Upload model

config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "/root/top2",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 15,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 1024000,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 40,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.42.4",
+  "use_cache": false,
+  "vocab_size": 131072
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "do_sample": true,
+  "eos_token_id": 2,
+  "transformers_version": "4.44.2"
+}

model-00001-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:caec62440df60066dbbd8fd7594c1f55873a0bc11cfc8397bb061938a72faf14
+size 2977966656

model-00002-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5b0f3cd66dc1318827b4442267c350e96f8dad16f344f58b8e108cf405ff619
+size 2978084776

model-00003-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c16c2f55b8fde6645cf7d4c42ecd878b06da3c3422d646d435e1d5986fed047c
+size 2873206016

model-00004-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe7e8d044d35186e4038a89c81d2eb6bcd8a660573bd63afbf2defb7594c44be
+size 2873206000

model-00005-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:874595be413521886d8c0eb77cf7f227f38cf7a042982904ee0579c52635d04e
+size 2978084792

model-00006-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:589d2194b9f7da35947b2880ba441b055d5b6d3eedaf2f556c9ef74e8edce655
+size 2873206008

model-00007-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:009d0082f96da146358d69c86883ec2c30195587c162d54e28233b319fe80eef
+size 2873206008

model-00008-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:880c38e3d0e2dbc230262855d0bb4226f42c7b58c5276c5d24bd14c3b6df9188
+size 2978084760

model-00009-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c802457dd859778a0183dd7f346c8fd6dea0df831e9580d3b30a026d6b40e09
+size 1090562072

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.4.4", "total_size": 24495564800}, "weight_map": {"lm_head.weight": "model-00001-of-00009.safetensors", "model.embed_tokens.weight": "model-00001-of-00009.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00009.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00009.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00009.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00002-of-00009.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00002-of-00009.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00002-of-00009.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00002-of-00009.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00002-of-00009.safetensors", "model.layers.1.input_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00002-of-00009.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00002-of-00009.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00002-of-00009.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00009.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00009.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00009.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00009.safetensors", "model.layers.10.input_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00002-of-00009.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00009.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00002-of-00009.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00009.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00009.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00009.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00009.safetensors", "model.layers.11.input_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00002-of-00009.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00009.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00002-of-00009.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00009.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00009.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00009.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00009.safetensors", "model.layers.12.input_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00002-of-00009.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00009.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00002-of-00009.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00009.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00009.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00009.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00009.safetensors", "model.layers.13.input_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00002-of-00009.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00009.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00002-of-00009.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00009.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00009.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00009.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00009.safetensors", "model.layers.14.input_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00003-of-00009.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00003-of-00009.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00003-of-00009.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00009.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00009.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00009.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00009.safetensors", "model.layers.15.input_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00003-of-00009.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00003-of-00009.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00003-of-00009.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00003-of-00009.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00009.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00003-of-00009.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00009.safetensors", "model.layers.16.input_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00003-of-00009.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00009.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00003-of-00009.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00009.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00009.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00009.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00009.safetensors", "model.layers.17.input_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00003-of-00009.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00009.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00003-of-00009.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00009.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00009.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00009.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00009.safetensors", "model.layers.18.input_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00003-of-00009.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00009.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00003-of-00009.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00009.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00009.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00009.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00009.safetensors", "model.layers.19.input_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00003-of-00009.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00004-of-00009.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00004-of-00009.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00004-of-00009.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00004-of-00009.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00004-of-00009.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00004-of-00009.safetensors", "model.layers.2.input_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00004-of-00009.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00004-of-00009.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00004-of-00009.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00004-of-00009.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00004-of-00009.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00004-of-00009.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00004-of-00009.safetensors", "model.layers.20.input_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00004-of-00009.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00004-of-00009.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00004-of-00009.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00004-of-00009.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00004-of-00009.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00004-of-00009.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00004-of-00009.safetensors", "model.layers.21.input_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00004-of-00009.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00004-of-00009.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00004-of-00009.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00004-of-00009.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00004-of-00009.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00004-of-00009.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00004-of-00009.safetensors", "model.layers.22.input_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00004-of-00009.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00004-of-00009.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00004-of-00009.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00004-of-00009.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00004-of-00009.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00004-of-00009.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00004-of-00009.safetensors", "model.layers.23.input_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00004-of-00009.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00004-of-00009.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00005-of-00009.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00005-of-00009.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00005-of-00009.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00005-of-00009.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00005-of-00009.safetensors", "model.layers.24.input_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00005-of-00009.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00005-of-00009.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00005-of-00009.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00005-of-00009.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00005-of-00009.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00005-of-00009.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00005-of-00009.safetensors", "model.layers.25.input_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00005-of-00009.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00005-of-00009.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00005-of-00009.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00005-of-00009.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00005-of-00009.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00005-of-00009.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00005-of-00009.safetensors", "model.layers.26.input_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00005-of-00009.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00005-of-00009.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00005-of-00009.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00005-of-00009.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00005-of-00009.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00005-of-00009.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00005-of-00009.safetensors", "model.layers.27.input_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00005-of-00009.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00005-of-00009.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00005-of-00009.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00005-of-00009.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00005-of-00009.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00005-of-00009.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00005-of-00009.safetensors", "model.layers.28.input_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00005-of-00009.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00005-of-00009.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00005-of-00009.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00005-of-00009.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00005-of-00009.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00005-of-00009.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00005-of-00009.safetensors", "model.layers.29.input_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00006-of-00009.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00006-of-00009.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00006-of-00009.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00006-of-00009.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00006-of-00009.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00006-of-00009.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00006-of-00009.safetensors", "model.layers.3.input_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00006-of-00009.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00006-of-00009.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00006-of-00009.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00006-of-00009.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00006-of-00009.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00006-of-00009.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00006-of-00009.safetensors", "model.layers.30.input_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00006-of-00009.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00006-of-00009.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00006-of-00009.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00006-of-00009.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00006-of-00009.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00006-of-00009.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00006-of-00009.safetensors", "model.layers.31.input_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00006-of-00009.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00006-of-00009.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00006-of-00009.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00006-of-00009.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00006-of-00009.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00006-of-00009.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00006-of-00009.safetensors", "model.layers.32.input_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00006-of-00009.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00006-of-00009.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00006-of-00009.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00006-of-00009.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00006-of-00009.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00006-of-00009.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00006-of-00009.safetensors", "model.layers.33.input_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00006-of-00009.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00007-of-00009.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00007-of-00009.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00007-of-00009.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00007-of-00009.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00007-of-00009.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00007-of-00009.safetensors", "model.layers.34.input_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00007-of-00009.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00007-of-00009.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00007-of-00009.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00007-of-00009.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00007-of-00009.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00007-of-00009.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00007-of-00009.safetensors", "model.layers.35.input_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00007-of-00009.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00007-of-00009.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00007-of-00009.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00007-of-00009.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00007-of-00009.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00007-of-00009.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00007-of-00009.safetensors", "model.layers.36.input_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00007-of-00009.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00007-of-00009.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00007-of-00009.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00007-of-00009.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00007-of-00009.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00007-of-00009.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00007-of-00009.safetensors", "model.layers.37.input_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00007-of-00009.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00007-of-00009.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00007-of-00009.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00007-of-00009.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00007-of-00009.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00007-of-00009.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00007-of-00009.safetensors", "model.layers.38.input_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00007-of-00009.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00007-of-00009.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00008-of-00009.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00008-of-00009.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00008-of-00009.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00008-of-00009.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00008-of-00009.safetensors", "model.layers.39.input_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00008-of-00009.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00008-of-00009.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00008-of-00009.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00008-of-00009.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00008-of-00009.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00008-of-00009.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00008-of-00009.safetensors", "model.layers.4.input_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00008-of-00009.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00008-of-00009.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00008-of-00009.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00008-of-00009.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00008-of-00009.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00008-of-00009.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00008-of-00009.safetensors", "model.layers.5.input_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00008-of-00009.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00008-of-00009.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00008-of-00009.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00008-of-00009.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00008-of-00009.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00008-of-00009.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00008-of-00009.safetensors", "model.layers.6.input_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00008-of-00009.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00008-of-00009.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00008-of-00009.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00008-of-00009.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00008-of-00009.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00008-of-00009.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00008-of-00009.safetensors", "model.layers.7.input_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00008-of-00009.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00008-of-00009.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00008-of-00009.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00008-of-00009.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00008-of-00009.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00008-of-00009.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00008-of-00009.safetensors", "model.layers.8.input_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00009-of-00009.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00009-of-00009.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00009-of-00009.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00009-of-00009.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00009-of-00009.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00009-of-00009.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00009-of-00009.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00009-of-00009.safetensors", "model.layers.9.input_layernorm.weight": "model-00009-of-00009.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00009-of-00009.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00009-of-00009.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00009-of-00009.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00009-of-00009.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00009-of-00009.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00009-of-00009.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00009-of-00009.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00009-of-00009.safetensors", "model.norm.weight": "model-00009-of-00009.safetensors"}}

special_tokens_map.json

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