initial merge using undi's ratios

config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "/workspace/Amethyst-part1",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 13824,
+  "max_position_embeddings": 4096,
+  "model_type": "llama",
+  "num_attention_heads": 40,
+  "num_hidden_layers": 40,
+  "num_key_value_heads": 40,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.33.2",
+  "use_cache": false,
+  "vocab_size": 32000
+}

generation_config.json

@@ -0,0 +1,10 @@
+{
+  "bos_token_id": 1,
+  "do_sample": true,
+  "eos_token_id": 2,
+  "max_length": 4096,
+  "pad_token_id": 0,
+  "temperature": 0.6,
+  "top_p": 0.9,
+  "transformers_version": "4.33.2"
+}

pytorch_model-00001-of-00013.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b9a826bbab7331ef1c16ab39cf524dec76a252968058dc46e9eaea8626999841
+size 2089337041

pytorch_model-00002-of-00013.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dfb5f1c1ff8c9d20fab74f2fda36ddd7a7de56de697d2850d058fc21b6aafe38
+size 2044815083

pytorch_model-00003-of-00013.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:532384f6e329a29e52021736396b80d7db390b90bf297271c7771f5c46b6b8c8
+size 2060523307

pytorch_model-00004-of-00013.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6481dcea2a5f1440696cc27986eba780c04da5f3bd29634cd36e264e21cb20d8
+size 1955665095

pytorch_model-00005-of-00013.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d29f3b6dea575fb6831c036b9a10cec734fef5328874a17f19229c1e835490fa
+size 2044794055

pytorch_model-00006-of-00013.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a3c10a28535934e3055b1d9ae9c442df881a7bd17b7df493dbf30a55889f6bf
+size 2044794055

pytorch_model-00007-of-00013.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6fc2f105651c6000bf857d41cf9c165dc17db70e9ce9ab80f23c9aee74cfe862
+size 2044815147

pytorch_model-00008-of-00013.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe5223977c97646d80a08d79d08e45638f3c29c627890ea72c37b0d1aee8ac0b
+size 2060523307

pytorch_model-00009-of-00013.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4860c059402f841f9aa49e2de722cf83e74a95120405e1e7c7508fd30347eab
+size 1955665095

pytorch_model-00010-of-00013.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cbb67bb2d2257f9e63ea2b3e427f46224b6bd9e8a839bf7414b452825c0b446d
+size 2044794055

pytorch_model-00011-of-00013.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84f8b3efc9afcdc66a883d599120a888ee2c3b133d520751a7cde7b0e2b58953
+size 2044794055

pytorch_model-00012-of-00013.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87cbbaa3733a54279f7a5e1bb06d6a0c066dc1509b9b8430603a355d34c50ed1
+size 2044815147

pytorch_model-00013-of-00013.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a5e5557f4327ea2e02408be0ac642618eba5082ebda2e531246784593358fa77
+size 1596514999

pytorch_model.bin.index.json

@@ -0,0 +1,370 @@
+{
+  "metadata": {
+    "total_size": 26031728640
+  },
+  "weight_map": {
+    "lm_head.weight": "pytorch_model-00013-of-00013.bin",
+    "model.embed_tokens.weight": "pytorch_model-00001-of-00013.bin",
+    "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00013.bin",
+    "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00013.bin",
+    "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00013.bin",
+    "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00013.bin",
+    "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00013.bin",
+    "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00013.bin",
+    "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00013.bin",
+    "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00013.bin",
+    "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00013.bin",
+    "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00013.bin",
+    "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00013.bin",
+    "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00013.bin",
+    "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00013.bin",
+    "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00013.bin",
+    "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00013.bin",
+    "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00013.bin",
+    "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00013.bin",
+    "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00013.bin",
+    "model.layers.10.input_layernorm.weight": "pytorch_model-00004-of-00013.bin",
+    "model.layers.10.mlp.down_proj.weight": "pytorch_model-00004-of-00013.bin",
+    "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00004-of-00013.bin",
+    "model.layers.10.mlp.up_proj.weight": "pytorch_model-00004-of-00013.bin",
+    "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00004-of-00013.bin",
+    "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00004-of-00013.bin",
+    "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00004-of-00013.bin",
+    "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00004-of-00013.bin",
+    "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00004-of-00013.bin",
+    "model.layers.11.input_layernorm.weight": "pytorch_model-00004-of-00013.bin",
+    "model.layers.11.mlp.down_proj.weight": "pytorch_model-00004-of-00013.bin",
+    "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00004-of-00013.bin",
+    "model.layers.11.mlp.up_proj.weight": "pytorch_model-00004-of-00013.bin",
+    "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00004-of-00013.bin",
+    "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00004-of-00013.bin",
+    "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00004-of-00013.bin",
+    "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00004-of-00013.bin",
+    "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00004-of-00013.bin",
+    "model.layers.12.input_layernorm.weight": "pytorch_model-00005-of-00013.bin",
+    "model.layers.12.mlp.down_proj.weight": "pytorch_model-00005-of-00013.bin",
+    "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00005-of-00013.bin",
+    "model.layers.12.mlp.up_proj.weight": "pytorch_model-00005-of-00013.bin",
+    "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00005-of-00013.bin",
+    "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00004-of-00013.bin",
+    "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00004-of-00013.bin",
+    "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00004-of-00013.bin",
+    "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00004-of-00013.bin",
+    "model.layers.13.input_layernorm.weight": "pytorch_model-00005-of-00013.bin",
+    "model.layers.13.mlp.down_proj.weight": "pytorch_model-00005-of-00013.bin",
+    "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00005-of-00013.bin",
+    "model.layers.13.mlp.up_proj.weight": "pytorch_model-00005-of-00013.bin",
+    "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00005-of-00013.bin",
+    "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00005-of-00013.bin",
+    "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00005-of-00013.bin",
+    "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00005-of-00013.bin",
+    "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00005-of-00013.bin",
+    "model.layers.14.input_layernorm.weight": "pytorch_model-00005-of-00013.bin",
+    "model.layers.14.mlp.down_proj.weight": "pytorch_model-00005-of-00013.bin",
+    "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00005-of-00013.bin",
+    "model.layers.14.mlp.up_proj.weight": "pytorch_model-00005-of-00013.bin",
+    "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00005-of-00013.bin",
+    "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00005-of-00013.bin",
+    "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00005-of-00013.bin",
+    "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00005-of-00013.bin",
+    "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00005-of-00013.bin",
+    "model.layers.15.input_layernorm.weight": "pytorch_model-00006-of-00013.bin",
+    "model.layers.15.mlp.down_proj.weight": "pytorch_model-00006-of-00013.bin",
+    "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00005-of-00013.bin",
+    "model.layers.15.mlp.up_proj.weight": "pytorch_model-00006-of-00013.bin",
+    "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00006-of-00013.bin",
+    "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00005-of-00013.bin",
+    "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00005-of-00013.bin",
+    "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00005-of-00013.bin",
+    "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00005-of-00013.bin",
+    "model.layers.16.input_layernorm.weight": "pytorch_model-00006-of-00013.bin",
+    "model.layers.16.mlp.down_proj.weight": "pytorch_model-00006-of-00013.bin",
+    "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00006-of-00013.bin",
+    "model.layers.16.mlp.up_proj.weight": "pytorch_model-00006-of-00013.bin",
+    "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00006-of-00013.bin",
+    "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00006-of-00013.bin",
+    "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00006-of-00013.bin",
+    "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00006-of-00013.bin",
+    "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00006-of-00013.bin",
+    "model.layers.17.input_layernorm.weight": "pytorch_model-00006-of-00013.bin",
+    "model.layers.17.mlp.down_proj.weight": "pytorch_model-00006-of-00013.bin",
+    "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00006-of-00013.bin",
+    "model.layers.17.mlp.up_proj.weight": "pytorch_model-00006-of-00013.bin",
+    "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00006-of-00013.bin",
+    "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00006-of-00013.bin",
+    "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00006-of-00013.bin",
+    "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00006-of-00013.bin",
+    "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00006-of-00013.bin",
+    "model.layers.18.input_layernorm.weight": "pytorch_model-00007-of-00013.bin",
+    "model.layers.18.mlp.down_proj.weight": "pytorch_model-00007-of-00013.bin",
+    "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00006-of-00013.bin",
+    "model.layers.18.mlp.up_proj.weight": "pytorch_model-00006-of-00013.bin",
+    "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00007-of-00013.bin",
+    "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00006-of-00013.bin",
+    "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00006-of-00013.bin",
+    "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00006-of-00013.bin",
+    "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00006-of-00013.bin",
+    "model.layers.19.input_layernorm.weight": "pytorch_model-00007-of-00013.bin",
+    "model.layers.19.mlp.down_proj.weight": "pytorch_model-00007-of-00013.bin",
+    "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00007-of-00013.bin",
+    "model.layers.19.mlp.up_proj.weight": "pytorch_model-00007-of-00013.bin",
+    "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00007-of-00013.bin",
+    "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00007-of-00013.bin",
+    "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00007-of-00013.bin",
+    "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00007-of-00013.bin",
+    "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00007-of-00013.bin",
+    "model.layers.2.input_layernorm.weight": "pytorch_model-00002-of-00013.bin",
+    "model.layers.2.mlp.down_proj.weight": "pytorch_model-00002-of-00013.bin",
+    "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00013.bin",
+    "model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00013.bin",
+    "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00002-of-00013.bin",
+    "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00013.bin",
+    "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00013.bin",
+    "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00013.bin",
+    "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00013.bin",
+    "model.layers.20.input_layernorm.weight": "pytorch_model-00007-of-00013.bin",
+    "model.layers.20.mlp.down_proj.weight": "pytorch_model-00007-of-00013.bin",
+    "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00007-of-00013.bin",
+    "model.layers.20.mlp.up_proj.weight": "pytorch_model-00007-of-00013.bin",
+    "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00007-of-00013.bin",
+    "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00007-of-00013.bin",
+    "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00007-of-00013.bin",
+    "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00007-of-00013.bin",
+    "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00007-of-00013.bin",
+    "model.layers.21.input_layernorm.weight": "pytorch_model-00007-of-00013.bin",
+    "model.layers.21.mlp.down_proj.weight": "pytorch_model-00007-of-00013.bin",
+    "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00007-of-00013.bin",
+    "model.layers.21.mlp.up_proj.weight": "pytorch_model-00007-of-00013.bin",
+    "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00007-of-00013.bin",
+    "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00007-of-00013.bin",
+    "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00007-of-00013.bin",
+    "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00007-of-00013.bin",
+    "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00007-of-00013.bin",
+    "model.layers.22.input_layernorm.weight": "pytorch_model-00008-of-00013.bin",
+    "model.layers.22.mlp.down_proj.weight": "pytorch_model-00008-of-00013.bin",
+    "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00008-of-00013.bin",
+    "model.layers.22.mlp.up_proj.weight": "pytorch_model-00008-of-00013.bin",
+    "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00008-of-00013.bin",
+    "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00008-of-00013.bin",
+    "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00008-of-00013.bin",
+    "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00008-of-00013.bin",
+    "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00008-of-00013.bin",
+    "model.layers.23.input_layernorm.weight": "pytorch_model-00008-of-00013.bin",
+    "model.layers.23.mlp.down_proj.weight": "pytorch_model-00008-of-00013.bin",
+    "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00008-of-00013.bin",
+    "model.layers.23.mlp.up_proj.weight": "pytorch_model-00008-of-00013.bin",
+    "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00008-of-00013.bin",
+    "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00008-of-00013.bin",
+    "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00008-of-00013.bin",
+    "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00008-of-00013.bin",
+    "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00008-of-00013.bin",
+    "model.layers.24.input_layernorm.weight": "pytorch_model-00008-of-00013.bin",
+    "model.layers.24.mlp.down_proj.weight": "pytorch_model-00008-of-00013.bin",
+    "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00008-of-00013.bin",
+    "model.layers.24.mlp.up_proj.weight": "pytorch_model-00008-of-00013.bin",
+    "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00008-of-00013.bin",
+    "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00008-of-00013.bin",
+    "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00008-of-00013.bin",
+    "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00008-of-00013.bin",
+    "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00008-of-00013.bin",
+    "model.layers.25.input_layernorm.weight": "pytorch_model-00009-of-00013.bin",
+    "model.layers.25.mlp.down_proj.weight": "pytorch_model-00009-of-00013.bin",
+    "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00009-of-00013.bin",
+    "model.layers.25.mlp.up_proj.weight": "pytorch_model-00009-of-00013.bin",
+    "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00009-of-00013.bin",
+    "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00008-of-00013.bin",
+    "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00009-of-00013.bin",
+    "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00008-of-00013.bin",
+    "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00008-of-00013.bin",
+    "model.layers.26.input_layernorm.weight": "pytorch_model-00009-of-00013.bin",
+    "model.layers.26.mlp.down_proj.weight": "pytorch_model-00009-of-00013.bin",
+    "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00009-of-00013.bin",
+    "model.layers.26.mlp.up_proj.weight": "pytorch_model-00009-of-00013.bin",
+    "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00009-of-00013.bin",
+    "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00009-of-00013.bin",
+    "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00009-of-00013.bin",
+    "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00009-of-00013.bin",
+    "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00009-of-00013.bin",
+    "model.layers.27.input_layernorm.weight": "pytorch_model-00009-of-00013.bin",
+    "model.layers.27.mlp.down_proj.weight": "pytorch_model-00009-of-00013.bin",
+    "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00009-of-00013.bin",
+    "model.layers.27.mlp.up_proj.weight": "pytorch_model-00009-of-00013.bin",
+    "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00009-of-00013.bin",
+    "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00009-of-00013.bin",
+    "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00009-of-00013.bin",
+    "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00009-of-00013.bin",
+    "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00009-of-00013.bin",
+    "model.layers.28.input_layernorm.weight": "pytorch_model-00010-of-00013.bin",
+    "model.layers.28.mlp.down_proj.weight": "pytorch_model-00010-of-00013.bin",
+    "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00010-of-00013.bin",
+    "model.layers.28.mlp.up_proj.weight": "pytorch_model-00010-of-00013.bin",
+    "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00010-of-00013.bin",
+    "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00009-of-00013.bin",
+    "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00009-of-00013.bin",
+    "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00009-of-00013.bin",
+    "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00009-of-00013.bin",
+    "model.layers.29.input_layernorm.weight": "pytorch_model-00010-of-00013.bin",
+    "model.layers.29.mlp.down_proj.weight": "pytorch_model-00010-of-00013.bin",
+    "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00010-of-00013.bin",
+    "model.layers.29.mlp.up_proj.weight": "pytorch_model-00010-of-00013.bin",
+    "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00010-of-00013.bin",
+    "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00010-of-00013.bin",
+    "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00010-of-00013.bin",
+    "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00010-of-00013.bin",
+    "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00010-of-00013.bin",
+    "model.layers.3.input_layernorm.weight": "pytorch_model-00002-of-00013.bin",
+    "model.layers.3.mlp.down_proj.weight": "pytorch_model-00002-of-00013.bin",
+    "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00002-of-00013.bin",
+    "model.layers.3.mlp.up_proj.weight": "pytorch_model-00002-of-00013.bin",
+    "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00002-of-00013.bin",
+    "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00002-of-00013.bin",
+    "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00002-of-00013.bin",
+    "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00002-of-00013.bin",
+    "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00002-of-00013.bin",
+    "model.layers.30.input_layernorm.weight": "pytorch_model-00010-of-00013.bin",
+    "model.layers.30.mlp.down_proj.weight": "pytorch_model-00010-of-00013.bin",
+    "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00010-of-00013.bin",
+    "model.layers.30.mlp.up_proj.weight": "pytorch_model-00010-of-00013.bin",
+    "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00010-of-00013.bin",
+    "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00010-of-00013.bin",
+    "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00010-of-00013.bin",
+    "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00010-of-00013.bin",
+    "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00010-of-00013.bin",
+    "model.layers.31.input_layernorm.weight": "pytorch_model-00011-of-00013.bin",
+    "model.layers.31.mlp.down_proj.weight": "pytorch_model-00011-of-00013.bin",
+    "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00010-of-00013.bin",
+    "model.layers.31.mlp.up_proj.weight": "pytorch_model-00011-of-00013.bin",
+    "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00011-of-00013.bin",
+    "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00010-of-00013.bin",
+    "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00010-of-00013.bin",
+    "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00010-of-00013.bin",
+    "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00010-of-00013.bin",
+    "model.layers.32.input_layernorm.weight": "pytorch_model-00011-of-00013.bin",
+    "model.layers.32.mlp.down_proj.weight": "pytorch_model-00011-of-00013.bin",
+    "model.layers.32.mlp.gate_proj.weight": "pytorch_model-00011-of-00013.bin",
+    "model.layers.32.mlp.up_proj.weight": "pytorch_model-00011-of-00013.bin",
+    "model.layers.32.post_attention_layernorm.weight": "pytorch_model-00011-of-00013.bin",
+    "model.layers.32.self_attn.k_proj.weight": "pytorch_model-00011-of-00013.bin",
+    "model.layers.32.self_attn.o_proj.weight": "pytorch_model-00011-of-00013.bin",
+    "model.layers.32.self_attn.q_proj.weight": "pytorch_model-00011-of-00013.bin",
+    "model.layers.32.self_attn.v_proj.weight": "pytorch_model-00011-of-00013.bin",
+    "model.layers.33.input_layernorm.weight": "pytorch_model-00011-of-00013.bin",
+    "model.layers.33.mlp.down_proj.weight": "pytorch_model-00011-of-00013.bin",
+    "model.layers.33.mlp.gate_proj.weight": "pytorch_model-00011-of-00013.bin",
+    "model.layers.33.mlp.up_proj.weight": "pytorch_model-00011-of-00013.bin",
+    "model.layers.33.post_attention_layernorm.weight": "pytorch_model-00011-of-00013.bin",
+    "model.layers.33.self_attn.k_proj.weight": "pytorch_model-00011-of-00013.bin",
+    "model.layers.33.self_attn.o_proj.weight": "pytorch_model-00011-of-00013.bin",
+    "model.layers.33.self_attn.q_proj.weight": "pytorch_model-00011-of-00013.bin",
+    "model.layers.33.self_attn.v_proj.weight": "pytorch_model-00011-of-00013.bin",
+    "model.layers.34.input_layernorm.weight": "pytorch_model-00012-of-00013.bin",
+    "model.layers.34.mlp.down_proj.weight": "pytorch_model-00012-of-00013.bin",
+    "model.layers.34.mlp.gate_proj.weight": "pytorch_model-00011-of-00013.bin",
+    "model.layers.34.mlp.up_proj.weight": "pytorch_model-00011-of-00013.bin",
+    "model.layers.34.post_attention_layernorm.weight": "pytorch_model-00012-of-00013.bin",
+    "model.layers.34.self_attn.k_proj.weight": "pytorch_model-00011-of-00013.bin",
+    "model.layers.34.self_attn.o_proj.weight": "pytorch_model-00011-of-00013.bin",
+    "model.layers.34.self_attn.q_proj.weight": "pytorch_model-00011-of-00013.bin",
+    "model.layers.34.self_attn.v_proj.weight": "pytorch_model-00011-of-00013.bin",
+    "model.layers.35.input_layernorm.weight": "pytorch_model-00012-of-00013.bin",
+    "model.layers.35.mlp.down_proj.weight": "pytorch_model-00012-of-00013.bin",
+    "model.layers.35.mlp.gate_proj.weight": "pytorch_model-00012-of-00013.bin",
+    "model.layers.35.mlp.up_proj.weight": "pytorch_model-00012-of-00013.bin",
+    "model.layers.35.post_attention_layernorm.weight": "pytorch_model-00012-of-00013.bin",
+    "model.layers.35.self_attn.k_proj.weight": "pytorch_model-00012-of-00013.bin",
+    "model.layers.35.self_attn.o_proj.weight": "pytorch_model-00012-of-00013.bin",
+    "model.layers.35.self_attn.q_proj.weight": "pytorch_model-00012-of-00013.bin",
+    "model.layers.35.self_attn.v_proj.weight": "pytorch_model-00012-of-00013.bin",
+    "model.layers.36.input_layernorm.weight": "pytorch_model-00012-of-00013.bin",
+    "model.layers.36.mlp.down_proj.weight": "pytorch_model-00012-of-00013.bin",
+    "model.layers.36.mlp.gate_proj.weight": "pytorch_model-00012-of-00013.bin",
+    "model.layers.36.mlp.up_proj.weight": "pytorch_model-00012-of-00013.bin",
+    "model.layers.36.post_attention_layernorm.weight": "pytorch_model-00012-of-00013.bin",
+    "model.layers.36.self_attn.k_proj.weight": "pytorch_model-00012-of-00013.bin",
+    "model.layers.36.self_attn.o_proj.weight": "pytorch_model-00012-of-00013.bin",
+    "model.layers.36.self_attn.q_proj.weight": "pytorch_model-00012-of-00013.bin",
+    "model.layers.36.self_attn.v_proj.weight": "pytorch_model-00012-of-00013.bin",
+    "model.layers.37.input_layernorm.weight": "pytorch_model-00012-of-00013.bin",
+    "model.layers.37.mlp.down_proj.weight": "pytorch_model-00012-of-00013.bin",
+    "model.layers.37.mlp.gate_proj.weight": "pytorch_model-00012-of-00013.bin",
+    "model.layers.37.mlp.up_proj.weight": "pytorch_model-00012-of-00013.bin",
+    "model.layers.37.post_attention_layernorm.weight": "pytorch_model-00012-of-00013.bin",
+    "model.layers.37.self_attn.k_proj.weight": "pytorch_model-00012-of-00013.bin",
+    "model.layers.37.self_attn.o_proj.weight": "pytorch_model-00012-of-00013.bin",
+    "model.layers.37.self_attn.q_proj.weight": "pytorch_model-00012-of-00013.bin",
+    "model.layers.37.self_attn.v_proj.weight": "pytorch_model-00012-of-00013.bin",
+    "model.layers.38.input_layernorm.weight": "pytorch_model-00013-of-00013.bin",
+    "model.layers.38.mlp.down_proj.weight": "pytorch_model-00013-of-00013.bin",
+    "model.layers.38.mlp.gate_proj.weight": "pytorch_model-00013-of-00013.bin",
+    "model.layers.38.mlp.up_proj.weight": "pytorch_model-00013-of-00013.bin",
+    "model.layers.38.post_attention_layernorm.weight": "pytorch_model-00013-of-00013.bin",
+    "model.layers.38.self_attn.k_proj.weight": "pytorch_model-00013-of-00013.bin",
+    "model.layers.38.self_attn.o_proj.weight": "pytorch_model-00013-of-00013.bin",
+    "model.layers.38.self_attn.q_proj.weight": "pytorch_model-00013-of-00013.bin",
+    "model.layers.38.self_attn.v_proj.weight": "pytorch_model-00013-of-00013.bin",
+    "model.layers.39.input_layernorm.weight": "pytorch_model-00013-of-00013.bin",
+    "model.layers.39.mlp.down_proj.weight": "pytorch_model-00013-of-00013.bin",
+    "model.layers.39.mlp.gate_proj.weight": "pytorch_model-00013-of-00013.bin",
+    "model.layers.39.mlp.up_proj.weight": "pytorch_model-00013-of-00013.bin",
+    "model.layers.39.post_attention_layernorm.weight": "pytorch_model-00013-of-00013.bin",
+    "model.layers.39.self_attn.k_proj.weight": "pytorch_model-00013-of-00013.bin",
+    "model.layers.39.self_attn.o_proj.weight": "pytorch_model-00013-of-00013.bin",
+    "model.layers.39.self_attn.q_proj.weight": "pytorch_model-00013-of-00013.bin",
+    "model.layers.39.self_attn.v_proj.weight": "pytorch_model-00013-of-00013.bin",
+    "model.layers.4.input_layernorm.weight": "pytorch_model-00002-of-00013.bin",
+    "model.layers.4.mlp.down_proj.weight": "pytorch_model-00002-of-00013.bin",
+    "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00002-of-00013.bin",
+    "model.layers.4.mlp.up_proj.weight": "pytorch_model-00002-of-00013.bin",
+    "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00002-of-00013.bin",
+    "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00002-of-00013.bin",
+    "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00002-of-00013.bin",
+    "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00002-of-00013.bin",
+    "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00002-of-00013.bin",
+    "model.layers.5.input_layernorm.weight": "pytorch_model-00002-of-00013.bin",
+    "model.layers.5.mlp.down_proj.weight": "pytorch_model-00002-of-00013.bin",
+    "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00002-of-00013.bin",
+    "model.layers.5.mlp.up_proj.weight": "pytorch_model-00002-of-00013.bin",
+    "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00002-of-00013.bin",
+    "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00002-of-00013.bin",
+    "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00002-of-00013.bin",
+    "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00002-of-00013.bin",
+    "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00002-of-00013.bin",
+    "model.layers.6.input_layernorm.weight": "pytorch_model-00003-of-00013.bin",
+    "model.layers.6.mlp.down_proj.weight": "pytorch_model-00003-of-00013.bin",
+    "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00003-of-00013.bin",
+    "model.layers.6.mlp.up_proj.weight": "pytorch_model-00003-of-00013.bin",
+    "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00003-of-00013.bin",
+    "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00003-of-00013.bin",
+    "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00003-of-00013.bin",
+    "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00003-of-00013.bin",
+    "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00003-of-00013.bin",
+    "model.layers.7.input_layernorm.weight": "pytorch_model-00003-of-00013.bin",
+    "model.layers.7.mlp.down_proj.weight": "pytorch_model-00003-of-00013.bin",
+    "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00003-of-00013.bin",
+    "model.layers.7.mlp.up_proj.weight": "pytorch_model-00003-of-00013.bin",
+    "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00003-of-00013.bin",
+    "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00003-of-00013.bin",
+    "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00003-of-00013.bin",
+    "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00003-of-00013.bin",
+    "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00003-of-00013.bin",
+    "model.layers.8.input_layernorm.weight": "pytorch_model-00003-of-00013.bin",
+    "model.layers.8.mlp.down_proj.weight": "pytorch_model-00003-of-00013.bin",
+    "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00003-of-00013.bin",
+    "model.layers.8.mlp.up_proj.weight": "pytorch_model-00003-of-00013.bin",
+    "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00003-of-00013.bin",
+    "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00003-of-00013.bin",
+    "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00003-of-00013.bin",
+    "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00003-of-00013.bin",
+    "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00003-of-00013.bin",
+    "model.layers.9.input_layernorm.weight": "pytorch_model-00004-of-00013.bin",
+    "model.layers.9.mlp.down_proj.weight": "pytorch_model-00004-of-00013.bin",
+    "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00004-of-00013.bin",
+    "model.layers.9.mlp.up_proj.weight": "pytorch_model-00004-of-00013.bin",
+    "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00004-of-00013.bin",
+    "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00003-of-00013.bin",
+    "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00004-of-00013.bin",
+    "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00003-of-00013.bin",
+    "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00003-of-00013.bin",
+    "model.norm.weight": "pytorch_model-00013-of-00013.bin"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<unk>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

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

tokenizer_config.json

@@ -0,0 +1,37 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "clean_up_tokenization_spaces": false,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "legacy": false,
+  "model_max_length": 4096,
+  "pad_token": null,
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "use_default_system_prompt": true
+}