Upload folder using huggingface_hub

README.md

@@ -1,3 +1,11 @@
 ---
 license: cc-by-nd-4.0
+base_model: []
+tags:
+- mergekit
+- merge
 ---
+# This is an experimental model that I made by merging two Llama2 70b models and gluing them together with the mergekit of llama70b. The mergekit is a tool that lets me mix and match different models into one big model, keeping all the smarts and skills of the original models. The llama70b is a huge language model that can make words for all kinds of things and ways, based on the GPT-4 thingy.
+
+The merged model has 55 billion parameters and was made trained on 640GB of vram cluster
+

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "rizla54b",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 8192,
+  "initializer_range": 0.02,
+  "intermediate_size": 28672,
+  "max_position_embeddings": 32764,
+  "model_type": "llama",
+  "num_attention_heads": 64,
+  "num_hidden_layers": 64,
+  "num_key_value_heads": 8,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.37.2",
+  "use_cache": true,
+  "vocab_size": 32000
+}

model-00001-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54b8f46c2110b39ddab602498b0fff0c2062606885ffb34c0daa7dbec2716091
+size 9852607016

model-00002-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3b4ea3a3a91d421bbf8655b90860eb98b4ea0e2c3a3e1f3965eed9bc897d0c1
+size 9798079672

model-00003-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:538defc3bbf646e1f6fce438b6856292a725b075f3a132ab54fa71de6fa0ce50
+size 9999423384

model-00004-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6f8fd83d89ae6ba26de007f7d46257fce5671338f3277f99e54a140f02e994b
+size 9932281752

model-00005-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:535175f2b54f6502c80b33f6cfa5456f30c3e92878d23caa8f1f17cb25adc0ea
+size 9798113416

model-00006-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01a991aa0d225921a56713dac08fad40bd8ee8b5d7b4a28054714c7ab4d9ad1c
+size 9932281752

model-00007-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:38f670f0f89bae8d077008ad6974b31ab827af3509004d2723456d7314f1e434
+size 9965885208

model-00008-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:871d98d82aba0ba32c26f3d03c6f8acdd56e5dc867289dff5142a1f86ab3a368
+size 9798080416

model-00009-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47634074fbb3651a269f166b820472da9c6c8041d97f63193cc838f150978626
+size 9965852208

model-00010-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c2c396f7d035b3cd3322d34b863fb1a36782858310bc1e8609fc4b8553fb37d
+size 9630308608

model-00011-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c473f2c726739132d9094529cbe0c3b0212266a9ad6a2fd0ab57a14afe4f5c4b
+size 9886193280

model-00012-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ea2773036ed3da9bfc959608c977923c5379db265ac8bc0a63bb3f956d66233
+size 2013316008

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.4"}, "weight_map": {"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00012.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00012.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00012.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00012.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00012.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00012.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00012.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00012.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00012.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00012.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00001-of-00012.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00001-of-00012.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00012.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00012.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00012.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00012.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00012.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00012.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00001-of-00012.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00012.safetensors", "model.embed_tokens.weight": "model-00001-of-00012.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00012.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00012.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00012.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00012.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00012.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00012.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00012.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00012.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00012.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00001-of-00012.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00001-of-00012.safetensors", "model.layers.4.input_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00012.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00012.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00012.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00012.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00012.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00001-of-00012.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00001-of-00012.safetensors", "model.layers.3.input_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00001-of-00012.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00001-of-00012.safetensors", "model.layers.2.input_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00012.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00012.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00012.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00012.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00012.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00012.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00012.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00012.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00002-of-00012.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00002-of-00012.safetensors", "model.layers.7.input_layernorm.weight": "model-00002-of-00012.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00012.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00012.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00012.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00012.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00012.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00012.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00002-of-00012.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00002-of-00012.safetensors", "model.layers.6.input_layernorm.weight": "model-00002-of-00012.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00012.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00012.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00002-of-00012.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00002-of-00012.safetensors", "model.layers.5.input_layernorm.weight": "model-00002-of-00012.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00012.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00012.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00012.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00012.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00012.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00012.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00002-of-00012.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00002-of-00012.safetensors", "model.layers.10.input_layernorm.weight": "model-00002-of-00012.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00012.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00012.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00012.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00012.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00012.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00012.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00002-of-00012.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00002-of-00012.safetensors", "model.layers.9.input_layernorm.weight": "model-00002-of-00012.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00012.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00012.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00012.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00002-of-00012.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00002-of-00012.safetensors", "model.layers.8.input_layernorm.weight": "model-00002-of-00012.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00012.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00012.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00012.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00012.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00012.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00003-of-00012.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00012.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00012.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00012.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00012.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00012.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00012.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00003-of-00012.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00003-of-00012.safetensors", "model.layers.12.input_layernorm.weight": "model-00003-of-00012.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00012.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00012.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00012.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00012.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00012.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00012.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00003-of-00012.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00003-of-00012.safetensors", "model.layers.11.input_layernorm.weight": "model-00003-of-00012.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00012.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00012.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00012.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00012.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00012.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00012.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00012.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00003-of-00012.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00003-of-00012.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00012.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00003-of-00012.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00003-of-00012.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00003-of-00012.safetensors", "model.layers.15.input_layernorm.weight": "model-00003-of-00012.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00012.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00012.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00012.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00012.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00012.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00003-of-00012.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00003-of-00012.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00003-of-00012.safetensors", "model.layers.14.input_layernorm.weight": "model-00003-of-00012.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00012.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00003-of-00012.safetensors", "model.layers.13.input_layernorm.weight": "model-00003-of-00012.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00012.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00003-of-00012.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00003-of-00012.safetensors", "model.layers.16.input_layernorm.weight": "model-00003-of-00012.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00012.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00012.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00004-of-00012.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00012.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00012.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00012.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00012.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00004-of-00012.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00012.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00004-of-00012.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00004-of-00012.safetensors", "model.layers.18.input_layernorm.weight": "model-00004-of-00012.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00012.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00012.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00012.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00012.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00012.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00004-of-00012.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00004-of-00012.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00004-of-00012.safetensors", "model.layers.17.input_layernorm.weight": "model-00004-of-00012.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00004-of-00012.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00004-of-00012.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00004-of-00012.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00004-of-00012.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00004-of-00012.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00004-of-00012.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00004-of-00012.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00004-of-00012.safetensors", "model.layers.21.input_layernorm.weight": "model-00004-of-00012.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00004-of-00012.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00004-of-00012.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00004-of-00012.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00004-of-00012.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00004-of-00012.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00004-of-00012.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00004-of-00012.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00004-of-00012.safetensors", "model.layers.20.input_layernorm.weight": "model-00004-of-00012.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00004-of-00012.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00004-of-00012.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00004-of-00012.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00004-of-00012.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00004-of-00012.safetensors", "model.layers.19.input_layernorm.weight": "model-00004-of-00012.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00004-of-00012.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00004-of-00012.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00004-of-00012.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00004-of-00012.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00004-of-00012.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00004-of-00012.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00004-of-00012.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00004-of-00012.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00004-of-00012.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00005-of-00012.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00005-of-00012.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00005-of-00012.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00005-of-00012.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00005-of-00012.safetensors", "model.layers.23.input_layernorm.weight": "model-00005-of-00012.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00005-of-00012.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00005-of-00012.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00005-of-00012.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00005-of-00012.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00005-of-00012.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00005-of-00012.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00005-of-00012.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00005-of-00012.safetensors", "model.layers.22.input_layernorm.weight": "model-00005-of-00012.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00005-of-00012.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00005-of-00012.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00005-of-00012.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00005-of-00012.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00005-of-00012.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00005-of-00012.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00005-of-00012.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00005-of-00012.safetensors", "model.layers.26.input_layernorm.weight": "model-00005-of-00012.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00005-of-00012.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00005-of-00012.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00005-of-00012.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00005-of-00012.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00005-of-00012.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00005-of-00012.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00005-of-00012.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00005-of-00012.safetensors", "model.layers.25.input_layernorm.weight": "model-00005-of-00012.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00005-of-00012.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00005-of-00012.safetensors", "model.layers.24.input_layernorm.weight": "model-00005-of-00012.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00005-of-00012.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00005-of-00012.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00005-of-00012.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00005-of-00012.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00005-of-00012.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00005-of-00012.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00005-of-00012.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00005-of-00012.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00005-of-00012.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00005-of-00012.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00005-of-00012.safetensors", "model.layers.27.input_layernorm.weight": "model-00005-of-00012.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00005-of-00012.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00005-of-00012.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00005-of-00012.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00005-of-00012.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00005-of-00012.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00005-of-00012.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00006-of-00012.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00006-of-00012.safetensors", "model.layers.30.input_layernorm.weight": "model-00006-of-00012.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00006-of-00012.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00006-of-00012.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00006-of-00012.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00006-of-00012.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00006-of-00012.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00006-of-00012.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00006-of-00012.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00006-of-00012.safetensors", "model.layers.29.input_layernorm.weight": "model-00006-of-00012.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00006-of-00012.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00006-of-00012.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00006-of-00012.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00006-of-00012.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00006-of-00012.safetensors", "model.layers.28.input_layernorm.weight": "model-00006-of-00012.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00006-of-00012.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00006-of-00012.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00006-of-00012.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00006-of-00012.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00006-of-00012.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00006-of-00012.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00006-of-00012.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00006-of-00012.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00006-of-00012.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00006-of-00012.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00006-of-00012.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00006-of-00012.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00006-of-00012.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00006-of-00012.safetensors", "model.layers.32.input_layernorm.weight": "model-00006-of-00012.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00006-of-00012.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00006-of-00012.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00006-of-00012.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00006-of-00012.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00006-of-00012.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00006-of-00012.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00006-of-00012.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00006-of-00012.safetensors", "model.layers.31.input_layernorm.weight": "model-00006-of-00012.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00006-of-00012.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00006-of-00012.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00006-of-00012.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00006-of-00012.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00006-of-00012.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00006-of-00012.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00006-of-00012.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00006-of-00012.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00006-of-00012.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00006-of-00012.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00007-of-00012.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00007-of-00012.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00007-of-00012.safetensors", "model.layers.35.input_layernorm.weight": "model-00007-of-00012.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00007-of-00012.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00007-of-00012.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00007-of-00012.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00007-of-00012.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00007-of-00012.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00007-of-00012.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00007-of-00012.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00007-of-00012.safetensors", "model.layers.34.input_layernorm.weight": "model-00007-of-00012.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00007-of-00012.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00007-of-00012.safetensors", "model.layers.33.input_layernorm.weight": "model-00007-of-00012.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00007-of-00012.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00007-of-00012.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00007-of-00012.safetensors", "model.layers.36.input_layernorm.weight": "model-00007-of-00012.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00007-of-00012.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00007-of-00012.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00007-of-00012.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00007-of-00012.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00007-of-00012.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00007-of-00012.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00007-of-00012.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00007-of-00012.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00007-of-00012.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00007-of-00012.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00007-of-00012.safetensors", "model.layers.39.input_layernorm.weight": "model-00007-of-00012.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00007-of-00012.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00007-of-00012.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00007-of-00012.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00007-of-00012.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00007-of-00012.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00007-of-00012.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00007-of-00012.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00007-of-00012.safetensors", "model.layers.38.input_layernorm.weight": "model-00007-of-00012.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00007-of-00012.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00007-of-00012.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00007-of-00012.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00007-of-00012.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00007-of-00012.safetensors", "model.layers.37.input_layernorm.weight": "model-00007-of-00012.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00007-of-00012.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00007-of-00012.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00007-of-00012.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00007-of-00012.safetensors", "model.layers.42.mlp.gate_proj.weight": "model-00008-of-00012.safetensors", "model.layers.42.mlp.up_proj.weight": "model-00008-of-00012.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00008-of-00012.safetensors", "model.layers.41.self_attn.v_proj.weight": "model-00008-of-00012.safetensors", "model.layers.41.self_attn.k_proj.weight": "model-00008-of-00012.safetensors", "model.layers.41.self_attn.q_proj.weight": "model-00008-of-00012.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00008-of-00012.safetensors", "model.layers.41.mlp.gate_proj.weight": "model-00008-of-00012.safetensors", "model.layers.41.mlp.down_proj.weight": "model-00008-of-00012.safetensors", "model.layers.41.mlp.up_proj.weight": "model-00008-of-00012.safetensors", "model.layers.41.input_layernorm.weight": "model-00008-of-00012.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00008-of-00012.safetensors", "model.layers.40.self_attn.v_proj.weight": "model-00008-of-00012.safetensors", "model.layers.40.self_attn.k_proj.weight": "model-00008-of-00012.safetensors", "model.layers.40.self_attn.q_proj.weight": "model-00008-of-00012.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00008-of-00012.safetensors", "model.layers.40.mlp.gate_proj.weight": "model-00008-of-00012.safetensors", "model.layers.40.mlp.down_proj.weight": "model-00008-of-00012.safetensors", "model.layers.40.mlp.up_proj.weight": "model-00008-of-00012.safetensors", "model.layers.40.input_layernorm.weight": "model-00008-of-00012.safetensors", "model.layers.45.self_attn.o_proj.weight": "model-00008-of-00012.safetensors", "model.layers.45.self_attn.v_proj.weight": "model-00008-of-00012.safetensors", "model.layers.45.self_attn.k_proj.weight": "model-00008-of-00012.safetensors", "model.layers.45.self_attn.q_proj.weight": "model-00008-of-00012.safetensors", "model.layers.45.mlp.gate_proj.weight": "model-00008-of-00012.safetensors", "model.layers.44.self_attn.o_proj.weight": "model-00008-of-00012.safetensors", "model.layers.44.self_attn.v_proj.weight": "model-00008-of-00012.safetensors", "model.layers.44.self_attn.k_proj.weight": "model-00008-of-00012.safetensors", "model.layers.44.self_attn.q_proj.weight": "model-00008-of-00012.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00008-of-00012.safetensors", "model.layers.44.mlp.gate_proj.weight": "model-00008-of-00012.safetensors", "model.layers.44.mlp.down_proj.weight": "model-00008-of-00012.safetensors", "model.layers.44.mlp.up_proj.weight": "model-00008-of-00012.safetensors", "model.layers.44.input_layernorm.weight": "model-00008-of-00012.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00008-of-00012.safetensors", "model.layers.43.self_attn.v_proj.weight": "model-00008-of-00012.safetensors", "model.layers.43.self_attn.k_proj.weight": "model-00008-of-00012.safetensors", "model.layers.43.self_attn.q_proj.weight": "model-00008-of-00012.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00008-of-00012.safetensors", "model.layers.43.mlp.gate_proj.weight": "model-00008-of-00012.safetensors", "model.layers.43.mlp.down_proj.weight": "model-00008-of-00012.safetensors", "model.layers.43.mlp.up_proj.weight": "model-00008-of-00012.safetensors", "model.layers.43.input_layernorm.weight": "model-00008-of-00012.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00008-of-00012.safetensors", "model.layers.42.mlp.down_proj.weight": "model-00008-of-00012.safetensors", "model.layers.42.input_layernorm.weight": "model-00008-of-00012.safetensors", "model.layers.46.self_attn.o_proj.weight": "model-00008-of-00012.safetensors", "model.layers.46.self_attn.v_proj.weight": "model-00008-of-00012.safetensors", "model.layers.46.self_attn.k_proj.weight": "model-00008-of-00012.safetensors", "model.layers.46.self_attn.q_proj.weight": "model-00008-of-00012.safetensors", "model.layers.46.post_attention_layernorm.weight": "model-00008-of-00012.safetensors", "model.layers.46.mlp.gate_proj.weight": "model-00008-of-00012.safetensors", "model.layers.46.mlp.down_proj.weight": "model-00009-of-00012.safetensors", "model.layers.46.mlp.up_proj.weight": "model-00009-of-00012.safetensors", "model.layers.46.input_layernorm.weight": "model-00009-of-00012.safetensors", "model.layers.45.post_attention_layernorm.weight": "model-00009-of-00012.safetensors", "model.layers.45.mlp.down_proj.weight": "model-00009-of-00012.safetensors", "model.layers.45.mlp.up_proj.weight": "model-00009-of-00012.safetensors", "model.layers.45.input_layernorm.weight": "model-00009-of-00012.safetensors", "model.layers.48.self_attn.v_proj.weight": "model-00009-of-00012.safetensors", "model.layers.48.self_attn.k_proj.weight": "model-00009-of-00012.safetensors", "model.layers.48.self_attn.q_proj.weight": "model-00009-of-00012.safetensors", "model.layers.47.self_attn.o_proj.weight": "model-00009-of-00012.safetensors", "model.layers.47.self_attn.v_proj.weight": "model-00009-of-00012.safetensors", "model.layers.47.self_attn.k_proj.weight": "model-00009-of-00012.safetensors", "model.layers.47.self_attn.q_proj.weight": "model-00009-of-00012.safetensors", "model.layers.47.post_attention_layernorm.weight": "model-00009-of-00012.safetensors", "model.layers.47.mlp.gate_proj.weight": "model-00009-of-00012.safetensors", "model.layers.47.mlp.down_proj.weight": "model-00009-of-00012.safetensors", "model.layers.47.mlp.up_proj.weight": "model-00009-of-00012.safetensors", "model.layers.47.input_layernorm.weight": "model-00009-of-00012.safetensors", "model.layers.50.self_attn.o_proj.weight": "model-00009-of-00012.safetensors", "model.layers.50.self_attn.v_proj.weight": "model-00009-of-00012.safetensors", "model.layers.50.self_attn.k_proj.weight": "model-00009-of-00012.safetensors", "model.layers.50.self_attn.q_proj.weight": "model-00009-of-00012.safetensors", "model.layers.50.post_attention_layernorm.weight": "model-00009-of-00012.safetensors", "model.layers.50.mlp.gate_proj.weight": "model-00009-of-00012.safetensors", "model.layers.50.mlp.down_proj.weight": "model-00009-of-00012.safetensors", "model.layers.50.mlp.up_proj.weight": "model-00009-of-00012.safetensors", "model.layers.50.input_layernorm.weight": "model-00009-of-00012.safetensors", "model.layers.49.self_attn.o_proj.weight": "model-00009-of-00012.safetensors", "model.layers.49.self_attn.v_proj.weight": "model-00009-of-00012.safetensors", "model.layers.49.self_attn.k_proj.weight": "model-00009-of-00012.safetensors", "model.layers.49.self_attn.q_proj.weight": "model-00009-of-00012.safetensors", "model.layers.49.post_attention_layernorm.weight": "model-00009-of-00012.safetensors", "model.layers.49.mlp.gate_proj.weight": "model-00009-of-00012.safetensors", "model.layers.49.mlp.down_proj.weight": "model-00009-of-00012.safetensors", "model.layers.49.mlp.up_proj.weight": "model-00009-of-00012.safetensors", "model.layers.49.input_layernorm.weight": "model-00009-of-00012.safetensors", "model.layers.48.self_attn.o_proj.weight": "model-00009-of-00012.safetensors", "model.layers.48.post_attention_layernorm.weight": "model-00009-of-00012.safetensors", "model.layers.48.mlp.gate_proj.weight": "model-00009-of-00012.safetensors", "model.layers.48.mlp.down_proj.weight": "model-00009-of-00012.safetensors", "model.layers.48.mlp.up_proj.weight": "model-00009-of-00012.safetensors", "model.layers.48.input_layernorm.weight": "model-00009-of-00012.safetensors", "model.layers.53.self_attn.o_proj.weight": "model-00009-of-00012.safetensors", "model.layers.53.self_attn.v_proj.weight": "model-00009-of-00012.safetensors", "model.layers.53.self_attn.k_proj.weight": "model-00009-of-00012.safetensors", "model.layers.53.self_attn.q_proj.weight": "model-00009-of-00012.safetensors", "model.layers.53.mlp.gate_proj.weight": "model-00009-of-00012.safetensors", "model.layers.53.mlp.up_proj.weight": "model-00009-of-00012.safetensors", "model.layers.52.self_attn.o_proj.weight": "model-00010-of-00012.safetensors", "model.layers.52.self_attn.v_proj.weight": "model-00010-of-00012.safetensors", "model.layers.52.self_attn.k_proj.weight": "model-00010-of-00012.safetensors", "model.layers.52.self_attn.q_proj.weight": "model-00010-of-00012.safetensors", "model.layers.52.post_attention_layernorm.weight": "model-00010-of-00012.safetensors", "model.layers.52.mlp.gate_proj.weight": "model-00010-of-00012.safetensors", "model.layers.52.mlp.down_proj.weight": "model-00010-of-00012.safetensors", "model.layers.52.mlp.up_proj.weight": "model-00010-of-00012.safetensors", "model.layers.52.input_layernorm.weight": "model-00010-of-00012.safetensors", "model.layers.51.self_attn.o_proj.weight": "model-00010-of-00012.safetensors", "model.layers.51.self_attn.v_proj.weight": "model-00010-of-00012.safetensors", "model.layers.51.self_attn.k_proj.weight": "model-00010-of-00012.safetensors", "model.layers.51.self_attn.q_proj.weight": "model-00010-of-00012.safetensors", "model.layers.51.post_attention_layernorm.weight": "model-00010-of-00012.safetensors", "model.layers.51.mlp.gate_proj.weight": "model-00010-of-00012.safetensors", "model.layers.51.mlp.down_proj.weight": "model-00010-of-00012.safetensors", "model.layers.51.mlp.up_proj.weight": "model-00010-of-00012.safetensors", "model.layers.51.input_layernorm.weight": "model-00010-of-00012.safetensors", "model.layers.56.self_attn.o_proj.weight": "model-00010-of-00012.safetensors", "model.layers.56.self_attn.v_proj.weight": "model-00010-of-00012.safetensors", "model.layers.56.self_attn.k_proj.weight": "model-00010-of-00012.safetensors", "model.layers.56.self_attn.q_proj.weight": "model-00010-of-00012.safetensors", "model.layers.56.mlp.gate_proj.weight": "model-00010-of-00012.safetensors", "model.layers.55.self_attn.o_proj.weight": "model-00010-of-00012.safetensors", "model.layers.55.self_attn.v_proj.weight": "model-00010-of-00012.safetensors", "model.layers.55.self_attn.k_proj.weight": "model-00010-of-00012.safetensors", "model.layers.55.self_attn.q_proj.weight": "model-00010-of-00012.safetensors", "model.layers.55.post_attention_layernorm.weight": "model-00010-of-00012.safetensors", "model.layers.55.mlp.gate_proj.weight": "model-00010-of-00012.safetensors", "model.layers.55.mlp.down_proj.weight": "model-00010-of-00012.safetensors", "model.layers.55.mlp.up_proj.weight": "model-00010-of-00012.safetensors", "model.layers.55.input_layernorm.weight": "model-00010-of-00012.safetensors", "model.layers.54.self_attn.o_proj.weight": "model-00010-of-00012.safetensors", "model.layers.54.self_attn.v_proj.weight": "model-00010-of-00012.safetensors", "model.layers.54.self_attn.k_proj.weight": "model-00010-of-00012.safetensors", "model.layers.54.self_attn.q_proj.weight": "model-00010-of-00012.safetensors", "model.layers.54.post_attention_layernorm.weight": "model-00010-of-00012.safetensors", "model.layers.54.mlp.gate_proj.weight": "model-00010-of-00012.safetensors", "model.layers.54.mlp.down_proj.weight": "model-00010-of-00012.safetensors", "model.layers.54.mlp.up_proj.weight": "model-00010-of-00012.safetensors", "model.layers.54.input_layernorm.weight": "model-00010-of-00012.safetensors", "model.layers.53.post_attention_layernorm.weight": "model-00010-of-00012.safetensors", "model.layers.53.mlp.down_proj.weight": "model-00010-of-00012.safetensors", "model.layers.53.input_layernorm.weight": "model-00010-of-00012.safetensors", "model.layers.59.self_attn.o_proj.weight": "model-00010-of-00012.safetensors", "model.layers.59.self_attn.v_proj.weight": "model-00010-of-00012.safetensors", "model.layers.59.self_attn.k_proj.weight": "model-00010-of-00012.safetensors", "model.layers.59.self_attn.q_proj.weight": "model-00010-of-00012.safetensors", "model.layers.58.self_attn.o_proj.weight": "model-00010-of-00012.safetensors", "model.layers.58.self_attn.v_proj.weight": "model-00010-of-00012.safetensors", "model.layers.58.self_attn.k_proj.weight": "model-00010-of-00012.safetensors", "model.layers.58.self_attn.q_proj.weight": "model-00010-of-00012.safetensors", "model.layers.58.post_attention_layernorm.weight": "model-00010-of-00012.safetensors", "model.layers.58.mlp.gate_proj.weight": "model-00010-of-00012.safetensors", "model.layers.58.mlp.down_proj.weight": "model-00010-of-00012.safetensors", "model.layers.58.mlp.up_proj.weight": "model-00011-of-00012.safetensors", "model.layers.58.input_layernorm.weight": "model-00011-of-00012.safetensors", "model.layers.57.self_attn.o_proj.weight": "model-00011-of-00012.safetensors", "model.layers.57.self_attn.v_proj.weight": "model-00011-of-00012.safetensors", "model.layers.57.self_attn.k_proj.weight": "model-00011-of-00012.safetensors", "model.layers.57.self_attn.q_proj.weight": "model-00011-of-00012.safetensors", "model.layers.57.post_attention_layernorm.weight": "model-00011-of-00012.safetensors", "model.layers.57.mlp.gate_proj.weight": "model-00011-of-00012.safetensors", "model.layers.57.mlp.down_proj.weight": "model-00011-of-00012.safetensors", "model.layers.57.mlp.up_proj.weight": "model-00011-of-00012.safetensors", "model.layers.57.input_layernorm.weight": "model-00011-of-00012.safetensors", "model.layers.56.post_attention_layernorm.weight": "model-00011-of-00012.safetensors", "model.layers.56.mlp.down_proj.weight": "model-00011-of-00012.safetensors", "model.layers.56.mlp.up_proj.weight": "model-00011-of-00012.safetensors", "model.layers.56.input_layernorm.weight": "model-00011-of-00012.safetensors", "model.layers.62.self_attn.v_proj.weight": "model-00011-of-00012.safetensors", "model.layers.62.self_attn.k_proj.weight": "model-00011-of-00012.safetensors", "model.layers.62.self_attn.q_proj.weight": "model-00011-of-00012.safetensors", "model.layers.61.self_attn.o_proj.weight": "model-00011-of-00012.safetensors", "model.layers.61.self_attn.v_proj.weight": "model-00011-of-00012.safetensors", "model.layers.61.self_attn.k_proj.weight": "model-00011-of-00012.safetensors", "model.layers.61.self_attn.q_proj.weight": "model-00011-of-00012.safetensors", "model.layers.61.post_attention_layernorm.weight": "model-00011-of-00012.safetensors", "model.layers.61.mlp.gate_proj.weight": "model-00011-of-00012.safetensors", "model.layers.61.mlp.down_proj.weight": "model-00011-of-00012.safetensors", "model.layers.61.mlp.up_proj.weight": "model-00011-of-00012.safetensors", "model.layers.61.input_layernorm.weight": "model-00011-of-00012.safetensors", "model.layers.60.self_attn.o_proj.weight": "model-00011-of-00012.safetensors", "model.layers.60.self_attn.v_proj.weight": "model-00011-of-00012.safetensors", "model.layers.60.self_attn.k_proj.weight": "model-00011-of-00012.safetensors", "model.layers.60.self_attn.q_proj.weight": "model-00011-of-00012.safetensors", "model.layers.60.post_attention_layernorm.weight": "model-00011-of-00012.safetensors", "model.layers.60.mlp.gate_proj.weight": "model-00011-of-00012.safetensors", "model.layers.60.mlp.down_proj.weight": "model-00011-of-00012.safetensors", "model.layers.60.mlp.up_proj.weight": "model-00011-of-00012.safetensors", "model.layers.60.input_layernorm.weight": "model-00011-of-00012.safetensors", "model.layers.59.post_attention_layernorm.weight": "model-00011-of-00012.safetensors", "model.layers.59.mlp.gate_proj.weight": "model-00011-of-00012.safetensors", "model.layers.59.mlp.down_proj.weight": "model-00011-of-00012.safetensors", "model.layers.59.mlp.up_proj.weight": "model-00011-of-00012.safetensors", "model.layers.59.input_layernorm.weight": "model-00011-of-00012.safetensors", "lm_head.weight": "model-00011-of-00012.safetensors", "model.norm.weight": "model-00011-of-00012.safetensors", "model.layers.63.self_attn.o_proj.weight": "model-00011-of-00012.safetensors", "model.layers.63.self_attn.v_proj.weight": "model-00011-of-00012.safetensors", "model.layers.63.self_attn.k_proj.weight": "model-00011-of-00012.safetensors", "model.layers.63.self_attn.q_proj.weight": "model-00011-of-00012.safetensors", "model.layers.63.post_attention_layernorm.weight": "model-00011-of-00012.safetensors", "model.layers.63.mlp.gate_proj.weight": "model-00011-of-00012.safetensors", "model.layers.63.mlp.down_proj.weight": "model-00011-of-00012.safetensors", "model.layers.63.mlp.up_proj.weight": "model-00012-of-00012.safetensors", "model.layers.63.input_layernorm.weight": "model-00012-of-00012.safetensors", "model.layers.62.self_attn.o_proj.weight": "model-00012-of-00012.safetensors", "model.layers.62.post_attention_layernorm.weight": "model-00012-of-00012.safetensors", "model.layers.62.mlp.gate_proj.weight": "model-00012-of-00012.safetensors", "model.layers.62.mlp.down_proj.weight": "model-00012-of-00012.safetensors", "model.layers.62.mlp.up_proj.weight": "model-00012-of-00012.safetensors", "model.layers.62.input_layernorm.weight": "model-00012-of-00012.safetensors"}}

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "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 +1,42 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token}}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<unk>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}