Upload folder using huggingface_hub

config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "SauerkrautLM-Phi-3-medium",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 32000,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 17920,
+  "max_position_embeddings": 4096,
+  "model_type": "mistral",
+  "num_attention_heads": 40,
+  "num_hidden_layers": 40,
+  "num_key_value_heads": 10,
+  "pad_token_id": 32009,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 10000.0,
+  "sliding_window": 2048,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.41.2",
+  "use_cache": true,
+  "vocab_size": 32064
+}

model-00001-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f3299b8496e4f20d976f8c75f7cf92d6911d75a1bacbcee7f60d3d2c22c30d7
+size 4929757784

model-00002-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8a076a6e10c8b0d549613dd33cc2f3e4543a84a11120c0270ca3d668cc191d3
+size 4954672440

model-00003-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d5ba632e55386033db7cc00288d7e54bcb874e677c5e28370475f2e351050354
+size 4967790112

model-00004-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d2b1fa3b36d7cfd644898790730e595461a76962f91d6e3d5439e88b4b94332c
+size 4889147016

model-00005-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7903e2ffef9570712bb7d36edf86c4603b40590ffe44e3847a6e221ac05c23d4
+size 4954672440

model-00006-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:167c2343adbb7017402a1c5d8714a3e3f91536d01a6d022c7e8ead02e93c4019
+size 3224478688

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.4.2", "total_size": 27920476160}, "weight_map": {"lm_head.weight": "model-00001-of-00006.safetensors", "model.embed_tokens.weight": "model-00001-of-00006.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00006.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00006.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00006.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00001-of-00006.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00006.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00006.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00006.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00006.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00006.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00006.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00001-of-00006.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00006.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00001-of-00006.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00006.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00006.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00006.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00006.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00006.safetensors", "model.layers.10.input_layernorm.weight": "model-00001-of-00006.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00001-of-00006.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00006.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00001-of-00006.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00006.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00006.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00006.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00006.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00006.safetensors", "model.layers.11.input_layernorm.weight": "model-00001-of-00006.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00001-of-00006.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00006.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00001-of-00006.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00006.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00006.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00006.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00006.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00006.safetensors", "model.layers.12.input_layernorm.weight": "model-00001-of-00006.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00001-of-00006.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00006.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00001-of-00006.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00006.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00006.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00006.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00006.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00006.safetensors", "model.layers.13.input_layernorm.weight": "model-00001-of-00006.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00001-of-00006.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00006.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00001-of-00006.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00006.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00006.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00006.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00006.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00006.safetensors", "model.layers.14.input_layernorm.weight": "model-00001-of-00006.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00001-of-00006.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00006.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00002-of-00006.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00006.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00006.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00006.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00006.safetensors", "model.layers.15.input_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00002-of-00006.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00006.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00002-of-00006.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00006.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00006.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00006.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00006.safetensors", "model.layers.16.input_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00002-of-00006.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00006.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00002-of-00006.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00006.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00006.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00006.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00006.safetensors", "model.layers.17.input_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00002-of-00006.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00006.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00002-of-00006.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00006.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00006.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00006.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00006.safetensors", "model.layers.18.input_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00002-of-00006.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00006.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00002-of-00006.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00006.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00006.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00006.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00006.safetensors", "model.layers.19.input_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00002-of-00006.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00006.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00002-of-00006.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00006.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00006.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00006.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00006.safetensors", "model.layers.2.input_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00002-of-00006.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00002-of-00006.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00002-of-00006.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00002-of-00006.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00002-of-00006.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00002-of-00006.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00002-of-00006.safetensors", "model.layers.20.input_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00002-of-00006.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00006.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00003-of-00006.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00006.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00006.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00006.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00006.safetensors", "model.layers.21.input_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00003-of-00006.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00006.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00003-of-00006.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00006.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00006.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00006.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00006.safetensors", "model.layers.22.input_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00003-of-00006.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00006.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00003-of-00006.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00006.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00006.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00006.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00006.safetensors", "model.layers.23.input_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00003-of-00006.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00006.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00003-of-00006.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00006.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00006.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00006.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00006.safetensors", "model.layers.24.input_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00003-of-00006.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00006.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00003-of-00006.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00006.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00006.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00006.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00006.safetensors", "model.layers.25.input_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00003-of-00006.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00006.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00003-of-00006.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00006.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00006.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00006.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00006.safetensors", "model.layers.26.input_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00003-of-00006.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00006.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00003-of-00006.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00006.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00006.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00006.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00006.safetensors", "model.layers.27.input_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00003-of-00006.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00006.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00003-of-00006.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00006.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00004-of-00006.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00004-of-00006.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00004-of-00006.safetensors", "model.layers.28.input_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00004-of-00006.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00004-of-00006.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00004-of-00006.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00004-of-00006.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00004-of-00006.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00004-of-00006.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00004-of-00006.safetensors", "model.layers.29.input_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00004-of-00006.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00004-of-00006.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00004-of-00006.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00004-of-00006.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00004-of-00006.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00004-of-00006.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00004-of-00006.safetensors", "model.layers.3.input_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00004-of-00006.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00004-of-00006.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00004-of-00006.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00004-of-00006.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00004-of-00006.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00004-of-00006.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00004-of-00006.safetensors", "model.layers.30.input_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00004-of-00006.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00004-of-00006.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00004-of-00006.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00004-of-00006.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00004-of-00006.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00004-of-00006.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00004-of-00006.safetensors", "model.layers.31.input_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00004-of-00006.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00004-of-00006.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00004-of-00006.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00004-of-00006.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00004-of-00006.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00004-of-00006.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00004-of-00006.safetensors", "model.layers.32.input_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00004-of-00006.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00004-of-00006.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00004-of-00006.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00004-of-00006.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00004-of-00006.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00004-of-00006.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00004-of-00006.safetensors", "model.layers.33.input_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00004-of-00006.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00004-of-00006.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00004-of-00006.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00004-of-00006.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00004-of-00006.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00004-of-00006.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00004-of-00006.safetensors", "model.layers.34.input_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00005-of-00006.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00005-of-00006.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00005-of-00006.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00005-of-00006.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00005-of-00006.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00005-of-00006.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00005-of-00006.safetensors", "model.layers.35.input_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00005-of-00006.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00005-of-00006.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00005-of-00006.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00005-of-00006.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00005-of-00006.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00005-of-00006.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00005-of-00006.safetensors", "model.layers.36.input_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00005-of-00006.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00005-of-00006.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00005-of-00006.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00005-of-00006.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00005-of-00006.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00005-of-00006.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00005-of-00006.safetensors", "model.layers.37.input_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00005-of-00006.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00005-of-00006.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00005-of-00006.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00005-of-00006.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00005-of-00006.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00005-of-00006.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00005-of-00006.safetensors", "model.layers.38.input_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00005-of-00006.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00005-of-00006.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00005-of-00006.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00005-of-00006.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00005-of-00006.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00005-of-00006.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00005-of-00006.safetensors", "model.layers.39.input_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00005-of-00006.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00005-of-00006.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00005-of-00006.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00005-of-00006.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00005-of-00006.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00005-of-00006.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00005-of-00006.safetensors", "model.layers.4.input_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00005-of-00006.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00005-of-00006.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00005-of-00006.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00005-of-00006.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00005-of-00006.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00005-of-00006.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00005-of-00006.safetensors", "model.layers.5.input_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00005-of-00006.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00006-of-00006.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00006-of-00006.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00006-of-00006.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00006-of-00006.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00006-of-00006.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00006-of-00006.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00006-of-00006.safetensors", "model.layers.6.input_layernorm.weight": "model-00006-of-00006.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00006-of-00006.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00006-of-00006.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00006-of-00006.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00006-of-00006.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00006-of-00006.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00006-of-00006.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00006-of-00006.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00006-of-00006.safetensors", "model.layers.7.input_layernorm.weight": "model-00006-of-00006.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00006-of-00006.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00006-of-00006.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00006-of-00006.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00006-of-00006.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00006-of-00006.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00006-of-00006.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00006-of-00006.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00006-of-00006.safetensors", "model.layers.8.input_layernorm.weight": "model-00006-of-00006.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00006-of-00006.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00006-of-00006.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00006-of-00006.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00006-of-00006.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00006-of-00006.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00006-of-00006.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00006-of-00006.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00006-of-00006.safetensors", "model.layers.9.input_layernorm.weight": "model-00006-of-00006.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00006-of-00006.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00006-of-00006.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00006-of-00006.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00006-of-00006.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00006-of-00006.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00006-of-00006.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00006-of-00006.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00006-of-00006.safetensors", "model.norm.weight": "model-00006-of-00006.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": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|placeholder6|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": true,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -0,0 +1,130 @@
+{
+  "add_bos_token": false,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "32000": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32001": {
+      "content": "<|assistant|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32002": {
+      "content": "<|placeholder1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32003": {
+      "content": "<|placeholder2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32004": {
+      "content": "<|placeholder3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32005": {
+      "content": "<|placeholder4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32006": {
+      "content": "<|system|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32007": {
+      "content": "<|end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32008": {
+      "content": "<|placeholder5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32009": {
+      "content": "<|placeholder6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32010": {
+      "content": "<|user|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "chat_template": "{% for message in messages %}{% if (message['role'] == 'user') %}{{'<|user|>' + '\n' + message['content'] + '<|end|>' + '\n' + '<|assistant|>' + '\n'}}{% elif (message['role'] == 'assistant') %}{{message['content'] + '<|end|>' + '\n'}}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "legacy": true,
+  "model_max_length": 4096,
+  "pad_token": "<|placeholder6|>",
+  "padding_side": "left",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}