AdaptLLM-law-v0

config.json

@@ -0,0 +1,21 @@
+{
+    "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": 32000,
+    "rms_norm_eps": 1e-06,
+    "torch_dtype": "float16",
+    "transformers_version": "4.27.0.dev0",
+    "use_cache": true,
+    "vocab_size": 32001
+}

generation_config.json

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

pytorch_model-00001-of-00033.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f622c2399de6a2102b6fb6412326331ffd3ebe3a392692dc549db6b3e08a2df0
+size 809520963

pytorch_model-00002-of-00033.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a70e341ed0a7bc4eb00fd1f3c4019d6c9c4f459b02b599e9cdf434bf708bb10
+size 809520963

pytorch_model-00003-of-00033.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fcdc4a22448fb4285a69dad41f3d572f7f302f95d047bec80afae7a48440312a
+size 809520963

pytorch_model-00004-of-00033.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:005969658feaaab13050844bb297556536942fcfce619b923afdb2e729218609
+size 809520963

pytorch_model-00005-of-00033.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9e4ed5aad4c73303094fd2fc542a22b1c5bc447456c45e6d19c191983a68055
+size 809520963

pytorch_model-00006-of-00033.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2147e47e821c01e1234481c6d3f9085200713c5d3a2776b87f0019f039956677
+size 809520963

pytorch_model-00007-of-00033.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:18626ae8d2d2bff6ad2096614d93ebf3ba3cb2aefa084c7db266d660d98d6d68
+size 809520963

pytorch_model-00008-of-00033.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e0ad2ddd370ce44b5fbaaff82cb451504396e0844a4ba2ce184046131df9564
+size 809520963

pytorch_model-00009-of-00033.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9a2263f5571330ec1c82ff56f5f586cc316b6da6c7b02cd78e77b0d6b0eaee6
+size 809520963

pytorch_model-00010-of-00033.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:999d226e42bab664f61470ef442b8f37d8517ca1f62299393c82e55e1f6c8db7
+size 809520963

pytorch_model-00011-of-00033.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:28284822a0345c267ad240fedc3c6aa166e2cc2a45a8c107751f947cff8acb4d
+size 809520963

pytorch_model-00012-of-00033.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6bc4404ec4168db5adc55dcf4e61bd43f2c6d834e270e1de79846d60f93f5150
+size 809520963

pytorch_model-00013-of-00033.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:58caed7f0aa4a12dab78b5fda83e5eaf635670abd5d11591d7dd372aa8c30d3f
+size 809520963

pytorch_model-00014-of-00033.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3af78f4f6ae5c4a934eee05de2b34e69ba90d7f72c631c307762132df4f29ccd
+size 809520963

pytorch_model-00015-of-00033.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:337fcc046f8fe8db5917e18a4e646f23df4ac40900098f8e1d673099bc073e52
+size 809520963

pytorch_model-00016-of-00033.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ddbda4128747268c581352e7944a8d48008db4843ea613e6b22b14481fa37339
+size 809520963

pytorch_model-00017-of-00033.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d0b2684def140c14484ba3aae08894c2ebb6788181fa175037dc0e059df50ba9
+size 809520963

pytorch_model-00018-of-00033.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:272c05c0bee082019abe54c1cb19b5c439ae1aa3cb250f3de8f44a84741494cc
+size 809520963

pytorch_model-00019-of-00033.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48f003ffcaf49ad26fad590ac15db8b7408c864ad436c6a98bd6de9256559675
+size 809520963

pytorch_model-00020-of-00033.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb0292f55eb1e64fb1e278a214d164ddb168a1cd917e06ce533b00ae30d434f9
+size 809520963

pytorch_model-00021-of-00033.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a740bcb6c1fbcca4ed0fec9803e49ac3eeab82333d1263fcfd0ef30934576a7
+size 809520963

pytorch_model-00022-of-00033.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae842ff87975caa06f20e3f89e9c3f65d80bca7f2006ec48158a71a56fe83921
+size 809520963

pytorch_model-00023-of-00033.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c23ea35d0786dbfb257b39ab54853ff4a812d51de651483ed027fd1885539db5
+size 809520963

pytorch_model-00024-of-00033.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:658c98a62291c50676c44b9da4774ba07334ff5bb71a7d0904cbb914cb0c8bf0
+size 809520963

pytorch_model-00025-of-00033.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f16e1ee74e4ef3600737ddd1e1955c02221d51519200ddec8bbe25c944fd733
+size 809520963

pytorch_model-00026-of-00033.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6d972ba0620cbe7f635a2fd6909c781ae09efd275139d17c92d4b338b728585
+size 809520963

pytorch_model-00027-of-00033.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c1e6acd611c3aa95a81572c9334d8c11ad170abe1aabf5bd1b8429d19c386d9
+size 809520963

pytorch_model-00028-of-00033.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d97720e2b553497e4dc19cbee8750819821ceae6adfedc6944f61399eebb5be
+size 809520963

pytorch_model-00029-of-00033.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:557a02a781c3e525d4f9b8fc21f93c6c9ffbf5fd8277465c3dc55c09cf006693
+size 809520963

pytorch_model-00030-of-00033.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ed9e1e173f43fe5c44988a7041229de8fdaae9db0a1a6f34951999b278b7823
+size 809520963

pytorch_model-00031-of-00033.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2334d0695389306a57bebedfcdb427510ae11aebd981e47ab26a4813dc6b4cb0
+size 809520963

pytorch_model-00032-of-00033.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c4dea5097bb1f7098f0bcb995c317d24319d3a1c918c92bf4ece69148a7aab79
+size 809520963

pytorch_model-00033-of-00033.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15c633883b2d2fca8b84ba56b3e71f0f54cbbef73bcb49cc84b5b69bc2a0e6d1
+size 524314060

pytorch_model.bin.index.json

@@ -0,0 +1 @@
+{"weight_map": {"model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00033.bin", "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00033.bin", "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00033.bin", "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00033.bin", "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00033.bin", "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00033.bin", "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00033.bin", "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00033.bin", "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00033.bin", "model.layers.0.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00033.bin", "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00002-of-00033.bin", "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00002-of-00033.bin", "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00002-of-00033.bin", "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00002-of-00033.bin", "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00002-of-00033.bin", "model.layers.1.mlp.down_proj.weight": "pytorch_model-00002-of-00033.bin", "model.layers.1.mlp.up_proj.weight": "pytorch_model-00002-of-00033.bin", "model.layers.1.input_layernorm.weight": "pytorch_model-00002-of-00033.bin", "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00002-of-00033.bin", "model.layers.1.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00033.bin", "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00003-of-00033.bin", "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00003-of-00033.bin", "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00003-of-00033.bin", "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00003-of-00033.bin", "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00003-of-00033.bin", "model.layers.2.mlp.down_proj.weight": "pytorch_model-00003-of-00033.bin", "model.layers.2.mlp.up_proj.weight": "pytorch_model-00003-of-00033.bin", "model.layers.2.input_layernorm.weight": "pytorch_model-00003-of-00033.bin", "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00003-of-00033.bin", "model.layers.2.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00033.bin", "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00004-of-00033.bin", "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00004-of-00033.bin", "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00004-of-00033.bin", "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00004-of-00033.bin", "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00004-of-00033.bin", "model.layers.3.mlp.down_proj.weight": "pytorch_model-00004-of-00033.bin", "model.layers.3.mlp.up_proj.weight": "pytorch_model-00004-of-00033.bin", "model.layers.3.input_layernorm.weight": "pytorch_model-00004-of-00033.bin", "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00004-of-00033.bin", "model.layers.3.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00033.bin", "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00005-of-00033.bin", "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00005-of-00033.bin", "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00005-of-00033.bin", "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00005-of-00033.bin", "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00005-of-00033.bin", "model.layers.4.mlp.down_proj.weight": "pytorch_model-00005-of-00033.bin", "model.layers.4.mlp.up_proj.weight": "pytorch_model-00005-of-00033.bin", "model.layers.4.input_layernorm.weight": "pytorch_model-00005-of-00033.bin", "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00005-of-00033.bin", "model.layers.4.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00033.bin", "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00006-of-00033.bin", "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00006-of-00033.bin", "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00006-of-00033.bin", "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00006-of-00033.bin", "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00006-of-00033.bin", "model.layers.5.mlp.down_proj.weight": "pytorch_model-00006-of-00033.bin", "model.layers.5.mlp.up_proj.weight": "pytorch_model-00006-of-00033.bin", "model.layers.5.input_layernorm.weight": "pytorch_model-00006-of-00033.bin", "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00006-of-00033.bin", "model.layers.5.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00033.bin", "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00007-of-00033.bin", "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00007-of-00033.bin", "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00007-of-00033.bin", "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00007-of-00033.bin", "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00007-of-00033.bin", "model.layers.6.mlp.down_proj.weight": "pytorch_model-00007-of-00033.bin", "model.layers.6.mlp.up_proj.weight": "pytorch_model-00007-of-00033.bin", "model.layers.6.input_layernorm.weight": "pytorch_model-00007-of-00033.bin", "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00007-of-00033.bin", "model.layers.6.self_attn.rotary_emb.inv_freq": "pytorch_model-00007-of-00033.bin", "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00008-of-00033.bin", "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00008-of-00033.bin", "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00008-of-00033.bin", "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00008-of-00033.bin", "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00008-of-00033.bin", "model.layers.7.mlp.down_proj.weight": "pytorch_model-00008-of-00033.bin", "model.layers.7.mlp.up_proj.weight": "pytorch_model-00008-of-00033.bin", "model.layers.7.input_layernorm.weight": "pytorch_model-00008-of-00033.bin", "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00008-of-00033.bin", "model.layers.7.self_attn.rotary_emb.inv_freq": "pytorch_model-00008-of-00033.bin", "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00009-of-00033.bin", "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00009-of-00033.bin", "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00009-of-00033.bin", "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00009-of-00033.bin", "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00009-of-00033.bin", "model.layers.8.mlp.down_proj.weight": "pytorch_model-00009-of-00033.bin", "model.layers.8.mlp.up_proj.weight": "pytorch_model-00009-of-00033.bin", "model.layers.8.input_layernorm.weight": "pytorch_model-00009-of-00033.bin", "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00009-of-00033.bin", "model.layers.8.self_attn.rotary_emb.inv_freq": "pytorch_model-00009-of-00033.bin", "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00010-of-00033.bin", "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00010-of-00033.bin", "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00010-of-00033.bin", "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00010-of-00033.bin", "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00010-of-00033.bin", "model.layers.9.mlp.down_proj.weight": "pytorch_model-00010-of-00033.bin", "model.layers.9.mlp.up_proj.weight": "pytorch_model-00010-of-00033.bin", "model.layers.9.input_layernorm.weight": "pytorch_model-00010-of-00033.bin", "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00010-of-00033.bin", "model.layers.9.self_attn.rotary_emb.inv_freq": "pytorch_model-00010-of-00033.bin", "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00011-of-00033.bin", "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00011-of-00033.bin", "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00011-of-00033.bin", "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00011-of-00033.bin", "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00011-of-00033.bin", "model.layers.10.mlp.down_proj.weight": "pytorch_model-00011-of-00033.bin", "model.layers.10.mlp.up_proj.weight": "pytorch_model-00011-of-00033.bin", "model.layers.10.input_layernorm.weight": "pytorch_model-00011-of-00033.bin", "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00011-of-00033.bin", "model.layers.10.self_attn.rotary_emb.inv_freq": "pytorch_model-00011-of-00033.bin", "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00012-of-00033.bin", "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00012-of-00033.bin", "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00012-of-00033.bin", "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00012-of-00033.bin", "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00012-of-00033.bin", "model.layers.11.mlp.down_proj.weight": "pytorch_model-00012-of-00033.bin", "model.layers.11.mlp.up_proj.weight": "pytorch_model-00012-of-00033.bin", "model.layers.11.input_layernorm.weight": "pytorch_model-00012-of-00033.bin", "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00012-of-00033.bin", "model.layers.11.self_attn.rotary_emb.inv_freq": "pytorch_model-00012-of-00033.bin", "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00013-of-00033.bin", "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00013-of-00033.bin", "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00013-of-00033.bin", "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00013-of-00033.bin", "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00013-of-00033.bin", "model.layers.12.mlp.down_proj.weight": "pytorch_model-00013-of-00033.bin", "model.layers.12.mlp.up_proj.weight": "pytorch_model-00013-of-00033.bin", "model.layers.12.input_layernorm.weight": "pytorch_model-00013-of-00033.bin", "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00013-of-00033.bin", "model.layers.12.self_attn.rotary_emb.inv_freq": "pytorch_model-00013-of-00033.bin", "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00014-of-00033.bin", "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00014-of-00033.bin", "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00014-of-00033.bin", "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00014-of-00033.bin", "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00014-of-00033.bin", "model.layers.13.mlp.down_proj.weight": "pytorch_model-00014-of-00033.bin", "model.layers.13.mlp.up_proj.weight": "pytorch_model-00014-of-00033.bin", "model.layers.13.input_layernorm.weight": "pytorch_model-00014-of-00033.bin", "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00014-of-00033.bin", "model.layers.13.self_attn.rotary_emb.inv_freq": "pytorch_model-00014-of-00033.bin", "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00015-of-00033.bin", "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00015-of-00033.bin", "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00015-of-00033.bin", "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00015-of-00033.bin", "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00015-of-00033.bin", "model.layers.14.mlp.down_proj.weight": "pytorch_model-00015-of-00033.bin", "model.layers.14.mlp.up_proj.weight": "pytorch_model-00015-of-00033.bin", "model.layers.14.input_layernorm.weight": "pytorch_model-00015-of-00033.bin", "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00015-of-00033.bin", "model.layers.14.self_attn.rotary_emb.inv_freq": "pytorch_model-00015-of-00033.bin", "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00016-of-00033.bin", "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00016-of-00033.bin", "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00016-of-00033.bin", "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00016-of-00033.bin", "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00016-of-00033.bin", "model.layers.15.mlp.down_proj.weight": "pytorch_model-00016-of-00033.bin", "model.layers.15.mlp.up_proj.weight": "pytorch_model-00016-of-00033.bin", "model.layers.15.input_layernorm.weight": "pytorch_model-00016-of-00033.bin", "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00016-of-00033.bin", "model.layers.15.self_attn.rotary_emb.inv_freq": "pytorch_model-00016-of-00033.bin", "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00017-of-00033.bin", "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00017-of-00033.bin", "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00017-of-00033.bin", "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00017-of-00033.bin", "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00017-of-00033.bin", "model.layers.16.mlp.down_proj.weight": "pytorch_model-00017-of-00033.bin", "model.layers.16.mlp.up_proj.weight": "pytorch_model-00017-of-00033.bin", "model.layers.16.input_layernorm.weight": "pytorch_model-00017-of-00033.bin", "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00017-of-00033.bin", "model.layers.16.self_attn.rotary_emb.inv_freq": "pytorch_model-00017-of-00033.bin", "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00018-of-00033.bin", "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00018-of-00033.bin", "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00018-of-00033.bin", "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00018-of-00033.bin", "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00018-of-00033.bin", "model.layers.17.mlp.down_proj.weight": "pytorch_model-00018-of-00033.bin", "model.layers.17.mlp.up_proj.weight": "pytorch_model-00018-of-00033.bin", "model.layers.17.input_layernorm.weight": "pytorch_model-00018-of-00033.bin", "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00018-of-00033.bin", "model.layers.17.self_attn.rotary_emb.inv_freq": "pytorch_model-00018-of-00033.bin", "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00019-of-00033.bin", "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00019-of-00033.bin", "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00019-of-00033.bin", "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00019-of-00033.bin", "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00019-of-00033.bin", "model.layers.18.mlp.down_proj.weight": "pytorch_model-00019-of-00033.bin", "model.layers.18.mlp.up_proj.weight": "pytorch_model-00019-of-00033.bin", "model.layers.18.input_layernorm.weight": "pytorch_model-00019-of-00033.bin", "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00019-of-00033.bin", "model.layers.18.self_attn.rotary_emb.inv_freq": "pytorch_model-00019-of-00033.bin", "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00020-of-00033.bin", "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00020-of-00033.bin", "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00020-of-00033.bin", "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00020-of-00033.bin", "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00020-of-00033.bin", "model.layers.19.mlp.down_proj.weight": "pytorch_model-00020-of-00033.bin", "model.layers.19.mlp.up_proj.weight": "pytorch_model-00020-of-00033.bin", "model.layers.19.input_layernorm.weight": "pytorch_model-00020-of-00033.bin", "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00020-of-00033.bin", "model.layers.19.self_attn.rotary_emb.inv_freq": "pytorch_model-00020-of-00033.bin", "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00021-of-00033.bin", "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00021-of-00033.bin", "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00021-of-00033.bin", "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00021-of-00033.bin", "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00021-of-00033.bin", "model.layers.20.mlp.down_proj.weight": "pytorch_model-00021-of-00033.bin", "model.layers.20.mlp.up_proj.weight": "pytorch_model-00021-of-00033.bin", "model.layers.20.input_layernorm.weight": "pytorch_model-00021-of-00033.bin", "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00021-of-00033.bin", "model.layers.20.self_attn.rotary_emb.inv_freq": "pytorch_model-00021-of-00033.bin", "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00022-of-00033.bin", "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00022-of-00033.bin", "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00022-of-00033.bin", "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00022-of-00033.bin", "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00022-of-00033.bin", "model.layers.21.mlp.down_proj.weight": "pytorch_model-00022-of-00033.bin", "model.layers.21.mlp.up_proj.weight": "pytorch_model-00022-of-00033.bin", "model.layers.21.input_layernorm.weight": "pytorch_model-00022-of-00033.bin", "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00022-of-00033.bin", "model.layers.21.self_attn.rotary_emb.inv_freq": "pytorch_model-00022-of-00033.bin", "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00023-of-00033.bin", "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00023-of-00033.bin", "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00023-of-00033.bin", "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00023-of-00033.bin", "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00023-of-00033.bin", "model.layers.22.mlp.down_proj.weight": "pytorch_model-00023-of-00033.bin", "model.layers.22.mlp.up_proj.weight": "pytorch_model-00023-of-00033.bin", "model.layers.22.input_layernorm.weight": "pytorch_model-00023-of-00033.bin", "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00023-of-00033.bin", "model.layers.22.self_attn.rotary_emb.inv_freq": "pytorch_model-00023-of-00033.bin", "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00024-of-00033.bin", "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00024-of-00033.bin", "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00024-of-00033.bin", "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00024-of-00033.bin", "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00024-of-00033.bin", "model.layers.23.mlp.down_proj.weight": "pytorch_model-00024-of-00033.bin", "model.layers.23.mlp.up_proj.weight": "pytorch_model-00024-of-00033.bin", "model.layers.23.input_layernorm.weight": "pytorch_model-00024-of-00033.bin", "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00024-of-00033.bin", "model.layers.23.self_attn.rotary_emb.inv_freq": "pytorch_model-00024-of-00033.bin", "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00025-of-00033.bin", "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00025-of-00033.bin", "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00025-of-00033.bin", "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00025-of-00033.bin", "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00025-of-00033.bin", "model.layers.24.mlp.down_proj.weight": "pytorch_model-00025-of-00033.bin", "model.layers.24.mlp.up_proj.weight": "pytorch_model-00025-of-00033.bin", "model.layers.24.input_layernorm.weight": "pytorch_model-00025-of-00033.bin", "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00025-of-00033.bin", "model.layers.24.self_attn.rotary_emb.inv_freq": "pytorch_model-00025-of-00033.bin", "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00026-of-00033.bin", "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00026-of-00033.bin", "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00026-of-00033.bin", "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00026-of-00033.bin", "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00026-of-00033.bin", "model.layers.25.mlp.down_proj.weight": "pytorch_model-00026-of-00033.bin", "model.layers.25.mlp.up_proj.weight": "pytorch_model-00026-of-00033.bin", "model.layers.25.input_layernorm.weight": "pytorch_model-00026-of-00033.bin", "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00026-of-00033.bin", "model.layers.25.self_attn.rotary_emb.inv_freq": "pytorch_model-00026-of-00033.bin", "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00027-of-00033.bin", "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00027-of-00033.bin", "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00027-of-00033.bin", "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00027-of-00033.bin", "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00027-of-00033.bin", "model.layers.26.mlp.down_proj.weight": "pytorch_model-00027-of-00033.bin", "model.layers.26.mlp.up_proj.weight": "pytorch_model-00027-of-00033.bin", "model.layers.26.input_layernorm.weight": "pytorch_model-00027-of-00033.bin", "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00027-of-00033.bin", "model.layers.26.self_attn.rotary_emb.inv_freq": "pytorch_model-00027-of-00033.bin", "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00028-of-00033.bin", "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00028-of-00033.bin", "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00028-of-00033.bin", "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00028-of-00033.bin", "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00028-of-00033.bin", "model.layers.27.mlp.down_proj.weight": "pytorch_model-00028-of-00033.bin", "model.layers.27.mlp.up_proj.weight": "pytorch_model-00028-of-00033.bin", "model.layers.27.input_layernorm.weight": "pytorch_model-00028-of-00033.bin", "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00028-of-00033.bin", "model.layers.27.self_attn.rotary_emb.inv_freq": "pytorch_model-00028-of-00033.bin", "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00029-of-00033.bin", "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00029-of-00033.bin", "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00029-of-00033.bin", "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00029-of-00033.bin", "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00029-of-00033.bin", "model.layers.28.mlp.down_proj.weight": "pytorch_model-00029-of-00033.bin", "model.layers.28.mlp.up_proj.weight": "pytorch_model-00029-of-00033.bin", "model.layers.28.input_layernorm.weight": "pytorch_model-00029-of-00033.bin", "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00029-of-00033.bin", "model.layers.28.self_attn.rotary_emb.inv_freq": "pytorch_model-00029-of-00033.bin", "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00030-of-00033.bin", "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00030-of-00033.bin", "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00030-of-00033.bin", "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00030-of-00033.bin", "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00030-of-00033.bin", "model.layers.29.mlp.down_proj.weight": "pytorch_model-00030-of-00033.bin", "model.layers.29.mlp.up_proj.weight": "pytorch_model-00030-of-00033.bin", "model.layers.29.input_layernorm.weight": "pytorch_model-00030-of-00033.bin", "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00030-of-00033.bin", "model.layers.29.self_attn.rotary_emb.inv_freq": "pytorch_model-00030-of-00033.bin", "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00031-of-00033.bin", "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00031-of-00033.bin", "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00031-of-00033.bin", "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00031-of-00033.bin", "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00031-of-00033.bin", "model.layers.30.mlp.down_proj.weight": "pytorch_model-00031-of-00033.bin", "model.layers.30.mlp.up_proj.weight": "pytorch_model-00031-of-00033.bin", "model.layers.30.input_layernorm.weight": "pytorch_model-00031-of-00033.bin", "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00031-of-00033.bin", "model.layers.30.self_attn.rotary_emb.inv_freq": "pytorch_model-00031-of-00033.bin", "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00032-of-00033.bin", "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00032-of-00033.bin", "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00032-of-00033.bin", "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00032-of-00033.bin", "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00032-of-00033.bin", "model.layers.31.mlp.down_proj.weight": "pytorch_model-00032-of-00033.bin", "model.layers.31.mlp.up_proj.weight": "pytorch_model-00032-of-00033.bin", "model.layers.31.input_layernorm.weight": "pytorch_model-00032-of-00033.bin", "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00032-of-00033.bin", "model.layers.31.self_attn.rotary_emb.inv_freq": "pytorch_model-00032-of-00033.bin", "model.embed_tokens.weight": "pytorch_model-00033-of-00033.bin", "model.norm.weight": "pytorch_model-00033-of-00033.bin", "lm_head.weight": "pytorch_model-00033-of-00033.bin"}, "metadata": {"total_size": 13476835328}}

special_tokens_map.json

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

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa299a0662fc3bf7ada4d816b1cb9fdeb472e9edf6c2ffbc7f00e1b5ff5ff968
+size 499739

tokenizer_config.json

@@ -0,0 +1,8 @@
+{
+    "bos_token": "<s>",
+    "eos_token": "</s>",
+    "model_max_length": 2048,
+    "tokenizer_class": "LlamaTokenizer",
+    "unk_token": "<unk>",
+    "pad_token": "<pad>"
+}