Upload folder using huggingface_hub

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "<|end_of_turn|>": 32000,
+  "<|pad_0|>": 32001
+}

config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "banghua/openchat-3.5-1210-bin",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "bos_token_id": 1,
+  "eos_token_id": 32000,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 8192,
+  "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": "4.35.2",
+  "use_cache": true,
+  "vocab_size": 32002
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 32000,
+  "transformers_version": "4.35.2"
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4fbde77e5aa9e13dd14cd2847f384b498987afb3b6b33f67687e06ff9c05bbac
+size 4970475216

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ac21cfa010b45143ac38109fbaedd6ddf4e63c89f14fbd716665184a9b7c1bd
+size 4915917240

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:abd6724d2016b1238c757c03adc8a1e2577c40f8c7da08cc650ad818bcc31b39
+size 4915917280

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84d69f8892140b9772d6b2a3b91f8c38545c532d8018718d954d03c55771746b
+size 3957531176

model.safetensors.index.json

@@ -0,0 +1,376 @@
+{
+  "metadata": {
+    "total_size": 18759794688
+  },
+  "weight_map": {
+    "base_model.lm_head.weight": "model-00004-of-00004.safetensors",
+    "base_model.model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "base_model.model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "base_model.model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "base_model.model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "base_model.model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "base_model.model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "base_model.model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "base_model.model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "base_model.model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "base_model.model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "base_model.model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "base_model.model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "base_model.model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "base_model.model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "base_model.model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "base_model.model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "base_model.model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "base_model.model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "base_model.model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "base_model.model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "base_model.model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "base_model.model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "base_model.model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "base_model.model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "base_model.model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "base_model.model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "base_model.model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "base_model.model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "base_model.model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "base_model.model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "base_model.model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "base_model.model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "base_model.model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "base_model.model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "base_model.model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "base_model.model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "base_model.model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "base_model.model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "base_model.model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "base_model.model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "base_model.model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "base_model.model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "base_model.model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "base_model.model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "base_model.model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "base_model.model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "base_model.model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "base_model.model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "base_model.model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "base_model.model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "base_model.model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "base_model.model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "base_model.model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "base_model.model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "base_model.model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "base_model.model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "base_model.model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "base_model.model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "base_model.model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "base_model.model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "base_model.model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "base_model.model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "base_model.model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "base_model.model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "base_model.model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "base_model.model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "base_model.model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "base_model.model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "base_model.model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "base_model.model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "base_model.model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "base_model.model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "base_model.model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "base_model.model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "base_model.model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "base_model.model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "base_model.model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "base_model.model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "base_model.model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "base_model.model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "base_model.model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "base_model.model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "base_model.model.layers.17.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "base_model.model.layers.17.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "base_model.model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "base_model.model.layers.17.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "base_model.model.layers.17.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "base_model.model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "base_model.model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "base_model.model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "base_model.model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "base_model.model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "base_model.model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "base_model.model.layers.18.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "base_model.model.layers.18.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "base_model.model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "base_model.model.layers.18.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "base_model.model.layers.18.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "base_model.model.layers.18.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "base_model.model.layers.18.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "base_model.model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "base_model.model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "base_model.model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "base_model.model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "base_model.model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "base_model.model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "base_model.model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "base_model.model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "base_model.model.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "base_model.model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "base_model.model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "base_model.model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "base_model.model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "base_model.model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "base_model.model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "base_model.model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "base_model.model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "base_model.model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "base_model.model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "base_model.model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "base_model.model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "base_model.model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "base_model.model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "base_model.model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "base_model.model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "base_model.model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "base_model.model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "base_model.model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "base_model.model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "base_model.model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "base_model.model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "base_model.model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "base_model.model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "base_model.model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "base_model.model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "base_model.model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "base_model.model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "base_model.model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "base_model.model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "base_model.model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "base_model.model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "base_model.model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "base_model.model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "base_model.model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "base_model.model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "base_model.model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "base_model.model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "base_model.model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "base_model.model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "base_model.model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "base_model.model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "base_model.model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "base_model.model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "base_model.model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "base_model.model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "base_model.model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "base_model.model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "base_model.model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "base_model.model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "base_model.model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "base_model.model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "base_model.model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "base_model.model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "base_model.model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "base_model.model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "base_model.model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "base_model.model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "base_model.model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "base_model.model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "base_model.model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "base_model.model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "base_model.model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "base_model.model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "base_model.model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "base_model.model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "base_model.model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "base_model.model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "base_model.model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "base_model.model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "base_model.model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "base_model.model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "base_model.model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "base_model.model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "base_model.model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "base_model.model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "base_model.model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "base_model.model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "base_model.model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "base_model.model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "base_model.model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "base_model.model.layers.28.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "base_model.model.layers.28.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "base_model.model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "base_model.model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "base_model.model.layers.28.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "base_model.model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "base_model.model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "base_model.model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "base_model.model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "base_model.model.layers.29.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "base_model.model.layers.29.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "base_model.model.layers.29.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "base_model.model.layers.29.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "base_model.model.layers.29.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "base_model.model.layers.29.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "base_model.model.layers.29.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "base_model.model.layers.29.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "base_model.model.layers.29.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "base_model.model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "base_model.model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "base_model.model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "base_model.model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "base_model.model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "base_model.model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "base_model.model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "base_model.model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "base_model.model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "base_model.model.layers.30.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "base_model.model.layers.30.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "base_model.model.layers.30.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "base_model.model.layers.30.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "base_model.model.layers.30.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "base_model.model.layers.30.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "base_model.model.layers.30.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "base_model.model.layers.30.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "base_model.model.layers.30.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "base_model.model.layers.31.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "base_model.model.layers.31.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "base_model.model.layers.31.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "base_model.model.layers.31.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "base_model.model.layers.31.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "base_model.model.layers.31.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "base_model.model.layers.31.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "base_model.model.layers.31.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "base_model.model.layers.31.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "base_model.model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "base_model.model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "base_model.model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "base_model.model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "base_model.model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "base_model.model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "base_model.model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "base_model.model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "base_model.model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "base_model.model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "base_model.model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "base_model.model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "base_model.model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "base_model.model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "base_model.model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "base_model.model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "base_model.model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "base_model.model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "base_model.model.layers.6.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "base_model.model.layers.6.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "base_model.model.layers.6.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "base_model.model.layers.6.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "base_model.model.layers.6.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "base_model.model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "base_model.model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "base_model.model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "base_model.model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "base_model.model.layers.7.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "base_model.model.layers.7.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "base_model.model.layers.7.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "base_model.model.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "base_model.model.layers.7.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "base_model.model.layers.7.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "base_model.model.layers.7.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "base_model.model.layers.7.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "base_model.model.layers.7.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "base_model.model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "base_model.model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "base_model.model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "base_model.model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "base_model.model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "base_model.model.layers.8.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "base_model.model.layers.8.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "base_model.model.layers.8.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "base_model.model.layers.8.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "base_model.model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "base_model.model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "base_model.model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "base_model.model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "base_model.model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "base_model.model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "base_model.model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "base_model.model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "base_model.model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "base_model.model.norm.weight": "model-00004-of-00004.safetensors",
+    "frozen_head.embed_tokens.weight": "model-00004-of-00004.safetensors",
+    "frozen_head.layers.0.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "frozen_head.layers.0.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "frozen_head.layers.0.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "frozen_head.layers.0.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "frozen_head.layers.0.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "frozen_head.layers.0.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "frozen_head.layers.0.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "frozen_head.layers.0.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "frozen_head.layers.0.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "frozen_head.layers.1.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "frozen_head.layers.1.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "frozen_head.layers.1.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "frozen_head.layers.1.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "frozen_head.layers.1.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "frozen_head.layers.1.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "frozen_head.layers.1.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "frozen_head.layers.1.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "frozen_head.layers.1.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "frozen_head.layers.2.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "frozen_head.layers.2.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "frozen_head.layers.2.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "frozen_head.layers.2.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "frozen_head.layers.2.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "frozen_head.layers.2.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "frozen_head.layers.2.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "frozen_head.layers.2.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "frozen_head.layers.2.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "frozen_head.layers.3.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "frozen_head.layers.3.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "frozen_head.layers.3.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "frozen_head.layers.3.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "frozen_head.layers.3.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "frozen_head.layers.3.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "frozen_head.layers.3.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "frozen_head.layers.3.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "frozen_head.layers.3.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "frozen_head.lm_head.weight": "model-00004-of-00004.safetensors",
+    "frozen_head.norm.weight": "model-00004-of-00004.safetensors",
+    "v_head.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "v_head.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "v_head.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "v_head.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "v_head.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "v_head.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "v_head.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "v_head.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "v_head.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "v_head.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "v_head.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "v_head.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "v_head.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "v_head.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "v_head.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "v_head.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "v_head.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "v_head.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "v_head.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "v_head.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "v_head.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "v_head.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "v_head.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "v_head.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "v_head.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "v_head.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "v_head.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "v_head.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "v_head.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "v_head.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "v_head.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "v_head.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "v_head.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "v_head.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "v_head.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "v_head.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "v_head.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "v_head.lm_head.weight": "model-00001-of-00004.safetensors",
+    "v_head.norm.weight": "model-00001-of-00004.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,29 @@
+{
+  "additional_special_tokens": [
+    "<|end_of_turn|>",
+    "<|pad_0|>"
+  ],
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|end_of_turn|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|end_of_turn|>",
+  "sep_token": "<sep>",
+  "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 +1,63 @@
+{
+  "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
+    },
+    "32000": {
+      "content": "<|end_of_turn|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32001": {
+      "content": "<|pad_0|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|end_of_turn|>",
+    "<|pad_0|>"
+  ],
+  "bos_token": "<s>",
+  "chat_template": "{{ bos_token }}{% for message in messages %}{{ 'GPT4 Correct ' + message['role'].title() + ': ' + message['content'] + '<|end_of_turn|>'}}{% endfor %}{% if add_generation_prompt %}{{ 'GPT4 Correct Assistant:' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|end_of_turn|>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<|end_of_turn|>",
+  "sep_token": "<sep>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true
+}