Upload with huggingface_hub

config.json

@@ -0,0 +1 @@
+{"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}

generation_config.json

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

pytorch_model-00000-of-00033.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:567614fd5d5f67f7b842db97b3c6929e2c52a0a4e958a70e62219fa515a4df90
+size 404770226

pytorch_model-00001-of-00033.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:60ff6110037a193bbf200595db1a3fd77ed1ab7f319a94d40b70cf3b6379bd2c
+size 404770226

pytorch_model-00002-of-00033.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51a8253e8491ba7ef587f69dc3d2a8e5f80e84839ff4069411fe9b410462fc08
+size 404770226

pytorch_model-00003-of-00033.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:077a4d84f00aa6493501389c9cc950a08f0e661e3b0a6f5bce94c8b2e90da18f
+size 404770226

pytorch_model-00004-of-00033.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8bcc4e78fb5199d554e615155a5290921f55f3deeac306d7d6a088032f373378
+size 404770226

pytorch_model-00005-of-00033.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:747e490a2d0dfae1170c206f078ae18ff7a2c7c641da31bcf2ed78a2ea532179
+size 404770226

pytorch_model-00006-of-00033.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e7003211167ef01dedd4bac9f1d7e591fa596f609ac8c6d046c5c19e43450fc
+size 404770226

pytorch_model-00007-of-00033.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce00e7d0a5de2429891f3107159089173f8a597df0aaf2125466b90a3189ebc9
+size 404770226

pytorch_model-00008-of-00033.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:edd2ab06484966296a80a4734b4354a01d1d20071e1676de3f86c673f7b24c08
+size 404770226

pytorch_model-00009-of-00033.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:beaaec63d191e65f2b3af8e9825b03e82e259f7380e3d1fbab41f5c062a1ed25
+size 404770226

pytorch_model-00010-of-00033.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5abc36a4f6822eeb96e8f0bf5c6c66fb9563c5d6686cf7b0629e65d867fc862d
+size 404770226

pytorch_model-00011-of-00033.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32d497845bfa272fd11ad5b142819e73eab736f9bde4f67ad7a6be6fd70a0379
+size 404770226

pytorch_model-00012-of-00033.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04a2b0091676594fd810b71fe316ba9920debaf7695bed4a477816c0a2210f8c
+size 404770226

pytorch_model-00013-of-00033.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f60056030f96ee13d948bba5d9509cf4f16d3800ad86672fa63a38f70e8409c1
+size 404770226

pytorch_model-00014-of-00033.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c0f0f76582a8cf959a2cdfce3cbae7c1e7f8ef03ce4be876a4ad5d696a3487f
+size 404770226

pytorch_model-00015-of-00033.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa5f6b1a755caca37c1e8b3953d41e689937318d38ff4b3ae5174819dfd2fbe3
+size 404770226

pytorch_model-00016-of-00033.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f30ea0b018c22a25114b88bf207a2281af82e7b08a24fac6190e70eb417298b
+size 404770226

pytorch_model-00017-of-00033.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55d8bce09535ad04e1e290adb777219495cb9e36e5447d3b03fb474c10fd314e
+size 404770226

pytorch_model-00018-of-00033.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a2d396d3b250b69c4c4445f54423560f03868e0cb7dc86160aa78255b8f87b7
+size 404770226

pytorch_model-00019-of-00033.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55b5ab4fde16177eaf89a46eec095cd695db417d7e5371a1958b2388cf7b5784
+size 404770226

pytorch_model-00020-of-00033.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3b239d339553c36d3a95085946420c7baacdf863b2bd2ce4bf46e33773782f1
+size 404770226

pytorch_model-00021-of-00033.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7db6248951d2d1ab94ef102a5e503abaa8c029273071961d03198d0cfde97782
+size 404770226

pytorch_model-00022-of-00033.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd0cd87675422553312bb55d4f953b98a885ce94751134a6e2f3166c47fae1b1
+size 404770226

pytorch_model-00023-of-00033.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe02742ac3765e9c0ef3a4698840719ba7bb2362b9c11db306942580dbcd6b78
+size 404770226

pytorch_model-00024-of-00033.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:feb660f69a00d73455ece0d3c460537f82e1baef33b56f6eea8df5c50db20237
+size 404770226

pytorch_model-00025-of-00033.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:717fdfe2e6d4cb716244aad651714915a88fb1bf0ee9ce044ed9ee6e95807a36
+size 404770226

pytorch_model-00026-of-00033.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e3f873655dedd2d02b051b3c7c8c697d964f8d2aabd1882933c7b42dd21009c
+size 404770226

pytorch_model-00027-of-00033.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:19bb56c23f532eba696984262d5cfc12a3120280f3e4d8f77b3ca72fc78bd64a
+size 404770226

pytorch_model-00028-of-00033.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5eb48c0940e06331577ad7c7ef1dd4957ead99943b20bd48bc09803d7a48a300
+size 404770226

pytorch_model-00029-of-00033.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f06f312dd27176f7d1c0a84619dc4ce7a0fa4e69d12b45b8ec37a6f2f3c8e52b
+size 404770226

pytorch_model-00030-of-00033.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d9ba390336793da349dc4e8ef05d18450395db14f44a81d918243758f85ad9a
+size 404770226

pytorch_model-00031-of-00033.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25cc4825db35dc104be623d65b3d728cfa504cb5f44f1e884d6d5ab1f526ff29
+size 404770226

pytorch_model-00032-of-00033.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c9b84c816865b75af37cb78fc7afde2394f3f410a6ba238907dc5ace79dd70f
+size 524297740

pytorch_model.bin.index.json

@@ -0,0 +1 @@
+{"weight_map": {"model.decoder.layers.0.self_attn.q_proj.weight": "pytorch_model-00000-of-00033.bin", "model.decoder.layers.0.self_attn.k_proj.weight": "pytorch_model-00000-of-00033.bin", "model.decoder.layers.0.self_attn.v_proj.weight": "pytorch_model-00000-of-00033.bin", "model.decoder.layers.0.self_attn.o_proj.weight": "pytorch_model-00000-of-00033.bin", "model.decoder.layers.0.feed_forward.w1.weight": "pytorch_model-00000-of-00033.bin", "model.decoder.layers.0.feed_forward.w2.weight": "pytorch_model-00000-of-00033.bin", "model.decoder.layers.0.feed_forward.w3.weight": "pytorch_model-00000-of-00033.bin", "model.decoder.layers.0.attention_norm.weight": "pytorch_model-00000-of-00033.bin", "model.decoder.layers.0.ffn_norm.weight": "pytorch_model-00000-of-00033.bin", "model.decoder.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00033.bin", "model.decoder.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00033.bin", "model.decoder.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00033.bin", "model.decoder.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00033.bin", "model.decoder.layers.1.feed_forward.w1.weight": "pytorch_model-00001-of-00033.bin", "model.decoder.layers.1.feed_forward.w2.weight": "pytorch_model-00001-of-00033.bin", "model.decoder.layers.1.feed_forward.w3.weight": "pytorch_model-00001-of-00033.bin", "model.decoder.layers.1.attention_norm.weight": "pytorch_model-00001-of-00033.bin", "model.decoder.layers.1.ffn_norm.weight": "pytorch_model-00001-of-00033.bin", "model.decoder.layers.2.self_attn.q_proj.weight": "pytorch_model-00002-of-00033.bin", "model.decoder.layers.2.self_attn.k_proj.weight": "pytorch_model-00002-of-00033.bin", "model.decoder.layers.2.self_attn.v_proj.weight": "pytorch_model-00002-of-00033.bin", "model.decoder.layers.2.self_attn.o_proj.weight": "pytorch_model-00002-of-00033.bin", "model.decoder.layers.2.feed_forward.w1.weight": "pytorch_model-00002-of-00033.bin", "model.decoder.layers.2.feed_forward.w2.weight": "pytorch_model-00002-of-00033.bin", "model.decoder.layers.2.feed_forward.w3.weight": "pytorch_model-00002-of-00033.bin", "model.decoder.layers.2.attention_norm.weight": "pytorch_model-00002-of-00033.bin", "model.decoder.layers.2.ffn_norm.weight": "pytorch_model-00002-of-00033.bin", "model.decoder.layers.3.self_attn.q_proj.weight": "pytorch_model-00003-of-00033.bin", "model.decoder.layers.3.self_attn.k_proj.weight": "pytorch_model-00003-of-00033.bin", "model.decoder.layers.3.self_attn.v_proj.weight": "pytorch_model-00003-of-00033.bin", "model.decoder.layers.3.self_attn.o_proj.weight": "pytorch_model-00003-of-00033.bin", "model.decoder.layers.3.feed_forward.w1.weight": "pytorch_model-00003-of-00033.bin", "model.decoder.layers.3.feed_forward.w2.weight": "pytorch_model-00003-of-00033.bin", "model.decoder.layers.3.feed_forward.w3.weight": "pytorch_model-00003-of-00033.bin", "model.decoder.layers.3.attention_norm.weight": "pytorch_model-00003-of-00033.bin", "model.decoder.layers.3.ffn_norm.weight": "pytorch_model-00003-of-00033.bin", "model.decoder.layers.4.self_attn.q_proj.weight": "pytorch_model-00004-of-00033.bin", "model.decoder.layers.4.self_attn.k_proj.weight": "pytorch_model-00004-of-00033.bin", "model.decoder.layers.4.self_attn.v_proj.weight": "pytorch_model-00004-of-00033.bin", "model.decoder.layers.4.self_attn.o_proj.weight": "pytorch_model-00004-of-00033.bin", "model.decoder.layers.4.feed_forward.w1.weight": "pytorch_model-00004-of-00033.bin", "model.decoder.layers.4.feed_forward.w2.weight": "pytorch_model-00004-of-00033.bin", "model.decoder.layers.4.feed_forward.w3.weight": "pytorch_model-00004-of-00033.bin", "model.decoder.layers.4.attention_norm.weight": "pytorch_model-00004-of-00033.bin", "model.decoder.layers.4.ffn_norm.weight": "pytorch_model-00004-of-00033.bin", "model.decoder.layers.5.self_attn.q_proj.weight": "pytorch_model-00005-of-00033.bin", "model.decoder.layers.5.self_attn.k_proj.weight": "pytorch_model-00005-of-00033.bin", "model.decoder.layers.5.self_attn.v_proj.weight": "pytorch_model-00005-of-00033.bin", "model.decoder.layers.5.self_attn.o_proj.weight": "pytorch_model-00005-of-00033.bin", "model.decoder.layers.5.feed_forward.w1.weight": "pytorch_model-00005-of-00033.bin", "model.decoder.layers.5.feed_forward.w2.weight": "pytorch_model-00005-of-00033.bin", "model.decoder.layers.5.feed_forward.w3.weight": "pytorch_model-00005-of-00033.bin", "model.decoder.layers.5.attention_norm.weight": "pytorch_model-00005-of-00033.bin", "model.decoder.layers.5.ffn_norm.weight": "pytorch_model-00005-of-00033.bin", "model.decoder.layers.6.self_attn.q_proj.weight": "pytorch_model-00006-of-00033.bin", "model.decoder.layers.6.self_attn.k_proj.weight": "pytorch_model-00006-of-00033.bin", "model.decoder.layers.6.self_attn.v_proj.weight": "pytorch_model-00006-of-00033.bin", "model.decoder.layers.6.self_attn.o_proj.weight": "pytorch_model-00006-of-00033.bin", "model.decoder.layers.6.feed_forward.w1.weight": "pytorch_model-00006-of-00033.bin", "model.decoder.layers.6.feed_forward.w2.weight": "pytorch_model-00006-of-00033.bin", "model.decoder.layers.6.feed_forward.w3.weight": "pytorch_model-00006-of-00033.bin", "model.decoder.layers.6.attention_norm.weight": "pytorch_model-00006-of-00033.bin", "model.decoder.layers.6.ffn_norm.weight": "pytorch_model-00006-of-00033.bin", "model.decoder.layers.7.self_attn.q_proj.weight": "pytorch_model-00007-of-00033.bin", "model.decoder.layers.7.self_attn.k_proj.weight": "pytorch_model-00007-of-00033.bin", "model.decoder.layers.7.self_attn.v_proj.weight": "pytorch_model-00007-of-00033.bin", "model.decoder.layers.7.self_attn.o_proj.weight": "pytorch_model-00007-of-00033.bin", "model.decoder.layers.7.feed_forward.w1.weight": "pytorch_model-00007-of-00033.bin", "model.decoder.layers.7.feed_forward.w2.weight": "pytorch_model-00007-of-00033.bin", "model.decoder.layers.7.feed_forward.w3.weight": "pytorch_model-00007-of-00033.bin", "model.decoder.layers.7.attention_norm.weight": "pytorch_model-00007-of-00033.bin", "model.decoder.layers.7.ffn_norm.weight": "pytorch_model-00007-of-00033.bin", "model.decoder.layers.8.self_attn.q_proj.weight": "pytorch_model-00008-of-00033.bin", "model.decoder.layers.8.self_attn.k_proj.weight": "pytorch_model-00008-of-00033.bin", "model.decoder.layers.8.self_attn.v_proj.weight": "pytorch_model-00008-of-00033.bin", "model.decoder.layers.8.self_attn.o_proj.weight": "pytorch_model-00008-of-00033.bin", "model.decoder.layers.8.feed_forward.w1.weight": "pytorch_model-00008-of-00033.bin", "model.decoder.layers.8.feed_forward.w2.weight": "pytorch_model-00008-of-00033.bin", "model.decoder.layers.8.feed_forward.w3.weight": "pytorch_model-00008-of-00033.bin", "model.decoder.layers.8.attention_norm.weight": "pytorch_model-00008-of-00033.bin", "model.decoder.layers.8.ffn_norm.weight": "pytorch_model-00008-of-00033.bin", "model.decoder.layers.9.self_attn.q_proj.weight": "pytorch_model-00009-of-00033.bin", "model.decoder.layers.9.self_attn.k_proj.weight": "pytorch_model-00009-of-00033.bin", "model.decoder.layers.9.self_attn.v_proj.weight": "pytorch_model-00009-of-00033.bin", "model.decoder.layers.9.self_attn.o_proj.weight": "pytorch_model-00009-of-00033.bin", "model.decoder.layers.9.feed_forward.w1.weight": "pytorch_model-00009-of-00033.bin", "model.decoder.layers.9.feed_forward.w2.weight": "pytorch_model-00009-of-00033.bin", "model.decoder.layers.9.feed_forward.w3.weight": "pytorch_model-00009-of-00033.bin", "model.decoder.layers.9.attention_norm.weight": "pytorch_model-00009-of-00033.bin", "model.decoder.layers.9.ffn_norm.weight": "pytorch_model-00009-of-00033.bin", "model.decoder.layers.10.self_attn.q_proj.weight": "pytorch_model-00010-of-00033.bin", "model.decoder.layers.10.self_attn.k_proj.weight": "pytorch_model-00010-of-00033.bin", "model.decoder.layers.10.self_attn.v_proj.weight": "pytorch_model-00010-of-00033.bin", "model.decoder.layers.10.self_attn.o_proj.weight": "pytorch_model-00010-of-00033.bin", "model.decoder.layers.10.feed_forward.w1.weight": "pytorch_model-00010-of-00033.bin", "model.decoder.layers.10.feed_forward.w2.weight": "pytorch_model-00010-of-00033.bin", "model.decoder.layers.10.feed_forward.w3.weight": "pytorch_model-00010-of-00033.bin", "model.decoder.layers.10.attention_norm.weight": "pytorch_model-00010-of-00033.bin", "model.decoder.layers.10.ffn_norm.weight": "pytorch_model-00010-of-00033.bin", "model.decoder.layers.11.self_attn.q_proj.weight": "pytorch_model-00011-of-00033.bin", "model.decoder.layers.11.self_attn.k_proj.weight": "pytorch_model-00011-of-00033.bin", "model.decoder.layers.11.self_attn.v_proj.weight": "pytorch_model-00011-of-00033.bin", "model.decoder.layers.11.self_attn.o_proj.weight": "pytorch_model-00011-of-00033.bin", "model.decoder.layers.11.feed_forward.w1.weight": "pytorch_model-00011-of-00033.bin", "model.decoder.layers.11.feed_forward.w2.weight": "pytorch_model-00011-of-00033.bin", "model.decoder.layers.11.feed_forward.w3.weight": "pytorch_model-00011-of-00033.bin", "model.decoder.layers.11.attention_norm.weight": "pytorch_model-00011-of-00033.bin", "model.decoder.layers.11.ffn_norm.weight": "pytorch_model-00011-of-00033.bin", "model.decoder.layers.12.self_attn.q_proj.weight": "pytorch_model-00012-of-00033.bin", "model.decoder.layers.12.self_attn.k_proj.weight": "pytorch_model-00012-of-00033.bin", "model.decoder.layers.12.self_attn.v_proj.weight": "pytorch_model-00012-of-00033.bin", "model.decoder.layers.12.self_attn.o_proj.weight": "pytorch_model-00012-of-00033.bin", "model.decoder.layers.12.feed_forward.w1.weight": "pytorch_model-00012-of-00033.bin", "model.decoder.layers.12.feed_forward.w2.weight": "pytorch_model-00012-of-00033.bin", "model.decoder.layers.12.feed_forward.w3.weight": "pytorch_model-00012-of-00033.bin", "model.decoder.layers.12.attention_norm.weight": "pytorch_model-00012-of-00033.bin", "model.decoder.layers.12.ffn_norm.weight": "pytorch_model-00012-of-00033.bin", "model.decoder.layers.13.self_attn.q_proj.weight": "pytorch_model-00013-of-00033.bin", "model.decoder.layers.13.self_attn.k_proj.weight": "pytorch_model-00013-of-00033.bin", "model.decoder.layers.13.self_attn.v_proj.weight": "pytorch_model-00013-of-00033.bin", "model.decoder.layers.13.self_attn.o_proj.weight": "pytorch_model-00013-of-00033.bin", "model.decoder.layers.13.feed_forward.w1.weight": "pytorch_model-00013-of-00033.bin", "model.decoder.layers.13.feed_forward.w2.weight": "pytorch_model-00013-of-00033.bin", "model.decoder.layers.13.feed_forward.w3.weight": "pytorch_model-00013-of-00033.bin", "model.decoder.layers.13.attention_norm.weight": "pytorch_model-00013-of-00033.bin", "model.decoder.layers.13.ffn_norm.weight": "pytorch_model-00013-of-00033.bin", "model.decoder.layers.14.self_attn.q_proj.weight": "pytorch_model-00014-of-00033.bin", "model.decoder.layers.14.self_attn.k_proj.weight": "pytorch_model-00014-of-00033.bin", "model.decoder.layers.14.self_attn.v_proj.weight": "pytorch_model-00014-of-00033.bin", "model.decoder.layers.14.self_attn.o_proj.weight": "pytorch_model-00014-of-00033.bin", "model.decoder.layers.14.feed_forward.w1.weight": "pytorch_model-00014-of-00033.bin", "model.decoder.layers.14.feed_forward.w2.weight": "pytorch_model-00014-of-00033.bin", "model.decoder.layers.14.feed_forward.w3.weight": "pytorch_model-00014-of-00033.bin", "model.decoder.layers.14.attention_norm.weight": "pytorch_model-00014-of-00033.bin", "model.decoder.layers.14.ffn_norm.weight": "pytorch_model-00014-of-00033.bin", "model.decoder.layers.15.self_attn.q_proj.weight": "pytorch_model-00015-of-00033.bin", "model.decoder.layers.15.self_attn.k_proj.weight": "pytorch_model-00015-of-00033.bin", "model.decoder.layers.15.self_attn.v_proj.weight": "pytorch_model-00015-of-00033.bin", "model.decoder.layers.15.self_attn.o_proj.weight": "pytorch_model-00015-of-00033.bin", "model.decoder.layers.15.feed_forward.w1.weight": "pytorch_model-00015-of-00033.bin", "model.decoder.layers.15.feed_forward.w2.weight": "pytorch_model-00015-of-00033.bin", "model.decoder.layers.15.feed_forward.w3.weight": "pytorch_model-00015-of-00033.bin", "model.decoder.layers.15.attention_norm.weight": "pytorch_model-00015-of-00033.bin", "model.decoder.layers.15.ffn_norm.weight": "pytorch_model-00015-of-00033.bin", "model.decoder.layers.16.self_attn.q_proj.weight": "pytorch_model-00016-of-00033.bin", "model.decoder.layers.16.self_attn.k_proj.weight": "pytorch_model-00016-of-00033.bin", "model.decoder.layers.16.self_attn.v_proj.weight": "pytorch_model-00016-of-00033.bin", "model.decoder.layers.16.self_attn.o_proj.weight": "pytorch_model-00016-of-00033.bin", "model.decoder.layers.16.feed_forward.w1.weight": "pytorch_model-00016-of-00033.bin", "model.decoder.layers.16.feed_forward.w2.weight": "pytorch_model-00016-of-00033.bin", "model.decoder.layers.16.feed_forward.w3.weight": "pytorch_model-00016-of-00033.bin", "model.decoder.layers.16.attention_norm.weight": "pytorch_model-00016-of-00033.bin", "model.decoder.layers.16.ffn_norm.weight": "pytorch_model-00016-of-00033.bin", "model.decoder.layers.17.self_attn.q_proj.weight": "pytorch_model-00017-of-00033.bin", "model.decoder.layers.17.self_attn.k_proj.weight": "pytorch_model-00017-of-00033.bin", "model.decoder.layers.17.self_attn.v_proj.weight": "pytorch_model-00017-of-00033.bin", "model.decoder.layers.17.self_attn.o_proj.weight": "pytorch_model-00017-of-00033.bin", "model.decoder.layers.17.feed_forward.w1.weight": "pytorch_model-00017-of-00033.bin", "model.decoder.layers.17.feed_forward.w2.weight": "pytorch_model-00017-of-00033.bin", "model.decoder.layers.17.feed_forward.w3.weight": "pytorch_model-00017-of-00033.bin", "model.decoder.layers.17.attention_norm.weight": "pytorch_model-00017-of-00033.bin", "model.decoder.layers.17.ffn_norm.weight": "pytorch_model-00017-of-00033.bin", "model.decoder.layers.18.self_attn.q_proj.weight": "pytorch_model-00018-of-00033.bin", "model.decoder.layers.18.self_attn.k_proj.weight": "pytorch_model-00018-of-00033.bin", "model.decoder.layers.18.self_attn.v_proj.weight": "pytorch_model-00018-of-00033.bin", "model.decoder.layers.18.self_attn.o_proj.weight": "pytorch_model-00018-of-00033.bin", "model.decoder.layers.18.feed_forward.w1.weight": "pytorch_model-00018-of-00033.bin", "model.decoder.layers.18.feed_forward.w2.weight": "pytorch_model-00018-of-00033.bin", "model.decoder.layers.18.feed_forward.w3.weight": "pytorch_model-00018-of-00033.bin", "model.decoder.layers.18.attention_norm.weight": "pytorch_model-00018-of-00033.bin", "model.decoder.layers.18.ffn_norm.weight": "pytorch_model-00018-of-00033.bin", "model.decoder.layers.19.self_attn.q_proj.weight": "pytorch_model-00019-of-00033.bin", "model.decoder.layers.19.self_attn.k_proj.weight": "pytorch_model-00019-of-00033.bin", "model.decoder.layers.19.self_attn.v_proj.weight": "pytorch_model-00019-of-00033.bin", "model.decoder.layers.19.self_attn.o_proj.weight": "pytorch_model-00019-of-00033.bin", "model.decoder.layers.19.feed_forward.w1.weight": "pytorch_model-00019-of-00033.bin", "model.decoder.layers.19.feed_forward.w2.weight": "pytorch_model-00019-of-00033.bin", "model.decoder.layers.19.feed_forward.w3.weight": "pytorch_model-00019-of-00033.bin", "model.decoder.layers.19.attention_norm.weight": "pytorch_model-00019-of-00033.bin", "model.decoder.layers.19.ffn_norm.weight": "pytorch_model-00019-of-00033.bin", "model.decoder.layers.20.self_attn.q_proj.weight": "pytorch_model-00020-of-00033.bin", "model.decoder.layers.20.self_attn.k_proj.weight": "pytorch_model-00020-of-00033.bin", "model.decoder.layers.20.self_attn.v_proj.weight": "pytorch_model-00020-of-00033.bin", "model.decoder.layers.20.self_attn.o_proj.weight": "pytorch_model-00020-of-00033.bin", "model.decoder.layers.20.feed_forward.w1.weight": "pytorch_model-00020-of-00033.bin", "model.decoder.layers.20.feed_forward.w2.weight": "pytorch_model-00020-of-00033.bin", "model.decoder.layers.20.feed_forward.w3.weight": "pytorch_model-00020-of-00033.bin", "model.decoder.layers.20.attention_norm.weight": "pytorch_model-00020-of-00033.bin", "model.decoder.layers.20.ffn_norm.weight": "pytorch_model-00020-of-00033.bin", "model.decoder.layers.21.self_attn.q_proj.weight": "pytorch_model-00021-of-00033.bin", "model.decoder.layers.21.self_attn.k_proj.weight": "pytorch_model-00021-of-00033.bin", "model.decoder.layers.21.self_attn.v_proj.weight": "pytorch_model-00021-of-00033.bin", "model.decoder.layers.21.self_attn.o_proj.weight": "pytorch_model-00021-of-00033.bin", "model.decoder.layers.21.feed_forward.w1.weight": "pytorch_model-00021-of-00033.bin", "model.decoder.layers.21.feed_forward.w2.weight": "pytorch_model-00021-of-00033.bin", "model.decoder.layers.21.feed_forward.w3.weight": "pytorch_model-00021-of-00033.bin", "model.decoder.layers.21.attention_norm.weight": "pytorch_model-00021-of-00033.bin", "model.decoder.layers.21.ffn_norm.weight": "pytorch_model-00021-of-00033.bin", "model.decoder.layers.22.self_attn.q_proj.weight": "pytorch_model-00022-of-00033.bin", "model.decoder.layers.22.self_attn.k_proj.weight": "pytorch_model-00022-of-00033.bin", "model.decoder.layers.22.self_attn.v_proj.weight": "pytorch_model-00022-of-00033.bin", "model.decoder.layers.22.self_attn.o_proj.weight": "pytorch_model-00022-of-00033.bin", "model.decoder.layers.22.feed_forward.w1.weight": "pytorch_model-00022-of-00033.bin", "model.decoder.layers.22.feed_forward.w2.weight": "pytorch_model-00022-of-00033.bin", "model.decoder.layers.22.feed_forward.w3.weight": "pytorch_model-00022-of-00033.bin", "model.decoder.layers.22.attention_norm.weight": "pytorch_model-00022-of-00033.bin", "model.decoder.layers.22.ffn_norm.weight": "pytorch_model-00022-of-00033.bin", "model.decoder.layers.23.self_attn.q_proj.weight": "pytorch_model-00023-of-00033.bin", "model.decoder.layers.23.self_attn.k_proj.weight": "pytorch_model-00023-of-00033.bin", "model.decoder.layers.23.self_attn.v_proj.weight": "pytorch_model-00023-of-00033.bin", "model.decoder.layers.23.self_attn.o_proj.weight": "pytorch_model-00023-of-00033.bin", "model.decoder.layers.23.feed_forward.w1.weight": "pytorch_model-00023-of-00033.bin", "model.decoder.layers.23.feed_forward.w2.weight": "pytorch_model-00023-of-00033.bin", "model.decoder.layers.23.feed_forward.w3.weight": "pytorch_model-00023-of-00033.bin", "model.decoder.layers.23.attention_norm.weight": "pytorch_model-00023-of-00033.bin", "model.decoder.layers.23.ffn_norm.weight": "pytorch_model-00023-of-00033.bin", "model.decoder.layers.24.self_attn.q_proj.weight": "pytorch_model-00024-of-00033.bin", "model.decoder.layers.24.self_attn.k_proj.weight": "pytorch_model-00024-of-00033.bin", "model.decoder.layers.24.self_attn.v_proj.weight": "pytorch_model-00024-of-00033.bin", "model.decoder.layers.24.self_attn.o_proj.weight": "pytorch_model-00024-of-00033.bin", "model.decoder.layers.24.feed_forward.w1.weight": "pytorch_model-00024-of-00033.bin", "model.decoder.layers.24.feed_forward.w2.weight": "pytorch_model-00024-of-00033.bin", "model.decoder.layers.24.feed_forward.w3.weight": "pytorch_model-00024-of-00033.bin", "model.decoder.layers.24.attention_norm.weight": "pytorch_model-00024-of-00033.bin", "model.decoder.layers.24.ffn_norm.weight": "pytorch_model-00024-of-00033.bin", "model.decoder.layers.25.self_attn.q_proj.weight": "pytorch_model-00025-of-00033.bin", "model.decoder.layers.25.self_attn.k_proj.weight": "pytorch_model-00025-of-00033.bin", "model.decoder.layers.25.self_attn.v_proj.weight": "pytorch_model-00025-of-00033.bin", "model.decoder.layers.25.self_attn.o_proj.weight": "pytorch_model-00025-of-00033.bin", "model.decoder.layers.25.feed_forward.w1.weight": "pytorch_model-00025-of-00033.bin", "model.decoder.layers.25.feed_forward.w2.weight": "pytorch_model-00025-of-00033.bin", "model.decoder.layers.25.feed_forward.w3.weight": "pytorch_model-00025-of-00033.bin", "model.decoder.layers.25.attention_norm.weight": "pytorch_model-00025-of-00033.bin", "model.decoder.layers.25.ffn_norm.weight": "pytorch_model-00025-of-00033.bin", "model.decoder.layers.26.self_attn.q_proj.weight": "pytorch_model-00026-of-00033.bin", "model.decoder.layers.26.self_attn.k_proj.weight": "pytorch_model-00026-of-00033.bin", "model.decoder.layers.26.self_attn.v_proj.weight": "pytorch_model-00026-of-00033.bin", "model.decoder.layers.26.self_attn.o_proj.weight": "pytorch_model-00026-of-00033.bin", "model.decoder.layers.26.feed_forward.w1.weight": "pytorch_model-00026-of-00033.bin", "model.decoder.layers.26.feed_forward.w2.weight": "pytorch_model-00026-of-00033.bin", "model.decoder.layers.26.feed_forward.w3.weight": "pytorch_model-00026-of-00033.bin", "model.decoder.layers.26.attention_norm.weight": "pytorch_model-00026-of-00033.bin", "model.decoder.layers.26.ffn_norm.weight": "pytorch_model-00026-of-00033.bin", "model.decoder.layers.27.self_attn.q_proj.weight": "pytorch_model-00027-of-00033.bin", "model.decoder.layers.27.self_attn.k_proj.weight": "pytorch_model-00027-of-00033.bin", "model.decoder.layers.27.self_attn.v_proj.weight": "pytorch_model-00027-of-00033.bin", "model.decoder.layers.27.self_attn.o_proj.weight": "pytorch_model-00027-of-00033.bin", "model.decoder.layers.27.feed_forward.w1.weight": "pytorch_model-00027-of-00033.bin", "model.decoder.layers.27.feed_forward.w2.weight": "pytorch_model-00027-of-00033.bin", "model.decoder.layers.27.feed_forward.w3.weight": "pytorch_model-00027-of-00033.bin", "model.decoder.layers.27.attention_norm.weight": "pytorch_model-00027-of-00033.bin", "model.decoder.layers.27.ffn_norm.weight": "pytorch_model-00027-of-00033.bin", "model.decoder.layers.28.self_attn.q_proj.weight": "pytorch_model-00028-of-00033.bin", "model.decoder.layers.28.self_attn.k_proj.weight": "pytorch_model-00028-of-00033.bin", "model.decoder.layers.28.self_attn.v_proj.weight": "pytorch_model-00028-of-00033.bin", "model.decoder.layers.28.self_attn.o_proj.weight": "pytorch_model-00028-of-00033.bin", "model.decoder.layers.28.feed_forward.w1.weight": "pytorch_model-00028-of-00033.bin", "model.decoder.layers.28.feed_forward.w2.weight": "pytorch_model-00028-of-00033.bin", "model.decoder.layers.28.feed_forward.w3.weight": "pytorch_model-00028-of-00033.bin", "model.decoder.layers.28.attention_norm.weight": "pytorch_model-00028-of-00033.bin", "model.decoder.layers.28.ffn_norm.weight": "pytorch_model-00028-of-00033.bin", "model.decoder.layers.29.self_attn.q_proj.weight": "pytorch_model-00029-of-00033.bin", "model.decoder.layers.29.self_attn.k_proj.weight": "pytorch_model-00029-of-00033.bin", "model.decoder.layers.29.self_attn.v_proj.weight": "pytorch_model-00029-of-00033.bin", "model.decoder.layers.29.self_attn.o_proj.weight": "pytorch_model-00029-of-00033.bin", "model.decoder.layers.29.feed_forward.w1.weight": "pytorch_model-00029-of-00033.bin", "model.decoder.layers.29.feed_forward.w2.weight": "pytorch_model-00029-of-00033.bin", "model.decoder.layers.29.feed_forward.w3.weight": "pytorch_model-00029-of-00033.bin", "model.decoder.layers.29.attention_norm.weight": "pytorch_model-00029-of-00033.bin", "model.decoder.layers.29.ffn_norm.weight": "pytorch_model-00029-of-00033.bin", "model.decoder.layers.30.self_attn.q_proj.weight": "pytorch_model-00030-of-00033.bin", "model.decoder.layers.30.self_attn.k_proj.weight": "pytorch_model-00030-of-00033.bin", "model.decoder.layers.30.self_attn.v_proj.weight": "pytorch_model-00030-of-00033.bin", "model.decoder.layers.30.self_attn.o_proj.weight": "pytorch_model-00030-of-00033.bin", "model.decoder.layers.30.feed_forward.w1.weight": "pytorch_model-00030-of-00033.bin", "model.decoder.layers.30.feed_forward.w2.weight": "pytorch_model-00030-of-00033.bin", "model.decoder.layers.30.feed_forward.w3.weight": "pytorch_model-00030-of-00033.bin", "model.decoder.layers.30.attention_norm.weight": "pytorch_model-00030-of-00033.bin", "model.decoder.layers.30.ffn_norm.weight": "pytorch_model-00030-of-00033.bin", "model.decoder.layers.31.self_attn.q_proj.weight": "pytorch_model-00031-of-00033.bin", "model.decoder.layers.31.self_attn.k_proj.weight": "pytorch_model-00031-of-00033.bin", "model.decoder.layers.31.self_attn.v_proj.weight": "pytorch_model-00031-of-00033.bin", "model.decoder.layers.31.self_attn.o_proj.weight": "pytorch_model-00031-of-00033.bin", "model.decoder.layers.31.feed_forward.w1.weight": "pytorch_model-00031-of-00033.bin", "model.decoder.layers.31.feed_forward.w2.weight": "pytorch_model-00031-of-00033.bin", "model.decoder.layers.31.feed_forward.w3.weight": "pytorch_model-00031-of-00033.bin", "model.decoder.layers.31.attention_norm.weight": "pytorch_model-00031-of-00033.bin", "model.decoder.layers.31.ffn_norm.weight": "pytorch_model-00031-of-00033.bin", "model.decoder.embed_tokens.weight": "pytorch_model-00032-of-00033.bin", "model.decoder.norm.weight": "pytorch_model-00032-of-00033.bin", "lm_head.weight": "pytorch_model-00032-of-00033.bin"}, "metadata": {"total_size": 13476831232}}

special_tokens_map.json

@@ -0,0 +1 @@
+{}

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