upload model

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "/hdd-6tb/nhanv/storage/LLM-storage/LLM-models/japanese-stablelm-base-gamma-7b",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 4096,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 10000.0,
+  "sliding_window": 4096,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.36.2",
+  "use_cache": true,
+  "vocab_size": 32000
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.36.2"
+}

model-00001-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62865b6bb090a7043af9dab8c6810b24be3a4e9f2c56afe362371fbd9ae7964f
+size 899696328

model-00002-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1cb67eb20860f3d05e975ec158df94bc1787094541a701a8eea32e4155c9552b
+size 989890696

model-00003-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:573cfda50d65ab3eed81d85b8038b95137119717bed12595303c8d1b4a38cc69
+size 989907312

model-00004-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a20ff92a86f4a9c42639239599f5bd1d7544e35b43f6655dce001b649374813c
+size 956336616

model-00005-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f90305b052575bacd7561db4c8ade43e576bcf7fe4422b364d51a468b4740baa
+size 989890712

model-00006-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5401dc1900c38ef63e957bb2ff8f98c8709c8d42265d63ca1eee7296c89fc933
+size 989890712

model-00007-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db9ed3c6a694f612d31de2644770bd722aa9540958d7cd33ce2ec105b1414776
+size 989907328

model-00008-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:903df26e6a96f53e3bf53c183f975a13e6849a14b77e684c0b70780fba4de041
+size 956336632

model-00009-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b4dd28c5675f7a769b2e40cfd34fcdd5ef550d67be5ba24846b4316a0c56ac4
+size 989890720

model-00010-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8af17b063259e2049797a316c1cd38861a13330239dfbdcff3db55670da2e458
+size 989890712

model-00011-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6025f0a7f6727a101410dec0a71270777903fc9369290e1b0af9c0c64e3257f9
+size 989907328

model-00012-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40a055e73f182b01449af1e1887be03ac8af8e73e0bc0d1312402797c764414d
+size 956336632

model-00013-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d6b892745a174a6d4e2f74c195fd0e51448ffac33d867220e7dab0d4e1fcbf33
+size 989890720

model-00014-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:65dd81716251b3c2acdab8405f338cfaa1d946150cf247ed736793039ab8d668
+size 989890712

model-00015-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac7901113b9ac854aaea338c64378d1e4514ef475b2a79d74a5232be2af8ef8b
+size 815834680

model.safetensors.index.json

@@ -0,0 +1,298 @@
+{
+  "metadata": {
+    "total_size": 14483464192
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00015-of-00015.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00015.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00015.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00015.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00015.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00015.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00015.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00015.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00015.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00015.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00015.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00002-of-00015.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00015.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00015.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00015.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00015.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00015.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00015.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00006-of-00015.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00006-of-00015.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00006-of-00015.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00006-of-00015.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00007-of-00015.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00007-of-00015.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00007-of-00015.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00007-of-00015.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00007-of-00015.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00007-of-00015.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00008-of-00015.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00008-of-00015.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00008-of-00015.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00008-of-00015.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00009-of-00015.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00009-of-00015.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00009-of-00015.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00009-of-00015.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00010-of-00015.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00010-of-00015.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00002-of-00015.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00015.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00010-of-00015.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00010-of-00015.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00011-of-00015.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00011-of-00015.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00011-of-00015.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00011-of-00015.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00011-of-00015.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00011-of-00015.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00012-of-00015.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00012-of-00015.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00012-of-00015.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00012-of-00015.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00013-of-00015.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00013-of-00015.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00013-of-00015.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00013-of-00015.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00014-of-00015.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00014-of-00015.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00014-of-00015.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00014-of-00015.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00003-of-00015.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00003-of-00015.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00015-of-00015.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00015-of-00015.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00015-of-00015.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00015-of-00015.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00015-of-00015.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00015-of-00015.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00015-of-00015.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00015-of-00015.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00015-of-00015.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00015-of-00015.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00015-of-00015.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00015-of-00015.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00003-of-00015.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00003-of-00015.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00003-of-00015.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00003-of-00015.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00004-of-00015.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00004-of-00015.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00004-of-00015.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00004-of-00015.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00005-of-00015.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00005-of-00015.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00005-of-00015.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00005-of-00015.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00005-of-00015.safetensors",
+    "model.norm.weight": "model-00015-of-00015.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "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
+  },
+  "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 +1,44 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "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": null,
+  "padding_side": "left",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "split_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true
+}