Upload folder using huggingface_hub

config.json

@@ -0,0 +1,32 @@
+{
+  "architectures": [
+    "Olmoe2ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "clip_qkv": null,
+  "eos_token_id": 100257,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 4096,
+  "model_type": "olmoe2",
+  "norm_topk_prob": false,
+  "num_attention_heads": 32,
+  "num_experts": 4,
+  "num_experts_per_tok": 4,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 32,
+  "output_router_logits": false,
+  "pad_token_id": 100277,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 500000,
+  "router_aux_loss_coef": 0.01,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.50.0.dev0",
+  "use_cache": true,
+  "vocab_size": 100352
+}

generation_config.json

@@ -0,0 +1,4 @@
+{
+  "_from_model_config": true,
+  "transformers_version": "4.50.0.dev0"
+}

model-00001-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3e3a73cc66405de888cc8f35902fcbabc7c397e842e7add8dfeaac079fbc1ae
+size 4886597344

model-00002-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d77a5043c72917491f779468de54ca5455482fcd24d5e7f7c66806d6a426ed9c
+size 4865659832

model-00003-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:85be08247019586708e15d73110a5ffbe155aa6e29c3cdd502e0bede4ab0d28e
+size 4865659832

model-00004-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91f444382af10a76197dd1ede7d6fb9cd000260fbc3d797329a46cf8f7edc826
+size 4865659832

model-00005-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3337e47c057db8fec9dc945efcc988f78d631c9a0e44dfb714f6c824eb409fb2
+size 4865659832

model-00006-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e9dd81898ffb6ddfe3129744c16c449208156e80a6997ab3b051dd7f534edb1
+size 4865659864

model-00007-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ad0124a7d81fa236faf467fa5a82d152bec176c113e2a4705f858ae85eccc51
+size 4865659872

model-00008-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ac93ff7c25c913c0462cd54f1e05841d0d2b431ce22a68476a3d3025a66ad7e
+size 4865659872

model-00009-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de300940ee66ae96ab523db1d7df0a1ac74026a77d46846e4d1fc9f65607ee4b
+size 4865659872

model-00010-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c7d71638f94d0ac205f69cdd5268bdc5196a399feb1530d27f5f848161652f11
+size 4865659872

model-00011-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf30ed02979bfd44693f39a1ced1b895afc35bbde4b4f7d859dab914d02b1cae
+size 4865659872

model-00012-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce12a445d65a23e6181c1d079f57e80b64e603987e95f30e10a7d67da3a6717f
+size 4865659872

model-00013-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40e06e6a167361a59d4875e9a2dd1822764e88eee6ea66ef0651cd02d5989328
+size 4865659872

model-00014-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f9ce043c8dd82ac9edb29e4acab5e8827e7f017dbda21323bac6cd86d2af1a0
+size 4865659872

model-00015-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ea0a62525b3e08af227c7f02620806e69392c84e40ead3cb06c8b2b285f4341
+size 4865659872

model-00016-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4bc3b766ba9e85a7409acb803ac81813c1a4b99c4930847e8ba6e2b161b16a7f
+size 4865659872

model-00017-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:def27aea55f5b9832b688805b4b4c16bb9679c036c27952fcb6a96571d372fb1
+size 3267413544

model.safetensors.index.json

@@ -0,0 +1,682 @@
+{
+  "metadata": {
+    "total_size": 81138827264
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00017-of-00017.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00017.safetensors",
+    "model.layers.0.mlp.experts.0.down_proj.weight": "model-00001-of-00017.safetensors",
+    "model.layers.0.mlp.experts.0.gate_proj.weight": "model-00001-of-00017.safetensors",
+    "model.layers.0.mlp.experts.0.up_proj.weight": "model-00001-of-00017.safetensors",
+    "model.layers.0.mlp.experts.1.down_proj.weight": "model-00001-of-00017.safetensors",
+    "model.layers.0.mlp.experts.1.gate_proj.weight": "model-00001-of-00017.safetensors",
+    "model.layers.0.mlp.experts.1.up_proj.weight": "model-00001-of-00017.safetensors",
+    "model.layers.0.mlp.experts.2.down_proj.weight": "model-00001-of-00017.safetensors",
+    "model.layers.0.mlp.experts.2.gate_proj.weight": "model-00001-of-00017.safetensors",
+    "model.layers.0.mlp.experts.2.up_proj.weight": "model-00001-of-00017.safetensors",
+    "model.layers.0.mlp.experts.3.down_proj.weight": "model-00001-of-00017.safetensors",
+    "model.layers.0.mlp.experts.3.gate_proj.weight": "model-00001-of-00017.safetensors",
+    "model.layers.0.mlp.experts.3.up_proj.weight": "model-00001-of-00017.safetensors",
+    "model.layers.0.mlp.gate.weight": "model-00001-of-00017.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00017.safetensors",
+    "model.layers.0.post_feedforward_layernorm.weight": "model-00001-of-00017.safetensors",
+    "model.layers.0.self_attn.k_norm.weight": "model-00001-of-00017.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00017.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00017.safetensors",
+    "model.layers.0.self_attn.q_norm.weight": "model-00001-of-00017.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00017.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00017.safetensors",
+    "model.layers.1.mlp.experts.0.down_proj.weight": "model-00001-of-00017.safetensors",
+    "model.layers.1.mlp.experts.0.gate_proj.weight": "model-00001-of-00017.safetensors",
+    "model.layers.1.mlp.experts.0.up_proj.weight": "model-00001-of-00017.safetensors",
+    "model.layers.1.mlp.experts.1.down_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.1.mlp.experts.1.gate_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.1.mlp.experts.1.up_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.1.mlp.experts.2.down_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.1.mlp.experts.2.gate_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.1.mlp.experts.2.up_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.1.mlp.experts.3.down_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.1.mlp.experts.3.gate_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.1.mlp.experts.3.up_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.1.mlp.gate.weight": "model-00001-of-00017.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00017.safetensors",
+    "model.layers.1.post_feedforward_layernorm.weight": "model-00002-of-00017.safetensors",
+    "model.layers.1.self_attn.k_norm.weight": "model-00001-of-00017.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00017.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00017.safetensors",
+    "model.layers.1.self_attn.q_norm.weight": "model-00001-of-00017.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00017.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00017.safetensors",
+    "model.layers.10.mlp.experts.0.down_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.10.mlp.experts.0.gate_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.10.mlp.experts.0.up_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.10.mlp.experts.1.down_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.10.mlp.experts.1.gate_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.10.mlp.experts.1.up_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.10.mlp.experts.2.down_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.10.mlp.experts.2.gate_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.10.mlp.experts.2.up_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.10.mlp.experts.3.down_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.10.mlp.experts.3.gate_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.10.mlp.experts.3.up_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.10.mlp.gate.weight": "model-00006-of-00017.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00006-of-00017.safetensors",
+    "model.layers.10.post_feedforward_layernorm.weight": "model-00006-of-00017.safetensors",
+    "model.layers.10.self_attn.k_norm.weight": "model-00006-of-00017.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.10.self_attn.q_norm.weight": "model-00006-of-00017.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.11.mlp.experts.0.down_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.11.mlp.experts.0.gate_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.11.mlp.experts.0.up_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.11.mlp.experts.1.down_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.11.mlp.experts.1.gate_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.11.mlp.experts.1.up_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.11.mlp.experts.2.down_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.11.mlp.experts.2.gate_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.11.mlp.experts.2.up_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.11.mlp.experts.3.down_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.11.mlp.experts.3.gate_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.11.mlp.experts.3.up_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.11.mlp.gate.weight": "model-00006-of-00017.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00007-of-00017.safetensors",
+    "model.layers.11.post_feedforward_layernorm.weight": "model-00007-of-00017.safetensors",
+    "model.layers.11.self_attn.k_norm.weight": "model-00006-of-00017.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.11.self_attn.q_norm.weight": "model-00006-of-00017.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.12.mlp.experts.0.down_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.12.mlp.experts.0.gate_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.12.mlp.experts.0.up_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.12.mlp.experts.1.down_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.12.mlp.experts.1.gate_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.12.mlp.experts.1.up_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.12.mlp.experts.2.down_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.12.mlp.experts.2.gate_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.12.mlp.experts.2.up_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.12.mlp.experts.3.down_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.12.mlp.experts.3.gate_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.12.mlp.experts.3.up_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.12.mlp.gate.weight": "model-00007-of-00017.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00007-of-00017.safetensors",
+    "model.layers.12.post_feedforward_layernorm.weight": "model-00007-of-00017.safetensors",
+    "model.layers.12.self_attn.k_norm.weight": "model-00007-of-00017.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.12.self_attn.q_norm.weight": "model-00007-of-00017.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.13.mlp.experts.0.down_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.13.mlp.experts.0.gate_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.13.mlp.experts.0.up_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.13.mlp.experts.1.down_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.13.mlp.experts.1.gate_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.13.mlp.experts.1.up_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.13.mlp.experts.2.down_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.13.mlp.experts.2.gate_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.13.mlp.experts.2.up_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.13.mlp.experts.3.down_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.13.mlp.experts.3.gate_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.13.mlp.experts.3.up_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.13.mlp.gate.weight": "model-00007-of-00017.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00008-of-00017.safetensors",
+    "model.layers.13.post_feedforward_layernorm.weight": "model-00008-of-00017.safetensors",
+    "model.layers.13.self_attn.k_norm.weight": "model-00007-of-00017.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.13.self_attn.q_norm.weight": "model-00007-of-00017.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.14.mlp.experts.0.down_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.14.mlp.experts.0.gate_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.14.mlp.experts.0.up_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.14.mlp.experts.1.down_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.14.mlp.experts.1.gate_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.14.mlp.experts.1.up_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.14.mlp.experts.2.down_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.14.mlp.experts.2.gate_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.14.mlp.experts.2.up_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.14.mlp.experts.3.down_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.14.mlp.experts.3.gate_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.14.mlp.experts.3.up_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.14.mlp.gate.weight": "model-00008-of-00017.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00008-of-00017.safetensors",
+    "model.layers.14.post_feedforward_layernorm.weight": "model-00008-of-00017.safetensors",
+    "model.layers.14.self_attn.k_norm.weight": "model-00008-of-00017.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.14.self_attn.q_norm.weight": "model-00008-of-00017.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.15.mlp.experts.0.down_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.15.mlp.experts.0.gate_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.15.mlp.experts.0.up_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.15.mlp.experts.1.down_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.15.mlp.experts.1.gate_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.15.mlp.experts.1.up_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.15.mlp.experts.2.down_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.15.mlp.experts.2.gate_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.15.mlp.experts.2.up_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.15.mlp.experts.3.down_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.15.mlp.experts.3.gate_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.15.mlp.experts.3.up_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.15.mlp.gate.weight": "model-00008-of-00017.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00009-of-00017.safetensors",
+    "model.layers.15.post_feedforward_layernorm.weight": "model-00009-of-00017.safetensors",
+    "model.layers.15.self_attn.k_norm.weight": "model-00008-of-00017.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.15.self_attn.q_norm.weight": "model-00008-of-00017.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.16.mlp.experts.0.down_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.16.mlp.experts.0.gate_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.16.mlp.experts.0.up_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.16.mlp.experts.1.down_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.16.mlp.experts.1.gate_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.16.mlp.experts.1.up_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.16.mlp.experts.2.down_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.16.mlp.experts.2.gate_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.16.mlp.experts.2.up_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.16.mlp.experts.3.down_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.16.mlp.experts.3.gate_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.16.mlp.experts.3.up_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.16.mlp.gate.weight": "model-00009-of-00017.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00009-of-00017.safetensors",
+    "model.layers.16.post_feedforward_layernorm.weight": "model-00009-of-00017.safetensors",
+    "model.layers.16.self_attn.k_norm.weight": "model-00009-of-00017.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.16.self_attn.q_norm.weight": "model-00009-of-00017.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.17.mlp.experts.0.down_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.17.mlp.experts.0.gate_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.17.mlp.experts.0.up_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.17.mlp.experts.1.down_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.17.mlp.experts.1.gate_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.17.mlp.experts.1.up_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.17.mlp.experts.2.down_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.17.mlp.experts.2.gate_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.17.mlp.experts.2.up_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.17.mlp.experts.3.down_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.17.mlp.experts.3.gate_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.17.mlp.experts.3.up_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.17.mlp.gate.weight": "model-00009-of-00017.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00010-of-00017.safetensors",
+    "model.layers.17.post_feedforward_layernorm.weight": "model-00010-of-00017.safetensors",
+    "model.layers.17.self_attn.k_norm.weight": "model-00009-of-00017.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.17.self_attn.q_norm.weight": "model-00009-of-00017.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.18.mlp.experts.0.down_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.18.mlp.experts.0.gate_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.18.mlp.experts.0.up_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.18.mlp.experts.1.down_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.18.mlp.experts.1.gate_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.18.mlp.experts.1.up_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.18.mlp.experts.2.down_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.18.mlp.experts.2.gate_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.18.mlp.experts.2.up_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.18.mlp.experts.3.down_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.18.mlp.experts.3.gate_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.18.mlp.experts.3.up_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.18.mlp.gate.weight": "model-00010-of-00017.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00010-of-00017.safetensors",
+    "model.layers.18.post_feedforward_layernorm.weight": "model-00010-of-00017.safetensors",
+    "model.layers.18.self_attn.k_norm.weight": "model-00010-of-00017.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.18.self_attn.q_norm.weight": "model-00010-of-00017.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.19.mlp.experts.0.down_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.19.mlp.experts.0.gate_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.19.mlp.experts.0.up_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.19.mlp.experts.1.down_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.19.mlp.experts.1.gate_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.19.mlp.experts.1.up_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.19.mlp.experts.2.down_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.19.mlp.experts.2.gate_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.19.mlp.experts.2.up_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.19.mlp.experts.3.down_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.19.mlp.experts.3.gate_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.19.mlp.experts.3.up_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.19.mlp.gate.weight": "model-00010-of-00017.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00011-of-00017.safetensors",
+    "model.layers.19.post_feedforward_layernorm.weight": "model-00011-of-00017.safetensors",
+    "model.layers.19.self_attn.k_norm.weight": "model-00010-of-00017.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.19.self_attn.q_norm.weight": "model-00010-of-00017.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.2.mlp.experts.0.down_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.2.mlp.experts.0.gate_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.2.mlp.experts.0.up_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.2.mlp.experts.1.down_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.2.mlp.experts.1.gate_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.2.mlp.experts.1.up_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.2.mlp.experts.2.down_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.2.mlp.experts.2.gate_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.2.mlp.experts.2.up_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.2.mlp.experts.3.down_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.2.mlp.experts.3.gate_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.2.mlp.experts.3.up_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.2.mlp.gate.weight": "model-00002-of-00017.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00017.safetensors",
+    "model.layers.2.post_feedforward_layernorm.weight": "model-00002-of-00017.safetensors",
+    "model.layers.2.self_attn.k_norm.weight": "model-00002-of-00017.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.2.self_attn.q_norm.weight": "model-00002-of-00017.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.20.mlp.experts.0.down_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.20.mlp.experts.0.gate_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.20.mlp.experts.0.up_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.20.mlp.experts.1.down_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.20.mlp.experts.1.gate_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.20.mlp.experts.1.up_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.20.mlp.experts.2.down_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.20.mlp.experts.2.gate_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.20.mlp.experts.2.up_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.20.mlp.experts.3.down_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.20.mlp.experts.3.gate_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.20.mlp.experts.3.up_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.20.mlp.gate.weight": "model-00011-of-00017.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00011-of-00017.safetensors",
+    "model.layers.20.post_feedforward_layernorm.weight": "model-00011-of-00017.safetensors",
+    "model.layers.20.self_attn.k_norm.weight": "model-00011-of-00017.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.20.self_attn.q_norm.weight": "model-00011-of-00017.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.21.mlp.experts.0.down_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.21.mlp.experts.0.gate_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.21.mlp.experts.0.up_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.21.mlp.experts.1.down_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.21.mlp.experts.1.gate_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.21.mlp.experts.1.up_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.21.mlp.experts.2.down_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.21.mlp.experts.2.gate_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.21.mlp.experts.2.up_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.21.mlp.experts.3.down_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.21.mlp.experts.3.gate_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.21.mlp.experts.3.up_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.21.mlp.gate.weight": "model-00011-of-00017.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00012-of-00017.safetensors",
+    "model.layers.21.post_feedforward_layernorm.weight": "model-00012-of-00017.safetensors",
+    "model.layers.21.self_attn.k_norm.weight": "model-00011-of-00017.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.21.self_attn.q_norm.weight": "model-00011-of-00017.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.22.mlp.experts.0.down_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.22.mlp.experts.0.gate_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.22.mlp.experts.0.up_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.22.mlp.experts.1.down_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.22.mlp.experts.1.gate_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.22.mlp.experts.1.up_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.22.mlp.experts.2.down_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.22.mlp.experts.2.gate_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.22.mlp.experts.2.up_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.22.mlp.experts.3.down_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.22.mlp.experts.3.gate_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.22.mlp.experts.3.up_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.22.mlp.gate.weight": "model-00012-of-00017.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00012-of-00017.safetensors",
+    "model.layers.22.post_feedforward_layernorm.weight": "model-00012-of-00017.safetensors",
+    "model.layers.22.self_attn.k_norm.weight": "model-00012-of-00017.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.22.self_attn.q_norm.weight": "model-00012-of-00017.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.23.mlp.experts.0.down_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.23.mlp.experts.0.gate_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.23.mlp.experts.0.up_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.23.mlp.experts.1.down_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.23.mlp.experts.1.gate_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.23.mlp.experts.1.up_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.23.mlp.experts.2.down_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.23.mlp.experts.2.gate_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.23.mlp.experts.2.up_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.23.mlp.experts.3.down_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.23.mlp.experts.3.gate_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.23.mlp.experts.3.up_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.23.mlp.gate.weight": "model-00012-of-00017.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00013-of-00017.safetensors",
+    "model.layers.23.post_feedforward_layernorm.weight": "model-00013-of-00017.safetensors",
+    "model.layers.23.self_attn.k_norm.weight": "model-00012-of-00017.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.23.self_attn.q_norm.weight": "model-00012-of-00017.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.24.mlp.experts.0.down_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.24.mlp.experts.0.gate_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.24.mlp.experts.0.up_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.24.mlp.experts.1.down_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.24.mlp.experts.1.gate_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.24.mlp.experts.1.up_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.24.mlp.experts.2.down_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.24.mlp.experts.2.gate_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.24.mlp.experts.2.up_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.24.mlp.experts.3.down_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.24.mlp.experts.3.gate_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.24.mlp.experts.3.up_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.24.mlp.gate.weight": "model-00013-of-00017.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00013-of-00017.safetensors",
+    "model.layers.24.post_feedforward_layernorm.weight": "model-00013-of-00017.safetensors",
+    "model.layers.24.self_attn.k_norm.weight": "model-00013-of-00017.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.24.self_attn.q_norm.weight": "model-00013-of-00017.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.25.mlp.experts.0.down_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.25.mlp.experts.0.gate_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.25.mlp.experts.0.up_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.25.mlp.experts.1.down_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.25.mlp.experts.1.gate_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.25.mlp.experts.1.up_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.25.mlp.experts.2.down_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.25.mlp.experts.2.gate_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.25.mlp.experts.2.up_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.25.mlp.experts.3.down_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.25.mlp.experts.3.gate_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.25.mlp.experts.3.up_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.25.mlp.gate.weight": "model-00013-of-00017.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00014-of-00017.safetensors",
+    "model.layers.25.post_feedforward_layernorm.weight": "model-00014-of-00017.safetensors",
+    "model.layers.25.self_attn.k_norm.weight": "model-00013-of-00017.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.25.self_attn.q_norm.weight": "model-00013-of-00017.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.26.mlp.experts.0.down_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.26.mlp.experts.0.gate_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.26.mlp.experts.0.up_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.26.mlp.experts.1.down_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.26.mlp.experts.1.gate_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.26.mlp.experts.1.up_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.26.mlp.experts.2.down_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.26.mlp.experts.2.gate_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.26.mlp.experts.2.up_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.26.mlp.experts.3.down_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.26.mlp.experts.3.gate_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.26.mlp.experts.3.up_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.26.mlp.gate.weight": "model-00014-of-00017.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00014-of-00017.safetensors",
+    "model.layers.26.post_feedforward_layernorm.weight": "model-00014-of-00017.safetensors",
+    "model.layers.26.self_attn.k_norm.weight": "model-00014-of-00017.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.26.self_attn.q_norm.weight": "model-00014-of-00017.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.27.mlp.experts.0.down_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.27.mlp.experts.0.gate_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.27.mlp.experts.0.up_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.27.mlp.experts.1.down_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.27.mlp.experts.1.gate_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.27.mlp.experts.1.up_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.27.mlp.experts.2.down_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.27.mlp.experts.2.gate_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.27.mlp.experts.2.up_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.27.mlp.experts.3.down_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.27.mlp.experts.3.gate_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.27.mlp.experts.3.up_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.27.mlp.gate.weight": "model-00014-of-00017.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00015-of-00017.safetensors",
+    "model.layers.27.post_feedforward_layernorm.weight": "model-00015-of-00017.safetensors",
+    "model.layers.27.self_attn.k_norm.weight": "model-00014-of-00017.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.27.self_attn.q_norm.weight": "model-00014-of-00017.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.28.mlp.experts.0.down_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.28.mlp.experts.0.gate_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.28.mlp.experts.0.up_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.28.mlp.experts.1.down_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.28.mlp.experts.1.gate_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.28.mlp.experts.1.up_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.28.mlp.experts.2.down_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.28.mlp.experts.2.gate_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.28.mlp.experts.2.up_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.28.mlp.experts.3.down_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.28.mlp.experts.3.gate_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.28.mlp.experts.3.up_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.28.mlp.gate.weight": "model-00015-of-00017.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00015-of-00017.safetensors",
+    "model.layers.28.post_feedforward_layernorm.weight": "model-00015-of-00017.safetensors",
+    "model.layers.28.self_attn.k_norm.weight": "model-00015-of-00017.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.28.self_attn.q_norm.weight": "model-00015-of-00017.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.29.mlp.experts.0.down_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.29.mlp.experts.0.gate_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.29.mlp.experts.0.up_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.29.mlp.experts.1.down_proj.weight": "model-00016-of-00017.safetensors",
+    "model.layers.29.mlp.experts.1.gate_proj.weight": "model-00016-of-00017.safetensors",
+    "model.layers.29.mlp.experts.1.up_proj.weight": "model-00016-of-00017.safetensors",
+    "model.layers.29.mlp.experts.2.down_proj.weight": "model-00016-of-00017.safetensors",
+    "model.layers.29.mlp.experts.2.gate_proj.weight": "model-00016-of-00017.safetensors",
+    "model.layers.29.mlp.experts.2.up_proj.weight": "model-00016-of-00017.safetensors",
+    "model.layers.29.mlp.experts.3.down_proj.weight": "model-00016-of-00017.safetensors",
+    "model.layers.29.mlp.experts.3.gate_proj.weight": "model-00016-of-00017.safetensors",
+    "model.layers.29.mlp.experts.3.up_proj.weight": "model-00016-of-00017.safetensors",
+    "model.layers.29.mlp.gate.weight": "model-00015-of-00017.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00016-of-00017.safetensors",
+    "model.layers.29.post_feedforward_layernorm.weight": "model-00016-of-00017.safetensors",
+    "model.layers.29.self_attn.k_norm.weight": "model-00015-of-00017.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.29.self_attn.q_norm.weight": "model-00015-of-00017.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.3.mlp.experts.0.down_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.3.mlp.experts.0.gate_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.3.mlp.experts.0.up_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.3.mlp.experts.1.down_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.3.mlp.experts.1.gate_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.3.mlp.experts.1.up_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.3.mlp.experts.2.down_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.3.mlp.experts.2.gate_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.3.mlp.experts.2.up_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.3.mlp.experts.3.down_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.3.mlp.experts.3.gate_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.3.mlp.experts.3.up_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.3.mlp.gate.weight": "model-00002-of-00017.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00003-of-00017.safetensors",
+    "model.layers.3.post_feedforward_layernorm.weight": "model-00003-of-00017.safetensors",
+    "model.layers.3.self_attn.k_norm.weight": "model-00002-of-00017.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.3.self_attn.q_norm.weight": "model-00002-of-00017.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.30.mlp.experts.0.down_proj.weight": "model-00016-of-00017.safetensors",
+    "model.layers.30.mlp.experts.0.gate_proj.weight": "model-00016-of-00017.safetensors",
+    "model.layers.30.mlp.experts.0.up_proj.weight": "model-00016-of-00017.safetensors",
+    "model.layers.30.mlp.experts.1.down_proj.weight": "model-00016-of-00017.safetensors",
+    "model.layers.30.mlp.experts.1.gate_proj.weight": "model-00016-of-00017.safetensors",
+    "model.layers.30.mlp.experts.1.up_proj.weight": "model-00016-of-00017.safetensors",
+    "model.layers.30.mlp.experts.2.down_proj.weight": "model-00016-of-00017.safetensors",
+    "model.layers.30.mlp.experts.2.gate_proj.weight": "model-00016-of-00017.safetensors",
+    "model.layers.30.mlp.experts.2.up_proj.weight": "model-00016-of-00017.safetensors",
+    "model.layers.30.mlp.experts.3.down_proj.weight": "model-00016-of-00017.safetensors",
+    "model.layers.30.mlp.experts.3.gate_proj.weight": "model-00016-of-00017.safetensors",
+    "model.layers.30.mlp.experts.3.up_proj.weight": "model-00016-of-00017.safetensors",
+    "model.layers.30.mlp.gate.weight": "model-00016-of-00017.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00016-of-00017.safetensors",
+    "model.layers.30.post_feedforward_layernorm.weight": "model-00016-of-00017.safetensors",
+    "model.layers.30.self_attn.k_norm.weight": "model-00016-of-00017.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00016-of-00017.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00016-of-00017.safetensors",
+    "model.layers.30.self_attn.q_norm.weight": "model-00016-of-00017.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00016-of-00017.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00016-of-00017.safetensors",
+    "model.layers.31.mlp.experts.0.down_proj.weight": "model-00016-of-00017.safetensors",
+    "model.layers.31.mlp.experts.0.gate_proj.weight": "model-00016-of-00017.safetensors",
+    "model.layers.31.mlp.experts.0.up_proj.weight": "model-00016-of-00017.safetensors",
+    "model.layers.31.mlp.experts.1.down_proj.weight": "model-00017-of-00017.safetensors",
+    "model.layers.31.mlp.experts.1.gate_proj.weight": "model-00017-of-00017.safetensors",
+    "model.layers.31.mlp.experts.1.up_proj.weight": "model-00017-of-00017.safetensors",
+    "model.layers.31.mlp.experts.2.down_proj.weight": "model-00017-of-00017.safetensors",
+    "model.layers.31.mlp.experts.2.gate_proj.weight": "model-00017-of-00017.safetensors",
+    "model.layers.31.mlp.experts.2.up_proj.weight": "model-00017-of-00017.safetensors",
+    "model.layers.31.mlp.experts.3.down_proj.weight": "model-00017-of-00017.safetensors",
+    "model.layers.31.mlp.experts.3.gate_proj.weight": "model-00017-of-00017.safetensors",
+    "model.layers.31.mlp.experts.3.up_proj.weight": "model-00017-of-00017.safetensors",
+    "model.layers.31.mlp.gate.weight": "model-00016-of-00017.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00017-of-00017.safetensors",
+    "model.layers.31.post_feedforward_layernorm.weight": "model-00017-of-00017.safetensors",
+    "model.layers.31.self_attn.k_norm.weight": "model-00016-of-00017.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00016-of-00017.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00016-of-00017.safetensors",
+    "model.layers.31.self_attn.q_norm.weight": "model-00016-of-00017.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00016-of-00017.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00016-of-00017.safetensors",
+    "model.layers.4.mlp.experts.0.down_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.4.mlp.experts.0.gate_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.4.mlp.experts.0.up_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.4.mlp.experts.1.down_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.4.mlp.experts.1.gate_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.4.mlp.experts.1.up_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.4.mlp.experts.2.down_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.4.mlp.experts.2.gate_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.4.mlp.experts.2.up_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.4.mlp.experts.3.down_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.4.mlp.experts.3.gate_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.4.mlp.experts.3.up_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.4.mlp.gate.weight": "model-00003-of-00017.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00003-of-00017.safetensors",
+    "model.layers.4.post_feedforward_layernorm.weight": "model-00003-of-00017.safetensors",
+    "model.layers.4.self_attn.k_norm.weight": "model-00003-of-00017.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.4.self_attn.q_norm.weight": "model-00003-of-00017.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.5.mlp.experts.0.down_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.5.mlp.experts.0.gate_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.5.mlp.experts.0.up_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.5.mlp.experts.1.down_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.5.mlp.experts.1.gate_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.5.mlp.experts.1.up_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.5.mlp.experts.2.down_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.5.mlp.experts.2.gate_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.5.mlp.experts.2.up_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.5.mlp.experts.3.down_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.5.mlp.experts.3.gate_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.5.mlp.experts.3.up_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.5.mlp.gate.weight": "model-00003-of-00017.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00004-of-00017.safetensors",
+    "model.layers.5.post_feedforward_layernorm.weight": "model-00004-of-00017.safetensors",
+    "model.layers.5.self_attn.k_norm.weight": "model-00003-of-00017.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.5.self_attn.q_norm.weight": "model-00003-of-00017.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.6.mlp.experts.0.down_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.6.mlp.experts.0.gate_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.6.mlp.experts.0.up_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.6.mlp.experts.1.down_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.6.mlp.experts.1.gate_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.6.mlp.experts.1.up_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.6.mlp.experts.2.down_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.6.mlp.experts.2.gate_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.6.mlp.experts.2.up_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.6.mlp.experts.3.down_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.6.mlp.experts.3.gate_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.6.mlp.experts.3.up_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.6.mlp.gate.weight": "model-00004-of-00017.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00004-of-00017.safetensors",
+    "model.layers.6.post_feedforward_layernorm.weight": "model-00004-of-00017.safetensors",
+    "model.layers.6.self_attn.k_norm.weight": "model-00004-of-00017.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.6.self_attn.q_norm.weight": "model-00004-of-00017.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.7.mlp.experts.0.down_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.7.mlp.experts.0.gate_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.7.mlp.experts.0.up_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.7.mlp.experts.1.down_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.7.mlp.experts.1.gate_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.7.mlp.experts.1.up_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.7.mlp.experts.2.down_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.7.mlp.experts.2.gate_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.7.mlp.experts.2.up_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.7.mlp.experts.3.down_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.7.mlp.experts.3.gate_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.7.mlp.experts.3.up_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.7.mlp.gate.weight": "model-00004-of-00017.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00005-of-00017.safetensors",
+    "model.layers.7.post_feedforward_layernorm.weight": "model-00005-of-00017.safetensors",
+    "model.layers.7.self_attn.k_norm.weight": "model-00004-of-00017.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.7.self_attn.q_norm.weight": "model-00004-of-00017.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.8.mlp.experts.0.down_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.8.mlp.experts.0.gate_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.8.mlp.experts.0.up_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.8.mlp.experts.1.down_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.8.mlp.experts.1.gate_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.8.mlp.experts.1.up_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.8.mlp.experts.2.down_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.8.mlp.experts.2.gate_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.8.mlp.experts.2.up_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.8.mlp.experts.3.down_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.8.mlp.experts.3.gate_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.8.mlp.experts.3.up_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.8.mlp.gate.weight": "model-00005-of-00017.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00005-of-00017.safetensors",
+    "model.layers.8.post_feedforward_layernorm.weight": "model-00005-of-00017.safetensors",
+    "model.layers.8.self_attn.k_norm.weight": "model-00005-of-00017.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.8.self_attn.q_norm.weight": "model-00005-of-00017.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.9.mlp.experts.0.down_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.9.mlp.experts.0.gate_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.9.mlp.experts.0.up_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.9.mlp.experts.1.down_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.9.mlp.experts.1.gate_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.9.mlp.experts.1.up_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.9.mlp.experts.2.down_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.9.mlp.experts.2.gate_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.9.mlp.experts.2.up_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.9.mlp.experts.3.down_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.9.mlp.experts.3.gate_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.9.mlp.experts.3.up_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.9.mlp.gate.weight": "model-00005-of-00017.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00006-of-00017.safetensors",
+    "model.layers.9.post_feedforward_layernorm.weight": "model-00006-of-00017.safetensors",
+    "model.layers.9.self_attn.k_norm.weight": "model-00005-of-00017.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.9.self_attn.q_norm.weight": "model-00005-of-00017.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00005-of-00017.safetensors",
+    "model.norm.weight": "model-00017-of-00017.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|pad|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,190 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "100256": {
+      "content": "<|extra_id_0|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100257": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100258": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100259": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100260": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100261": {
+      "content": "|||PHONE_NUMBER|||",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100262": {
+      "content": "|||EMAIL_ADDRESS|||",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100263": {
+      "content": "|||IP_ADDRESS|||",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100264": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100265": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100266": {
+      "content": "<|extra_id_1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100267": {
+      "content": "<|extra_id_2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100268": {
+      "content": "<|extra_id_3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100269": {
+      "content": "<|extra_id_4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100270": {
+      "content": "<|extra_id_5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100271": {
+      "content": "<|extra_id_6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100272": {
+      "content": "<|extra_id_7|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100273": {
+      "content": "<|extra_id_8|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100274": {
+      "content": "<|extra_id_9|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100275": {
+      "content": "<|extra_id_10|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100276": {
+      "content": "<|endofprompt|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100277": {
+      "content": "<|pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "extra_special_tokens": {},
+  "model_max_length": 8192,
+  "pad_token": "<|pad|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}