Upload fp32 model files

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "[PAD]": 32000
+}

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "OrcaMaid",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 13824,
+  "max_position_embeddings": 4096,
+  "model_type": "llama",
+  "num_attention_heads": 40,
+  "num_hidden_layers": 40,
+  "num_key_value_heads": 40,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.35.2",
+  "use_cache": false,
+  "vocab_size": 32001
+}

model-00001-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7fd4cbea7eb7f724641849bb00310df2c087473b5125a78f13c773a4203ebeae
+size 3759270376

model-00002-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3e64659e22bcfb51be8596596482181525929dac025bd4e39d4ffa39709bf0e
+size 3806477456

model-00003-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e5f2ca5fe65c1451a027bdcf03e28e6f554aa5efd63bf41b3b79f10c7001f04
+size 3942751536

model-00004-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:56b255c332ade65e71c45f3c5a4224f9d88f9c9891eeb5087b1bcb9d6178646f
+size 3806456904

model-00005-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25000be00fc08039683d9c412a4ce6b8fe7fcea2617062d0c9698a5c0b02598b
+size 3879877680

model-00006-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6afa878371ab9e24050b6fb25d827468bc46250a6ff2961ba2d0e08284fef79e
+size 3984714832

model-00007-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa5ac2ea496339529ff2dd13481739eaba79fd43d8c1fc14ea1736bca3c415c8
+size 3911314624

model-00008-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94974f1e5ada840ce63bd8539ac0b75859311892a15ec50e00dab40e419b5c4f
+size 3911314624

model-00009-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:884b69d2dfc3355ec6b5e3ffa292fbd781e038ec61aa98513f2a9165b9e938a0
+size 3911335216

model-00010-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d0790888dac95f3f9433174c9100deef5fa1c0369b17656b761794d1e381af8
+size 3806456912

model-00011-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:023bd0c029314a43438203c091507cbbc1565a01fd37ee6edd7fa99ab6a0a28a
+size 3806456912

model-00012-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27ec4260fee78a9f9f77299f1c339cf23a7841a6953036f707f965cb56c94bca
+size 3806456912

model-00013-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f32f4f43d4f60f87de83942d8a7be4f8c26b85da7ea952376ae81b69b60a9475
+size 3895565032

model-00014-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70c5d05ffee8c51bf1340a64995d46fc11ecb359946437e62ad5e3586a5f63cf
+size 1835091424

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.3"}, "weight_map": {"model.embed_tokens.weight": "model-00001-of-00014.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00014.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00014.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00014.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00001-of-00014.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00014.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00014.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00014.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00014.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00014.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00014.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00001-of-00014.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00014.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00001-of-00014.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00014.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00014.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00014.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00014.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00014.safetensors", "model.layers.2.input_layernorm.weight": "model-00001-of-00014.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00001-of-00014.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00014.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00002-of-00014.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00014.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00002-of-00014.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00002-of-00014.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00002-of-00014.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00002-of-00014.safetensors", "model.layers.3.input_layernorm.weight": "model-00002-of-00014.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00002-of-00014.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00014.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00002-of-00014.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00014.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00014.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00014.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00014.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00014.safetensors", "model.layers.4.input_layernorm.weight": "model-00002-of-00014.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00002-of-00014.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00014.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00002-of-00014.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00014.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00014.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00014.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00014.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00014.safetensors", "model.layers.5.input_layernorm.weight": "model-00002-of-00014.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00002-of-00014.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00014.safetensors", "model.layers.10.input_layernorm.weight": "model-00002-of-00014.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00003-of-00014.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00014.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00003-of-00014.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00014.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00014.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00014.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00014.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00014.safetensors", "model.layers.11.input_layernorm.weight": "model-00003-of-00014.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00003-of-00014.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00003-of-00014.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00003-of-00014.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00003-of-00014.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00003-of-00014.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00003-of-00014.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00003-of-00014.safetensors", "model.layers.6.input_layernorm.weight": "model-00003-of-00014.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00003-of-00014.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00003-of-00014.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00003-of-00014.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00003-of-00014.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00003-of-00014.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00003-of-00014.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00003-of-00014.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00003-of-00014.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00003-of-00014.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00003-of-00014.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00003-of-00014.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00003-of-00014.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00004-of-00014.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00004-of-00014.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00004-of-00014.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00004-of-00014.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00004-of-00014.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00004-of-00014.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00004-of-00014.safetensors", "model.layers.12.input_layernorm.weight": "model-00004-of-00014.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00004-of-00014.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00004-of-00014.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00004-of-00014.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00004-of-00014.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00004-of-00014.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00004-of-00014.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00004-of-00014.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00004-of-00014.safetensors", "model.layers.13.input_layernorm.weight": "model-00004-of-00014.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00004-of-00014.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00004-of-00014.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00004-of-00014.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00004-of-00014.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00004-of-00014.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00004-of-00014.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00004-of-00014.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00004-of-00014.safetensors", "model.layers.14.input_layernorm.weight": "model-00004-of-00014.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00004-of-00014.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00005-of-00014.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00005-of-00014.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00005-of-00014.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00005-of-00014.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00005-of-00014.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00005-of-00014.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00005-of-00014.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00005-of-00014.safetensors", "model.layers.7.input_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00005-of-00014.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00005-of-00014.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00005-of-00014.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.8.input_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00005-of-00014.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00005-of-00014.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00005-of-00014.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00005-of-00014.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00005-of-00014.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00005-of-00014.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00005-of-00014.safetensors", "model.layers.9.input_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00005-of-00014.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00005-of-00014.safetensors", "model.layers.15.input_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00006-of-00014.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00006-of-00014.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00006-of-00014.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00006-of-00014.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00006-of-00014.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00006-of-00014.safetensors", "model.layers.16.input_layernorm.weight": "model-00006-of-00014.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00006-of-00014.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00006-of-00014.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00006-of-00014.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00006-of-00014.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00006-of-00014.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00006-of-00014.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00006-of-00014.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00006-of-00014.safetensors", "model.layers.17.input_layernorm.weight": "model-00006-of-00014.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00006-of-00014.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00006-of-00014.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00006-of-00014.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00006-of-00014.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00006-of-00014.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00006-of-00014.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00006-of-00014.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00006-of-00014.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00006-of-00014.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00006-of-00014.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00006-of-00014.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00007-of-00014.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00007-of-00014.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00007-of-00014.safetensors", "model.layers.18.input_layernorm.weight": "model-00007-of-00014.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00007-of-00014.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00007-of-00014.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00007-of-00014.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00007-of-00014.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00007-of-00014.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00007-of-00014.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00007-of-00014.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00007-of-00014.safetensors", "model.layers.19.input_layernorm.weight": "model-00007-of-00014.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00007-of-00014.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00007-of-00014.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00007-of-00014.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00007-of-00014.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00007-of-00014.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00007-of-00014.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00007-of-00014.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00007-of-00014.safetensors", "model.layers.20.input_layernorm.weight": "model-00007-of-00014.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00007-of-00014.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00007-of-00014.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00007-of-00014.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00007-of-00014.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00007-of-00014.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00007-of-00014.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00008-of-00014.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00008-of-00014.safetensors", "model.layers.21.input_layernorm.weight": "model-00008-of-00014.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00008-of-00014.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00008-of-00014.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00008-of-00014.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00008-of-00014.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00008-of-00014.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00008-of-00014.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00008-of-00014.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00008-of-00014.safetensors", "model.layers.22.input_layernorm.weight": "model-00008-of-00014.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00008-of-00014.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00008-of-00014.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00008-of-00014.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00008-of-00014.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00008-of-00014.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00008-of-00014.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00008-of-00014.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00008-of-00014.safetensors", "model.layers.23.input_layernorm.weight": "model-00008-of-00014.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00008-of-00014.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00008-of-00014.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00008-of-00014.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00008-of-00014.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00008-of-00014.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00008-of-00014.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00008-of-00014.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00009-of-00014.safetensors", "model.layers.24.input_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00009-of-00014.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00009-of-00014.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00009-of-00014.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00009-of-00014.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00009-of-00014.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00009-of-00014.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00009-of-00014.safetensors", "model.layers.25.input_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00009-of-00014.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00009-of-00014.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00009-of-00014.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00009-of-00014.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00009-of-00014.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00009-of-00014.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00009-of-00014.safetensors", "model.layers.26.input_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00009-of-00014.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00009-of-00014.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00009-of-00014.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00009-of-00014.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00009-of-00014.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00009-of-00014.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00009-of-00014.safetensors", "model.layers.27.input_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00010-of-00014.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00010-of-00014.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00010-of-00014.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00010-of-00014.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00010-of-00014.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00010-of-00014.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00010-of-00014.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00010-of-00014.safetensors", "model.layers.28.input_layernorm.weight": "model-00010-of-00014.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00010-of-00014.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00010-of-00014.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00010-of-00014.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00010-of-00014.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00010-of-00014.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00010-of-00014.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00010-of-00014.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00010-of-00014.safetensors", "model.layers.29.input_layernorm.weight": "model-00010-of-00014.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00010-of-00014.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00010-of-00014.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00010-of-00014.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00010-of-00014.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00010-of-00014.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00010-of-00014.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00010-of-00014.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00010-of-00014.safetensors", "model.layers.30.input_layernorm.weight": "model-00010-of-00014.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00011-of-00014.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00011-of-00014.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00011-of-00014.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00011-of-00014.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00011-of-00014.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00011-of-00014.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00011-of-00014.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00011-of-00014.safetensors", "model.layers.31.input_layernorm.weight": "model-00011-of-00014.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00011-of-00014.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00011-of-00014.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00011-of-00014.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00011-of-00014.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00011-of-00014.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00011-of-00014.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00011-of-00014.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00011-of-00014.safetensors", "model.layers.32.input_layernorm.weight": "model-00011-of-00014.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00011-of-00014.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00011-of-00014.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00011-of-00014.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00011-of-00014.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00011-of-00014.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00011-of-00014.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00011-of-00014.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00011-of-00014.safetensors", "model.layers.33.input_layernorm.weight": "model-00011-of-00014.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00012-of-00014.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00012-of-00014.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00012-of-00014.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00012-of-00014.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00012-of-00014.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00012-of-00014.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00012-of-00014.safetensors", "model.layers.34.input_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00012-of-00014.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00012-of-00014.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00012-of-00014.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00012-of-00014.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00012-of-00014.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00012-of-00014.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00012-of-00014.safetensors", "model.layers.35.input_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00012-of-00014.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00012-of-00014.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00012-of-00014.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00012-of-00014.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00012-of-00014.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00012-of-00014.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00012-of-00014.safetensors", "model.layers.36.input_layernorm.weight": "model-00012-of-00014.safetensors", "lm_head.weight": "model-00013-of-00014.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00013-of-00014.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00013-of-00014.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00013-of-00014.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00013-of-00014.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00013-of-00014.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00013-of-00014.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00013-of-00014.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00013-of-00014.safetensors", "model.layers.37.input_layernorm.weight": "model-00013-of-00014.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00013-of-00014.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00013-of-00014.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00013-of-00014.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00013-of-00014.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00013-of-00014.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00013-of-00014.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00013-of-00014.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00013-of-00014.safetensors", "model.layers.38.input_layernorm.weight": "model-00013-of-00014.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00013-of-00014.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00013-of-00014.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00013-of-00014.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00013-of-00014.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00013-of-00014.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00014-of-00014.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00014-of-00014.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00014-of-00014.safetensors", "model.layers.39.input_layernorm.weight": "model-00014-of-00014.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00014-of-00014.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00014-of-00014.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00014-of-00014.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00014-of-00014.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00014-of-00014.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00014-of-00014.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00014-of-00014.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00014-of-00014.safetensors", "model.norm.weight": "model-00014-of-00014.safetensors"}}

special_tokens_map.json

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

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -0,0 +1,49 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32000": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 2048,
+  "pad_token": "[PAD]",
+  "padding_side": "left",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false,
+  "use_fast": true
+}