experts.1.w1.weight": "model-00016-of-00032.safetensors", "model.layers.23.block_sparse_moe.experts.0.w2.weight": "model-00016-of-00032.safetensors", "model.layers.23.block_sparse_moe.experts.1.w2.weight": "model-00016-of-00032.safetensors", "model.layers.24.input_layernorm.weight": "model-00016-of-00032.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00016-of-00032.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00016-of-00032.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00016-of-00032.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00016-of-00032.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00016-of-00032.safetensors", "model.layers.24.block_sparse_moe.experts.0.w3.weight": "model-00016-of-00032.safetensors", "model.layers.24.block_sparse_moe.experts.1.w3.weight": "model-00017-of-00032.safetensors", "model.layers.24.block_sparse_moe.experts.0.w1.weight": "model-00017-of-00032.safetensors", "model.layers.24.block_sparse_moe.experts.1.w1.weight": "model-00017-of-00032.safetensors", "model.layers.24.block_sparse_moe.experts.0.w2.weight": "model-00017-of-00032.safetensors", "model.layers.24.block_sparse_moe.experts.1.w2.weight": "model-00017-of-00032.safetensors", "model.layers.25.input_layernorm.weight": "model-00017-of-00032.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00017-of-00032.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00017-of-00032.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00017-of-00032.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00017-of-00032.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00017-of-00032.safetensors", "model.layers.25.block_sparse_moe.experts.0.w3.weight": "model-00017-of-00032.safetensors", "model.layers.25.block_sparse_moe.experts.1.w3.weight": "model-00017-of-00032.safetensors", "model.layers.25.block_sparse_moe.experts.0.w1.weight": "model-00017-of-00032.safetensors", "model.layers.25.block_sparse_moe.experts.1.w1.weight": "model-00017-of-00032.safetensors", "model.layers.25.block_sparse_moe.experts.0.w2.weight": "model-00017-of-00032.safetensors", "model.layers.25.block_sparse_moe.experts.1.w2.weight": "model-00018-of-00032.safetensors", "model.layers.26.input_layernorm.weight": "model-00018-of-00032.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00018-of-00032.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00018-of-00032.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00018-of-00032.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00018-of-00032.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00018-of-00032.safetensors", "model.layers.26.block_sparse_moe.experts.0.w3.weight": "model-00018-of-00032.safetensors", "model.layers.26.block_sparse_moe.experts.1.w3.weight": "model-00018-of-00032.safetensors", "model.layers.26.block_sparse_moe.experts.0.w1.weight": "model-00018-of-00032.safetensors", "model.layers.26.block_sparse_moe.experts.1.w1.weight": "model-00018-of-00032.safetensors", "model.layers.26.block_sparse_moe.experts.0.w2.weight": "model-00018-of-00032.safetensors", "model.layers.26.block_sparse_moe.experts.1.w2.weight": "model-00018-of-00032.safetensors", "model.layers.27.input_layernorm.weight": "model-00018-of-00032.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00018-of-00032.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00018-of-00032.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00018-of-00032.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00018-of-00032.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00018-of-00032.safetensors", "model.layers.27.block_sparse_moe.experts.0.w3.weight": "model-00018-of-00032.safetensors", "model.layers.27.block_sparse_moe.experts.1.w3.weight": "model-00018-of-00032.safetensors", "model.layers.27.block_sparse_moe.experts.0.w1.weight": "model-00019-of-00032.safetensors", "model.layers.27.block_sparse_moe.experts.1.w1.weight": "model-00019-of-00032.safetensors", "model.layers.27.block_sparse_moe.experts.0.w2.weight": "model-00019-of-00032.safetensors", "model.layers.27.block_sparse_moe.experts.1.w2.weight": "model-00019-of-00032.safetensors", "model.layers.28.input_layernorm.weight": "model-00019-of-00032.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00019-of-00032.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00019-of-00032.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00019-of-00032.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00019-of-00032.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00019-of-00032.safetensors", "model.layers.28.block_sparse_moe.experts.0.w3.weight": "model-00019-of-00032.safetensors", "model.layers.28.block_sparse_moe.experts.1.w3.weight": "model-00019-of-00032.safetensors", "model.layers.28.block_sparse_moe.experts.0.w1.weight": "model-00019-of-00032.safetensors", "model.layers.28.block_sparse_moe.experts.1.w1.weight": "model-00019-of-00032.safetensors", "model.layers.28.block_sparse_moe.experts.0.w2.weight": "model-00019-of-00032.safetensors", "model.layers.28.block_sparse_moe.experts.1.w2.weight": "model-00019-of-00032.safetensors", "model.layers.29.input_layernorm.weight": "model-00019-of-00032.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00020-of-00032.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00020-of-00032.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00020-of-00032.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00020-of-00032.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00020-of-00032.safetensors", "model.layers.29.block_sparse_moe.experts.0.w3.weight": "model-00020-of-00032.safetensors", "model.layers.29.block_sparse_moe.experts.1.w3.weight": "model-00020-of-00032.safetensors", "model.layers.29.block_sparse_moe.experts.0.w1.weight": "model-00020-of-00032.safetensors", "model.layers.29.block_sparse_moe.experts.1.w1.weight": "model-00020-of-00032.safetensors", "model.layers.29.block_sparse_moe.experts.0.w2.weight": "model-00020-of-00032.safetensors", "model.layers.29.block_sparse_moe.experts.1.w2.weight": "model-00020-of-00032.safetensors", "model.layers.30.input_layernorm.weight": "model-00020-of-00032.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00020-of-00032.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00020-of-00032.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00020-of-00032.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00020-of-00032.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00020-of-00032.safetensors", "model.layers.30.block_sparse_moe.experts.0.w3.weight": "model-00020-of-00032.safetensors", "model.layers.30.block_sparse_moe.experts.1.w3.weight": "model-00020-of-00032.safetensors", "model.layers.30.block_sparse_moe.experts.0.w1.weight": "model-00020-of-00032.safetensors", "model.layers.30.block_sparse_moe.experts.1.w1.weight": "model-00021-of-00032.safetensors", "model.layers.30.block_sparse_moe.experts.0.w2.weight": "model-00021-of-00032.safetensors", "model.layers.30.block_sparse_moe.experts.1.w2.weight": "model-00021-of-00032.safetensors", "model.layers.31.input_layernorm.weight": "model-00021-of-00032.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00021-of-00032.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00021-of-00032.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00021-of-00032.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00021-of-00032.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00021-of-00032.safetensors", "model.layers.31.block_sparse_moe.experts.0.w3.weight": "model-00021-of-00032.safetensors", "model.layers.31.block_sparse_moe.experts.1.w3.weight": "model-00021-of-00032.safetensors", "model.layers.31.block_sparse_moe.experts.0.w1.weight": "model-00021-of-00032.safetensors", "model.layers.31.block_sparse_moe.experts.1.w1.weight": "model-00021-of-00032.safetensors", "model.layers.31.block_sparse_moe.experts.0.w2.weight": "model-00021-of-00032.safetensors", "model.layers.31.block_sparse_moe.experts.1.w2.weight": "model-00021-of-00032.safetensors", "model.layers.32.input_layernorm.weight": "model-00021-of-00032.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00021-of-00032.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00021-of-00032.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00021-of-00032.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00021-of-00032.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00021-of-00032.safetensors", "model.layers.32.block_sparse_moe.experts.0.w3.weight": "model-00022-of-00032.safetensors", "model.layers.32.block_sparse_moe.experts.1.w3.weight": "model-00022-of-00032.safetensors", "model.layers.32.block_sparse_moe.experts.0.w1.weight": "model-00022-of-00032.safetensors", "model.layers.32.block_sparse_moe.experts.1.w1.weight": "model-00022-of-00032.safetensors", "model.layers.32.block_sparse_moe.experts.0.w2.weight": "model-00022-of-00032.safetensors", "model.layers.32.block_sparse_moe.experts.1.w2.weight": "model-00022-of-00032.safetensors", "model.layers.33.input_layernorm.weight": "model-00022-of-00032.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00022-of-00032.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00022-of-00032.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00022-of-00032.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00022-of-00032.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00022-of-00032.safetensors", "model.layers.33.block_sparse_moe.experts.0.w3.weight": "model-00022-of-00032.safetensors", "model.layers.33.block_sparse_moe.experts.1.w3.weight": "model-00022-of-00032.safetensors", "model.layers.33.block_sparse_moe.experts.0.w1.weight": "model-00022-of-00032.safetensors", "model.layers.33.block_sparse_moe.experts.1.w1.weight": "model-00022-of-00032.safetensors", "model.layers.33.block_sparse_moe.experts.0.w2.weight": "model-00023-of-00032.safetensors", "model.layers.33.block_sparse_moe.experts.1.w2.weight": "model-00023-of-00032.safetensors", "model.layers.34.input_layernorm.weight": "model-00023-of-00032.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00023-of-00032.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00023-of-00032.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00023-of-00032.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00023-of-00032.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00023-of-00032.safetensors", "model.layers.34.block_sparse_moe.experts.0.w3.weight": "model-00023-of-00032.safetensors", "model.layers.34.block_sparse_moe.experts.1.w3.weight": "model-00023-of-00032.safetensors", "model.layers.34.block_sparse_moe.experts.0.w1.weight": "model-00023-of-00032.safetensors", "model.layers.34.block_sparse_moe.experts.1.w1.weight": "model-00023-of-00032.safetensors", "model.layers.34.block_sparse_moe.experts.0.w2.weight": "model-00023-of-00032.safetensors", "model.layers.34.block_sparse_moe.experts.1.w2.weight": "model-00023-of-00032.safetensors", "model.layers.35.input_layernorm.weight": "model-00023-of-00032.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00023-of-00032.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00023-of-00032.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00023-of-00032.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00023-of-00032.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00023-of-00032.safetensors", "model.layers.35.block_sparse_moe.experts.0.w3.weight": "model-00023-of-00032.safetensors", "model.layers.35.block_sparse_moe.experts.1.w3.weight": "model-00024-of-00032.safetensors", "model.layers.35.block_sparse_moe.experts.0.w1.weight": "model-00024-of-00032.safetensors", "model.layers.35.block_sparse_moe.experts.1.w1.weight": "model-00024-of-00032.safetensors", "model.layers.35.block_sparse_moe.experts.0.w2.weight": "model-00024-of-00032.safetensors", "model.layers.35.block_sparse_moe.experts.1.w2.weight": "model-00024-of-00032.safetensors", "model.layers.36.input_layernorm.weight": "model-00024-of-00032.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00024-of-00032.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00024-of-00032.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00024-of-00032.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00024-of-00032.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00024-of-00032.safetensors", "model.layers.36.block_sparse_moe.experts.0.w3.weight": "model-00024-of-00032.safetensors", "model.layers.36.block_sparse_moe.experts.1.w3.weight": "model-00024-of-00032.safetensors", "model.layers.36.block_sparse_moe.experts.0.w1.weight": "model-00024-of-00032.safetensors", "model.layers.36.block_sparse_moe.experts.1.w1.weight": "model-00024-of-00032.safetensors", "model.layers.36.block_sparse_moe.experts.0.w2.weight": "model-00024-of-00032.safetensors", "model.layers.36.block_sparse_moe.experts.1.w2.weight": "model-00025-of-00032.safetensors", "model.layers.37.input_layernorm.weight": "model-00025-of-00032.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00025-of-00032.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00025-of-00032.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00025-of-00032.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00025-of-00032.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00025-of-00032.safetensors", "model.layers.37.block_sparse_moe.experts.0.w3.weight": "model-00025-of-00032.safetensors", "model.layers.37.block_sparse_moe.experts.1.w3.weight": "model-00025-of-00032.safetensors", "model.layers.37.block_sparse_moe.experts.0.w1.weight": "model-00025-of-00032.safetensors", "model.layers.37.block_sparse_moe.experts.1.w1.weight": "model-00025-of-00032.safetensors", "model.layers.37.block_sparse_moe.experts.0.w2.weight": "model-00025-of-00032.safetensors", "model.layers.37.block_sparse_moe.experts.1.w2.weight": "model-00025-of-00032.safetensors", "model.layers.38.input_layernorm.weight": "model-00025-of-00032.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00025-of-00032.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00025-of-00032.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00025-of-00032.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00025-of-00032.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00025-of-00032.safetensors", "model.layers.38.block_sparse_moe.experts.0.w3.weight": "model-00025-of-00032.safetensors", "model.layers.38.block_sparse_moe.experts.1.w3.weight": "model-00025-of-00032.safetensors", "model.layers.38.block_sparse_moe.experts.0.w1.weight": "model-00026-of-00032.safetensors", "model.layers.38.block_sparse_moe.experts.1.w1.weight": "model-00026-of-00032.safetensors", "model.layers.38.block_sparse_moe.experts.0.w2.weight": "model-00026-of-00032.safetensors", "model.layers.38.block_sparse_moe.experts.1.w2.weight": "model-00026-of-00032.safetensors", "model.layers.39.input_layernorm.weight": "model-00026-of-00032.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00026-of-00032.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00026-of-00032.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00026-of-00032.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00026-of-00032.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00026-of-00032.safetensors", "model.layers.39.block_sparse_moe.experts.0.w3.weight": "model-00026-of-00032.safetensors", "model.layers.39.block_sparse_moe.experts.1.w3.weight": "model-00026-of-00032.safetensors", "model.layers.39.block_sparse_moe.experts.0.w1.weight": "model-00026-of-00032.safetensors", "model.layers.39.block_sparse_moe.experts.1.w1.weight": "model-00026-of-00032.safetensors", "model.layers.39.block_sparse_moe.experts.0.w2.weight": "model-00026-of-00032.safetensors", "model.layers.39.block_sparse_moe.experts.1.w2.weight": "model-00026-of-00032.safetensors", "model.layers.40.input_layernorm.weight": "model-00026-of-00032.safetensors", "model.layers.40.self_attn.q_proj.weight": "model-00027-of-00032.safetensors", "model.layers.40.self_attn.k_proj.weight": "model-00027-of-00032.safetensors", "model.layers.40.self_attn.v_proj.weight": "model-00027-of-00032.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00027-of-00032.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00027-of-00032.safetensors", "model.layers.40.block_sparse_moe.experts.0.w3.weight": "model-00027-of-00032.safetensors", "model.layers.40.block_sparse_moe.experts.1.w3.weight": "model-00027-of-00032.safetensors", "model.layers.40.block_sparse_moe.experts.0.w1.weight": "model-00027-of-00032.safetensors", "model.layers.40.block_sparse_moe.experts.1.w1.weight": "model-00027-of-00032.safetensors", "model.layers.40.block_sparse_moe.experts.0.w2.weight": "model-00027-of-00032.safetensors", "model.layers.40.block_sparse_moe.experts.1.w2.weight": "model-00027-of-00032.safetensors", "model.layers.41.input_layernorm.weight": "model-00027-of-00032.safetensors", "model.layers.41.self_attn.q_proj.weight": "model-00027-of-00032.safetensors", "model.layers.41.self_attn.k_proj.weight": "model-00027-of-00032.safetensors", "model.layers.41.self_attn.v_proj.weight": "model-00027-of-00032.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00027-of-00032.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00027-of-00032.safetensors", "model.layers.41.block_sparse_moe.experts.0.w3.weight": "model-00027-of-00032.safetensors", "model.layers.41.block_sparse_moe.experts.1.w3.weight": "model-00027-of-00032.safetensors", "model.layers.41.block_sparse_moe.experts.0.w1.weight": "model-00027-of-00032.safetensors", "model.layers.41.block_sparse_moe.experts.1.w1.weight": "model-00028-of-00032.safetensors", "model.layers.41.block_sparse_moe.experts.0.w2.weight": "model-00028-of-00032.safetensors", "model.layers.41.block_sparse_moe.experts.1.w2.weight": "model-00028-of-00032.safetensors", "model.layers.42.input_layernorm.weight": "model-00028-of-00032.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00028-of-00032.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00028-of-00032.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00028-of-00032.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00028-of-00032.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00028-of-00032.safetensors", "model.layers.42.block_sparse_moe.experts.0.w3.weight": "model-00028-of-00032.safetensors", "model.layers.42.block_sparse_moe.experts.1.w3.weight": "model-00028-of-00032.safetensors", "model.layers.42.block_sparse_moe.experts.0.w1.weight": "model-00028-of-00032.safetensors", "model.layers.42.block_sparse_moe.experts.1.w1.weight": "model-00028-of-00032.safetensors", "model.layers.42.block_sparse_moe.experts.0.w2.weight": "model-00028-of-00032.safetensors", "model.layers.42.block_sparse_moe.experts.1.w2.weight": "model-00028-of-00032.safetensors", "model.layers.43.input_layernorm.weight": "model-00028-of-00032.safetensors", "model.layers.43.self_attn.q_proj.weight": "model-00028-of-00032.safetensors", "model.layers.43.self_attn.k_proj.weight": "model-00028-of-00032.safetensors", "model.layers.43.self_attn.v_proj.weight": "model-00028-of-00032.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00028-of-00032.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00028-of-00032.safetensors", "model.layers.43.block_sparse_moe.experts.0.w3.weight": "model-00029-of-00032.safetensors", "model.layers.43.block_sparse_moe.experts.1.w3.weight": "model-00029-of-00032.safetensors", "model.layers.43.block_sparse_moe.experts.0.w1.weight": "model-00029-of-00032.safetensors", "model.layers.43.block_sparse_moe.experts.1.w1.weight": "model-00029-of-00032.safetensors", "model.layers.43.block_sparse_moe.experts.0.w2.weight": "model-00029-of-00032.safetensors", "model.layers.43.block_sparse_moe.experts.1.w2.weight": "model-00029-of-00032.safetensors", "model.layers.44.input_layernorm.weight": "model-00029-of-00032.safetensors", "model.layers.44.self_attn.q_proj.weight": "model-00029-of-00032.safetensors", "model.layers.44.self_attn.k_proj.weight": "model-00029-of-00032.safetensors", "model.layers.44.self_attn.v_proj.weight": "model-00029-of-00032.safetensors", "model.layers.44.self_attn.o_proj.weight": "model-00029-of-00032.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00029-of-00032.safetensors", "model.layers.44.block_sparse_moe.experts.0.w3.weight": "model-00029-of-00032.safetensors", "model.layers.44.block_sparse_moe.experts.1.w3.weight": "model-00029-of-00032.safetensors", "model.layers.44.block_sparse_moe.experts.0.w1.weight": "model-00029-of-00032.safetensors", "model.layers.44.block_sparse_moe.experts.1.w1.weight": "model-00029-of-00032.safetensors", "model.layers.44.block_sparse_moe.experts.0.w2.weight": "model-00030-of-00032.safetensors", "model.layers.44.block_sparse_moe.experts.1.w2.weight": "model-00030-of-00032.safetensors", "model.layers.45.input_layernorm.weight": "model-00030-of-00032.safetensors", "model.layers.45.self_attn.q_proj.weight": "model-00030-of-00032.safetensors", "model.layers.45.self_attn.k_proj.weight": "model-00030-of-00032.safetensors", "model.layers.45.self_attn.v_proj.weight": "model-00030-of-00032.safetensors", "model.layers.45.self_attn.o_proj.weight": "model-00030-of-00032.safetensors", "model.layers.45.post_attention_layernorm.weight": "model-00030-of-00032.safetensors", "model.layers.45.block_sparse_moe.experts.0.w3.weight": "model-00030-of-00032.safetensors", "model.layers.45.block_sparse_moe.experts.1.w3.weight": "model-00030-of-00032.safetensors", "model.layers.45.block_sparse_moe.experts.0.w1.weight": "model-00030-of-00032.safetensors", "model.layers.45.block_sparse_moe.experts.1.w1.weight": "model-00030-of-00032.safetensors", "model.layers.45.block_sparse_moe.experts.0.w2.weight": "model-00030-of-00032.safetensors", "model.layers.45.block_sparse_moe.experts.1.w2.weight": "model-00030-of-00032.safetensors", "model.layers.46.input_layernorm.weight": "model-00030-of-00032.safetensors", "model.layers.46.self_attn.q_proj.weight": "model-00030-of-00032.safetensors", "model.layers.46.self_attn.k_proj.weight": "model-00030-of-00032.safetensors", "model.layers.46.self_attn.v_proj.weight": "model-00030-of-00032.safetensors", "model.layers.46.self_attn.o_proj.weight": "model-00030-of-00032.safetensors", "model.layers.46.post_attention_layernorm.weight": "model-00030-of-00032.safetensors", "model.layers.46.block_sparse_moe.experts.0.w3.weight": "model-00030-of-00032.safetensors", "model.layers.46.block_sparse_moe.experts.1.w3.weight": "model-00031-of-00032.safetensors", "model.layers.46.block_sparse_moe.experts.0.w1.weight": "model-00031-of-00032.safetensors", "model.layers.46.block_sparse_moe.experts.1.w1.weight": "model-00031-of-00032.safetensors", "model.layers.46.block_sparse_moe.experts.0.w2.weight": "model-00031-of-00032.safetensors", "model.layers.46.block_sparse_moe.experts.1.w2.weight": "model-00031-of-00032.safetensors", "model.layers.47.input_layernorm.weight": "model-00031-of-00032.safetensors", "model.layers.47.self_attn.q_proj.weight": "model-00031-of-00032.safetensors", "model.layers.47.self_attn.k_proj.weight": "model-00031-of-00032.safetensors", "model.layers.47.self_attn.v_proj.weight": "model-00031-of-00032.safetensors", "model.layers.47.self_attn.o_proj.weight": "model-00031-of-00032.safetensors", "model.layers.47.post_attention_layernorm.weight": "model-00031-of-00032.safetensors", "model.layers.47.block_sparse_moe.experts.0.w3.weight": "model-00031-of-00032.safetensors", "model.layers.47.block_sparse_moe.experts.1.w3.weight": "model-00031-of-00032.safetensors", "model.layers.47.block_sparse_moe.experts.0.w1.weight": "model-00031-of-00032.safetensors", "model.layers.47.block_sparse_moe.experts.1.w1.weight": "model-00031-of-00032.safetensors", "model.layers.47.block_sparse_moe.experts.0.w2.weight": "model-00031-of-00032.safetensors", "model.layers.47.block_sparse_moe.experts.1.w2.weight": "model-00032-of-00032.safetensors", "model.norm.weight": "model-00032-of-00032.safetensors", "lm_head.weight": "model-00032-of-00032.safetensors", "model.layers.0.block_sparse_moe.gate.weight": "model-00032-of-00032.safetensors", "model.layers.1.block_sparse_moe.gate.weight": "model-00032-of-00032.safetensors", "model.layers.2.block_sparse_moe.gate.weight": "model-00032-of-00032.safetensors", "model.layers.3.block_sparse_moe.gate.weight": "model-00032-of-00032.safetensors", "model.layers.4.block_sparse_moe.gate.weight": "model-00032-of-00032.safetensors", "model.layers.5.block_sparse_moe.gate.weight": "model-00032-of-00032.safetensors", "model.layers.6.block_sparse_moe.gate.weight": "model-00032-of-00032.safetensors", "model.layers.7.block_sparse_moe.gate.weight": "model-00032-of-00032.safetensors", "model.layers.8.block_sparse_moe.gate.weight": "model-00032-of-00032.safetensors", "model.layers.9.block_sparse_moe.gate.weight": "model-00032-of-00032.safetensors", "model.layers.10.block_sparse_moe.gate.weight": "model-00032-of-00032.safetensors", "model.layers.11.block_sparse_moe.gate.weight": "model-00032-of-00032.safetensors", "model.layers.12.block_sparse_moe.gate.weight": "model-00032-of-00032.safetensors", "model.layers.13.block_sparse_moe.gate.weight": "model-00032-of-00032.safetensors", "model.layers.14.block_sparse_moe.gate.weight": "model-00032-of-00032.safetensors", "model.layers.15.block_sparse_moe.gate.weight": "model-00032-of-00032.safetensors", "model.layers.16.block_sparse_moe.gate.weight": "model-00032-of-00032.safetensors", "model.layers.17.block_sparse_moe.gate.weight": "model-00032-of-00032.safetensors", "model.layers.18.block_sparse_moe.gate.weight": "model-00032-of-00032.safetensors", "model.layers.19.block_sparse_moe.gate.weight": "model-00032-of-00032.safetensors", "model.layers.20.block_sparse_moe.gate.weight": "model-00032-of-00032.safetensors", "model.layers.21.block_sparse_moe.gate.weight": "model-00032-of-00032.safetensors", "model.layers.22.block_sparse_moe.gate.weight": "model-00032-of-00032.safetensors", "model.layers.23.block_sparse_moe.gate.weight": "model-00032-of-00032.safetensors", "model.layers.24.block_sparse_moe.gate.weight": "model-00032-of-00032.safetensors", "model.layers.25.block_sparse_moe.gate.weight": "model-00032-of-00032.safetensors", "model.layers.26.block_sparse_moe.gate.weight": "model-00032-of-00032.safetensors", "model.layers.27.block_sparse_moe.gate.weight": "model-00032-of-00032.safetensors", "model.layers.28.block_sparse_moe.gate.weight": "model-00032-of-00032.safetensors", "model.layers.29.block_sparse_moe.gate.weight": "model-00032-of-00032.safetensors", "model.layers.30.block_sparse_moe.gate.weight": "model-00032-of-00032.safetensors", "model.layers.31.block_sparse_moe.gate.weight": "model-00032-of-00032.safetensors", "model.layers.32.block_sparse_moe.gate.weight": "model-00032-of-00032.safetensors", "model.layers.33.block_sparse_moe.gate.weight": "model-00032-of-00032.safetensors", "model.layers.34.block_sparse_moe.gate.weight": "model-00032-of-00032.safetensors", "model.layers.35.block_sparse_moe.gate.weight": "model-00032-of-00032.safetensors", "model.layers.36.block_sparse_moe.gate.weight": "model-00032-of-00032.safetensors", "model.layers.37.block_sparse_moe.gate.weight": "model-00032-of-00032.safetensors", "model.layers.38.block_sparse_moe.gate.weight": "model-00032-of-00032.safetensors", "model.layers.39.block_sparse_moe.gate.weight": "model-00032-of-00032.safetensors", "model.layers.40.block_sparse_moe.gate.weight": "model-00032-of-00032.safetensors", "model.layers.41.block_sparse_moe.gate.weight": "model-00032-of-00032.safetensors", "model.layers.42.block_sparse_moe.gate.weight": "model-00032-of-00032.safetensors", "model.layers.43.block_sparse_moe.gate.weight": "model-00032-of-00032.safetensors", "model.layers.44.block_sparse_moe.gate.weight": "model-00032-of-00032.safetensors", "model.layers.45.block_sparse_moe.gate.weight": "model-00032-of-00032.safetensors", "model.layers.46.block_sparse_moe.gate.weight": "model-00032-of-00032.safetensors", "model.layers.47.block_sparse_moe.gate.weight": "model-00032-of-00032.safetensors"}}

special_tokens_map.json

@@ -0,0 +1,27 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>"
+  ],
+  "bos_token": {
+    "content": "<|startoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|startoftext|>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,63 @@
+{
+  "add_bos_token": false,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<|startoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "7": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>"
+  ],
+  "bos_token": "<|startoftext|>",
+  "chat_template": "{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{% if system_message is defined %}{{ '<|im_start|>system\\n' + system_message + '<|im_end|>\\n' }}{% endif %}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|im_start|>user\\n' + content + '<|im_end|>\\n<|im_start|>assistant\\n' }}{% elif message['role'] == 'assistant' %}{{ content + '<|im_end|>' + '\\n' }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "legacy": true,
+  "model_max_length": 4096,
+  "pad_token": "<|startoftext|>",
+  "padding_side": "left",
+  "sp_model_kwargs": {},
+  "split_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}