Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+checkpoint-1232/optimizer_0/__0_0.distcp filter=lfs diff=lfs merge=lfs -text
+checkpoint-1232/pytorch_model_fsdp_0/__0_0.distcp filter=lfs diff=lfs merge=lfs -text

checkpoint-1232/optimizer_0/__0_0.distcp

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a36509c004a2cde5984d3c9645918986a00c95978dabc4b82341e2b063187b3f
+size 22238956312

checkpoint-1232/pytorch_model_fsdp_0/__0_0.distcp

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6434114fee729bac855e6251b4a9fbf5c99472720929043eec23c2761ade718a
+size 5559902220

checkpoint-1232/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8e8bba27ffdd90b1a083bb9633c5e25c4d8e168cd7cbe25c40c326c93bcc3c6
+size 14244

checkpoint-1232/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe33f0ec3a453056861919c737ad5ab66021a1ef5d9a6ced53825e39637352b4
+size 1064

checkpoint-1232/trainer_state.json

@@ -0,0 +1,197 @@
+{
+  "best_metric": 1.1404521465301514,
+  "best_model_checkpoint": "./checkpoints/dpo-mix-7k/phi-2-dpo-mix-7k-ORPO-16-20-9/checkpoint-1232",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 1232,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.04,
+      "grad_norm": 140.0,
+      "learning_rate": 2.5e-06,
+      "loss": 9.455,
+      "step": 50
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 95.0,
+      "learning_rate": 5e-06,
+      "loss": 7.3937,
+      "step": 100
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 19.0,
+      "learning_rate": 4.975969658958691e-06,
+      "loss": 1.5555,
+      "step": 150
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 7.90625,
+      "learning_rate": 4.904340601667208e-06,
+      "loss": 1.2716,
+      "step": 200
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 9.375,
+      "learning_rate": 4.786489844665701e-06,
+      "loss": 1.1798,
+      "step": 250
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 38.75,
+      "learning_rate": 4.624682983060346e-06,
+      "loss": 1.2401,
+      "step": 300
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 6.15625,
+      "learning_rate": 4.422030636104903e-06,
+      "loss": 1.2003,
+      "step": 350
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 7.46875,
+      "learning_rate": 4.182428647807503e-06,
+      "loss": 1.1913,
+      "step": 400
+    },
+    {
+      "epoch": 0.37,
+      "grad_norm": 19.125,
+      "learning_rate": 3.910483192162515e-06,
+      "loss": 1.1505,
+      "step": 450
+    },
+    {
+      "epoch": 0.41,
+      "grad_norm": 10.375,
+      "learning_rate": 3.6114222228049657e-06,
+      "loss": 1.1917,
+      "step": 500
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 10.3125,
+      "learning_rate": 3.2909949694035004e-06,
+      "loss": 1.2068,
+      "step": 550
+    },
+    {
+      "epoch": 0.49,
+      "grad_norm": 34.5,
+      "learning_rate": 2.9553614129006543e-06,
+      "loss": 1.1559,
+      "step": 600
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 7.40625,
+      "learning_rate": 2.610973864358563e-06,
+      "loss": 1.2084,
+      "step": 650
+    },
+    {
+      "epoch": 0.57,
+      "grad_norm": 5.25,
+      "learning_rate": 2.2644529239707054e-06,
+      "loss": 1.1095,
+      "step": 700
+    },
+    {
+      "epoch": 0.61,
+      "grad_norm": 11.25,
+      "learning_rate": 1.9224602048374618e-06,
+      "loss": 1.127,
+      "step": 750
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 50.0,
+      "learning_rate": 1.5915702682983657e-06,
+      "loss": 1.1861,
+      "step": 800
+    },
+    {
+      "epoch": 0.69,
+      "grad_norm": 9.1875,
+      "learning_rate": 1.278144232771154e-06,
+      "loss": 1.2159,
+      "step": 850
+    },
+    {
+      "epoch": 0.73,
+      "grad_norm": 12.3125,
+      "learning_rate": 9.88207485875784e-07,
+      "loss": 1.1351,
+      "step": 900
+    },
+    {
+      "epoch": 0.77,
+      "grad_norm": 12.5625,
+      "learning_rate": 7.273338507388969e-07,
+      "loss": 1.1951,
+      "step": 950
+    },
+    {
+      "epoch": 0.81,
+      "grad_norm": 11.3125,
+      "learning_rate": 5.005384332973154e-07,
+      "loss": 1.1518,
+      "step": 1000
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 5.34375,
+      "learning_rate": 3.121812105332203e-07,
+      "loss": 1.1758,
+      "step": 1050
+    },
+    {
+      "epoch": 0.89,
+      "grad_norm": 30.0,
+      "learning_rate": 1.6588321308710409e-07,
+      "loss": 1.1458,
+      "step": 1100
+    },
+    {
+      "epoch": 0.93,
+      "grad_norm": 7.53125,
+      "learning_rate": 6.44569135767989e-08,
+      "loss": 1.2038,
+      "step": 1150
+    },
+    {
+      "epoch": 0.97,
+      "grad_norm": 5.5,
+      "learning_rate": 9.852158856538118e-09,
+      "loss": 1.2168,
+      "step": 1200
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 1.1404521465301514,
+      "eval_runtime": 2329.2969,
+      "eval_samples_per_second": 2.115,
+      "eval_steps_per_second": 0.529,
+      "step": 1232
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 1232,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "total_flos": 1.6032229924379034e+17,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

config.json

@@ -0,0 +1,34 @@
+{
+  "_name_or_path": "microsoft/phi-2",
+  "architectures": [
+    "PhiForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "auto_map": {
+    "AutoConfig": "microsoft/phi-2--configuration_phi.PhiConfig",
+    "AutoModelForCausalLM": "microsoft/phi-2--modeling_phi.PhiForCausalLM"
+  },
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.0,
+  "eos_token_id": 50256,
+  "hidden_act": "gelu_new",
+  "hidden_size": 2560,
+  "initializer_range": 0.02,
+  "intermediate_size": 10240,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 2048,
+  "model_type": "phi",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 32,
+  "partial_rotary_factor": 0.4,
+  "qk_layernorm": false,
+  "resid_pdrop": 0.1,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.38.2",
+  "use_cache": true,
+  "vocab_size": 51200
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "4.38.2"
+}

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1c2ad02a37a6228c635c72831fed0159ce9dedc620e60ef814fa5e6dd6fab15
+size 4995589080

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:81a1ffe2b9ee3214a165994c73924d569990876255a3290a3e28a91276312cfd
+size 563833304

model.safetensors.index.json

@@ -0,0 +1,460 @@
+{
+  "metadata": {
+    "total_size": 5559367680
+  },
+  "weight_map": {
+    "_orig_mod.lm_head.bias": "model-00002-of-00002.safetensors",
+    "_orig_mod.lm_head.weight": "model-00002-of-00002.safetensors",
+    "_orig_mod.model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.final_layernorm.bias": "model-00002-of-00002.safetensors",
+    "_orig_mod.model.final_layernorm.weight": "model-00002-of-00002.safetensors",
+    "_orig_mod.model.layers.0.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.0.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.0.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.0.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.0.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.0.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.0.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.1.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.1.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.1.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.1.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.1.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.1.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.1.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.10.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.10.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.10.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.10.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.10.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.10.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.10.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.11.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.11.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.11.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.11.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.11.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.11.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.11.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.12.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.12.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.12.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.12.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.12.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.12.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.12.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.13.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.13.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.13.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.13.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.13.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.13.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.13.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.14.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.14.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.14.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.14.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.14.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.14.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.14.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.15.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.15.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.15.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.15.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.15.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.15.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.15.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.16.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.16.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.16.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.16.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.16.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.16.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.16.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.17.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.17.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.17.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.17.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.17.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.17.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.17.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.18.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.18.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.18.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.18.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.18.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.18.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.18.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.19.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.19.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.19.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.19.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.19.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.19.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.19.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.2.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.2.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.2.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.2.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.2.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.2.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.2.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.20.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.20.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.20.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.20.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.20.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.20.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.20.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.20.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.20.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.20.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.21.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.21.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.21.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.21.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.21.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.21.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.21.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.21.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.21.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.22.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.22.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.22.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.22.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.22.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.22.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.22.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.22.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.22.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.22.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.23.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.23.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.23.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.23.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.23.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.23.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.23.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.23.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.23.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.23.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.24.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.24.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.24.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.24.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.24.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.24.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.24.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.24.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.24.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.24.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.24.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.25.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.25.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.25.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.25.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.25.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.25.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.25.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.25.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.25.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.25.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.25.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.25.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.26.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.26.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.26.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.26.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.26.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.26.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.26.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.26.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.26.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.26.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.26.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.26.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.26.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.26.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.27.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.27.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.27.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.27.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.27.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.27.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.27.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.27.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.27.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.27.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.27.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.27.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.27.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.27.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.28.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.28.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.28.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.28.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.28.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.28.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.28.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.28.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.28.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.28.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.28.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.28.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.28.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.28.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.29.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.29.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.29.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.29.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.29.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.29.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.29.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.29.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.29.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.29.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.29.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.29.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.29.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.29.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.3.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.3.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.3.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.3.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.3.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.3.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.3.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.30.input_layernorm.bias": "model-00002-of-00002.safetensors",
+    "_orig_mod.model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "_orig_mod.model.layers.30.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "_orig_mod.model.layers.30.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "_orig_mod.model.layers.30.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "_orig_mod.model.layers.30.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "_orig_mod.model.layers.30.self_attn.dense.bias": "model-00002-of-00002.safetensors",
+    "_orig_mod.model.layers.30.self_attn.dense.weight": "model-00002-of-00002.safetensors",
+    "_orig_mod.model.layers.30.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "_orig_mod.model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "_orig_mod.model.layers.30.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.30.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.30.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "_orig_mod.model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "_orig_mod.model.layers.31.input_layernorm.bias": "model-00002-of-00002.safetensors",
+    "_orig_mod.model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "_orig_mod.model.layers.31.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "_orig_mod.model.layers.31.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "_orig_mod.model.layers.31.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "_orig_mod.model.layers.31.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "_orig_mod.model.layers.31.self_attn.dense.bias": "model-00002-of-00002.safetensors",
+    "_orig_mod.model.layers.31.self_attn.dense.weight": "model-00002-of-00002.safetensors",
+    "_orig_mod.model.layers.31.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "_orig_mod.model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "_orig_mod.model.layers.31.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "_orig_mod.model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "_orig_mod.model.layers.31.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "_orig_mod.model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "_orig_mod.model.layers.4.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.4.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.4.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.4.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.4.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.4.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.4.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.5.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.5.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.5.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.5.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.5.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.5.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.5.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.6.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.6.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.6.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.6.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.6.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.6.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.6.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.7.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.7.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.7.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.7.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.7.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.7.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.7.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.8.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.8.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.8.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.8.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.8.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.8.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.8.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.9.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.9.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.9.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.9.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.9.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.9.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.9.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors"
+  }
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da5eb84b27d1f27a72fa3c9c1688eb1d49f86242057e3a90e7ce8b000d5d9a71
+size 4984