Upload GSAForCausalLM

config.json

@@ -0,0 +1,43 @@
+{
+  "_name_or_path": "fla-hub/gsa-2.7B-100B",
+  "architectures": [
+    "GSAForCausalLM"
+  ],
+  "bos_token_id": 1,
+  "clamp_max": null,
+  "clamp_min": null,
+  "conv_size": 4,
+  "elementwise_affine": false,
+  "eos_token_id": 2,
+  "expand_k": 1,
+  "expand_v": 1,
+  "feature_map": "swish",
+  "fuse_cross_entropy": true,
+  "fuse_norm": true,
+  "gate_logit_normalizer": 8,
+  "gate_low_rank_dim": null,
+  "hidden_act": "swish",
+  "hidden_ratio": 4,
+  "hidden_size": 2560,
+  "initializer_range": 0.02,
+  "intermediate_size": null,
+  "max_position_embeddings": 2048,
+  "model_type": "gsa",
+  "norm_eps": 1e-06,
+  "norm_first": true,
+  "num_heads": 5,
+  "num_hidden_layers": 32,
+  "num_kv_heads": null,
+  "num_slots": 64,
+  "pad_token_id": 2,
+  "share_conv_kernel": true,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.40.2",
+  "use_cache": true,
+  "use_norm": true,
+  "use_output_gate": false,
+  "use_rope": false,
+  "use_short_conv": false,
+  "vocab_size": 32000
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.40.2"
+}

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:10a81e67b41435a90b9559f03a44622ea57bba7b538be85a68dcc04c83a1bfc8
+size 4997462776

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62fea47173b0014dfe79328d71ea851f1d49f5c90d538e79a9056f41a0fcfb42
+size 458118984

model.safetensors.index.json

@@ -0,0 +1,298 @@
+{
+  "metadata": {
+    "total_size": 5455549440
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00002-of-00002.safetensors",
+    "model.embeddings.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.attn.f_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.attn.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.attn.f_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.attn.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.attn.f_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.attn.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.attn.f_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.attn.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.attn.f_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.attn.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.attn.f_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.attn.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.attn.f_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.attn.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.attn.f_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.attn.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.attn.f_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.attn.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.attn.f_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.attn.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.attn.f_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.attn.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.attn.f_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.attn.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.attn.f_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.attn.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.attn.f_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.attn.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.attn.f_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.attn.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.attn.f_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.attn.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.attn.f_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.attn.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.mlp.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.attn.f_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.attn.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.mlp.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.attn.f_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.attn.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.mlp.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.attn.f_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.attn.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.mlp.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.attn.f_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.attn.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.attn.f_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.attn.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.mlp.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.29.attn.f_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.29.attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.29.attn.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.29.attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.29.attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.29.attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.29.mlp.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.attn.f_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.attn.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.30.attn.f_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.30.attn.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.30.attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.30.attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.attn.f_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.attn.norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.4.attn.f_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.attn.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.attn.f_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.attn.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.attn.f_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.attn.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.attn.f_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.attn.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.attn.f_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.attn.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.attn.f_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.attn.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.norm.weight": "model-00001-of-00002.safetensors",
+    "model.norm.weight": "model-00002-of-00002.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

tokenizer_config.json

@@ -0,0 +1,43 @@
+{
+  "add_bos_token": false,
+  "add_eos_token": true,
+  "add_prefix_space": true,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}