Releasing my best base model so far, pretraining notes released soon.

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "TroyDoesAI/RAG-16B",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 6144,
+  "initializer_range": 0.02,
+  "intermediate_size": 16384,
+  "max_position_embeddings": 32768,
+  "model_type": "mistral",
+  "num_attention_heads": 48,
+  "num_hidden_layers": 38,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.41.1",
+  "use_cache": true,
+  "vocab_size": 32768
+}

model-00001-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd5ed6010ee4694d3d26b4c1214b99250dfc45f6fc229f3d6b42c4f484cd0c00
+size 4907476464

model-00002-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:28ca93f09b7f7ba9ed3c738d5b8ba66da42752fa3dad5ce9e35c781a159d8ed0
+size 4882323696

model-00003-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59224f2aa014297645156c29cb559dfccc223e63c9f7408d0f784de57189723c
+size 4970416704

model-00004-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f1cd0f4e8c23ef2e40d001f2fe52e2478c9d4fe2c0dec78f73a3307a3222a3e
+size 4970416688

model-00005-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b28657768381526d710596bd789505b7555a50feae69585057535a3c006b9253
+size 4882323696

model-00006-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b56b0346cddba61abc5bd15c99a1804c3fa2c2d7233ffa2e89922591d2d8f68a
+size 4970416696

model-00007-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bdc84d7542afe58390d4032744881519b3287a809160186cef8877fc7360098e
+size 868259152

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.4.2", "total_size": 30451593216}, "weight_map": {"lm_head.weight": "model-00001-of-00007.safetensors", "model.embed_tokens.weight": "model-00001-of-00007.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", "model.layers.7.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00007.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", "model.layers.8.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00007.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", "model.layers.9.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00007.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", "model.layers.10.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.input_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", "model.layers.12.input_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", "model.layers.13.input_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", "model.layers.14.input_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", "model.layers.15.input_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", "model.layers.16.input_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", "model.layers.2.input_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.input_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", "model.layers.18.input_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", "model.layers.19.input_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", "model.layers.20.input_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", "model.layers.21.input_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.input_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.input_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", "model.layers.24.input_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", "model.layers.25.input_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", "model.layers.26.input_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", "model.layers.3.input_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", "model.layers.27.input_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.input_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.input_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", "model.layers.30.input_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", "model.layers.31.input_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", "model.layers.32.input_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", "model.layers.33.input_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.input_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.input_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.input_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", "model.layers.37.input_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", "model.layers.4.input_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", "model.layers.5.input_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00007-of-00007.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.layers.6.input_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00007-of-00007.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00007-of-00007.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.norm.weight": "model-00007-of-00007.safetensors"}}

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "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
+  },
+  "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 sha256:9addc8bdce5988448ae81b729336f43a81262160ae8da760674badab9d4c7d33
+size 587591

tokenizer_config.json

@@ -0,0 +1,90 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": true,
+  "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
+    },
+    "3": {
+      "content": "[INST]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "4": {
+      "content": "[/INST]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "10": {
+      "content": "[IMG]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "11": {
+      "content": "[PREFIX]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "12": {
+      "content": "[MIDDLE]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "13": {
+      "content": "[SUFFIX]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": null,
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}