init

config.json

@@ -1 +1,22 @@
-{"architectures": ["LLaMAForCausalLM"], "bos_token_id": 0, "eos_token_id": 1, "hidden_act": "silu", "hidden_size": 4096, "intermediate_size": 11008, "initializer_range": 0.02, "max_sequence_length": 2048, "model_type": "llama", "num_attention_heads": 32, "num_hidden_layers": 32, "pad_token_id": -1, "rms_norm_eps": 1e-06, "torch_dtype": "float16", "transformers_version": "4.27.0.dev0", "use_cache": true, "vocab_size": 32000}
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 2048,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "pad_token_id": 0,
+  "rms_norm_eps": 1e-06,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.28.1",
+  "use_cache": true,
+  "vocab_size": 32000
+}

generation_config.json

@@ -1 +1,7 @@
-{"_from_model_config": true, "bos_token_id": 0, "eos_token_id": 1, "pad_token_id": -1, "transformers_version": "4.27.0.dev0"}
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": 0,
+  "transformers_version": "4.28.1"
+}

pytorch_model-1-of-33.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:6822dc2c981024e865b450310a35479099592a26c2571b8f6f4d12faaaeff4e9
-size 404770607

pytorch_model-10-of-33.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:f2364473cfcbdf7c078b223626c06788a8782ecc438fee45d5316a30454019e1
-size 404770683

pytorch_model-11-of-33.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:f4f6cf1ad50eb5f68a22e6fc351b865f997365f6cf8b2798ccfb4e05544acdf5
-size 404770683

pytorch_model-12-of-33.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:6db0d48d25bbf79e679ffb4a357f05776453d50dbd056a44996ea308c84b5249
-size 404770683

pytorch_model-13-of-33.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:da5bd94f19bcf55fffff382399c2177d60a11a4f888703ae396d30e689ffead9
-size 404770683

pytorch_model-14-of-33.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:f7b54464b069b3407dee32918457a76683c0545391f1a4959e4cc4d9a26b5fac
-size 404770683

pytorch_model-15-of-33.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:1f90ffebb26734b186d6511f4a8b5d62a598116c68de6e3f33fd93501edbc55a
-size 404770683

pytorch_model-16-of-33.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:14f1bf43fd27f097f56bd28834f56423915849f7d9b37e3f3ed4b6cf406deae6
-size 404770683

pytorch_model-17-of-33.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:1746ad56f35b8cdc438dfed5c1290b8cc36837cb84b718dc295f40bcc4f522dd
-size 404770683

pytorch_model-18-of-33.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:9c7d72f0a4707419f3430c06b752a94784526817f17a909fe31f8fb08589c5bc
-size 404770683

pytorch_model-19-of-33.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:cf570b83c4bc38428aa011c398502590d19fe202e8e4abf2641841e23731e9c6
-size 404770683

pytorch_model-2-of-33.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:15760b94654846c417007e873f00e3965460935fa93450a1252766ba19cff848
-size 404770607

pytorch_model-20-of-33.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:80279b6323b5ed6a29d525f0fd85bf2ad0f6c5de7363d7dcef88a53fb295fa79
-size 404770683

pytorch_model-21-of-33.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:4f5a0200d810863670f0ae6a3cb319cfb6e1c3a5a1dbcbcfb71347e74d8b51b6
-size 404770683

pytorch_model-22-of-33.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:b3d3b529996bad8e8938e455c00716d50e9a75d3d96bf27e2b0ad2c4b9aba273
-size 404770683

pytorch_model-23-of-33.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:3dd4e62593d4c7293789a6a0677f4948bcef80238b05d69f293a8573802ed311
-size 404770683

pytorch_model-24-of-33.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:a2b104c15008ab8ac15da21426d3a398d2dfc900c9d05537f3bdf26fbc1c7b2e
-size 404770683

pytorch_model-25-of-33.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:a934339bae1e2d13f006d58d0606926d1d0842c14cdfc1e6df383ac2db153152
-size 404770683

pytorch_model-26-of-33.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:aafa436df42aa03a53bf04991c23af66e66a473525d00ffddaae429b9bdb1cb1
-size 404770683

pytorch_model-27-of-33.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:dbe3d36b0f416e456d6aa55b1135efb5d85568ebea1bf94bf65c4a7ba807ef9e
-size 404770683

pytorch_model-28-of-33.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:a0262afff2177b0550b56a9d2a480d0b779761e4bfaa8201bb73a907dee54e44
-size 404770683

pytorch_model-29-of-33.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:6a0fa558c2969358fa4a3b74da8e8271ca7c9d9089bc18d66e099bc372d9a874
-size 404770683

pytorch_model-3-of-33.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:0b95978e158847ea1fe4848268bff851d2d6b34daf8ec32d541b3b65da0a1ec9
-size 404770607

pytorch_model-30-of-33.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:47fd34bbb30707fb03fd7815ee635b098c86df8ad0d23076f22775c371fd3cdb
-size 404770683

pytorch_model-31-of-33.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:ddb8eb92976e2b98d7a2867ce40b528da15683a568394e70cc4677224547d58b
-size 404770683

pytorch_model-32-of-33.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:3b05f25d7b2ba4f8f2a5a7f96823222f0e43772dca48ade0adc2b4f3f80fc9e0
-size 404770683

pytorch_model-33-of-33.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:58d46674e3e9904252cd51461b8efb46ab3a09c4b507ec608b6a5af8f8c099ab
-size 524297646

pytorch_model-4-of-33.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:c4c41a71c9e4515cae0c97ff532a77a3fa64a5be4a805658b6a464a0f501e070
-size 404770607

pytorch_model-5-of-33.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:f1f23fba5f5e3afe044d1c9ac24683f5307fc2223536b5a4dab8ee5f49810f21
-size 404770607

pytorch_model-6-of-33.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:7962a3cb8698071c069af5c7f9ef7fbccfbc0e6b186ebfe24bcb11239c1d0285
-size 404770607

pytorch_model-7-of-33.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:0f7a22e55706467f213888a6abe3a6b0b0887da22db65b652f89e58b8a5e25eb
-size 404770607

pytorch_model-8-of-33.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:daa203ceab60bc7016f7080046f76a69d0fe511442b9ddae3f9115c3382ca59a
-size 404770607

pytorch_model-9-of-33.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:8ef69569ce33d0f3c6d79b85bcb069cb081ba32b84a0a8a9a5fabc6a5cf83bfe
-size 404770607

pytorch_model.bin.index.json

@@ -1 +1,330 @@
-{"weight_map": {"model.layers.0.self_attn.q_proj.weight": "pytorch_model-1-of-33.bin", "model.layers.0.self_attn.k_proj.weight": "pytorch_model-1-of-33.bin", "model.layers.0.self_attn.v_proj.weight": "pytorch_model-1-of-33.bin", "model.layers.0.self_attn.o_proj.weight": "pytorch_model-1-of-33.bin", "model.layers.0.input_layernorm.weight": "pytorch_model-1-of-33.bin", "model.layers.0.mlp.gate_proj.weight": "pytorch_model-1-of-33.bin", "model.layers.0.mlp.up_proj.weight": "pytorch_model-1-of-33.bin", "model.layers.0.mlp.down_proj.weight": "pytorch_model-1-of-33.bin", "model.layers.0.post_attention_layernorm.weight": "pytorch_model-1-of-33.bin", "model.layers.0.self_attn.rotary_emb.inv_freq": "pytorch_model-1-of-33.bin", "model.layers.1.self_attn.q_proj.weight": "pytorch_model-2-of-33.bin", "model.layers.1.self_attn.k_proj.weight": "pytorch_model-2-of-33.bin", "model.layers.1.self_attn.v_proj.weight": "pytorch_model-2-of-33.bin", "model.layers.1.self_attn.o_proj.weight": "pytorch_model-2-of-33.bin", "model.layers.1.input_layernorm.weight": "pytorch_model-2-of-33.bin", "model.layers.1.mlp.gate_proj.weight": "pytorch_model-2-of-33.bin", "model.layers.1.mlp.up_proj.weight": "pytorch_model-2-of-33.bin", "model.layers.1.mlp.down_proj.weight": "pytorch_model-2-of-33.bin", "model.layers.1.post_attention_layernorm.weight": "pytorch_model-2-of-33.bin", "model.layers.1.self_attn.rotary_emb.inv_freq": "pytorch_model-2-of-33.bin", "model.layers.2.self_attn.q_proj.weight": "pytorch_model-3-of-33.bin", "model.layers.2.self_attn.k_proj.weight": "pytorch_model-3-of-33.bin", "model.layers.2.self_attn.v_proj.weight": "pytorch_model-3-of-33.bin", "model.layers.2.self_attn.o_proj.weight": "pytorch_model-3-of-33.bin", "model.layers.2.input_layernorm.weight": "pytorch_model-3-of-33.bin", "model.layers.2.mlp.gate_proj.weight": "pytorch_model-3-of-33.bin", "model.layers.2.mlp.up_proj.weight": "pytorch_model-3-of-33.bin", "model.layers.2.mlp.down_proj.weight": "pytorch_model-3-of-33.bin", "model.layers.2.post_attention_layernorm.weight": "pytorch_model-3-of-33.bin", "model.layers.2.self_attn.rotary_emb.inv_freq": "pytorch_model-3-of-33.bin", "model.layers.3.self_attn.q_proj.weight": "pytorch_model-4-of-33.bin", "model.layers.3.self_attn.k_proj.weight": "pytorch_model-4-of-33.bin", "model.layers.3.self_attn.v_proj.weight": "pytorch_model-4-of-33.bin", "model.layers.3.self_attn.o_proj.weight": "pytorch_model-4-of-33.bin", "model.layers.3.input_layernorm.weight": "pytorch_model-4-of-33.bin", "model.layers.3.mlp.gate_proj.weight": "pytorch_model-4-of-33.bin", "model.layers.3.mlp.up_proj.weight": "pytorch_model-4-of-33.bin", "model.layers.3.mlp.down_proj.weight": "pytorch_model-4-of-33.bin", "model.layers.3.post_attention_layernorm.weight": "pytorch_model-4-of-33.bin", "model.layers.3.self_attn.rotary_emb.inv_freq": "pytorch_model-4-of-33.bin", "model.layers.4.self_attn.q_proj.weight": "pytorch_model-5-of-33.bin", "model.layers.4.self_attn.k_proj.weight": "pytorch_model-5-of-33.bin", "model.layers.4.self_attn.v_proj.weight": "pytorch_model-5-of-33.bin", "model.layers.4.self_attn.o_proj.weight": "pytorch_model-5-of-33.bin", "model.layers.4.input_layernorm.weight": "pytorch_model-5-of-33.bin", "model.layers.4.mlp.gate_proj.weight": "pytorch_model-5-of-33.bin", "model.layers.4.mlp.up_proj.weight": "pytorch_model-5-of-33.bin", "model.layers.4.mlp.down_proj.weight": "pytorch_model-5-of-33.bin", "model.layers.4.post_attention_layernorm.weight": "pytorch_model-5-of-33.bin", "model.layers.4.self_attn.rotary_emb.inv_freq": "pytorch_model-5-of-33.bin", "model.layers.5.self_attn.q_proj.weight": "pytorch_model-6-of-33.bin", "model.layers.5.self_attn.k_proj.weight": "pytorch_model-6-of-33.bin", "model.layers.5.self_attn.v_proj.weight": "pytorch_model-6-of-33.bin", "model.layers.5.self_attn.o_proj.weight": "pytorch_model-6-of-33.bin", "model.layers.5.input_layernorm.weight": "pytorch_model-6-of-33.bin", "model.layers.5.mlp.gate_proj.weight": "pytorch_model-6-of-33.bin", "model.layers.5.mlp.up_proj.weight": "pytorch_model-6-of-33.bin", "model.layers.5.mlp.down_proj.weight": "pytorch_model-6-of-33.bin", "model.layers.5.post_attention_layernorm.weight": "pytorch_model-6-of-33.bin", "model.layers.5.self_attn.rotary_emb.inv_freq": "pytorch_model-6-of-33.bin", "model.layers.6.self_attn.q_proj.weight": "pytorch_model-7-of-33.bin", "model.layers.6.self_attn.k_proj.weight": "pytorch_model-7-of-33.bin", "model.layers.6.self_attn.v_proj.weight": "pytorch_model-7-of-33.bin", "model.layers.6.self_attn.o_proj.weight": "pytorch_model-7-of-33.bin", "model.layers.6.input_layernorm.weight": "pytorch_model-7-of-33.bin", "model.layers.6.mlp.gate_proj.weight": "pytorch_model-7-of-33.bin", "model.layers.6.mlp.up_proj.weight": "pytorch_model-7-of-33.bin", "model.layers.6.mlp.down_proj.weight": "pytorch_model-7-of-33.bin", "model.layers.6.post_attention_layernorm.weight": "pytorch_model-7-of-33.bin", "model.layers.6.self_attn.rotary_emb.inv_freq": "pytorch_model-7-of-33.bin", "model.layers.7.self_attn.q_proj.weight": "pytorch_model-8-of-33.bin", "model.layers.7.self_attn.k_proj.weight": "pytorch_model-8-of-33.bin", "model.layers.7.self_attn.v_proj.weight": "pytorch_model-8-of-33.bin", "model.layers.7.self_attn.o_proj.weight": "pytorch_model-8-of-33.bin", "model.layers.7.input_layernorm.weight": "pytorch_model-8-of-33.bin", "model.layers.7.mlp.gate_proj.weight": "pytorch_model-8-of-33.bin", "model.layers.7.mlp.up_proj.weight": "pytorch_model-8-of-33.bin", "model.layers.7.mlp.down_proj.weight": "pytorch_model-8-of-33.bin", "model.layers.7.post_attention_layernorm.weight": "pytorch_model-8-of-33.bin", "model.layers.7.self_attn.rotary_emb.inv_freq": "pytorch_model-8-of-33.bin", "model.layers.8.self_attn.q_proj.weight": "pytorch_model-9-of-33.bin", "model.layers.8.self_attn.k_proj.weight": "pytorch_model-9-of-33.bin", "model.layers.8.self_attn.v_proj.weight": "pytorch_model-9-of-33.bin", "model.layers.8.self_attn.o_proj.weight": "pytorch_model-9-of-33.bin", "model.layers.8.input_layernorm.weight": "pytorch_model-9-of-33.bin", "model.layers.8.mlp.gate_proj.weight": "pytorch_model-9-of-33.bin", "model.layers.8.mlp.up_proj.weight": "pytorch_model-9-of-33.bin", "model.layers.8.mlp.down_proj.weight": "pytorch_model-9-of-33.bin", "model.layers.8.post_attention_layernorm.weight": "pytorch_model-9-of-33.bin", "model.layers.8.self_attn.rotary_emb.inv_freq": "pytorch_model-9-of-33.bin", "model.layers.9.self_attn.q_proj.weight": "pytorch_model-10-of-33.bin", "model.layers.9.self_attn.k_proj.weight": "pytorch_model-10-of-33.bin", "model.layers.9.self_attn.v_proj.weight": "pytorch_model-10-of-33.bin", "model.layers.9.self_attn.o_proj.weight": "pytorch_model-10-of-33.bin", "model.layers.9.input_layernorm.weight": "pytorch_model-10-of-33.bin", "model.layers.9.mlp.gate_proj.weight": "pytorch_model-10-of-33.bin", "model.layers.9.mlp.up_proj.weight": "pytorch_model-10-of-33.bin", "model.layers.9.mlp.down_proj.weight": "pytorch_model-10-of-33.bin", "model.layers.9.post_attention_layernorm.weight": "pytorch_model-10-of-33.bin", "model.layers.9.self_attn.rotary_emb.inv_freq": "pytorch_model-10-of-33.bin", "model.layers.10.self_attn.q_proj.weight": "pytorch_model-11-of-33.bin", "model.layers.10.self_attn.k_proj.weight": "pytorch_model-11-of-33.bin", "model.layers.10.self_attn.v_proj.weight": "pytorch_model-11-of-33.bin", "model.layers.10.self_attn.o_proj.weight": "pytorch_model-11-of-33.bin", "model.layers.10.input_layernorm.weight": "pytorch_model-11-of-33.bin", "model.layers.10.mlp.gate_proj.weight": "pytorch_model-11-of-33.bin", "model.layers.10.mlp.up_proj.weight": "pytorch_model-11-of-33.bin", "model.layers.10.mlp.down_proj.weight": "pytorch_model-11-of-33.bin", "model.layers.10.post_attention_layernorm.weight": "pytorch_model-11-of-33.bin", "model.layers.10.self_attn.rotary_emb.inv_freq": "pytorch_model-11-of-33.bin", "model.layers.11.self_attn.q_proj.weight": "pytorch_model-12-of-33.bin", "model.layers.11.self_attn.k_proj.weight": "pytorch_model-12-of-33.bin", "model.layers.11.self_attn.v_proj.weight": "pytorch_model-12-of-33.bin", "model.layers.11.self_attn.o_proj.weight": "pytorch_model-12-of-33.bin", "model.layers.11.input_layernorm.weight": "pytorch_model-12-of-33.bin", "model.layers.11.mlp.gate_proj.weight": "pytorch_model-12-of-33.bin", "model.layers.11.mlp.up_proj.weight": "pytorch_model-12-of-33.bin", "model.layers.11.mlp.down_proj.weight": "pytorch_model-12-of-33.bin", "model.layers.11.post_attention_layernorm.weight": "pytorch_model-12-of-33.bin", "model.layers.11.self_attn.rotary_emb.inv_freq": "pytorch_model-12-of-33.bin", "model.layers.12.self_attn.q_proj.weight": "pytorch_model-13-of-33.bin", "model.layers.12.self_attn.k_proj.weight": "pytorch_model-13-of-33.bin", "model.layers.12.self_attn.v_proj.weight": "pytorch_model-13-of-33.bin", "model.layers.12.self_attn.o_proj.weight": "pytorch_model-13-of-33.bin", "model.layers.12.input_layernorm.weight": "pytorch_model-13-of-33.bin", "model.layers.12.mlp.gate_proj.weight": "pytorch_model-13-of-33.bin", "model.layers.12.mlp.up_proj.weight": "pytorch_model-13-of-33.bin", "model.layers.12.mlp.down_proj.weight": "pytorch_model-13-of-33.bin", "model.layers.12.post_attention_layernorm.weight": "pytorch_model-13-of-33.bin", "model.layers.12.self_attn.rotary_emb.inv_freq": "pytorch_model-13-of-33.bin", "model.layers.13.self_attn.q_proj.weight": "pytorch_model-14-of-33.bin", "model.layers.13.self_attn.k_proj.weight": "pytorch_model-14-of-33.bin", "model.layers.13.self_attn.v_proj.weight": "pytorch_model-14-of-33.bin", "model.layers.13.self_attn.o_proj.weight": "pytorch_model-14-of-33.bin", "model.layers.13.input_layernorm.weight": "pytorch_model-14-of-33.bin", "model.layers.13.mlp.gate_proj.weight": "pytorch_model-14-of-33.bin", "model.layers.13.mlp.up_proj.weight": "pytorch_model-14-of-33.bin", "model.layers.13.mlp.down_proj.weight": "pytorch_model-14-of-33.bin", "model.layers.13.post_attention_layernorm.weight": "pytorch_model-14-of-33.bin", "model.layers.13.self_attn.rotary_emb.inv_freq": "pytorch_model-14-of-33.bin", "model.layers.14.self_attn.q_proj.weight": "pytorch_model-15-of-33.bin", "model.layers.14.self_attn.k_proj.weight": "pytorch_model-15-of-33.bin", "model.layers.14.self_attn.v_proj.weight": "pytorch_model-15-of-33.bin", "model.layers.14.self_attn.o_proj.weight": "pytorch_model-15-of-33.bin", "model.layers.14.input_layernorm.weight": "pytorch_model-15-of-33.bin", "model.layers.14.mlp.gate_proj.weight": "pytorch_model-15-of-33.bin", "model.layers.14.mlp.up_proj.weight": "pytorch_model-15-of-33.bin", "model.layers.14.mlp.down_proj.weight": "pytorch_model-15-of-33.bin", "model.layers.14.post_attention_layernorm.weight": "pytorch_model-15-of-33.bin", "model.layers.14.self_attn.rotary_emb.inv_freq": "pytorch_model-15-of-33.bin", "model.layers.15.self_attn.q_proj.weight": "pytorch_model-16-of-33.bin", "model.layers.15.self_attn.k_proj.weight": "pytorch_model-16-of-33.bin", "model.layers.15.self_attn.v_proj.weight": "pytorch_model-16-of-33.bin", "model.layers.15.self_attn.o_proj.weight": "pytorch_model-16-of-33.bin", "model.layers.15.input_layernorm.weight": "pytorch_model-16-of-33.bin", "model.layers.15.mlp.gate_proj.weight": "pytorch_model-16-of-33.bin", "model.layers.15.mlp.up_proj.weight": "pytorch_model-16-of-33.bin", "model.layers.15.mlp.down_proj.weight": "pytorch_model-16-of-33.bin", "model.layers.15.post_attention_layernorm.weight": "pytorch_model-16-of-33.bin", "model.layers.15.self_attn.rotary_emb.inv_freq": "pytorch_model-16-of-33.bin", "model.layers.16.self_attn.q_proj.weight": "pytorch_model-17-of-33.bin", "model.layers.16.self_attn.k_proj.weight": "pytorch_model-17-of-33.bin", "model.layers.16.self_attn.v_proj.weight": "pytorch_model-17-of-33.bin", "model.layers.16.self_attn.o_proj.weight": "pytorch_model-17-of-33.bin", "model.layers.16.input_layernorm.weight": "pytorch_model-17-of-33.bin", "model.layers.16.mlp.gate_proj.weight": "pytorch_model-17-of-33.bin", "model.layers.16.mlp.up_proj.weight": "pytorch_model-17-of-33.bin", "model.layers.16.mlp.down_proj.weight": "pytorch_model-17-of-33.bin", "model.layers.16.post_attention_layernorm.weight": "pytorch_model-17-of-33.bin", "model.layers.16.self_attn.rotary_emb.inv_freq": "pytorch_model-17-of-33.bin", "model.layers.17.self_attn.q_proj.weight": "pytorch_model-18-of-33.bin", "model.layers.17.self_attn.k_proj.weight": "pytorch_model-18-of-33.bin", "model.layers.17.self_attn.v_proj.weight": "pytorch_model-18-of-33.bin", "model.layers.17.self_attn.o_proj.weight": "pytorch_model-18-of-33.bin", "model.layers.17.input_layernorm.weight": "pytorch_model-18-of-33.bin", "model.layers.17.mlp.gate_proj.weight": "pytorch_model-18-of-33.bin", "model.layers.17.mlp.up_proj.weight": "pytorch_model-18-of-33.bin", "model.layers.17.mlp.down_proj.weight": "pytorch_model-18-of-33.bin", "model.layers.17.post_attention_layernorm.weight": "pytorch_model-18-of-33.bin", "model.layers.17.self_attn.rotary_emb.inv_freq": "pytorch_model-18-of-33.bin", "model.layers.18.self_attn.q_proj.weight": "pytorch_model-19-of-33.bin", "model.layers.18.self_attn.k_proj.weight": "pytorch_model-19-of-33.bin", "model.layers.18.self_attn.v_proj.weight": "pytorch_model-19-of-33.bin", "model.layers.18.self_attn.o_proj.weight": "pytorch_model-19-of-33.bin", "model.layers.18.input_layernorm.weight": "pytorch_model-19-of-33.bin", "model.layers.18.mlp.gate_proj.weight": "pytorch_model-19-of-33.bin", "model.layers.18.mlp.up_proj.weight": "pytorch_model-19-of-33.bin", "model.layers.18.mlp.down_proj.weight": "pytorch_model-19-of-33.bin", "model.layers.18.post_attention_layernorm.weight": "pytorch_model-19-of-33.bin", "model.layers.18.self_attn.rotary_emb.inv_freq": "pytorch_model-19-of-33.bin", "model.layers.19.self_attn.q_proj.weight": "pytorch_model-20-of-33.bin", "model.layers.19.self_attn.k_proj.weight": "pytorch_model-20-of-33.bin", "model.layers.19.self_attn.v_proj.weight": "pytorch_model-20-of-33.bin", "model.layers.19.self_attn.o_proj.weight": "pytorch_model-20-of-33.bin", "model.layers.19.input_layernorm.weight": "pytorch_model-20-of-33.bin", "model.layers.19.mlp.gate_proj.weight": "pytorch_model-20-of-33.bin", "model.layers.19.mlp.up_proj.weight": "pytorch_model-20-of-33.bin", "model.layers.19.mlp.down_proj.weight": "pytorch_model-20-of-33.bin", "model.layers.19.post_attention_layernorm.weight": "pytorch_model-20-of-33.bin", "model.layers.19.self_attn.rotary_emb.inv_freq": "pytorch_model-20-of-33.bin", "model.layers.20.self_attn.q_proj.weight": "pytorch_model-21-of-33.bin", "model.layers.20.self_attn.k_proj.weight": "pytorch_model-21-of-33.bin", "model.layers.20.self_attn.v_proj.weight": "pytorch_model-21-of-33.bin", "model.layers.20.self_attn.o_proj.weight": "pytorch_model-21-of-33.bin", "model.layers.20.input_layernorm.weight": "pytorch_model-21-of-33.bin", "model.layers.20.mlp.gate_proj.weight": "pytorch_model-21-of-33.bin", "model.layers.20.mlp.up_proj.weight": "pytorch_model-21-of-33.bin", "model.layers.20.mlp.down_proj.weight": "pytorch_model-21-of-33.bin", "model.layers.20.post_attention_layernorm.weight": "pytorch_model-21-of-33.bin", "model.layers.20.self_attn.rotary_emb.inv_freq": "pytorch_model-21-of-33.bin", "model.layers.21.self_attn.q_proj.weight": "pytorch_model-22-of-33.bin", "model.layers.21.self_attn.k_proj.weight": "pytorch_model-22-of-33.bin", "model.layers.21.self_attn.v_proj.weight": "pytorch_model-22-of-33.bin", "model.layers.21.self_attn.o_proj.weight": "pytorch_model-22-of-33.bin", "model.layers.21.input_layernorm.weight": "pytorch_model-22-of-33.bin", "model.layers.21.mlp.gate_proj.weight": "pytorch_model-22-of-33.bin", "model.layers.21.mlp.up_proj.weight": "pytorch_model-22-of-33.bin", "model.layers.21.mlp.down_proj.weight": "pytorch_model-22-of-33.bin", "model.layers.21.post_attention_layernorm.weight": "pytorch_model-22-of-33.bin", "model.layers.21.self_attn.rotary_emb.inv_freq": "pytorch_model-22-of-33.bin", "model.layers.22.self_attn.q_proj.weight": "pytorch_model-23-of-33.bin", "model.layers.22.self_attn.k_proj.weight": "pytorch_model-23-of-33.bin", "model.layers.22.self_attn.v_proj.weight": "pytorch_model-23-of-33.bin", "model.layers.22.self_attn.o_proj.weight": "pytorch_model-23-of-33.bin", "model.layers.22.input_layernorm.weight": "pytorch_model-23-of-33.bin", "model.layers.22.mlp.gate_proj.weight": "pytorch_model-23-of-33.bin", "model.layers.22.mlp.up_proj.weight": "pytorch_model-23-of-33.bin", "model.layers.22.mlp.down_proj.weight": "pytorch_model-23-of-33.bin", "model.layers.22.post_attention_layernorm.weight": "pytorch_model-23-of-33.bin", "model.layers.22.self_attn.rotary_emb.inv_freq": "pytorch_model-23-of-33.bin", "model.layers.23.self_attn.q_proj.weight": "pytorch_model-24-of-33.bin", "model.layers.23.self_attn.k_proj.weight": "pytorch_model-24-of-33.bin", "model.layers.23.self_attn.v_proj.weight": "pytorch_model-24-of-33.bin", "model.layers.23.self_attn.o_proj.weight": "pytorch_model-24-of-33.bin", "model.layers.23.input_layernorm.weight": "pytorch_model-24-of-33.bin", "model.layers.23.mlp.gate_proj.weight": "pytorch_model-24-of-33.bin", "model.layers.23.mlp.up_proj.weight": "pytorch_model-24-of-33.bin", "model.layers.23.mlp.down_proj.weight": "pytorch_model-24-of-33.bin", "model.layers.23.post_attention_layernorm.weight": "pytorch_model-24-of-33.bin", "model.layers.23.self_attn.rotary_emb.inv_freq": "pytorch_model-24-of-33.bin", "model.layers.24.self_attn.q_proj.weight": "pytorch_model-25-of-33.bin", "model.layers.24.self_attn.k_proj.weight": "pytorch_model-25-of-33.bin", "model.layers.24.self_attn.v_proj.weight": "pytorch_model-25-of-33.bin", "model.layers.24.self_attn.o_proj.weight": "pytorch_model-25-of-33.bin", "model.layers.24.input_layernorm.weight": "pytorch_model-25-of-33.bin", "model.layers.24.mlp.gate_proj.weight": "pytorch_model-25-of-33.bin", "model.layers.24.mlp.up_proj.weight": "pytorch_model-25-of-33.bin", "model.layers.24.mlp.down_proj.weight": "pytorch_model-25-of-33.bin", "model.layers.24.post_attention_layernorm.weight": "pytorch_model-25-of-33.bin", "model.layers.24.self_attn.rotary_emb.inv_freq": "pytorch_model-25-of-33.bin", "model.layers.25.self_attn.q_proj.weight": "pytorch_model-26-of-33.bin", "model.layers.25.self_attn.k_proj.weight": "pytorch_model-26-of-33.bin", "model.layers.25.self_attn.v_proj.weight": "pytorch_model-26-of-33.bin", "model.layers.25.self_attn.o_proj.weight": "pytorch_model-26-of-33.bin", "model.layers.25.input_layernorm.weight": "pytorch_model-26-of-33.bin", "model.layers.25.mlp.gate_proj.weight": "pytorch_model-26-of-33.bin", "model.layers.25.mlp.up_proj.weight": "pytorch_model-26-of-33.bin", "model.layers.25.mlp.down_proj.weight": "pytorch_model-26-of-33.bin", "model.layers.25.post_attention_layernorm.weight": "pytorch_model-26-of-33.bin", "model.layers.25.self_attn.rotary_emb.inv_freq": "pytorch_model-26-of-33.bin", "model.layers.26.self_attn.q_proj.weight": "pytorch_model-27-of-33.bin", "model.layers.26.self_attn.k_proj.weight": "pytorch_model-27-of-33.bin", "model.layers.26.self_attn.v_proj.weight": "pytorch_model-27-of-33.bin", "model.layers.26.self_attn.o_proj.weight": "pytorch_model-27-of-33.bin", "model.layers.26.input_layernorm.weight": "pytorch_model-27-of-33.bin", "model.layers.26.mlp.gate_proj.weight": "pytorch_model-27-of-33.bin", "model.layers.26.mlp.up_proj.weight": "pytorch_model-27-of-33.bin", "model.layers.26.mlp.down_proj.weight": "pytorch_model-27-of-33.bin", "model.layers.26.post_attention_layernorm.weight": "pytorch_model-27-of-33.bin", "model.layers.26.self_attn.rotary_emb.inv_freq": "pytorch_model-27-of-33.bin", "model.layers.27.self_attn.q_proj.weight": "pytorch_model-28-of-33.bin", "model.layers.27.self_attn.k_proj.weight": "pytorch_model-28-of-33.bin", "model.layers.27.self_attn.v_proj.weight": "pytorch_model-28-of-33.bin", "model.layers.27.self_attn.o_proj.weight": "pytorch_model-28-of-33.bin", "model.layers.27.input_layernorm.weight": "pytorch_model-28-of-33.bin", "model.layers.27.mlp.gate_proj.weight": "pytorch_model-28-of-33.bin", "model.layers.27.mlp.up_proj.weight": "pytorch_model-28-of-33.bin", "model.layers.27.mlp.down_proj.weight": "pytorch_model-28-of-33.bin", "model.layers.27.post_attention_layernorm.weight": "pytorch_model-28-of-33.bin", "model.layers.27.self_attn.rotary_emb.inv_freq": "pytorch_model-28-of-33.bin", "model.layers.28.self_attn.q_proj.weight": "pytorch_model-29-of-33.bin", "model.layers.28.self_attn.k_proj.weight": "pytorch_model-29-of-33.bin", "model.layers.28.self_attn.v_proj.weight": "pytorch_model-29-of-33.bin", "model.layers.28.self_attn.o_proj.weight": "pytorch_model-29-of-33.bin", "model.layers.28.input_layernorm.weight": "pytorch_model-29-of-33.bin", "model.layers.28.mlp.gate_proj.weight": "pytorch_model-29-of-33.bin", "model.layers.28.mlp.up_proj.weight": "pytorch_model-29-of-33.bin", "model.layers.28.mlp.down_proj.weight": "pytorch_model-29-of-33.bin", "model.layers.28.post_attention_layernorm.weight": "pytorch_model-29-of-33.bin", "model.layers.28.self_attn.rotary_emb.inv_freq": "pytorch_model-29-of-33.bin", "model.layers.29.self_attn.q_proj.weight": "pytorch_model-30-of-33.bin", "model.layers.29.self_attn.k_proj.weight": "pytorch_model-30-of-33.bin", "model.layers.29.self_attn.v_proj.weight": "pytorch_model-30-of-33.bin", "model.layers.29.self_attn.o_proj.weight": "pytorch_model-30-of-33.bin", "model.layers.29.input_layernorm.weight": "pytorch_model-30-of-33.bin", "model.layers.29.mlp.gate_proj.weight": "pytorch_model-30-of-33.bin", "model.layers.29.mlp.up_proj.weight": "pytorch_model-30-of-33.bin", "model.layers.29.mlp.down_proj.weight": "pytorch_model-30-of-33.bin", "model.layers.29.post_attention_layernorm.weight": "pytorch_model-30-of-33.bin", "model.layers.29.self_attn.rotary_emb.inv_freq": "pytorch_model-30-of-33.bin", "model.layers.30.self_attn.q_proj.weight": "pytorch_model-31-of-33.bin", "model.layers.30.self_attn.k_proj.weight": "pytorch_model-31-of-33.bin", "model.layers.30.self_attn.v_proj.weight": "pytorch_model-31-of-33.bin", "model.layers.30.self_attn.o_proj.weight": "pytorch_model-31-of-33.bin", "model.layers.30.input_layernorm.weight": "pytorch_model-31-of-33.bin", "model.layers.30.mlp.gate_proj.weight": "pytorch_model-31-of-33.bin", "model.layers.30.mlp.up_proj.weight": "pytorch_model-31-of-33.bin", "model.layers.30.mlp.down_proj.weight": "pytorch_model-31-of-33.bin", "model.layers.30.post_attention_layernorm.weight": "pytorch_model-31-of-33.bin", "model.layers.30.self_attn.rotary_emb.inv_freq": "pytorch_model-31-of-33.bin", "model.layers.31.self_attn.q_proj.weight": "pytorch_model-32-of-33.bin", "model.layers.31.self_attn.k_proj.weight": "pytorch_model-32-of-33.bin", "model.layers.31.self_attn.v_proj.weight": "pytorch_model-32-of-33.bin", "model.layers.31.self_attn.o_proj.weight": "pytorch_model-32-of-33.bin", "model.layers.31.input_layernorm.weight": "pytorch_model-32-of-33.bin", "model.layers.31.mlp.gate_proj.weight": "pytorch_model-32-of-33.bin", "model.layers.31.mlp.up_proj.weight": "pytorch_model-32-of-33.bin", "model.layers.31.mlp.down_proj.weight": "pytorch_model-32-of-33.bin", "model.layers.31.post_attention_layernorm.weight": "pytorch_model-32-of-33.bin", "model.layers.31.self_attn.rotary_emb.inv_freq": "pytorch_model-32-of-33.bin"}, "metadata": {"total_size": 12952539136}}
+{
+  "metadata": {
+    "total_size": 13476839424
+  },
+  "weight_map": {
+    "lm_head.weight": "pytorch_model-00002-of-00002.bin",
+    "model.embed_tokens.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.0.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.1.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.10.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.10.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.10.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.10.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.11.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.11.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.11.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.11.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.12.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.12.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.12.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.12.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.13.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.13.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.13.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.13.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.14.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.14.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.14.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.14.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.15.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.15.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.15.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.15.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.16.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.16.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.16.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.16.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.17.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.17.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.17.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.17.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.18.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.18.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.18.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.18.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.19.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.19.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.19.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.19.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.2.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.20.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.20.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.20.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.20.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.21.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.21.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.21.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.21.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.22.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.22.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.22.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.22.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.23.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.23.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.23.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.23.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.24.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.24.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.24.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.24.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
+    "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.25.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.25.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.25.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.25.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
+    "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.26.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.26.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.26.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.26.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
+    "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.27.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.27.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.27.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.27.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
+    "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.28.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.28.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.28.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.28.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
+    "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.29.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.29.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.29.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.29.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
+    "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.3.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.30.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.30.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.30.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.30.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
+    "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.31.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.31.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.31.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.31.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
+    "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.4.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.5.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.6.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.7.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.7.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.8.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.8.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.8.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.9.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.9.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.9.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.9.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.norm.weight": "pytorch_model-00002-of-00002.bin"
+  }
+}

tokenizer_config.json

@@ -1 +1 @@
-{"bos_token": "", "eos_token": "", "model_max_length": 1000000000000000019884624838656, "tokenizer_class": "LLaMATokenizer", "unk_token": ""}
+{"bos_token": "", "eos_token": "", "model_max_length": 1000000000000000019884624838656, "tokenizer_class": "LlamaTokenizer", "unk_token": ""}