Upload 11 files

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "mistal-nerd-7B-v1",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 32768,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "pad_token_id": 2,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 100000.0,
+  "sliding_window": 16384,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.0",
+  "unsloth_version": "2024.1",
+  "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": "4.46.0"
+}

layer_stats.json

@@ -0,0 +1,293 @@
+{
+    "model.embed_tokens": "100.0%",
+    "model.layers.0.self_attn.q_proj": "100.0%",
+    "model.layers.0.self_attn.k_proj": "48.3%",
+    "model.layers.0.self_attn.v_proj": "48.4%",
+    "model.layers.0.self_attn.o_proj": "48.5%",
+    "model.layers.0.mlp.gate_proj": "80.2%",
+    "model.layers.0.mlp.up_proj": "79.1%",
+    "model.layers.0.mlp.down_proj": "86.9%",
+    "model.layers.0.input_layernorm": "78.9%",
+    "model.layers.0.post_attention_layernorm": "88.8%",
+    "model.layers.1.self_attn.q_proj": "50.5%",
+    "model.layers.1.self_attn.k_proj": "100.0%",
+    "model.layers.1.self_attn.v_proj": "49.3%",
+    "model.layers.1.self_attn.o_proj": "49.2%",
+    "model.layers.1.mlp.gate_proj": "100.0%",
+    "model.layers.1.mlp.up_proj": "100.0%",
+    "model.layers.1.mlp.down_proj": "100.0%",
+    "model.layers.1.input_layernorm": "71.8%",
+    "model.layers.1.post_attention_layernorm": "97.3%",
+    "model.layers.2.self_attn.q_proj": "51.4%",
+    "model.layers.2.self_attn.k_proj": "52.0%",
+    "model.layers.2.self_attn.v_proj": "49.8%",
+    "model.layers.2.self_attn.o_proj": "49.4%",
+    "model.layers.2.mlp.gate_proj": "100.0%",
+    "model.layers.2.mlp.up_proj": "100.0%",
+    "model.layers.2.mlp.down_proj": "100.0%",
+    "model.layers.2.input_layernorm": "88.9%",
+    "model.layers.2.post_attention_layernorm": "84.6%",
+    "model.layers.3.self_attn.q_proj": "52.3%",
+    "model.layers.3.self_attn.k_proj": "53.3%",
+    "model.layers.3.self_attn.v_proj": "100.0%",
+    "model.layers.3.self_attn.o_proj": "100.0%",
+    "model.layers.3.mlp.gate_proj": "100.0%",
+    "model.layers.3.mlp.up_proj": "100.0%",
+    "model.layers.3.mlp.down_proj": "100.0%",
+    "model.layers.3.input_layernorm": "90.5%",
+    "model.layers.3.post_attention_layernorm": "83.2%",
+    "model.layers.4.self_attn.q_proj": "52.2%",
+    "model.layers.4.self_attn.k_proj": "100.0%",
+    "model.layers.4.self_attn.v_proj": "100.0%",
+    "model.layers.4.self_attn.o_proj": "50.5%",
+    "model.layers.4.mlp.gate_proj": "100.0%",
+    "model.layers.4.mlp.up_proj": "100.0%",
+    "model.layers.4.mlp.down_proj": "100.0%",
+    "model.layers.4.input_layernorm": "87.8%",
+    "model.layers.4.post_attention_layernorm": "95.4%",
+    "model.layers.5.self_attn.q_proj": "53.3%",
+    "model.layers.5.self_attn.k_proj": "100.0%",
+    "model.layers.5.self_attn.v_proj": "100.0%",
+    "model.layers.5.self_attn.o_proj": "100.0%",
+    "model.layers.5.mlp.gate_proj": "100.0%",
+    "model.layers.5.mlp.up_proj": "100.0%",
+    "model.layers.5.mlp.down_proj": "100.0%",
+    "model.layers.5.input_layernorm": "100.0%",
+    "model.layers.5.post_attention_layernorm": "98.1%",
+    "model.layers.6.self_attn.q_proj": "53.8%",
+    "model.layers.6.self_attn.k_proj": "55.0%",
+    "model.layers.6.self_attn.v_proj": "51.5%",
+    "model.layers.6.self_attn.o_proj": "51.9%",
+    "model.layers.6.mlp.gate_proj": "100.0%",
+    "model.layers.6.mlp.up_proj": "100.0%",
+    "model.layers.6.mlp.down_proj": "100.0%",
+    "model.layers.6.input_layernorm": "100.0%",
+    "model.layers.6.post_attention_layernorm": "96.5%",
+    "model.layers.7.self_attn.q_proj": "100.0%",
+    "model.layers.7.self_attn.k_proj": "100.0%",
+    "model.layers.7.self_attn.v_proj": "51.8%",
+    "model.layers.7.self_attn.o_proj": "52.3%",
+    "model.layers.7.mlp.gate_proj": "100.0%",
+    "model.layers.7.mlp.up_proj": "100.0%",
+    "model.layers.7.mlp.down_proj": "100.0%",
+    "model.layers.7.input_layernorm": "100.0%",
+    "model.layers.7.post_attention_layernorm": "100.0%",
+    "model.layers.8.self_attn.q_proj": "100.0%",
+    "model.layers.8.self_attn.k_proj": "100.0%",
+    "model.layers.8.self_attn.v_proj": "50.7%",
+    "model.layers.8.self_attn.o_proj": "100.0%",
+    "model.layers.8.mlp.gate_proj": "100.0%",
+    "model.layers.8.mlp.up_proj": "100.0%",
+    "model.layers.8.mlp.down_proj": "100.0%",
+    "model.layers.8.input_layernorm": "100.0%",
+    "model.layers.8.post_attention_layernorm": "100.0%",
+    "model.layers.9.self_attn.q_proj": "54.0%",
+    "model.layers.9.self_attn.k_proj": "100.0%",
+    "model.layers.9.self_attn.v_proj": "100.0%",
+    "model.layers.9.self_attn.o_proj": "100.0%",
+    "model.layers.9.mlp.gate_proj": "100.0%",
+    "model.layers.9.mlp.up_proj": "100.0%",
+    "model.layers.9.mlp.down_proj": "100.0%",
+    "model.layers.9.input_layernorm": "88.2%",
+    "model.layers.9.post_attention_layernorm": "100.0%",
+    "model.layers.10.self_attn.q_proj": "100.0%",
+    "model.layers.10.self_attn.k_proj": "100.0%",
+    "model.layers.10.self_attn.v_proj": "100.0%",
+    "model.layers.10.self_attn.o_proj": "52.3%",
+    "model.layers.10.mlp.gate_proj": "100.0%",
+    "model.layers.10.mlp.up_proj": "100.0%",
+    "model.layers.10.mlp.down_proj": "100.0%",
+    "model.layers.10.input_layernorm": "89.7%",
+    "model.layers.10.post_attention_layernorm": "100.0%",
+    "model.layers.11.self_attn.q_proj": "100.0%",
+    "model.layers.11.self_attn.k_proj": "54.7%",
+    "model.layers.11.self_attn.v_proj": "100.0%",
+    "model.layers.11.self_attn.o_proj": "100.0%",
+    "model.layers.11.mlp.gate_proj": "100.0%",
+    "model.layers.11.mlp.up_proj": "100.0%",
+    "model.layers.11.mlp.down_proj": "57.0%",
+    "model.layers.11.input_layernorm": "90.6%",
+    "model.layers.11.post_attention_layernorm": "100.0%",
+    "model.layers.12.self_attn.q_proj": "100.0%",
+    "model.layers.12.self_attn.k_proj": "100.0%",
+    "model.layers.12.self_attn.v_proj": "51.4%",
+    "model.layers.12.self_attn.o_proj": "52.1%",
+    "model.layers.12.mlp.gate_proj": "100.0%",
+    "model.layers.12.mlp.up_proj": "100.0%",
+    "model.layers.12.mlp.down_proj": "100.0%",
+    "model.layers.12.input_layernorm": "89.9%",
+    "model.layers.12.post_attention_layernorm": "100.0%",
+    "model.layers.13.self_attn.q_proj": "53.2%",
+    "model.layers.13.self_attn.k_proj": "54.3%",
+    "model.layers.13.self_attn.v_proj": "100.0%",
+    "model.layers.13.self_attn.o_proj": "51.9%",
+    "model.layers.13.mlp.gate_proj": "100.0%",
+    "model.layers.13.mlp.up_proj": "100.0%",
+    "model.layers.13.mlp.down_proj": "100.0%",
+    "model.layers.13.input_layernorm": "89.2%",
+    "model.layers.13.post_attention_layernorm": "86.6%",
+    "model.layers.14.self_attn.q_proj": "100.0%",
+    "model.layers.14.self_attn.k_proj": "53.3%",
+    "model.layers.14.self_attn.v_proj": "100.0%",
+    "model.layers.14.self_attn.o_proj": "52.0%",
+    "model.layers.14.mlp.gate_proj": "100.0%",
+    "model.layers.14.mlp.up_proj": "100.0%",
+    "model.layers.14.mlp.down_proj": "100.0%",
+    "model.layers.14.input_layernorm": "89.4%",
+    "model.layers.14.post_attention_layernorm": "85.8%",
+    "model.layers.15.self_attn.q_proj": "52.4%",
+    "model.layers.15.self_attn.k_proj": "53.0%",
+    "model.layers.15.self_attn.v_proj": "51.6%",
+    "model.layers.15.self_attn.o_proj": "51.8%",
+    "model.layers.15.mlp.gate_proj": "100.0%",
+    "model.layers.15.mlp.up_proj": "100.0%",
+    "model.layers.15.mlp.down_proj": "100.0%",
+    "model.layers.15.input_layernorm": "100.0%",
+    "model.layers.15.post_attention_layernorm": "87.6%",
+    "model.layers.16.self_attn.q_proj": "52.6%",
+    "model.layers.16.self_attn.k_proj": "53.4%",
+    "model.layers.16.self_attn.v_proj": "51.7%",
+    "model.layers.16.self_attn.o_proj": "52.0%",
+    "model.layers.16.mlp.gate_proj": "100.0%",
+    "model.layers.16.mlp.up_proj": "100.0%",
+    "model.layers.16.mlp.down_proj": "100.0%",
+    "model.layers.16.input_layernorm": "100.0%",
+    "model.layers.16.post_attention_layernorm": "98.8%",
+    "model.layers.17.self_attn.q_proj": "52.9%",
+    "model.layers.17.self_attn.k_proj": "100.0%",
+    "model.layers.17.self_attn.v_proj": "100.0%",
+    "model.layers.17.self_attn.o_proj": "52.1%",
+    "model.layers.17.mlp.gate_proj": "100.0%",
+    "model.layers.17.mlp.up_proj": "100.0%",
+    "model.layers.17.mlp.down_proj": "100.0%",
+    "model.layers.17.input_layernorm": "98.6%",
+    "model.layers.17.post_attention_layernorm": "100.0%",
+    "model.layers.18.self_attn.q_proj": "53.4%",
+    "model.layers.18.self_attn.k_proj": "54.0%",
+    "model.layers.18.self_attn.v_proj": "52.3%",
+    "model.layers.18.self_attn.o_proj": "100.0%",
+    "model.layers.18.mlp.gate_proj": "100.0%",
+    "model.layers.18.mlp.up_proj": "100.0%",
+    "model.layers.18.mlp.down_proj": "100.0%",
+    "model.layers.18.input_layernorm": "100.0%",
+    "model.layers.18.post_attention_layernorm": "100.0%",
+    "model.layers.19.self_attn.q_proj": "53.2%",
+    "model.layers.19.self_attn.k_proj": "54.4%",
+    "model.layers.19.self_attn.v_proj": "52.3%",
+    "model.layers.19.self_attn.o_proj": "52.1%",
+    "model.layers.19.mlp.gate_proj": "100.0%",
+    "model.layers.19.mlp.up_proj": "100.0%",
+    "model.layers.19.mlp.down_proj": "100.0%",
+    "model.layers.19.input_layernorm": "100.0%",
+    "model.layers.19.post_attention_layernorm": "100.0%",
+    "model.layers.20.self_attn.q_proj": "55.9%",
+    "model.layers.20.self_attn.k_proj": "100.0%",
+    "model.layers.20.self_attn.v_proj": "100.0%",
+    "model.layers.20.self_attn.o_proj": "54.4%",
+    "model.layers.20.mlp.gate_proj": "100.0%",
+    "model.layers.20.mlp.up_proj": "100.0%",
+    "model.layers.20.mlp.down_proj": "100.0%",
+    "model.layers.20.input_layernorm": "100.0%",
+    "model.layers.20.post_attention_layernorm": "100.0%",
+    "model.layers.21.self_attn.q_proj": "56.6%",
+    "model.layers.21.self_attn.k_proj": "100.0%",
+    "model.layers.21.self_attn.v_proj": "55.0%",
+    "model.layers.21.self_attn.o_proj": "54.8%",
+    "model.layers.21.mlp.gate_proj": "100.0%",
+    "model.layers.21.mlp.up_proj": "100.0%",
+    "model.layers.21.mlp.down_proj": "100.0%",
+    "model.layers.21.input_layernorm": "100.0%",
+    "model.layers.21.post_attention_layernorm": "100.0%",
+    "model.layers.22.self_attn.q_proj": "100.0%",
+    "model.layers.22.self_attn.k_proj": "100.0%",
+    "model.layers.22.self_attn.v_proj": "100.0%",
+    "model.layers.22.self_attn.o_proj": "55.7%",
+    "model.layers.22.mlp.gate_proj": "100.0%",
+    "model.layers.22.mlp.up_proj": "100.0%",
+    "model.layers.22.mlp.down_proj": "54.3%",
+    "model.layers.22.input_layernorm": "100.0%",
+    "model.layers.22.post_attention_layernorm": "100.0%",
+    "model.layers.23.self_attn.q_proj": "100.0%",
+    "model.layers.23.self_attn.k_proj": "58.9%",
+    "model.layers.23.self_attn.v_proj": "56.5%",
+    "model.layers.23.self_attn.o_proj": "55.9%",
+    "model.layers.23.mlp.gate_proj": "53.9%",
+    "model.layers.23.mlp.up_proj": "53.4%",
+    "model.layers.23.mlp.down_proj": "100.0%",
+    "model.layers.23.input_layernorm": "100.0%",
+    "model.layers.23.post_attention_layernorm": "100.0%",
+    "model.layers.24.self_attn.q_proj": "58.3%",
+    "model.layers.24.self_attn.k_proj": "59.2%",
+    "model.layers.24.self_attn.v_proj": "56.9%",
+    "model.layers.24.self_attn.o_proj": "100.0%",
+    "model.layers.24.mlp.gate_proj": "100.0%",
+    "model.layers.24.mlp.up_proj": "100.0%",
+    "model.layers.24.mlp.down_proj": "100.0%",
+    "model.layers.24.input_layernorm": "90.4%",
+    "model.layers.24.post_attention_layernorm": "97.6%",
+    "model.layers.25.self_attn.q_proj": "59.6%",
+    "model.layers.25.self_attn.k_proj": "60.6%",
+    "model.layers.25.self_attn.v_proj": "58.9%",
+    "model.layers.25.self_attn.o_proj": "59.0%",
+    "model.layers.25.mlp.gate_proj": "53.1%",
+    "model.layers.25.mlp.up_proj": "52.7%",
+    "model.layers.25.mlp.down_proj": "53.4%",
+    "model.layers.25.input_layernorm": "88.3%",
+    "model.layers.25.post_attention_layernorm": "98.5%",
+    "model.layers.26.self_attn.q_proj": "60.1%",
+    "model.layers.26.self_attn.k_proj": "60.9%",
+    "model.layers.26.self_attn.v_proj": "59.9%",
+    "model.layers.26.self_attn.o_proj": "59.5%",
+    "model.layers.26.mlp.gate_proj": "100.0%",
+    "model.layers.26.mlp.up_proj": "52.4%",
+    "model.layers.26.mlp.down_proj": "100.0%",
+    "model.layers.26.input_layernorm": "93.0%",
+    "model.layers.26.post_attention_layernorm": "97.7%",
+    "model.layers.27.self_attn.q_proj": "62.4%",
+    "model.layers.27.self_attn.k_proj": "63.4%",
+    "model.layers.27.self_attn.v_proj": "61.1%",
+    "model.layers.27.self_attn.o_proj": "61.5%",
+    "model.layers.27.mlp.gate_proj": "52.2%",
+    "model.layers.27.mlp.up_proj": "51.9%",
+    "model.layers.27.mlp.down_proj": "100.0%",
+    "model.layers.27.input_layernorm": "90.0%",
+    "model.layers.27.post_attention_layernorm": "99.3%",
+    "model.layers.28.self_attn.q_proj": "63.6%",
+    "model.layers.28.self_attn.k_proj": "63.9%",
+    "model.layers.28.self_attn.v_proj": "64.9%",
+    "model.layers.28.self_attn.o_proj": "63.7%",
+    "model.layers.28.mlp.gate_proj": "51.7%",
+    "model.layers.28.mlp.up_proj": "51.5%",
+    "model.layers.28.mlp.down_proj": "52.2%",
+    "model.layers.28.input_layernorm": "100.0%",
+    "model.layers.28.post_attention_layernorm": "98.9%",
+    "model.layers.29.self_attn.q_proj": "66.8%",
+    "model.layers.29.self_attn.k_proj": "66.9%",
+    "model.layers.29.self_attn.v_proj": "70.3%",
+    "model.layers.29.self_attn.o_proj": "67.9%",
+    "model.layers.29.mlp.gate_proj": "100.0%",
+    "model.layers.29.mlp.up_proj": "51.2%",
+    "model.layers.29.mlp.down_proj": "51.8%",
+    "model.layers.29.input_layernorm": "87.3%",
+    "model.layers.29.post_attention_layernorm": "97.5%",
+    "model.layers.30.self_attn.q_proj": "100.0%",
+    "model.layers.30.self_attn.k_proj": "100.0%",
+    "model.layers.30.self_attn.v_proj": "76.8%",
+    "model.layers.30.self_attn.o_proj": "100.0%",
+    "model.layers.30.mlp.gate_proj": "50.9%",
+    "model.layers.30.mlp.up_proj": "100.0%",
+    "model.layers.30.mlp.down_proj": "100.0%",
+    "model.layers.30.input_layernorm": "100.0%",
+    "model.layers.30.post_attention_layernorm": "92.7%",
+    "model.layers.31.self_attn.q_proj": "100.0%",
+    "model.layers.31.self_attn.k_proj": "100.0%",
+    "model.layers.31.self_attn.v_proj": "100.0%",
+    "model.layers.31.self_attn.o_proj": "100.0%",
+    "model.layers.31.mlp.gate_proj": "100.0%",
+    "model.layers.31.mlp.up_proj": "100.0%",
+    "model.layers.31.mlp.down_proj": "50.7%",
+    "model.layers.31.input_layernorm": "100.0%",
+    "model.layers.31.post_attention_layernorm": "87.4%",
+    "model.norm": "100.0%",
+    "lm_head": "100.0%"
+}

model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5862897ccc81931b09adc690607f547b04d95dd9eb0ac90e591ebb642d90ad0f
+size 4943162336

model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad314b0b73c85b78546f5c2f1327e2431155ffd10b7bf7571e27f92ec4123d47
+size 4999819336

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:75ae379d2cfb5f1544c5cc52d58705a104d01b571d050b666b2f1fc590a4e300
+size 4540516344

model.safetensors.index.json

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

special_tokens_map.json

@@ -0,0 +1,29 @@
+{
+  "additional_special_tokens": [
+    "<unk>",
+    "<s>",
+    "</s>"
+  ],
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<unk>",
+  "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 +1,52 @@
+{
+  "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": [
+    "<unk>",
+    "<s>",
+    "</s>"
+  ],
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "device_map": "auto",
+  "eos_token": "<|im_end|>",
+  "legacy": true,
+  "max_length": 16384,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": null,
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "trust_remote_code": false,
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true,
+  "use_fast": true
+}