Upload 20 files

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "/DATA4T/text-generation-webui/models/deepsex-6b-base/",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 4096,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 4,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 5000000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.36.0",
+  "use_cache": true,
+  "vocab_size": 64000
+}

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": "4.36.0"
+}

model-00001-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f8da099b725124146f4bfc3e506455ed24cb4f59713cacbaacb3bfc4f59f9a88
+size 945833552

model-00002-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:553eec78a46d28cc6c18192bab050a0c5f3d5d2fbaa2a0d061aa7daaf3413c21
+size 996199096

model-00003-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63f82326f5c9bd6f40df968f0d4c3c45c66a9d9b8ad3f43e23fd3205c715779f
+size 914393672

model-00004-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0051518075738d2798661026586261a6478adf9f83a829537e50895fce61b3d3
+size 947964832

model-00005-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34bc3ef5b81c4280db211c7260b39e1f97498aa47af343b96a74d22fcb94dd7d
+size 947964856

model-00006-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00d5c5cea193db74199e58578f2178f883a746ff702cb02a968d4452005a56fa
+size 996199120

model-00007-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:28fde63a522dcb86a51db7ca459ee3e3ab90d30d5be57636755e2a5407330f6e
+size 914393696

model-00008-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7e3662ed9c7001daadc4c9a5d14e4a3f46744f84e6857a18fd300047b55ebbc
+size 947964856

model-00009-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:097808fcf1f6bca85abd996876bb1d97dec50bb00269adeff6489001f16a9aa1
+size 947964856

model-00010-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b65c39513c1875a5fc6245a92193bf2862c41fe97fc85464587b8e0d4e4ff960
+size 996199120

model-00011-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:13e241455394ed717ab2d936044af6b567dfdd1985d470d01ffae1830ea23660
+size 914393696

model-00012-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c47ed1507b5c02272da65cb42626a63afdc1eb35f11c77e45d15446afa8ec477
+size 947964856

model-00013-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a8741744f6106fef636362aeaf206a1d751206d99ea3eec2c844436231c5611
+size 704668320

model.safetensors.index.json

@@ -0,0 +1,298 @@
+{
+  "metadata": {
+    "total_size": 12122071040
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00013-of-00013.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00013.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00013.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00013.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00013.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00013.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00013.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00013.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00013.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00013.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00013.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00002-of-00013.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00002-of-00013.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00002-of-00013.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00002-of-00013.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00013.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00013.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00013.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00013.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00013.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00005-of-00013.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00005-of-00013.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00005-of-00013.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00005-of-00013.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00005-of-00013.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00005-of-00013.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00005-of-00013.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00005-of-00013.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00005-of-00013.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00005-of-00013.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00005-of-00013.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00005-of-00013.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00005-of-00013.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00005-of-00013.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00005-of-00013.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00005-of-00013.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00005-of-00013.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00005-of-00013.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00006-of-00013.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00006-of-00013.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00006-of-00013.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00006-of-00013.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00006-of-00013.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00005-of-00013.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00005-of-00013.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00005-of-00013.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00005-of-00013.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00006-of-00013.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00006-of-00013.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00006-of-00013.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00006-of-00013.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00006-of-00013.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00006-of-00013.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00006-of-00013.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00006-of-00013.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00006-of-00013.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00006-of-00013.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00006-of-00013.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00006-of-00013.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00006-of-00013.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00006-of-00013.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00006-of-00013.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00006-of-00013.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00006-of-00013.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00006-of-00013.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00007-of-00013.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00007-of-00013.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00007-of-00013.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00007-of-00013.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00007-of-00013.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00007-of-00013.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00007-of-00013.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00006-of-00013.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00007-of-00013.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00007-of-00013.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00007-of-00013.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00007-of-00013.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00007-of-00013.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00007-of-00013.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00007-of-00013.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00007-of-00013.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00007-of-00013.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00007-of-00013.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00008-of-00013.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00008-of-00013.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00007-of-00013.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00007-of-00013.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00008-of-00013.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00007-of-00013.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00007-of-00013.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00007-of-00013.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00007-of-00013.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00008-of-00013.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00008-of-00013.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00008-of-00013.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00008-of-00013.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00008-of-00013.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00008-of-00013.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00008-of-00013.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00008-of-00013.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00008-of-00013.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00008-of-00013.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00008-of-00013.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00008-of-00013.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00008-of-00013.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00008-of-00013.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00008-of-00013.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00008-of-00013.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00008-of-00013.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00008-of-00013.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00002-of-00013.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00002-of-00013.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00002-of-00013.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00002-of-00013.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00013.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00002-of-00013.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00002-of-00013.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00002-of-00013.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00002-of-00013.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00009-of-00013.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00009-of-00013.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00008-of-00013.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00009-of-00013.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00009-of-00013.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00008-of-00013.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00008-of-00013.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00008-of-00013.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00008-of-00013.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00009-of-00013.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00009-of-00013.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00009-of-00013.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00009-of-00013.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00009-of-00013.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00009-of-00013.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00009-of-00013.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00009-of-00013.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00009-of-00013.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00009-of-00013.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00009-of-00013.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00009-of-00013.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00009-of-00013.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00009-of-00013.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00009-of-00013.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00009-of-00013.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00009-of-00013.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00009-of-00013.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00010-of-00013.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00010-of-00013.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00010-of-00013.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00010-of-00013.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00010-of-00013.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00009-of-00013.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00009-of-00013.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00009-of-00013.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00009-of-00013.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00010-of-00013.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00010-of-00013.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00010-of-00013.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00010-of-00013.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00010-of-00013.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00010-of-00013.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00010-of-00013.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00010-of-00013.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00010-of-00013.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00010-of-00013.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00010-of-00013.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00010-of-00013.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00010-of-00013.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00010-of-00013.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00010-of-00013.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00010-of-00013.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00010-of-00013.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00010-of-00013.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00011-of-00013.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00011-of-00013.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00011-of-00013.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00011-of-00013.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00011-of-00013.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00011-of-00013.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00011-of-00013.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00010-of-00013.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00011-of-00013.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00011-of-00013.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00011-of-00013.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00011-of-00013.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00011-of-00013.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00011-of-00013.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00011-of-00013.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00011-of-00013.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00011-of-00013.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00011-of-00013.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00012-of-00013.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00012-of-00013.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00011-of-00013.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00011-of-00013.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00012-of-00013.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00011-of-00013.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00011-of-00013.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00011-of-00013.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00011-of-00013.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00012-of-00013.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00012-of-00013.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00012-of-00013.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00012-of-00013.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00012-of-00013.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00012-of-00013.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00012-of-00013.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00012-of-00013.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00012-of-00013.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00002-of-00013.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00002-of-00013.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00013.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00002-of-00013.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00013.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00013.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00013.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00013.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00013.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00012-of-00013.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00012-of-00013.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00012-of-00013.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00012-of-00013.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00012-of-00013.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00012-of-00013.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00012-of-00013.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00012-of-00013.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00012-of-00013.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00013-of-00013.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00013-of-00013.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00012-of-00013.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00013-of-00013.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00013-of-00013.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00012-of-00013.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00012-of-00013.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00012-of-00013.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00012-of-00013.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00003-of-00013.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00003-of-00013.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00003-of-00013.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00003-of-00013.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00003-of-00013.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00003-of-00013.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00003-of-00013.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00013.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00003-of-00013.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00003-of-00013.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00003-of-00013.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00003-of-00013.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00003-of-00013.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00003-of-00013.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00003-of-00013.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00003-of-00013.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00003-of-00013.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00003-of-00013.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00004-of-00013.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00004-of-00013.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00003-of-00013.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00003-of-00013.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00004-of-00013.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00003-of-00013.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00003-of-00013.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00003-of-00013.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00003-of-00013.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00004-of-00013.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00004-of-00013.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00004-of-00013.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00004-of-00013.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00004-of-00013.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00004-of-00013.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00004-of-00013.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00004-of-00013.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00004-of-00013.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00004-of-00013.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00004-of-00013.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00004-of-00013.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00004-of-00013.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00004-of-00013.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00004-of-00013.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00004-of-00013.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00004-of-00013.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00004-of-00013.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00005-of-00013.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00005-of-00013.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00004-of-00013.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00005-of-00013.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00005-of-00013.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00004-of-00013.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00004-of-00013.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00004-of-00013.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00004-of-00013.safetensors",
+    "model.norm.weight": "model-00013-of-00013.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<|startoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<unk>",
+    "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 sha256:386c49cf943d71aa110361135338c50e38beeff0a66593480421f37b319e1a39
+size 1033105

tokenizer_config.json

@@ -0,0 +1,42 @@
+{
+  "add_bos_token": false,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<|startoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|startoftext|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "legacy": true,
+  "model_max_length": 4096,
+  "pad_token": "<unk>",
+  "padding_side": "left",
+  "sp_model_kwargs": {},
+  "split_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}