Upload folder using huggingface_hub

README.md

@@ -0,0 +1,9 @@
+---
+library_name: peft
+---
+## Training procedure
+
+### Framework versions
+
+
+- PEFT 0.4.0

adapter_config.json

@@ -0,0 +1,26 @@
+{
+  "auto_mapping": null,
+  "base_model_name_or_path": "pretrained-models/Llama-2-70b-hf",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "o_proj",
+    "q_proj",
+    "up_proj",
+    "v_proj",
+    "down_proj",
+    "k_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e2cafd0afccf0506c88474f36d878a7cb268e335e50f7a9336d4007260ec209
+size 1284218069

checkpoint-100-adapter/adapter_config.json

@@ -0,0 +1,26 @@
+{
+  "auto_mapping": null,
+  "base_model_name_or_path": "pretrained-models/Llama-2-70b-hf",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "o_proj",
+    "q_proj",
+    "up_proj",
+    "v_proj",
+    "down_proj",
+    "k_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

checkpoint-100-adapter/adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d408b8994d226185c29438435e5278170f050e0a6d23ea80f77d3a5ad1592391
+size 1656926781

checkpoint-100/README.md

@@ -0,0 +1,21 @@
+---
+library_name: peft
+---
+## Training procedure
+
+
+The following `bitsandbytes` quantization config was used during training:
+- quant_method: bitsandbytes
+- load_in_8bit: False
+- load_in_4bit: True
+- llm_int8_threshold: 6.0
+- llm_int8_skip_modules: None
+- llm_int8_enable_fp32_cpu_offload: False
+- llm_int8_has_fp16_weight: False
+- bnb_4bit_quant_type: nf4
+- bnb_4bit_use_double_quant: True
+- bnb_4bit_compute_dtype: bfloat16
+### Framework versions
+
+
+- PEFT 0.5.0

checkpoint-100/added_tokens.json

@@ -0,0 +1,6 @@
+{
+  "</s>": 2,
+  "<pad>": 32000,
+  "<s>": 1,
+  "<unk>": 0
+}

checkpoint-100/config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "pretrained-models/Llama-2-70b-hf/",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 8192,
+  "initializer_range": 0.02,
+  "intermediate_size": 28672,
+  "max_position_embeddings": 2048,
+  "model_type": "llama",
+  "num_attention_heads": 64,
+  "num_hidden_layers": 80,
+  "num_key_value_heads": 8,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.34.0",
+  "use_cache": true,
+  "vocab_size": 32000
+}

checkpoint-100/pytorch_model-00001-of-00029.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:20b61cc0e10a30c3e1e9a48b1b0d1bdad48b6c976ada77c37fdb19413a58944a
+size 9437323399

checkpoint-100/pytorch_model-00002-of-00029.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1461ecc80c5cce5d575cde37c8b4fe8c47c64931bff9def1128d4f71d9ef4e8b
+size 9328337655

checkpoint-100/pytorch_model-00003-of-00029.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7c19c745ee070ca5c871f3a12f39bb6cf03522697c2389b7ea910c1719c9e0e
+size 9999426295

checkpoint-100/pytorch_model-00004-of-00029.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e03629e0b86e6c4f4c2dd1ea51b15e763b794d553e9e1f0a6bed09ea4fdc337d
+size 9932316819

checkpoint-100/pytorch_model-00005-of-00029.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e137bfcc44a57893146c9534d121c57ba4128080c1d41fac8fa0146b22665925
+size 9328271411

checkpoint-100/pytorch_model-00006-of-00029.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c74be7e352e4325f316d0af85bef6e378b291b0ccef4d2c863d7c2d089d67db
+size 9328337707

checkpoint-100/pytorch_model-00007-of-00029.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:008ac3b879398af8a2732efa46e0636cc9bc9d1674d48265999134f1d35802a7
+size 9328337655

checkpoint-100/pytorch_model-00008-of-00029.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54324cdcdfff5c07eb1f296e581066514d8df4ee1426f7322324be2623dcbb26
+size 9999426295

checkpoint-100/pytorch_model-00009-of-00029.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea4a5d0e2130bf125d8c21724a640c79602def03b98be87a06fb1971338fb416
+size 9932316819

checkpoint-100/pytorch_model-00010-of-00029.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c1b4bcc3f06c8590107484a47a675fa2e5c3128e8913d3aef08b9000aae5aa7
+size 9328271411

checkpoint-100/pytorch_model-00011-of-00029.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:73ddf271578b1480568e59c5254b37a59276cbd07e3aa0d42f3562ea6fa57f8a
+size 9328337707

checkpoint-100/pytorch_model-00012-of-00029.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f1b2ccf43fa257b7d006569770d53000075ce32ab6f4635c90f01720a2bcdeb
+size 9328337655

checkpoint-100/pytorch_model-00013-of-00029.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f280b2ec424cd7fbb1da236aff1f9f91f2a25ba0ee47f926e5c45146fcecae8c
+size 9999426295

checkpoint-100/pytorch_model-00014-of-00029.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc4fece06e530f61470db5ab20194e13eb8a80dbf5542f9ef9e5ab53a7eeebf8
+size 9932316819

checkpoint-100/pytorch_model-00015-of-00029.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4af4ed7a37c1d3151968eca76219c7a195e6ff2ce22178451fe9e1fb11c20d50
+size 9328271411

checkpoint-100/pytorch_model-00016-of-00029.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36868a955d42593277d9ccd54b1af77c1202c6c2047aee7f23dcaf48d2c7b76b
+size 9328337707

checkpoint-100/pytorch_model-00017-of-00029.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d23a7d171832c3db5a15d4ba303c51761036de607d8d9390680be0771db155b
+size 9328337655

checkpoint-100/pytorch_model-00018-of-00029.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:230f6ebf146567d4f15a3e1aab594aafeb9ea0f7a6c1aed0bc0a533903be2ee2
+size 9999426295

checkpoint-100/pytorch_model-00019-of-00029.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee42621a77731a5870840e1b73a37e1629c29f266b4e75dc7e5c8f0798486ab9
+size 9932316819

checkpoint-100/pytorch_model-00020-of-00029.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49e4e02b566100d0319d8de8dfa93d03096925b7f3ec15473e3c7cd4b6aad979
+size 9328271411

checkpoint-100/pytorch_model-00021-of-00029.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc1f42bbc7ba5d0f5bcdf90bf208d94969bf52ff24448f79d4a6d213726feb95
+size 9328337707

checkpoint-100/pytorch_model-00022-of-00029.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:378e9336f514b7ce0350393d35d51734274a33f230902ebba58029b314af7ea3
+size 9328337655

checkpoint-100/pytorch_model-00023-of-00029.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c67efa8181e2f733cd49f656ffbfd7ce725ab7cb9782f3a3697b0c29a96e401
+size 9999426295

checkpoint-100/pytorch_model-00024-of-00029.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:38bb25224f3488d419c4b61104367bb2591f28f0c6016652cf93f0a15df51b1d
+size 9932316819

checkpoint-100/pytorch_model-00025-of-00029.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b961846de1615d5ff6b1347bc3c6067879a508c1eb65f25be2319fd19fabcb06
+size 9328271411

checkpoint-100/pytorch_model-00026-of-00029.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:42eb77a87f6b0bb52b3498719472a14ecd094ab35d367d502fd035118585c9e2
+size 9328337707

checkpoint-100/pytorch_model-00027-of-00029.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61dbfa62a082b27786c1c005a94115694c9efdab0cbdf41f066789276a87d4d4
+size 9328337655

checkpoint-100/pytorch_model-00028-of-00029.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c22ac59cfe6697893c1d5d08a294f13dd81540b7d3b4812c8df6fa90f64d0ba
+size 9999426295

checkpoint-100/pytorch_model-00029-of-00029.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32bb4a562901bc7b71ce4aa74782c4270e3c62e53844ef654b78ee76c4bf83b4
+size 7558305653

checkpoint-100/pytorch_model.bin.index.json

@@ -0,0 +1,730 @@
+{
+  "metadata": {
+    "total_size": 275906592768
+  },
+  "weight_map": {
+    "lm_head.weight": "pytorch_model-00029-of-00029.bin",
+    "model.embed_tokens.weight": "pytorch_model-00001-of-00029.bin",
+    "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00029.bin",
+    "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00029.bin",
+    "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00029.bin",
+    "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00029.bin",
+    "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00029.bin",
+    "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00029.bin",
+    "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00029.bin",
+    "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00029.bin",
+    "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00029.bin",
+    "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00029.bin",
+    "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00029.bin",
+    "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00029.bin",
+    "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00029.bin",
+    "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00029.bin",
+    "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00029.bin",
+    "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00029.bin",
+    "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00029.bin",
+    "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00029.bin",
+    "model.layers.10.input_layernorm.weight": "pytorch_model-00004-of-00029.bin",
+    "model.layers.10.mlp.down_proj.weight": "pytorch_model-00004-of-00029.bin",
+    "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00004-of-00029.bin",
+    "model.layers.10.mlp.up_proj.weight": "pytorch_model-00004-of-00029.bin",
+    "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00004-of-00029.bin",
+    "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00004-of-00029.bin",
+    "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00004-of-00029.bin",
+    "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00004-of-00029.bin",
+    "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00004-of-00029.bin",
+    "model.layers.11.input_layernorm.weight": "pytorch_model-00005-of-00029.bin",
+    "model.layers.11.mlp.down_proj.weight": "pytorch_model-00005-of-00029.bin",
+    "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00005-of-00029.bin",
+    "model.layers.11.mlp.up_proj.weight": "pytorch_model-00005-of-00029.bin",
+    "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00005-of-00029.bin",
+    "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00005-of-00029.bin",
+    "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00005-of-00029.bin",
+    "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00005-of-00029.bin",
+    "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00005-of-00029.bin",
+    "model.layers.12.input_layernorm.weight": "pytorch_model-00005-of-00029.bin",
+    "model.layers.12.mlp.down_proj.weight": "pytorch_model-00005-of-00029.bin",
+    "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00005-of-00029.bin",
+    "model.layers.12.mlp.up_proj.weight": "pytorch_model-00005-of-00029.bin",
+    "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00005-of-00029.bin",
+    "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00005-of-00029.bin",
+    "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00005-of-00029.bin",
+    "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00005-of-00029.bin",
+    "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00005-of-00029.bin",
+    "model.layers.13.input_layernorm.weight": "pytorch_model-00006-of-00029.bin",
+    "model.layers.13.mlp.down_proj.weight": "pytorch_model-00006-of-00029.bin",
+    "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00005-of-00029.bin",
+    "model.layers.13.mlp.up_proj.weight": "pytorch_model-00005-of-00029.bin",
+    "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00006-of-00029.bin",
+    "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00005-of-00029.bin",
+    "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00005-of-00029.bin",
+    "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00005-of-00029.bin",
+    "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00005-of-00029.bin",
+    "model.layers.14.input_layernorm.weight": "pytorch_model-00006-of-00029.bin",
+    "model.layers.14.mlp.down_proj.weight": "pytorch_model-00006-of-00029.bin",
+    "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00006-of-00029.bin",
+    "model.layers.14.mlp.up_proj.weight": "pytorch_model-00006-of-00029.bin",
+    "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00006-of-00029.bin",
+    "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00006-of-00029.bin",
+    "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00006-of-00029.bin",
+    "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00006-of-00029.bin",
+    "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00006-of-00029.bin",
+    "model.layers.15.input_layernorm.weight": "pytorch_model-00006-of-00029.bin",
+    "model.layers.15.mlp.down_proj.weight": "pytorch_model-00006-of-00029.bin",
+    "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00006-of-00029.bin",
+    "model.layers.15.mlp.up_proj.weight": "pytorch_model-00006-of-00029.bin",
+    "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00006-of-00029.bin",
+    "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00006-of-00029.bin",
+    "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00006-of-00029.bin",
+    "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00006-of-00029.bin",
+    "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00006-of-00029.bin",
+    "model.layers.16.input_layernorm.weight": "pytorch_model-00007-of-00029.bin",
+    "model.layers.16.mlp.down_proj.weight": "pytorch_model-00007-of-00029.bin",
+    "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00006-of-00029.bin",
+    "model.layers.16.mlp.up_proj.weight": "pytorch_model-00007-of-00029.bin",
+    "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00007-of-00029.bin",
+    "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00006-of-00029.bin",
+    "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00006-of-00029.bin",
+    "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00006-of-00029.bin",
+    "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00006-of-00029.bin",
+    "model.layers.17.input_layernorm.weight": "pytorch_model-00007-of-00029.bin",
+    "model.layers.17.mlp.down_proj.weight": "pytorch_model-00007-of-00029.bin",
+    "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00007-of-00029.bin",
+    "model.layers.17.mlp.up_proj.weight": "pytorch_model-00007-of-00029.bin",
+    "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00007-of-00029.bin",
+    "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00007-of-00029.bin",
+    "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00007-of-00029.bin",
+    "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00007-of-00029.bin",
+    "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00007-of-00029.bin",
+    "model.layers.18.input_layernorm.weight": "pytorch_model-00007-of-00029.bin",
+    "model.layers.18.mlp.down_proj.weight": "pytorch_model-00007-of-00029.bin",
+    "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00007-of-00029.bin",
+    "model.layers.18.mlp.up_proj.weight": "pytorch_model-00007-of-00029.bin",
+    "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00007-of-00029.bin",
+    "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00007-of-00029.bin",
+    "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00007-of-00029.bin",
+    "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00007-of-00029.bin",
+    "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00007-of-00029.bin",
+    "model.layers.19.input_layernorm.weight": "pytorch_model-00008-of-00029.bin",
+    "model.layers.19.mlp.down_proj.weight": "pytorch_model-00008-of-00029.bin",
+    "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00008-of-00029.bin",
+    "model.layers.19.mlp.up_proj.weight": "pytorch_model-00008-of-00029.bin",
+    "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00008-of-00029.bin",
+    "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00007-of-00029.bin",
+    "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00007-of-00029.bin",
+    "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00007-of-00029.bin",
+    "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00007-of-00029.bin",
+    "model.layers.2.input_layernorm.weight": "pytorch_model-00002-of-00029.bin",
+    "model.layers.2.mlp.down_proj.weight": "pytorch_model-00002-of-00029.bin",
+    "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00029.bin",
+    "model.layers.2.mlp.up_proj.weight": "pytorch_model-00002-of-00029.bin",
+    "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00002-of-00029.bin",
+    "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00029.bin",
+    "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00029.bin",
+    "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00029.bin",
+    "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00029.bin",
+    "model.layers.20.input_layernorm.weight": "pytorch_model-00008-of-00029.bin",
+    "model.layers.20.mlp.down_proj.weight": "pytorch_model-00008-of-00029.bin",
+    "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00008-of-00029.bin",
+    "model.layers.20.mlp.up_proj.weight": "pytorch_model-00008-of-00029.bin",
+    "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00008-of-00029.bin",
+    "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00008-of-00029.bin",
+    "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00008-of-00029.bin",
+    "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00008-of-00029.bin",
+    "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00008-of-00029.bin",
+    "model.layers.21.input_layernorm.weight": "pytorch_model-00008-of-00029.bin",
+    "model.layers.21.mlp.down_proj.weight": "pytorch_model-00008-of-00029.bin",
+    "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00008-of-00029.bin",
+    "model.layers.21.mlp.up_proj.weight": "pytorch_model-00008-of-00029.bin",
+    "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00008-of-00029.bin",
+    "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00008-of-00029.bin",
+    "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00008-of-00029.bin",
+    "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00008-of-00029.bin",
+    "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00008-of-00029.bin",
+    "model.layers.22.input_layernorm.weight": "pytorch_model-00009-of-00029.bin",
+    "model.layers.22.mlp.down_proj.weight": "pytorch_model-00009-of-00029.bin",
+    "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00009-of-00029.bin",
+    "model.layers.22.mlp.up_proj.weight": "pytorch_model-00009-of-00029.bin",
+    "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00009-of-00029.bin",
+    "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00008-of-00029.bin",
+    "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00009-of-00029.bin",
+    "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00008-of-00029.bin",
+    "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00008-of-00029.bin",
+    "model.layers.23.input_layernorm.weight": "pytorch_model-00009-of-00029.bin",
+    "model.layers.23.mlp.down_proj.weight": "pytorch_model-00009-of-00029.bin",
+    "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00009-of-00029.bin",
+    "model.layers.23.mlp.up_proj.weight": "pytorch_model-00009-of-00029.bin",
+    "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00009-of-00029.bin",
+    "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00009-of-00029.bin",
+    "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00009-of-00029.bin",
+    "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00009-of-00029.bin",
+    "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00009-of-00029.bin",
+    "model.layers.24.input_layernorm.weight": "pytorch_model-00009-of-00029.bin",
+    "model.layers.24.mlp.down_proj.weight": "pytorch_model-00009-of-00029.bin",
+    "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00009-of-00029.bin",
+    "model.layers.24.mlp.up_proj.weight": "pytorch_model-00009-of-00029.bin",
+    "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00009-of-00029.bin",
+    "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00009-of-00029.bin",
+    "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00009-of-00029.bin",
+    "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00009-of-00029.bin",
+    "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00009-of-00029.bin",
+    "model.layers.25.input_layernorm.weight": "pytorch_model-00010-of-00029.bin",
+    "model.layers.25.mlp.down_proj.weight": "pytorch_model-00010-of-00029.bin",
+    "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00010-of-00029.bin",
+    "model.layers.25.mlp.up_proj.weight": "pytorch_model-00010-of-00029.bin",
+    "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00010-of-00029.bin",
+    "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00010-of-00029.bin",
+    "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00010-of-00029.bin",
+    "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00010-of-00029.bin",
+    "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00010-of-00029.bin",
+    "model.layers.26.input_layernorm.weight": "pytorch_model-00010-of-00029.bin",
+    "model.layers.26.mlp.down_proj.weight": "pytorch_model-00010-of-00029.bin",
+    "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00010-of-00029.bin",
+    "model.layers.26.mlp.up_proj.weight": "pytorch_model-00010-of-00029.bin",
+    "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00010-of-00029.bin",
+    "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00010-of-00029.bin",
+    "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00010-of-00029.bin",
+    "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00010-of-00029.bin",
+    "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00010-of-00029.bin",
+    "model.layers.27.input_layernorm.weight": "pytorch_model-00011-of-00029.bin",
+    "model.layers.27.mlp.down_proj.weight": "pytorch_model-00011-of-00029.bin",
+    "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00010-of-00029.bin",
+    "model.layers.27.mlp.up_proj.weight": "pytorch_model-00010-of-00029.bin",
+    "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00011-of-00029.bin",
+    "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00010-of-00029.bin",
+    "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00010-of-00029.bin",
+    "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00010-of-00029.bin",
+    "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00010-of-00029.bin",
+    "model.layers.28.input_layernorm.weight": "pytorch_model-00011-of-00029.bin",
+    "model.layers.28.mlp.down_proj.weight": "pytorch_model-00011-of-00029.bin",
+    "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00011-of-00029.bin",
+    "model.layers.28.mlp.up_proj.weight": "pytorch_model-00011-of-00029.bin",
+    "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00011-of-00029.bin",
+    "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00011-of-00029.bin",
+    "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00011-of-00029.bin",
+    "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00011-of-00029.bin",
+    "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00011-of-00029.bin",
+    "model.layers.29.input_layernorm.weight": "pytorch_model-00011-of-00029.bin",
+    "model.layers.29.mlp.down_proj.weight": "pytorch_model-00011-of-00029.bin",
+    "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00011-of-00029.bin",
+    "model.layers.29.mlp.up_proj.weight": "pytorch_model-00011-of-00029.bin",
+    "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00011-of-00029.bin",
+    "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00011-of-00029.bin",
+    "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00011-of-00029.bin",
+    "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00011-of-00029.bin",
+    "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00011-of-00029.bin",
+    "model.layers.3.input_layernorm.weight": "pytorch_model-00002-of-00029.bin",
+    "model.layers.3.mlp.down_proj.weight": "pytorch_model-00002-of-00029.bin",
+    "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00002-of-00029.bin",
+    "model.layers.3.mlp.up_proj.weight": "pytorch_model-00002-of-00029.bin",
+    "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00002-of-00029.bin",
+    "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00002-of-00029.bin",
+    "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00002-of-00029.bin",
+    "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00002-of-00029.bin",
+    "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00002-of-00029.bin",
+    "model.layers.30.input_layernorm.weight": "pytorch_model-00012-of-00029.bin",
+    "model.layers.30.mlp.down_proj.weight": "pytorch_model-00012-of-00029.bin",
+    "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00011-of-00029.bin",
+    "model.layers.30.mlp.up_proj.weight": "pytorch_model-00012-of-00029.bin",
+    "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00012-of-00029.bin",
+    "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00011-of-00029.bin",
+    "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00011-of-00029.bin",
+    "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00011-of-00029.bin",
+    "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00011-of-00029.bin",
+    "model.layers.31.input_layernorm.weight": "pytorch_model-00012-of-00029.bin",
+    "model.layers.31.mlp.down_proj.weight": "pytorch_model-00012-of-00029.bin",
+    "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00012-of-00029.bin",
+    "model.layers.31.mlp.up_proj.weight": "pytorch_model-00012-of-00029.bin",
+    "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00012-of-00029.bin",
+    "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00012-of-00029.bin",
+    "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00012-of-00029.bin",
+    "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00012-of-00029.bin",
+    "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00012-of-00029.bin",
+    "model.layers.32.input_layernorm.weight": "pytorch_model-00012-of-00029.bin",
+    "model.layers.32.mlp.down_proj.weight": "pytorch_model-00012-of-00029.bin",
+    "model.layers.32.mlp.gate_proj.weight": "pytorch_model-00012-of-00029.bin",
+    "model.layers.32.mlp.up_proj.weight": "pytorch_model-00012-of-00029.bin",
+    "model.layers.32.post_attention_layernorm.weight": "pytorch_model-00012-of-00029.bin",
+    "model.layers.32.self_attn.k_proj.weight": "pytorch_model-00012-of-00029.bin",
+    "model.layers.32.self_attn.o_proj.weight": "pytorch_model-00012-of-00029.bin",
+    "model.layers.32.self_attn.q_proj.weight": "pytorch_model-00012-of-00029.bin",
+    "model.layers.32.self_attn.v_proj.weight": "pytorch_model-00012-of-00029.bin",
+    "model.layers.33.input_layernorm.weight": "pytorch_model-00013-of-00029.bin",
+    "model.layers.33.mlp.down_proj.weight": "pytorch_model-00013-of-00029.bin",
+    "model.layers.33.mlp.gate_proj.weight": "pytorch_model-00013-of-00029.bin",
+    "model.layers.33.mlp.up_proj.weight": "pytorch_model-00013-of-00029.bin",
+    "model.layers.33.post_attention_layernorm.weight": "pytorch_model-00013-of-00029.bin",
+    "model.layers.33.self_attn.k_proj.weight": "pytorch_model-00012-of-00029.bin",
+    "model.layers.33.self_attn.o_proj.weight": "pytorch_model-00012-of-00029.bin",
+    "model.layers.33.self_attn.q_proj.weight": "pytorch_model-00012-of-00029.bin",
+    "model.layers.33.self_attn.v_proj.weight": "pytorch_model-00012-of-00029.bin",
+    "model.layers.34.input_layernorm.weight": "pytorch_model-00013-of-00029.bin",
+    "model.layers.34.mlp.down_proj.weight": "pytorch_model-00013-of-00029.bin",
+    "model.layers.34.mlp.gate_proj.weight": "pytorch_model-00013-of-00029.bin",
+    "model.layers.34.mlp.up_proj.weight": "pytorch_model-00013-of-00029.bin",
+    "model.layers.34.post_attention_layernorm.weight": "pytorch_model-00013-of-00029.bin",
+    "model.layers.34.self_attn.k_proj.weight": "pytorch_model-00013-of-00029.bin",
+    "model.layers.34.self_attn.o_proj.weight": "pytorch_model-00013-of-00029.bin",
+    "model.layers.34.self_attn.q_proj.weight": "pytorch_model-00013-of-00029.bin",
+    "model.layers.34.self_attn.v_proj.weight": "pytorch_model-00013-of-00029.bin",
+    "model.layers.35.input_layernorm.weight": "pytorch_model-00013-of-00029.bin",
+    "model.layers.35.mlp.down_proj.weight": "pytorch_model-00013-of-00029.bin",
+    "model.layers.35.mlp.gate_proj.weight": "pytorch_model-00013-of-00029.bin",
+    "model.layers.35.mlp.up_proj.weight": "pytorch_model-00013-of-00029.bin",
+    "model.layers.35.post_attention_layernorm.weight": "pytorch_model-00013-of-00029.bin",
+    "model.layers.35.self_attn.k_proj.weight": "pytorch_model-00013-of-00029.bin",
+    "model.layers.35.self_attn.o_proj.weight": "pytorch_model-00013-of-00029.bin",
+    "model.layers.35.self_attn.q_proj.weight": "pytorch_model-00013-of-00029.bin",
+    "model.layers.35.self_attn.v_proj.weight": "pytorch_model-00013-of-00029.bin",
+    "model.layers.36.input_layernorm.weight": "pytorch_model-00014-of-00029.bin",
+    "model.layers.36.mlp.down_proj.weight": "pytorch_model-00014-of-00029.bin",
+    "model.layers.36.mlp.gate_proj.weight": "pytorch_model-00014-of-00029.bin",
+    "model.layers.36.mlp.up_proj.weight": "pytorch_model-00014-of-00029.bin",
+    "model.layers.36.post_attention_layernorm.weight": "pytorch_model-00014-of-00029.bin",
+    "model.layers.36.self_attn.k_proj.weight": "pytorch_model-00013-of-00029.bin",
+    "model.layers.36.self_attn.o_proj.weight": "pytorch_model-00014-of-00029.bin",
+    "model.layers.36.self_attn.q_proj.weight": "pytorch_model-00013-of-00029.bin",
+    "model.layers.36.self_attn.v_proj.weight": "pytorch_model-00013-of-00029.bin",
+    "model.layers.37.input_layernorm.weight": "pytorch_model-00014-of-00029.bin",
+    "model.layers.37.mlp.down_proj.weight": "pytorch_model-00014-of-00029.bin",
+    "model.layers.37.mlp.gate_proj.weight": "pytorch_model-00014-of-00029.bin",
+    "model.layers.37.mlp.up_proj.weight": "pytorch_model-00014-of-00029.bin",
+    "model.layers.37.post_attention_layernorm.weight": "pytorch_model-00014-of-00029.bin",
+    "model.layers.37.self_attn.k_proj.weight": "pytorch_model-00014-of-00029.bin",
+    "model.layers.37.self_attn.o_proj.weight": "pytorch_model-00014-of-00029.bin",
+    "model.layers.37.self_attn.q_proj.weight": "pytorch_model-00014-of-00029.bin",
+    "model.layers.37.self_attn.v_proj.weight": "pytorch_model-00014-of-00029.bin",
+    "model.layers.38.input_layernorm.weight": "pytorch_model-00014-of-00029.bin",
+    "model.layers.38.mlp.down_proj.weight": "pytorch_model-00014-of-00029.bin",
+    "model.layers.38.mlp.gate_proj.weight": "pytorch_model-00014-of-00029.bin",
+    "model.layers.38.mlp.up_proj.weight": "pytorch_model-00014-of-00029.bin",
+    "model.layers.38.post_attention_layernorm.weight": "pytorch_model-00014-of-00029.bin",
+    "model.layers.38.self_attn.k_proj.weight": "pytorch_model-00014-of-00029.bin",
+    "model.layers.38.self_attn.o_proj.weight": "pytorch_model-00014-of-00029.bin",
+    "model.layers.38.self_attn.q_proj.weight": "pytorch_model-00014-of-00029.bin",
+    "model.layers.38.self_attn.v_proj.weight": "pytorch_model-00014-of-00029.bin",
+    "model.layers.39.input_layernorm.weight": "pytorch_model-00015-of-00029.bin",
+    "model.layers.39.mlp.down_proj.weight": "pytorch_model-00015-of-00029.bin",
+    "model.layers.39.mlp.gate_proj.weight": "pytorch_model-00015-of-00029.bin",
+    "model.layers.39.mlp.up_proj.weight": "pytorch_model-00015-of-00029.bin",
+    "model.layers.39.post_attention_layernorm.weight": "pytorch_model-00015-of-00029.bin",
+    "model.layers.39.self_attn.k_proj.weight": "pytorch_model-00015-of-00029.bin",
+    "model.layers.39.self_attn.o_proj.weight": "pytorch_model-00015-of-00029.bin",
+    "model.layers.39.self_attn.q_proj.weight": "pytorch_model-00015-of-00029.bin",
+    "model.layers.39.self_attn.v_proj.weight": "pytorch_model-00015-of-00029.bin",
+    "model.layers.4.input_layernorm.weight": "pytorch_model-00002-of-00029.bin",
+    "model.layers.4.mlp.down_proj.weight": "pytorch_model-00002-of-00029.bin",
+    "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00002-of-00029.bin",
+    "model.layers.4.mlp.up_proj.weight": "pytorch_model-00002-of-00029.bin",
+    "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00002-of-00029.bin",
+    "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00002-of-00029.bin",
+    "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00002-of-00029.bin",
+    "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00002-of-00029.bin",
+    "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00002-of-00029.bin",
+    "model.layers.40.input_layernorm.weight": "pytorch_model-00015-of-00029.bin",
+    "model.layers.40.mlp.down_proj.weight": "pytorch_model-00015-of-00029.bin",
+    "model.layers.40.mlp.gate_proj.weight": "pytorch_model-00015-of-00029.bin",
+    "model.layers.40.mlp.up_proj.weight": "pytorch_model-00015-of-00029.bin",
+    "model.layers.40.post_attention_layernorm.weight": "pytorch_model-00015-of-00029.bin",
+    "model.layers.40.self_attn.k_proj.weight": "pytorch_model-00015-of-00029.bin",
+    "model.layers.40.self_attn.o_proj.weight": "pytorch_model-00015-of-00029.bin",
+    "model.layers.40.self_attn.q_proj.weight": "pytorch_model-00015-of-00029.bin",
+    "model.layers.40.self_attn.v_proj.weight": "pytorch_model-00015-of-00029.bin",
+    "model.layers.41.input_layernorm.weight": "pytorch_model-00016-of-00029.bin",
+    "model.layers.41.mlp.down_proj.weight": "pytorch_model-00016-of-00029.bin",
+    "model.layers.41.mlp.gate_proj.weight": "pytorch_model-00015-of-00029.bin",
+    "model.layers.41.mlp.up_proj.weight": "pytorch_model-00015-of-00029.bin",
+    "model.layers.41.post_attention_layernorm.weight": "pytorch_model-00016-of-00029.bin",
+    "model.layers.41.self_attn.k_proj.weight": "pytorch_model-00015-of-00029.bin",
+    "model.layers.41.self_attn.o_proj.weight": "pytorch_model-00015-of-00029.bin",
+    "model.layers.41.self_attn.q_proj.weight": "pytorch_model-00015-of-00029.bin",
+    "model.layers.41.self_attn.v_proj.weight": "pytorch_model-00015-of-00029.bin",
+    "model.layers.42.input_layernorm.weight": "pytorch_model-00016-of-00029.bin",
+    "model.layers.42.mlp.down_proj.weight": "pytorch_model-00016-of-00029.bin",
+    "model.layers.42.mlp.gate_proj.weight": "pytorch_model-00016-of-00029.bin",
+    "model.layers.42.mlp.up_proj.weight": "pytorch_model-00016-of-00029.bin",
+    "model.layers.42.post_attention_layernorm.weight": "pytorch_model-00016-of-00029.bin",
+    "model.layers.42.self_attn.k_proj.weight": "pytorch_model-00016-of-00029.bin",
+    "model.layers.42.self_attn.o_proj.weight": "pytorch_model-00016-of-00029.bin",
+    "model.layers.42.self_attn.q_proj.weight": "pytorch_model-00016-of-00029.bin",
+    "model.layers.42.self_attn.v_proj.weight": "pytorch_model-00016-of-00029.bin",
+    "model.layers.43.input_layernorm.weight": "pytorch_model-00016-of-00029.bin",
+    "model.layers.43.mlp.down_proj.weight": "pytorch_model-00016-of-00029.bin",
+    "model.layers.43.mlp.gate_proj.weight": "pytorch_model-00016-of-00029.bin",
+    "model.layers.43.mlp.up_proj.weight": "pytorch_model-00016-of-00029.bin",
+    "model.layers.43.post_attention_layernorm.weight": "pytorch_model-00016-of-00029.bin",
+    "model.layers.43.self_attn.k_proj.weight": "pytorch_model-00016-of-00029.bin",
+    "model.layers.43.self_attn.o_proj.weight": "pytorch_model-00016-of-00029.bin",
+    "model.layers.43.self_attn.q_proj.weight": "pytorch_model-00016-of-00029.bin",
+    "model.layers.43.self_attn.v_proj.weight": "pytorch_model-00016-of-00029.bin",
+    "model.layers.44.input_layernorm.weight": "pytorch_model-00017-of-00029.bin",
+    "model.layers.44.mlp.down_proj.weight": "pytorch_model-00017-of-00029.bin",
+    "model.layers.44.mlp.gate_proj.weight": "pytorch_model-00016-of-00029.bin",
+    "model.layers.44.mlp.up_proj.weight": "pytorch_model-00017-of-00029.bin",
+    "model.layers.44.post_attention_layernorm.weight": "pytorch_model-00017-of-00029.bin",
+    "model.layers.44.self_attn.k_proj.weight": "pytorch_model-00016-of-00029.bin",
+    "model.layers.44.self_attn.o_proj.weight": "pytorch_model-00016-of-00029.bin",
+    "model.layers.44.self_attn.q_proj.weight": "pytorch_model-00016-of-00029.bin",
+    "model.layers.44.self_attn.v_proj.weight": "pytorch_model-00016-of-00029.bin",
+    "model.layers.45.input_layernorm.weight": "pytorch_model-00017-of-00029.bin",
+    "model.layers.45.mlp.down_proj.weight": "pytorch_model-00017-of-00029.bin",
+    "model.layers.45.mlp.gate_proj.weight": "pytorch_model-00017-of-00029.bin",
+    "model.layers.45.mlp.up_proj.weight": "pytorch_model-00017-of-00029.bin",
+    "model.layers.45.post_attention_layernorm.weight": "pytorch_model-00017-of-00029.bin",
+    "model.layers.45.self_attn.k_proj.weight": "pytorch_model-00017-of-00029.bin",
+    "model.layers.45.self_attn.o_proj.weight": "pytorch_model-00017-of-00029.bin",
+    "model.layers.45.self_attn.q_proj.weight": "pytorch_model-00017-of-00029.bin",
+    "model.layers.45.self_attn.v_proj.weight": "pytorch_model-00017-of-00029.bin",
+    "model.layers.46.input_layernorm.weight": "pytorch_model-00017-of-00029.bin",
+    "model.layers.46.mlp.down_proj.weight": "pytorch_model-00017-of-00029.bin",
+    "model.layers.46.mlp.gate_proj.weight": "pytorch_model-00017-of-00029.bin",
+    "model.layers.46.mlp.up_proj.weight": "pytorch_model-00017-of-00029.bin",
+    "model.layers.46.post_attention_layernorm.weight": "pytorch_model-00017-of-00029.bin",
+    "model.layers.46.self_attn.k_proj.weight": "pytorch_model-00017-of-00029.bin",
+    "model.layers.46.self_attn.o_proj.weight": "pytorch_model-00017-of-00029.bin",
+    "model.layers.46.self_attn.q_proj.weight": "pytorch_model-00017-of-00029.bin",
+    "model.layers.46.self_attn.v_proj.weight": "pytorch_model-00017-of-00029.bin",
+    "model.layers.47.input_layernorm.weight": "pytorch_model-00018-of-00029.bin",
+    "model.layers.47.mlp.down_proj.weight": "pytorch_model-00018-of-00029.bin",
+    "model.layers.47.mlp.gate_proj.weight": "pytorch_model-00018-of-00029.bin",
+    "model.layers.47.mlp.up_proj.weight": "pytorch_model-00018-of-00029.bin",
+    "model.layers.47.post_attention_layernorm.weight": "pytorch_model-00018-of-00029.bin",
+    "model.layers.47.self_attn.k_proj.weight": "pytorch_model-00017-of-00029.bin",
+    "model.layers.47.self_attn.o_proj.weight": "pytorch_model-00017-of-00029.bin",
+    "model.layers.47.self_attn.q_proj.weight": "pytorch_model-00017-of-00029.bin",
+    "model.layers.47.self_attn.v_proj.weight": "pytorch_model-00017-of-00029.bin",
+    "model.layers.48.input_layernorm.weight": "pytorch_model-00018-of-00029.bin",
+    "model.layers.48.mlp.down_proj.weight": "pytorch_model-00018-of-00029.bin",
+    "model.layers.48.mlp.gate_proj.weight": "pytorch_model-00018-of-00029.bin",
+    "model.layers.48.mlp.up_proj.weight": "pytorch_model-00018-of-00029.bin",
+    "model.layers.48.post_attention_layernorm.weight": "pytorch_model-00018-of-00029.bin",
+    "model.layers.48.self_attn.k_proj.weight": "pytorch_model-00018-of-00029.bin",
+    "model.layers.48.self_attn.o_proj.weight": "pytorch_model-00018-of-00029.bin",
+    "model.layers.48.self_attn.q_proj.weight": "pytorch_model-00018-of-00029.bin",
+    "model.layers.48.self_attn.v_proj.weight": "pytorch_model-00018-of-00029.bin",
+    "model.layers.49.input_layernorm.weight": "pytorch_model-00018-of-00029.bin",
+    "model.layers.49.mlp.down_proj.weight": "pytorch_model-00018-of-00029.bin",
+    "model.layers.49.mlp.gate_proj.weight": "pytorch_model-00018-of-00029.bin",
+    "model.layers.49.mlp.up_proj.weight": "pytorch_model-00018-of-00029.bin",
+    "model.layers.49.post_attention_layernorm.weight": "pytorch_model-00018-of-00029.bin",
+    "model.layers.49.self_attn.k_proj.weight": "pytorch_model-00018-of-00029.bin",
+    "model.layers.49.self_attn.o_proj.weight": "pytorch_model-00018-of-00029.bin",
+    "model.layers.49.self_attn.q_proj.weight": "pytorch_model-00018-of-00029.bin",
+    "model.layers.49.self_attn.v_proj.weight": "pytorch_model-00018-of-00029.bin",
+    "model.layers.5.input_layernorm.weight": "pytorch_model-00003-of-00029.bin",
+    "model.layers.5.mlp.down_proj.weight": "pytorch_model-00003-of-00029.bin",
+    "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00003-of-00029.bin",
+    "model.layers.5.mlp.up_proj.weight": "pytorch_model-00003-of-00029.bin",
+    "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00003-of-00029.bin",
+    "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00002-of-00029.bin",
+    "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00002-of-00029.bin",
+    "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00002-of-00029.bin",
+    "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00002-of-00029.bin",
+    "model.layers.50.input_layernorm.weight": "pytorch_model-00019-of-00029.bin",
+    "model.layers.50.mlp.down_proj.weight": "pytorch_model-00019-of-00029.bin",
+    "model.layers.50.mlp.gate_proj.weight": "pytorch_model-00019-of-00029.bin",
+    "model.layers.50.mlp.up_proj.weight": "pytorch_model-00019-of-00029.bin",
+    "model.layers.50.post_attention_layernorm.weight": "pytorch_model-00019-of-00029.bin",
+    "model.layers.50.self_attn.k_proj.weight": "pytorch_model-00018-of-00029.bin",
+    "model.layers.50.self_attn.o_proj.weight": "pytorch_model-00019-of-00029.bin",
+    "model.layers.50.self_attn.q_proj.weight": "pytorch_model-00018-of-00029.bin",
+    "model.layers.50.self_attn.v_proj.weight": "pytorch_model-00018-of-00029.bin",
+    "model.layers.51.input_layernorm.weight": "pytorch_model-00019-of-00029.bin",
+    "model.layers.51.mlp.down_proj.weight": "pytorch_model-00019-of-00029.bin",
+    "model.layers.51.mlp.gate_proj.weight": "pytorch_model-00019-of-00029.bin",
+    "model.layers.51.mlp.up_proj.weight": "pytorch_model-00019-of-00029.bin",
+    "model.layers.51.post_attention_layernorm.weight": "pytorch_model-00019-of-00029.bin",
+    "model.layers.51.self_attn.k_proj.weight": "pytorch_model-00019-of-00029.bin",
+    "model.layers.51.self_attn.o_proj.weight": "pytorch_model-00019-of-00029.bin",
+    "model.layers.51.self_attn.q_proj.weight": "pytorch_model-00019-of-00029.bin",
+    "model.layers.51.self_attn.v_proj.weight": "pytorch_model-00019-of-00029.bin",
+    "model.layers.52.input_layernorm.weight": "pytorch_model-00019-of-00029.bin",
+    "model.layers.52.mlp.down_proj.weight": "pytorch_model-00019-of-00029.bin",
+    "model.layers.52.mlp.gate_proj.weight": "pytorch_model-00019-of-00029.bin",
+    "model.layers.52.mlp.up_proj.weight": "pytorch_model-00019-of-00029.bin",
+    "model.layers.52.post_attention_layernorm.weight": "pytorch_model-00019-of-00029.bin",
+    "model.layers.52.self_attn.k_proj.weight": "pytorch_model-00019-of-00029.bin",
+    "model.layers.52.self_attn.o_proj.weight": "pytorch_model-00019-of-00029.bin",
+    "model.layers.52.self_attn.q_proj.weight": "pytorch_model-00019-of-00029.bin",
+    "model.layers.52.self_attn.v_proj.weight": "pytorch_model-00019-of-00029.bin",
+    "model.layers.53.input_layernorm.weight": "pytorch_model-00020-of-00029.bin",
+    "model.layers.53.mlp.down_proj.weight": "pytorch_model-00020-of-00029.bin",
+    "model.layers.53.mlp.gate_proj.weight": "pytorch_model-00020-of-00029.bin",
+    "model.layers.53.mlp.up_proj.weight": "pytorch_model-00020-of-00029.bin",
+    "model.layers.53.post_attention_layernorm.weight": "pytorch_model-00020-of-00029.bin",
+    "model.layers.53.self_attn.k_proj.weight": "pytorch_model-00020-of-00029.bin",
+    "model.layers.53.self_attn.o_proj.weight": "pytorch_model-00020-of-00029.bin",
+    "model.layers.53.self_attn.q_proj.weight": "pytorch_model-00020-of-00029.bin",
+    "model.layers.53.self_attn.v_proj.weight": "pytorch_model-00020-of-00029.bin",
+    "model.layers.54.input_layernorm.weight": "pytorch_model-00020-of-00029.bin",
+    "model.layers.54.mlp.down_proj.weight": "pytorch_model-00020-of-00029.bin",
+    "model.layers.54.mlp.gate_proj.weight": "pytorch_model-00020-of-00029.bin",
+    "model.layers.54.mlp.up_proj.weight": "pytorch_model-00020-of-00029.bin",
+    "model.layers.54.post_attention_layernorm.weight": "pytorch_model-00020-of-00029.bin",
+    "model.layers.54.self_attn.k_proj.weight": "pytorch_model-00020-of-00029.bin",
+    "model.layers.54.self_attn.o_proj.weight": "pytorch_model-00020-of-00029.bin",
+    "model.layers.54.self_attn.q_proj.weight": "pytorch_model-00020-of-00029.bin",
+    "model.layers.54.self_attn.v_proj.weight": "pytorch_model-00020-of-00029.bin",
+    "model.layers.55.input_layernorm.weight": "pytorch_model-00021-of-00029.bin",
+    "model.layers.55.mlp.down_proj.weight": "pytorch_model-00021-of-00029.bin",
+    "model.layers.55.mlp.gate_proj.weight": "pytorch_model-00020-of-00029.bin",
+    "model.layers.55.mlp.up_proj.weight": "pytorch_model-00020-of-00029.bin",
+    "model.layers.55.post_attention_layernorm.weight": "pytorch_model-00021-of-00029.bin",
+    "model.layers.55.self_attn.k_proj.weight": "pytorch_model-00020-of-00029.bin",
+    "model.layers.55.self_attn.o_proj.weight": "pytorch_model-00020-of-00029.bin",
+    "model.layers.55.self_attn.q_proj.weight": "pytorch_model-00020-of-00029.bin",
+    "model.layers.55.self_attn.v_proj.weight": "pytorch_model-00020-of-00029.bin",
+    "model.layers.56.input_layernorm.weight": "pytorch_model-00021-of-00029.bin",
+    "model.layers.56.mlp.down_proj.weight": "pytorch_model-00021-of-00029.bin",
+    "model.layers.56.mlp.gate_proj.weight": "pytorch_model-00021-of-00029.bin",
+    "model.layers.56.mlp.up_proj.weight": "pytorch_model-00021-of-00029.bin",
+    "model.layers.56.post_attention_layernorm.weight": "pytorch_model-00021-of-00029.bin",
+    "model.layers.56.self_attn.k_proj.weight": "pytorch_model-00021-of-00029.bin",
+    "model.layers.56.self_attn.o_proj.weight": "pytorch_model-00021-of-00029.bin",
+    "model.layers.56.self_attn.q_proj.weight": "pytorch_model-00021-of-00029.bin",
+    "model.layers.56.self_attn.v_proj.weight": "pytorch_model-00021-of-00029.bin",
+    "model.layers.57.input_layernorm.weight": "pytorch_model-00021-of-00029.bin",
+    "model.layers.57.mlp.down_proj.weight": "pytorch_model-00021-of-00029.bin",
+    "model.layers.57.mlp.gate_proj.weight": "pytorch_model-00021-of-00029.bin",
+    "model.layers.57.mlp.up_proj.weight": "pytorch_model-00021-of-00029.bin",
+    "model.layers.57.post_attention_layernorm.weight": "pytorch_model-00021-of-00029.bin",
+    "model.layers.57.self_attn.k_proj.weight": "pytorch_model-00021-of-00029.bin",
+    "model.layers.57.self_attn.o_proj.weight": "pytorch_model-00021-of-00029.bin",
+    "model.layers.57.self_attn.q_proj.weight": "pytorch_model-00021-of-00029.bin",
+    "model.layers.57.self_attn.v_proj.weight": "pytorch_model-00021-of-00029.bin",
+    "model.layers.58.input_layernorm.weight": "pytorch_model-00022-of-00029.bin",
+    "model.layers.58.mlp.down_proj.weight": "pytorch_model-00022-of-00029.bin",
+    "model.layers.58.mlp.gate_proj.weight": "pytorch_model-00021-of-00029.bin",
+    "model.layers.58.mlp.up_proj.weight": "pytorch_model-00022-of-00029.bin",
+    "model.layers.58.post_attention_layernorm.weight": "pytorch_model-00022-of-00029.bin",
+    "model.layers.58.self_attn.k_proj.weight": "pytorch_model-00021-of-00029.bin",
+    "model.layers.58.self_attn.o_proj.weight": "pytorch_model-00021-of-00029.bin",
+    "model.layers.58.self_attn.q_proj.weight": "pytorch_model-00021-of-00029.bin",
+    "model.layers.58.self_attn.v_proj.weight": "pytorch_model-00021-of-00029.bin",
+    "model.layers.59.input_layernorm.weight": "pytorch_model-00022-of-00029.bin",
+    "model.layers.59.mlp.down_proj.weight": "pytorch_model-00022-of-00029.bin",
+    "model.layers.59.mlp.gate_proj.weight": "pytorch_model-00022-of-00029.bin",
+    "model.layers.59.mlp.up_proj.weight": "pytorch_model-00022-of-00029.bin",
+    "model.layers.59.post_attention_layernorm.weight": "pytorch_model-00022-of-00029.bin",
+    "model.layers.59.self_attn.k_proj.weight": "pytorch_model-00022-of-00029.bin",
+    "model.layers.59.self_attn.o_proj.weight": "pytorch_model-00022-of-00029.bin",
+    "model.layers.59.self_attn.q_proj.weight": "pytorch_model-00022-of-00029.bin",
+    "model.layers.59.self_attn.v_proj.weight": "pytorch_model-00022-of-00029.bin",
+    "model.layers.6.input_layernorm.weight": "pytorch_model-00003-of-00029.bin",
+    "model.layers.6.mlp.down_proj.weight": "pytorch_model-00003-of-00029.bin",
+    "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00003-of-00029.bin",
+    "model.layers.6.mlp.up_proj.weight": "pytorch_model-00003-of-00029.bin",
+    "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00003-of-00029.bin",
+    "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00003-of-00029.bin",
+    "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00003-of-00029.bin",
+    "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00003-of-00029.bin",
+    "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00003-of-00029.bin",
+    "model.layers.60.input_layernorm.weight": "pytorch_model-00022-of-00029.bin",
+    "model.layers.60.mlp.down_proj.weight": "pytorch_model-00022-of-00029.bin",
+    "model.layers.60.mlp.gate_proj.weight": "pytorch_model-00022-of-00029.bin",
+    "model.layers.60.mlp.up_proj.weight": "pytorch_model-00022-of-00029.bin",
+    "model.layers.60.post_attention_layernorm.weight": "pytorch_model-00022-of-00029.bin",
+    "model.layers.60.self_attn.k_proj.weight": "pytorch_model-00022-of-00029.bin",
+    "model.layers.60.self_attn.o_proj.weight": "pytorch_model-00022-of-00029.bin",
+    "model.layers.60.self_attn.q_proj.weight": "pytorch_model-00022-of-00029.bin",
+    "model.layers.60.self_attn.v_proj.weight": "pytorch_model-00022-of-00029.bin",
+    "model.layers.61.input_layernorm.weight": "pytorch_model-00023-of-00029.bin",
+    "model.layers.61.mlp.down_proj.weight": "pytorch_model-00023-of-00029.bin",
+    "model.layers.61.mlp.gate_proj.weight": "pytorch_model-00023-of-00029.bin",
+    "model.layers.61.mlp.up_proj.weight": "pytorch_model-00023-of-00029.bin",
+    "model.layers.61.post_attention_layernorm.weight": "pytorch_model-00023-of-00029.bin",
+    "model.layers.61.self_attn.k_proj.weight": "pytorch_model-00022-of-00029.bin",
+    "model.layers.61.self_attn.o_proj.weight": "pytorch_model-00022-of-00029.bin",
+    "model.layers.61.self_attn.q_proj.weight": "pytorch_model-00022-of-00029.bin",
+    "model.layers.61.self_attn.v_proj.weight": "pytorch_model-00022-of-00029.bin",
+    "model.layers.62.input_layernorm.weight": "pytorch_model-00023-of-00029.bin",
+    "model.layers.62.mlp.down_proj.weight": "pytorch_model-00023-of-00029.bin",
+    "model.layers.62.mlp.gate_proj.weight": "pytorch_model-00023-of-00029.bin",
+    "model.layers.62.mlp.up_proj.weight": "pytorch_model-00023-of-00029.bin",
+    "model.layers.62.post_attention_layernorm.weight": "pytorch_model-00023-of-00029.bin",
+    "model.layers.62.self_attn.k_proj.weight": "pytorch_model-00023-of-00029.bin",
+    "model.layers.62.self_attn.o_proj.weight": "pytorch_model-00023-of-00029.bin",
+    "model.layers.62.self_attn.q_proj.weight": "pytorch_model-00023-of-00029.bin",
+    "model.layers.62.self_attn.v_proj.weight": "pytorch_model-00023-of-00029.bin",
+    "model.layers.63.input_layernorm.weight": "pytorch_model-00023-of-00029.bin",
+    "model.layers.63.mlp.down_proj.weight": "pytorch_model-00023-of-00029.bin",
+    "model.layers.63.mlp.gate_proj.weight": "pytorch_model-00023-of-00029.bin",
+    "model.layers.63.mlp.up_proj.weight": "pytorch_model-00023-of-00029.bin",
+    "model.layers.63.post_attention_layernorm.weight": "pytorch_model-00023-of-00029.bin",
+    "model.layers.63.self_attn.k_proj.weight": "pytorch_model-00023-of-00029.bin",
+    "model.layers.63.self_attn.o_proj.weight": "pytorch_model-00023-of-00029.bin",
+    "model.layers.63.self_attn.q_proj.weight": "pytorch_model-00023-of-00029.bin",
+    "model.layers.63.self_attn.v_proj.weight": "pytorch_model-00023-of-00029.bin",
+    "model.layers.64.input_layernorm.weight": "pytorch_model-00024-of-00029.bin",
+    "model.layers.64.mlp.down_proj.weight": "pytorch_model-00024-of-00029.bin",
+    "model.layers.64.mlp.gate_proj.weight": "pytorch_model-00024-of-00029.bin",
+    "model.layers.64.mlp.up_proj.weight": "pytorch_model-00024-of-00029.bin",
+    "model.layers.64.post_attention_layernorm.weight": "pytorch_model-00024-of-00029.bin",
+    "model.layers.64.self_attn.k_proj.weight": "pytorch_model-00023-of-00029.bin",
+    "model.layers.64.self_attn.o_proj.weight": "pytorch_model-00024-of-00029.bin",
+    "model.layers.64.self_attn.q_proj.weight": "pytorch_model-00023-of-00029.bin",
+    "model.layers.64.self_attn.v_proj.weight": "pytorch_model-00023-of-00029.bin",
+    "model.layers.65.input_layernorm.weight": "pytorch_model-00024-of-00029.bin",
+    "model.layers.65.mlp.down_proj.weight": "pytorch_model-00024-of-00029.bin",
+    "model.layers.65.mlp.gate_proj.weight": "pytorch_model-00024-of-00029.bin",
+    "model.layers.65.mlp.up_proj.weight": "pytorch_model-00024-of-00029.bin",
+    "model.layers.65.post_attention_layernorm.weight": "pytorch_model-00024-of-00029.bin",
+    "model.layers.65.self_attn.k_proj.weight": "pytorch_model-00024-of-00029.bin",
+    "model.layers.65.self_attn.o_proj.weight": "pytorch_model-00024-of-00029.bin",
+    "model.layers.65.self_attn.q_proj.weight": "pytorch_model-00024-of-00029.bin",
+    "model.layers.65.self_attn.v_proj.weight": "pytorch_model-00024-of-00029.bin",
+    "model.layers.66.input_layernorm.weight": "pytorch_model-00024-of-00029.bin",
+    "model.layers.66.mlp.down_proj.weight": "pytorch_model-00024-of-00029.bin",
+    "model.layers.66.mlp.gate_proj.weight": "pytorch_model-00024-of-00029.bin",
+    "model.layers.66.mlp.up_proj.weight": "pytorch_model-00024-of-00029.bin",
+    "model.layers.66.post_attention_layernorm.weight": "pytorch_model-00024-of-00029.bin",
+    "model.layers.66.self_attn.k_proj.weight": "pytorch_model-00024-of-00029.bin",
+    "model.layers.66.self_attn.o_proj.weight": "pytorch_model-00024-of-00029.bin",
+    "model.layers.66.self_attn.q_proj.weight": "pytorch_model-00024-of-00029.bin",
+    "model.layers.66.self_attn.v_proj.weight": "pytorch_model-00024-of-00029.bin",
+    "model.layers.67.input_layernorm.weight": "pytorch_model-00025-of-00029.bin",
+    "model.layers.67.mlp.down_proj.weight": "pytorch_model-00025-of-00029.bin",
+    "model.layers.67.mlp.gate_proj.weight": "pytorch_model-00025-of-00029.bin",
+    "model.layers.67.mlp.up_proj.weight": "pytorch_model-00025-of-00029.bin",
+    "model.layers.67.post_attention_layernorm.weight": "pytorch_model-00025-of-00029.bin",
+    "model.layers.67.self_attn.k_proj.weight": "pytorch_model-00025-of-00029.bin",
+    "model.layers.67.self_attn.o_proj.weight": "pytorch_model-00025-of-00029.bin",
+    "model.layers.67.self_attn.q_proj.weight": "pytorch_model-00025-of-00029.bin",
+    "model.layers.67.self_attn.v_proj.weight": "pytorch_model-00025-of-00029.bin",
+    "model.layers.68.input_layernorm.weight": "pytorch_model-00025-of-00029.bin",
+    "model.layers.68.mlp.down_proj.weight": "pytorch_model-00025-of-00029.bin",
+    "model.layers.68.mlp.gate_proj.weight": "pytorch_model-00025-of-00029.bin",
+    "model.layers.68.mlp.up_proj.weight": "pytorch_model-00025-of-00029.bin",
+    "model.layers.68.post_attention_layernorm.weight": "pytorch_model-00025-of-00029.bin",
+    "model.layers.68.self_attn.k_proj.weight": "pytorch_model-00025-of-00029.bin",
+    "model.layers.68.self_attn.o_proj.weight": "pytorch_model-00025-of-00029.bin",
+    "model.layers.68.self_attn.q_proj.weight": "pytorch_model-00025-of-00029.bin",
+    "model.layers.68.self_attn.v_proj.weight": "pytorch_model-00025-of-00029.bin",
+    "model.layers.69.input_layernorm.weight": "pytorch_model-00026-of-00029.bin",
+    "model.layers.69.mlp.down_proj.weight": "pytorch_model-00026-of-00029.bin",
+    "model.layers.69.mlp.gate_proj.weight": "pytorch_model-00025-of-00029.bin",
+    "model.layers.69.mlp.up_proj.weight": "pytorch_model-00025-of-00029.bin",
+    "model.layers.69.post_attention_layernorm.weight": "pytorch_model-00026-of-00029.bin",
+    "model.layers.69.self_attn.k_proj.weight": "pytorch_model-00025-of-00029.bin",
+    "model.layers.69.self_attn.o_proj.weight": "pytorch_model-00025-of-00029.bin",
+    "model.layers.69.self_attn.q_proj.weight": "pytorch_model-00025-of-00029.bin",
+    "model.layers.69.self_attn.v_proj.weight": "pytorch_model-00025-of-00029.bin",
+    "model.layers.7.input_layernorm.weight": "pytorch_model-00003-of-00029.bin",
+    "model.layers.7.mlp.down_proj.weight": "pytorch_model-00003-of-00029.bin",
+    "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00003-of-00029.bin",
+    "model.layers.7.mlp.up_proj.weight": "pytorch_model-00003-of-00029.bin",
+    "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00003-of-00029.bin",
+    "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00003-of-00029.bin",
+    "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00003-of-00029.bin",
+    "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00003-of-00029.bin",
+    "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00003-of-00029.bin",
+    "model.layers.70.input_layernorm.weight": "pytorch_model-00026-of-00029.bin",
+    "model.layers.70.mlp.down_proj.weight": "pytorch_model-00026-of-00029.bin",
+    "model.layers.70.mlp.gate_proj.weight": "pytorch_model-00026-of-00029.bin",
+    "model.layers.70.mlp.up_proj.weight": "pytorch_model-00026-of-00029.bin",
+    "model.layers.70.post_attention_layernorm.weight": "pytorch_model-00026-of-00029.bin",
+    "model.layers.70.self_attn.k_proj.weight": "pytorch_model-00026-of-00029.bin",
+    "model.layers.70.self_attn.o_proj.weight": "pytorch_model-00026-of-00029.bin",
+    "model.layers.70.self_attn.q_proj.weight": "pytorch_model-00026-of-00029.bin",
+    "model.layers.70.self_attn.v_proj.weight": "pytorch_model-00026-of-00029.bin",
+    "model.layers.71.input_layernorm.weight": "pytorch_model-00026-of-00029.bin",
+    "model.layers.71.mlp.down_proj.weight": "pytorch_model-00026-of-00029.bin",
+    "model.layers.71.mlp.gate_proj.weight": "pytorch_model-00026-of-00029.bin",
+    "model.layers.71.mlp.up_proj.weight": "pytorch_model-00026-of-00029.bin",
+    "model.layers.71.post_attention_layernorm.weight": "pytorch_model-00026-of-00029.bin",
+    "model.layers.71.self_attn.k_proj.weight": "pytorch_model-00026-of-00029.bin",
+    "model.layers.71.self_attn.o_proj.weight": "pytorch_model-00026-of-00029.bin",
+    "model.layers.71.self_attn.q_proj.weight": "pytorch_model-00026-of-00029.bin",
+    "model.layers.71.self_attn.v_proj.weight": "pytorch_model-00026-of-00029.bin",
+    "model.layers.72.input_layernorm.weight": "pytorch_model-00027-of-00029.bin",
+    "model.layers.72.mlp.down_proj.weight": "pytorch_model-00027-of-00029.bin",
+    "model.layers.72.mlp.gate_proj.weight": "pytorch_model-00026-of-00029.bin",
+    "model.layers.72.mlp.up_proj.weight": "pytorch_model-00027-of-00029.bin",
+    "model.layers.72.post_attention_layernorm.weight": "pytorch_model-00027-of-00029.bin",
+    "model.layers.72.self_attn.k_proj.weight": "pytorch_model-00026-of-00029.bin",
+    "model.layers.72.self_attn.o_proj.weight": "pytorch_model-00026-of-00029.bin",
+    "model.layers.72.self_attn.q_proj.weight": "pytorch_model-00026-of-00029.bin",
+    "model.layers.72.self_attn.v_proj.weight": "pytorch_model-00026-of-00029.bin",
+    "model.layers.73.input_layernorm.weight": "pytorch_model-00027-of-00029.bin",
+    "model.layers.73.mlp.down_proj.weight": "pytorch_model-00027-of-00029.bin",
+    "model.layers.73.mlp.gate_proj.weight": "pytorch_model-00027-of-00029.bin",
+    "model.layers.73.mlp.up_proj.weight": "pytorch_model-00027-of-00029.bin",
+    "model.layers.73.post_attention_layernorm.weight": "pytorch_model-00027-of-00029.bin",
+    "model.layers.73.self_attn.k_proj.weight": "pytorch_model-00027-of-00029.bin",
+    "model.layers.73.self_attn.o_proj.weight": "pytorch_model-00027-of-00029.bin",
+    "model.layers.73.self_attn.q_proj.weight": "pytorch_model-00027-of-00029.bin",
+    "model.layers.73.self_attn.v_proj.weight": "pytorch_model-00027-of-00029.bin",
+    "model.layers.74.input_layernorm.weight": "pytorch_model-00027-of-00029.bin",
+    "model.layers.74.mlp.down_proj.weight": "pytorch_model-00027-of-00029.bin",
+    "model.layers.74.mlp.gate_proj.weight": "pytorch_model-00027-of-00029.bin",
+    "model.layers.74.mlp.up_proj.weight": "pytorch_model-00027-of-00029.bin",
+    "model.layers.74.post_attention_layernorm.weight": "pytorch_model-00027-of-00029.bin",
+    "model.layers.74.self_attn.k_proj.weight": "pytorch_model-00027-of-00029.bin",
+    "model.layers.74.self_attn.o_proj.weight": "pytorch_model-00027-of-00029.bin",
+    "model.layers.74.self_attn.q_proj.weight": "pytorch_model-00027-of-00029.bin",
+    "model.layers.74.self_attn.v_proj.weight": "pytorch_model-00027-of-00029.bin",
+    "model.layers.75.input_layernorm.weight": "pytorch_model-00028-of-00029.bin",
+    "model.layers.75.mlp.down_proj.weight": "pytorch_model-00028-of-00029.bin",
+    "model.layers.75.mlp.gate_proj.weight": "pytorch_model-00028-of-00029.bin",
+    "model.layers.75.mlp.up_proj.weight": "pytorch_model-00028-of-00029.bin",
+    "model.layers.75.post_attention_layernorm.weight": "pytorch_model-00028-of-00029.bin",
+    "model.layers.75.self_attn.k_proj.weight": "pytorch_model-00027-of-00029.bin",
+    "model.layers.75.self_attn.o_proj.weight": "pytorch_model-00027-of-00029.bin",
+    "model.layers.75.self_attn.q_proj.weight": "pytorch_model-00027-of-00029.bin",
+    "model.layers.75.self_attn.v_proj.weight": "pytorch_model-00027-of-00029.bin",
+    "model.layers.76.input_layernorm.weight": "pytorch_model-00028-of-00029.bin",
+    "model.layers.76.mlp.down_proj.weight": "pytorch_model-00028-of-00029.bin",
+    "model.layers.76.mlp.gate_proj.weight": "pytorch_model-00028-of-00029.bin",
+    "model.layers.76.mlp.up_proj.weight": "pytorch_model-00028-of-00029.bin",
+    "model.layers.76.post_attention_layernorm.weight": "pytorch_model-00028-of-00029.bin",
+    "model.layers.76.self_attn.k_proj.weight": "pytorch_model-00028-of-00029.bin",
+    "model.layers.76.self_attn.o_proj.weight": "pytorch_model-00028-of-00029.bin",
+    "model.layers.76.self_attn.q_proj.weight": "pytorch_model-00028-of-00029.bin",
+    "model.layers.76.self_attn.v_proj.weight": "pytorch_model-00028-of-00029.bin",
+    "model.layers.77.input_layernorm.weight": "pytorch_model-00028-of-00029.bin",
+    "model.layers.77.mlp.down_proj.weight": "pytorch_model-00028-of-00029.bin",
+    "model.layers.77.mlp.gate_proj.weight": "pytorch_model-00028-of-00029.bin",
+    "model.layers.77.mlp.up_proj.weight": "pytorch_model-00028-of-00029.bin",
+    "model.layers.77.post_attention_layernorm.weight": "pytorch_model-00028-of-00029.bin",
+    "model.layers.77.self_attn.k_proj.weight": "pytorch_model-00028-of-00029.bin",
+    "model.layers.77.self_attn.o_proj.weight": "pytorch_model-00028-of-00029.bin",
+    "model.layers.77.self_attn.q_proj.weight": "pytorch_model-00028-of-00029.bin",
+    "model.layers.77.self_attn.v_proj.weight": "pytorch_model-00028-of-00029.bin",
+    "model.layers.78.input_layernorm.weight": "pytorch_model-00029-of-00029.bin",
+    "model.layers.78.mlp.down_proj.weight": "pytorch_model-00029-of-00029.bin",
+    "model.layers.78.mlp.gate_proj.weight": "pytorch_model-00029-of-00029.bin",
+    "model.layers.78.mlp.up_proj.weight": "pytorch_model-00029-of-00029.bin",
+    "model.layers.78.post_attention_layernorm.weight": "pytorch_model-00029-of-00029.bin",
+    "model.layers.78.self_attn.k_proj.weight": "pytorch_model-00028-of-00029.bin",
+    "model.layers.78.self_attn.o_proj.weight": "pytorch_model-00029-of-00029.bin",
+    "model.layers.78.self_attn.q_proj.weight": "pytorch_model-00028-of-00029.bin",
+    "model.layers.78.self_attn.v_proj.weight": "pytorch_model-00028-of-00029.bin",
+    "model.layers.79.input_layernorm.weight": "pytorch_model-00029-of-00029.bin",
+    "model.layers.79.mlp.down_proj.weight": "pytorch_model-00029-of-00029.bin",
+    "model.layers.79.mlp.gate_proj.weight": "pytorch_model-00029-of-00029.bin",
+    "model.layers.79.mlp.up_proj.weight": "pytorch_model-00029-of-00029.bin",
+    "model.layers.79.post_attention_layernorm.weight": "pytorch_model-00029-of-00029.bin",
+    "model.layers.79.self_attn.k_proj.weight": "pytorch_model-00029-of-00029.bin",
+    "model.layers.79.self_attn.o_proj.weight": "pytorch_model-00029-of-00029.bin",
+    "model.layers.79.self_attn.q_proj.weight": "pytorch_model-00029-of-00029.bin",
+    "model.layers.79.self_attn.v_proj.weight": "pytorch_model-00029-of-00029.bin",
+    "model.layers.8.input_layernorm.weight": "pytorch_model-00004-of-00029.bin",
+    "model.layers.8.mlp.down_proj.weight": "pytorch_model-00004-of-00029.bin",
+    "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00004-of-00029.bin",
+    "model.layers.8.mlp.up_proj.weight": "pytorch_model-00004-of-00029.bin",
+    "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00004-of-00029.bin",
+    "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00003-of-00029.bin",
+    "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00004-of-00029.bin",
+    "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00003-of-00029.bin",
+    "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00003-of-00029.bin",
+    "model.layers.9.input_layernorm.weight": "pytorch_model-00004-of-00029.bin",
+    "model.layers.9.mlp.down_proj.weight": "pytorch_model-00004-of-00029.bin",
+    "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00004-of-00029.bin",
+    "model.layers.9.mlp.up_proj.weight": "pytorch_model-00004-of-00029.bin",
+    "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00004-of-00029.bin",
+    "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00004-of-00029.bin",
+    "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00004-of-00029.bin",
+    "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00004-of-00029.bin",
+    "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00004-of-00029.bin",
+    "model.norm.weight": "pytorch_model-00029-of-00029.bin"
+  }
+}

checkpoint-100/special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "pad_token": "<unk>",
+  "unk_token": "<unk>"
+}

checkpoint-100/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

checkpoint-100/tokenizer_config.json

@@ -0,0 +1,50 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32000": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<unk>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true
+}

checkpoint-100/training_config.yaml

@@ -0,0 +1,136 @@
+train_file: wiki_erica_path/v9.1_fixed/distant_path_v9.1_fix_no_shuffle.train.0.pkl_llama_False_3_6_512_0.4_5_1.0_1.0_0.0_8_path_v9.1.2_seq2seq_bin_filter
+test_file: null
+model:
+  _target_: models.llama.LlamaForConditionalGenerationFlan.from_pretrained
+  use_peft: true
+  lora_config:
+    _recursive_: false
+    _target_: models.llama.LoraConfig
+    task_type: CAUSAL_LM
+    inference_mode: false
+    target_modules:
+      _target_: models.llama.find_all_linear_names
+      bits: 4
+    r: 64
+    lora_alpha: 16
+    lora_dropout: 0.05
+  gradient_checkpointing: true
+  torch_dtype:
+    _target_: general_util.training_utils.return_torch_dtype
+    dtype: bfloat16
+  quantization_config:
+    _target_: transformers.utils.quantization_config.BitsAndBytesConfig
+    load_in_4bit: true
+    bnb_4bit_compute_dtype:
+      _target_: general_util.training_utils.return_torch_dtype
+      dtype: bfloat16
+    bnb_4bit_use_double_quant: true
+    bnb_4bit_quant_type: nf4
+  device_map:
+    _target_: models.llama.return_single_device_map
+  load_in_4bit: true
+  low_cpu_mem_usage: true
+  max_memory: true
+  use_flash_attention_2: true
+dist_load_data_barrier: false
+read_tensor_train:
+  _target_: data.collators.wiki.WikiPathDatasetV5.init_from_bin_file
+extended_vocab: null
+collator:
+  _target_: data.collators.wiki_seq2seq_collator.WikiSeq2SeqCollatorWithCausalLMFixPaddingSide
+  max_seq_length: 512
+  tokenizer: ${model_name_or_path}
+  causal_lm: true
+  causal_lm_add_eos: false
+  generative_mode: true
+  padding_side: right
+num_workers: 4
+prefetch_factor: 2
+do_preprocess: false
+model_name_or_path: pretrained-models/Llama-2-70b-hf
+pretrain: null
+exp_name: llama2.70b.q_lora.merit_v91_v91.seq2seq.v5.0.6aug.filter.w4.adamw.500steps.NA100.1010
+exp_notes: null
+output_dir: experiments/${exp_name}
+do_train: true
+evaluate_during_training: false
+do_eval: true
+eval_sub_path: checkpoint-*
+per_gpu_train_batch_size: 8
+per_gpu_eval_batch_size: 16
+learning_rate: 0.0002
+gradient_accumulation_steps: 128
+weight_decay: 0.0
+adam_epsilon: 1.0e-06
+adam_betas: (0.9, 0.99)
+max_grad_norm: 0.3
+num_train_epochs: 1
+max_steps: -1
+warmup_proportion: 0
+warmup_steps: 50
+total_dataset_len: 1808348
+optimizer: null
+use_nvlamb: null
+bit_training: null
+logging_steps: 1
+save_best: false
+save_steps: 100
+eval_steps: -1
+ddp_eval: true
+no_cuda: false
+seed: 42
+local_rank: 0
+fp16: true
+fp16_opt_level: O1
+fp16_bfloat16: true
+prediction_cfg:
+  metric: acc
+  measure: 1
+  best_checkpoint: null
+  best_result: null
+eval_forward_fn:
+  _target_: general_util.evaluator.DiscriminatorForwardFn
+post_process: null
+compile: false
+fairscale_config: null
+fsdp_config: null
+ds_cfg:
+  train_micro_batch_size_per_gpu: ${per_gpu_train_batch_size}
+  gradient_accumulation_steps: ${gradient_accumulation_steps}
+  optimizer:
+    type: AdamW
+    params:
+      lr: ${learning_rate}
+      betas:
+      - 0.9
+      - 0.999
+      eps: ${adam_epsilon}
+      weight_decay: ${weight_decay}
+  scheduler:
+    type: WarmupLR
+    params:
+      warmup_max_lr: ${learning_rate}
+      warmup_num_steps: 50
+      warmup_type: linear
+  gradient_clipping: ${max_grad_norm}
+  bf16:
+    enabled: ${fp16}
+  zero_optimization:
+    stage: 1
+    contiguous_gradients: true
+    overlap_comm: true
+    reduce_scatter: true
+    reduce_bucket_size: 500000000.0
+    allgather_bucket_size: 500000000.0
+  steps_per_print: 1024
+with_lightseq: false
+summary_helper:
+  _target_: general_util.tensorboard_helper.WandbWriter
+  batch_index_or_keys: null
+  outputs_index_or_keys:
+    train/mlm_loss: mlm_loss
+n_gpu: 1
+device: cuda:0
+train_batch_size: 8
+eval_batch_size: null
+world_size: 4

global_step100/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:870333b8d093604e80228e5b1ed955d72c0eb15c9f8de99c5dc37b55226c78af
+size 2485158743

global_step100/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0167e60ca87b267ac0669e0e4067d4ad14105356f1883249cc7ba135ee0e3e27
+size 2485158871

global_step100/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48df928c6d4dcfcc18331ca4d026be1bc2f6c3d964a23aa0649b8e6727ad30a3
+size 2485158871

global_step100/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47c53efd2234d9e5d6e3a3d7d2b8cfad2c0ad19c7808f0bed8ffbec5d0ea0371
+size 2485158871

global_step100/mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:42661318ba11b267ad6758483a7c24c5b8abbee627b3dc34d76e4f5234ef9fca
+size 36934524465

latest

@@ -0,0 +1 @@
+global_step100

logiqav2_test_mc_0shot.v1.0/test-checkpoint-100/decode_results.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c7bd830f9fc03be25a06f8e245a210d6939c516180264f8a730bdfbd9ae9584
+size 12704