pushing 500B token checkpoint

config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "NucleusAI/test-9k-fn",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 6656,
+  "initializer_range": 0.02,
+  "intermediate_size": 17920,
+  "max_position_embeddings": 2048,
+  "max_sequence_length": 2048,
+  "model_type": "llama",
+  "num_attention_heads": 52,
+  "num_hidden_layers": 40,
+  "num_key_value_heads": 52,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.30.2",
+  "use_cache": true,
+  "vocab_size": 32000
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": 0,
+  "transformers_version": "4.30.2"
+}

model-00001-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00e7a41342638aa1bca3fa879ef1cee17ff74ab7ff6f41a31bfcd900ee0f400d
+size 9944389584

model-00002-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:58ad98b7b2f8a9446338199c68782766f884ead49238e34824e7ae36ff5e2ee1
+size 9692207312

model-00003-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3fe2a1144b2fcf7c0288829cd65e14d038d7a5d6d19adac0077fb5232b09fad
+size 9746787008

model-00004-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eecd1103c8de5728d54c7d5711a3cefd3c1ab9388f830160d9506041f08d927e
+size 9992153192

model-00005-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:513b3505ef2015ba5964d7481a5ac3f48491bae6c281b78083745a9f4757d34d
+size 9746733544

model-00006-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d51bea26310158cdf92cfcdcd22b012d8286178f168c93d718a9768fb53b182
+size 9869469920

model-00007-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4fa74c99e8c5825be472e9c0eedb49d9ec5ace76bb976222e03eef3b5570f9e6
+size 9869416816

model-00008-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0511a669a8efbdca08c351b40ebbd0d822ee17d067b5bae10941d29e02aee753
+size 9746787016

model-00009-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:18e2cb5ab08ae126edeb389c635fa61d35065c0d60a0ed0e8955022f8f917a0a
+size 8703949736

model.safetensors.index.json

@@ -0,0 +1,410 @@
+{
+  "metadata": {
+    "total_size": 87311847424
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00009-of-00009.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00009.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00009.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00009.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.0.self_attn.rotary_emb.inv_freq": "model-00001-of-00009.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00009.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00009.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.1.self_attn.rotary_emb.inv_freq": "model-00001-of-00009.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.10.self_attn.rotary_emb.inv_freq": "model-00003-of-00009.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.11.self_attn.rotary_emb.inv_freq": "model-00003-of-00009.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.12.self_attn.rotary_emb.inv_freq": "model-00003-of-00009.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.13.self_attn.rotary_emb.inv_freq": "model-00003-of-00009.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.14.self_attn.rotary_emb.inv_freq": "model-00004-of-00009.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.15.self_attn.rotary_emb.inv_freq": "model-00004-of-00009.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.16.self_attn.rotary_emb.inv_freq": "model-00004-of-00009.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.17.self_attn.rotary_emb.inv_freq": "model-00004-of-00009.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.18.self_attn.rotary_emb.inv_freq": "model-00005-of-00009.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.19.self_attn.rotary_emb.inv_freq": "model-00005-of-00009.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00009.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00009.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.2.self_attn.rotary_emb.inv_freq": "model-00001-of-00009.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.20.self_attn.rotary_emb.inv_freq": "model-00005-of-00009.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.21.self_attn.rotary_emb.inv_freq": "model-00005-of-00009.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.22.self_attn.rotary_emb.inv_freq": "model-00005-of-00009.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.23.self_attn.rotary_emb.inv_freq": "model-00006-of-00009.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.24.self_attn.rotary_emb.inv_freq": "model-00006-of-00009.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.25.self_attn.rotary_emb.inv_freq": "model-00006-of-00009.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.26.self_attn.rotary_emb.inv_freq": "model-00006-of-00009.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.27.self_attn.rotary_emb.inv_freq": "model-00007-of-00009.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.28.self_attn.rotary_emb.inv_freq": "model-00007-of-00009.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.29.self_attn.rotary_emb.inv_freq": "model-00007-of-00009.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00009.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00009.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.3.self_attn.rotary_emb.inv_freq": "model-00001-of-00009.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.30.self_attn.rotary_emb.inv_freq": "model-00007-of-00009.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.31.self_attn.rotary_emb.inv_freq": "model-00007-of-00009.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.32.self_attn.rotary_emb.inv_freq": "model-00008-of-00009.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.33.self_attn.rotary_emb.inv_freq": "model-00008-of-00009.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.34.self_attn.rotary_emb.inv_freq": "model-00008-of-00009.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.35.self_attn.rotary_emb.inv_freq": "model-00008-of-00009.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-00009-of-00009.safetensors",
+    "model.layers.36.mlp.down_proj.weight": "model-00009-of-00009.safetensors",
+    "model.layers.36.mlp.gate_proj.weight": "model-00009-of-00009.safetensors",
+    "model.layers.36.mlp.up_proj.weight": "model-00009-of-00009.safetensors",
+    "model.layers.36.post_attention_layernorm.weight": "model-00009-of-00009.safetensors",
+    "model.layers.36.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.36.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.36.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.36.self_attn.rotary_emb.inv_freq": "model-00008-of-00009.safetensors",
+    "model.layers.36.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.37.input_layernorm.weight": "model-00009-of-00009.safetensors",
+    "model.layers.37.mlp.down_proj.weight": "model-00009-of-00009.safetensors",
+    "model.layers.37.mlp.gate_proj.weight": "model-00009-of-00009.safetensors",
+    "model.layers.37.mlp.up_proj.weight": "model-00009-of-00009.safetensors",
+    "model.layers.37.post_attention_layernorm.weight": "model-00009-of-00009.safetensors",
+    "model.layers.37.self_attn.k_proj.weight": "model-00009-of-00009.safetensors",
+    "model.layers.37.self_attn.o_proj.weight": "model-00009-of-00009.safetensors",
+    "model.layers.37.self_attn.q_proj.weight": "model-00009-of-00009.safetensors",
+    "model.layers.37.self_attn.rotary_emb.inv_freq": "model-00009-of-00009.safetensors",
+    "model.layers.37.self_attn.v_proj.weight": "model-00009-of-00009.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-00009-of-00009.safetensors",
+    "model.layers.38.mlp.down_proj.weight": "model-00009-of-00009.safetensors",
+    "model.layers.38.mlp.gate_proj.weight": "model-00009-of-00009.safetensors",
+    "model.layers.38.mlp.up_proj.weight": "model-00009-of-00009.safetensors",
+    "model.layers.38.post_attention_layernorm.weight": "model-00009-of-00009.safetensors",
+    "model.layers.38.self_attn.k_proj.weight": "model-00009-of-00009.safetensors",
+    "model.layers.38.self_attn.o_proj.weight": "model-00009-of-00009.safetensors",
+    "model.layers.38.self_attn.q_proj.weight": "model-00009-of-00009.safetensors",
+    "model.layers.38.self_attn.rotary_emb.inv_freq": "model-00009-of-00009.safetensors",
+    "model.layers.38.self_attn.v_proj.weight": "model-00009-of-00009.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-00009-of-00009.safetensors",
+    "model.layers.39.mlp.down_proj.weight": "model-00009-of-00009.safetensors",
+    "model.layers.39.mlp.gate_proj.weight": "model-00009-of-00009.safetensors",
+    "model.layers.39.mlp.up_proj.weight": "model-00009-of-00009.safetensors",
+    "model.layers.39.post_attention_layernorm.weight": "model-00009-of-00009.safetensors",
+    "model.layers.39.self_attn.k_proj.weight": "model-00009-of-00009.safetensors",
+    "model.layers.39.self_attn.o_proj.weight": "model-00009-of-00009.safetensors",
+    "model.layers.39.self_attn.q_proj.weight": "model-00009-of-00009.safetensors",
+    "model.layers.39.self_attn.rotary_emb.inv_freq": "model-00009-of-00009.safetensors",
+    "model.layers.39.self_attn.v_proj.weight": "model-00009-of-00009.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00002-of-00009.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.4.self_attn.rotary_emb.inv_freq": "model-00002-of-00009.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00002-of-00009.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.5.self_attn.rotary_emb.inv_freq": "model-00002-of-00009.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00002-of-00009.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.6.self_attn.rotary_emb.inv_freq": "model-00002-of-00009.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00002-of-00009.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.7.self_attn.rotary_emb.inv_freq": "model-00002-of-00009.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.8.self_attn.rotary_emb.inv_freq": "model-00002-of-00009.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.9.self_attn.rotary_emb.inv_freq": "model-00003-of-00009.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
+    "model.norm.weight": "model-00009-of-00009.safetensors"
+  }
+}